Skip to content

Annotators

import supervision as sv

image = ...
key_points = sv.KeyPoints(...)

vertex_annotator = sv.VertexAnnotator(
    color=sv.Color.GREEN,
    radius=10,
)
annotated_frame = vertex_annotator.annotate(
    scene=image.copy(),
    key_points=key_points,
)

vertex-annotator-example

import supervision as sv

image = ...
key_points = sv.KeyPoints(...)

edge_annotator = sv.EdgeAnnotator(
    color=sv.Color.GREEN,
    thickness=5,
)
annotated_frame = edge_annotator.annotate(
    scene=image.copy(),
    key_points=key_points,
)

edge-annotator-example

import supervision as sv

image = ...
key_points = sv.KeyPoints(...)

vertex_label_annotator = sv.VertexLabelAnnotator(
    color=sv.Color.GREEN,
    text_color=sv.Color.BLACK,
    border_radius=5,
)
annotated_frame = vertex_label_annotator.annotate(
    scene=image.copy(),
    key_points=key_points,
)

vertex-label-annotator-example

import supervision as sv

image = ...
key_points = sv.KeyPoints(...)

area_annotator = sv.VertexEllipseAreaAnnotator(
    color=sv.Color.GREEN,
    sigma=2.0,
)
annotated_frame = area_annotator.annotate(
    scene=image.copy(),
    key_points=key_points,
)

import supervision as sv

image = ...
key_points = sv.KeyPoints(...)

outline_annotator = sv.VertexEllipseOutlineAnnotator(
    color=sv.Color.GREEN,
    sigma=2.0,
    thickness=2,
)
annotated_frame = outline_annotator.annotate(
    scene=image.copy(),
    key_points=key_points,
)

import supervision as sv

image = ...
key_points = sv.KeyPoints(...)

halo_annotator = sv.VertexEllipseHaloAnnotator(
    color=sv.Color.GREEN,
    sigma=2.0,
)
annotated_frame = halo_annotator.annotate(
    scene=image.copy(),
    key_points=key_points,
)

VertexAnnotator

supervision.key_points.annotators.VertexAnnotator

Bases: BaseKeyPointAnnotator

A class that specializes in drawing skeleton vertices on images. It uses specified key points to determine the locations where the vertices should be drawn.

Source code in src/supervision/key_points/annotators.py 
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
class VertexAnnotator(BaseKeyPointAnnotator):
    """
    A class that specializes in drawing skeleton vertices on images. It uses
    specified key points to determine the locations where the vertices should be
    drawn.
    """

    def __init__(
        self,
        color: Color = Color.ROBOFLOW,
        radius: int = 4,
    ) -> None:
        """
        Args:
            color: The color to use for annotating key points.
            radius: The radius of the circles used to represent the key points.
        """
        self.color = color
        self.radius = radius

    @ensure_cv2_image_for_class_method
    def annotate(self, scene: ImageType, key_points: KeyPoints) -> ImageType:
        """
        Annotates the given scene with skeleton vertices based on the provided key
        points. It draws circles at each key point location. Anchors marked as
        not visible via ``key_points.visible`` are skipped.

        Args:
            scene: The image where skeleton vertices will be drawn. `ImageType` is a
                flexible type, accepting either `numpy.ndarray` or `PIL.Image.Image`.
            key_points: A collection of key points where each key point consists of x
                and y coordinates.

        Returns:
            The annotated image, matching the type of `scene` (`numpy.ndarray`
                or `PIL.Image.Image`)

        Example:
            ```pycon
            >>> import numpy as np
            >>> import supervision as sv
            >>> image = np.zeros((800, 800, 3), dtype=np.uint8)
            >>> key_points = sv.KeyPoints(
            ...     xy=np.array(
            ...         [[[400, 200], [300, 500], [500, 500]]],
            ...         dtype=np.float32,
            ...     ),
            ...     class_id=np.array([0]),
            ...     visible=np.array([[True, True, True]]),
            ... )
            >>> annotator = sv.VertexAnnotator(
            ...     color=sv.Color.ROBOFLOW, radius=10
            ... )
            >>> result = annotator.annotate(image.copy(), key_points)

            ```
        """
        assert isinstance(scene, np.ndarray)
        if len(key_points) == 0:
            return scene

        for detection_index, xy in enumerate(key_points.xy):
            for point_index, (x, y) in enumerate(xy):
                if np.allclose((x, y), 0):
                    continue
                if (
                    key_points.visible is not None
                    and not key_points.visible[detection_index, point_index]
                ):
                    continue
                cv2.circle(
                    img=scene,
                    center=(int(x), int(y)),
                    radius=self.radius,
                    color=self.color.as_bgr(),
                    thickness=-1,
                )

        return scene

Functions

__init__(color: Color = Color.ROBOFLOW, radius: int = 4) -> None

Parameters:

Name Type Description Default
color
Color

The color to use for annotating key points.

 ROBOFLOW
radius
int

The radius of the circles used to represent the key points.

 4
Source code in src/supervision/key_points/annotators.py 
37
38
39
40
41
42
43
44
45
46
47
48
def __init__(
    self,
    color: Color = Color.ROBOFLOW,
    radius: int = 4,
) -> None:
    """
    Args:
        color: The color to use for annotating key points.
        radius: The radius of the circles used to represent the key points.
    """
    self.color = color
    self.radius = radius

annotate(scene: ImageType, key_points: KeyPoints) -> ImageType

Annotates the given scene with skeleton vertices based on the provided key points. It draws circles at each key point location. Anchors marked as not visible via key_points.visible are skipped.

Parameters:

Name Type Description Default
scene
ImageType

The image where skeleton vertices will be drawn. ImageType is a flexible type, accepting either numpy.ndarray or PIL.Image.Image.

 required
key_points
KeyPoints

A collection of key points where each key point consists of x and y coordinates.

 required

Returns:

Type Description
ImageType

The annotated image, matching the type of scene (numpy.ndarray or PIL.Image.Image)
Example 
>>> import numpy as np
>>> import supervision as sv
>>> image = np.zeros((800, 800, 3), dtype=np.uint8)
>>> key_points = sv.KeyPoints(
...     xy=np.array(
...         [[[400, 200], [300, 500], [500, 500]]],
...         dtype=np.float32,
...     ),
...     class_id=np.array([0]),
...     visible=np.array([[True, True, True]]),
... )
>>> annotator = sv.VertexAnnotator(
...     color=sv.Color.ROBOFLOW, radius=10
... )
>>> result = annotator.annotate(image.copy(), key_points)
Source code in src/supervision/key_points/annotators.py 
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
@ensure_cv2_image_for_class_method
def annotate(self, scene: ImageType, key_points: KeyPoints) -> ImageType:
    """
    Annotates the given scene with skeleton vertices based on the provided key
    points. It draws circles at each key point location. Anchors marked as
    not visible via ``key_points.visible`` are skipped.

    Args:
        scene: The image where skeleton vertices will be drawn. `ImageType` is a
            flexible type, accepting either `numpy.ndarray` or `PIL.Image.Image`.
        key_points: A collection of key points where each key point consists of x
            and y coordinates.

    Returns:
        The annotated image, matching the type of `scene` (`numpy.ndarray`
            or `PIL.Image.Image`)

    Example:
        ```pycon
        >>> import numpy as np
        >>> import supervision as sv
        >>> image = np.zeros((800, 800, 3), dtype=np.uint8)
        >>> key_points = sv.KeyPoints(
        ...     xy=np.array(
        ...         [[[400, 200], [300, 500], [500, 500]]],
        ...         dtype=np.float32,
        ...     ),
        ...     class_id=np.array([0]),
        ...     visible=np.array([[True, True, True]]),
        ... )
        >>> annotator = sv.VertexAnnotator(
        ...     color=sv.Color.ROBOFLOW, radius=10
        ... )
        >>> result = annotator.annotate(image.copy(), key_points)

        ```
    """
    assert isinstance(scene, np.ndarray)
    if len(key_points) == 0:
        return scene

    for detection_index, xy in enumerate(key_points.xy):
        for point_index, (x, y) in enumerate(xy):
            if np.allclose((x, y), 0):
                continue
            if (
                key_points.visible is not None
                and not key_points.visible[detection_index, point_index]
            ):
                continue
            cv2.circle(
                img=scene,
                center=(int(x), int(y)),
                radius=self.radius,
                color=self.color.as_bgr(),
                thickness=-1,
            )

    return scene

EdgeAnnotator

supervision.key_points.annotators.EdgeAnnotator

Bases: BaseKeyPointAnnotator

A class that specializes in drawing skeleton edges on images using specified key points. It connects key points with lines to form the skeleton structure.

Source code in src/supervision/key_points/annotators.py 
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
class EdgeAnnotator(BaseKeyPointAnnotator):
    """
    A class that specializes in drawing skeleton edges on images using specified key
    points. It connects key points with lines to form the skeleton structure.
    """

    def __init__(
        self,
        color: Color = Color.ROBOFLOW,
        thickness: int = 2,
        edges: (
            Sequence[tuple[int, int]] | dict[int, Sequence[tuple[int, int]]] | None
        ) = None,
    ) -> None:
        """
        Args:
            color: The color to use for the edges.
            thickness: The thickness of the edges.
            edges: The edges to draw. If set to ``None``, will attempt to
                auto-detect the skeleton by vertex count. A
                ``Sequence[tuple[int, int]]`` applies a single skeleton to
                every instance. A ``dict[int, Sequence[tuple[int, int]]]``
                maps ``class_id`` to skeleton edges, enabling correct
                rendering for datasets with multiple skeleton types.
        """
        self.color = color
        self.thickness = thickness
        self.edges = edges

    @ensure_cv2_image_for_class_method
    def annotate(self, scene: ImageType, key_points: KeyPoints) -> ImageType:
        """
        Annotates the given scene by drawing lines between specified key points to form
        edges. Edges where either endpoint is marked as not visible via
        ``key_points.visible`` are skipped.

        Args:
            scene: The image where skeleton edges will be drawn. `ImageType` is a
                flexible type, accepting either `numpy.ndarray` or `PIL.Image.Image`.
            key_points: A collection of key points where each key point consists of x
                and y coordinates.

        Returns:
            The annotated image, matching the type of `scene` (`numpy.ndarray`
                or `PIL.Image.Image`)

        Example:
            Single-skeleton example:

            ```pycon
            >>> import numpy as np
            >>> import supervision as sv
            >>> image = np.zeros((800, 800, 3), dtype=np.uint8)
            >>> key_points = sv.KeyPoints(
            ...     xy=np.array(
            ...         [[[400, 200], [300, 500], [500, 500]]],
            ...         dtype=np.float32,
            ...     ),
            ...     class_id=np.array([0]),
            ...     visible=np.array([[True, True, True]]),
            ... )
            >>> annotator = sv.EdgeAnnotator(
            ...     color=sv.Color.ROBOFLOW,
            ...     thickness=3,
            ...     edges=[(1, 2), (1, 3)],
            ... )
            >>> result = annotator.annotate(image.copy(), key_points)

            ```

            Multi-skeleton example with per-class edges:

            ```pycon
            >>> import numpy as np
            >>> import supervision as sv
            >>> image = np.zeros((800, 800, 3), dtype=np.uint8)
            >>> key_points = sv.KeyPoints(
            ...     xy=np.array(
            ...         [[[400, 200], [300, 500], [500, 500]],
            ...          [[700, 300], [650, 500], [0, 0]]],
            ...         dtype=np.float32,
            ...     ),
            ...     class_id=np.array([0, 1]),
            ...     visible=np.array(
            ...         [[True, True, True],
            ...          [True, True, False]],
            ...     ),
            ... )
            >>> annotator = sv.EdgeAnnotator(
            ...     color=sv.Color.ROBOFLOW,
            ...     thickness=3,
            ...     edges={0: [(1, 2), (1, 3)], 1: [(1, 2)]},
            ... )
            >>> result = annotator.annotate(image.copy(), key_points)

            ```
        """
        assert isinstance(scene, np.ndarray)
        if len(key_points) == 0:
            return scene

        for detection_index, xy in enumerate(key_points.xy):
            if isinstance(self.edges, dict):
                class_id = (
                    int(key_points.class_id[detection_index])
                    if key_points.class_id is not None
                    else None
                )
                if class_id is None:
                    raise ValueError(
                        "edges is a dict but class_id is None; "
                        "KeyPoints must have class_id set."
                    )
                if class_id not in self.edges:
                    raise ValueError(f"No edges defined for class_id={class_id}.")
                edges = self.edges[class_id]
            elif self.edges:
                edges = self.edges
            else:
                _looked_up = SKELETONS_BY_VERTEX_COUNT.get(len(xy))
                if not _looked_up:
                    logger.warning("No skeleton found with %d vertices", len(xy))
                    continue
                edges = _looked_up

            for class_a, class_b in edges:
                idx_a = class_a - 1
                idx_b = class_b - 1
                xy_a = xy[idx_a]
                xy_b = xy[idx_b]
                if np.allclose(xy_a, 0) or np.allclose(xy_b, 0):
                    continue
                if key_points.visible is not None:
                    if (
                        not key_points.visible[detection_index, idx_a]
                        or not key_points.visible[detection_index, idx_b]
                    ):
                        continue

                cv2.line(
                    img=scene,
                    pt1=(int(xy_a[0]), int(xy_a[1])),
                    pt2=(int(xy_b[0]), int(xy_b[1])),
                    color=self.color.as_bgr(),
                    thickness=self.thickness,
                )

        return scene

Functions

__init__(color: Color = Color.ROBOFLOW, thickness: int = 2, edges: Sequence[tuple[int, int]] | dict[int, Sequence[tuple[int, int]]] | None = None) -> None

Parameters:

Name Type Description Default
color
Color

The color to use for the edges.

 ROBOFLOW
thickness
int

The thickness of the edges.

 2
edges
Sequence[tuple[int, int]] | dict[int, Sequence[tuple[int, int]]] | None

The edges to draw. If set to None, will attempt to auto-detect the skeleton by vertex count. A Sequence[tuple[int, int]] applies a single skeleton to every instance. A dict[int, Sequence[tuple[int, int]]] maps class_id to skeleton edges, enabling correct rendering for datasets with multiple skeleton types.

 None
Source code in src/supervision/key_points/annotators.py 
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
def __init__(
    self,
    color: Color = Color.ROBOFLOW,
    thickness: int = 2,
    edges: (
        Sequence[tuple[int, int]] | dict[int, Sequence[tuple[int, int]]] | None
    ) = None,
) -> None:
    """
    Args:
        color: The color to use for the edges.
        thickness: The thickness of the edges.
        edges: The edges to draw. If set to ``None``, will attempt to
            auto-detect the skeleton by vertex count. A
            ``Sequence[tuple[int, int]]`` applies a single skeleton to
            every instance. A ``dict[int, Sequence[tuple[int, int]]]``
            maps ``class_id`` to skeleton edges, enabling correct
            rendering for datasets with multiple skeleton types.
    """
    self.color = color
    self.thickness = thickness
    self.edges = edges

annotate(scene: ImageType, key_points: KeyPoints) -> ImageType

Annotates the given scene by drawing lines between specified key points to form edges. Edges where either endpoint is marked as not visible via key_points.visible are skipped.

Parameters:

Name Type Description Default
scene
ImageType

The image where skeleton edges will be drawn. ImageType is a flexible type, accepting either numpy.ndarray or PIL.Image.Image.

 required
key_points
KeyPoints

A collection of key points where each key point consists of x and y coordinates.

 required

Returns:

Type Description
ImageType

The annotated image, matching the type of scene (numpy.ndarray or PIL.Image.Image)
Example

Single-skeleton example:

>>> import numpy as np
>>> import supervision as sv
>>> image = np.zeros((800, 800, 3), dtype=np.uint8)
>>> key_points = sv.KeyPoints(
...     xy=np.array(
...         [[[400, 200], [300, 500], [500, 500]]],
...         dtype=np.float32,
...     ),
...     class_id=np.array([0]),
...     visible=np.array([[True, True, True]]),
... )
>>> annotator = sv.EdgeAnnotator(
...     color=sv.Color.ROBOFLOW,
...     thickness=3,
...     edges=[(1, 2), (1, 3)],
... )
>>> result = annotator.annotate(image.copy(), key_points)

Multi-skeleton example with per-class edges:

>>> import numpy as np
>>> import supervision as sv
>>> image = np.zeros((800, 800, 3), dtype=np.uint8)
>>> key_points = sv.KeyPoints(
...     xy=np.array(
...         [[[400, 200], [300, 500], [500, 500]],
...          [[700, 300], [650, 500], [0, 0]]],
...         dtype=np.float32,
...     ),
...     class_id=np.array([0, 1]),
...     visible=np.array(
...         [[True, True, True],
...          [True, True, False]],
...     ),
... )
>>> annotator = sv.EdgeAnnotator(
...     color=sv.Color.ROBOFLOW,
...     thickness=3,
...     edges={0: [(1, 2), (1, 3)], 1: [(1, 2)]},
... )
>>> result = annotator.annotate(image.copy(), key_points)
Source code in src/supervision/key_points/annotators.py 
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
@ensure_cv2_image_for_class_method
def annotate(self, scene: ImageType, key_points: KeyPoints) -> ImageType:
    """
    Annotates the given scene by drawing lines between specified key points to form
    edges. Edges where either endpoint is marked as not visible via
    ``key_points.visible`` are skipped.

    Args:
        scene: The image where skeleton edges will be drawn. `ImageType` is a
            flexible type, accepting either `numpy.ndarray` or `PIL.Image.Image`.
        key_points: A collection of key points where each key point consists of x
            and y coordinates.

    Returns:
        The annotated image, matching the type of `scene` (`numpy.ndarray`
            or `PIL.Image.Image`)

    Example:
        Single-skeleton example:

        ```pycon
        >>> import numpy as np
        >>> import supervision as sv
        >>> image = np.zeros((800, 800, 3), dtype=np.uint8)
        >>> key_points = sv.KeyPoints(
        ...     xy=np.array(
        ...         [[[400, 200], [300, 500], [500, 500]]],
        ...         dtype=np.float32,
        ...     ),
        ...     class_id=np.array([0]),
        ...     visible=np.array([[True, True, True]]),
        ... )
        >>> annotator = sv.EdgeAnnotator(
        ...     color=sv.Color.ROBOFLOW,
        ...     thickness=3,
        ...     edges=[(1, 2), (1, 3)],
        ... )
        >>> result = annotator.annotate(image.copy(), key_points)

        ```

        Multi-skeleton example with per-class edges:

        ```pycon
        >>> import numpy as np
        >>> import supervision as sv
        >>> image = np.zeros((800, 800, 3), dtype=np.uint8)
        >>> key_points = sv.KeyPoints(
        ...     xy=np.array(
        ...         [[[400, 200], [300, 500], [500, 500]],
        ...          [[700, 300], [650, 500], [0, 0]]],
        ...         dtype=np.float32,
        ...     ),
        ...     class_id=np.array([0, 1]),
        ...     visible=np.array(
        ...         [[True, True, True],
        ...          [True, True, False]],
        ...     ),
        ... )
        >>> annotator = sv.EdgeAnnotator(
        ...     color=sv.Color.ROBOFLOW,
        ...     thickness=3,
        ...     edges={0: [(1, 2), (1, 3)], 1: [(1, 2)]},
        ... )
        >>> result = annotator.annotate(image.copy(), key_points)

        ```
    """
    assert isinstance(scene, np.ndarray)
    if len(key_points) == 0:
        return scene

    for detection_index, xy in enumerate(key_points.xy):
        if isinstance(self.edges, dict):
            class_id = (
                int(key_points.class_id[detection_index])
                if key_points.class_id is not None
                else None
            )
            if class_id is None:
                raise ValueError(
                    "edges is a dict but class_id is None; "
                    "KeyPoints must have class_id set."
                )
            if class_id not in self.edges:
                raise ValueError(f"No edges defined for class_id={class_id}.")
            edges = self.edges[class_id]
        elif self.edges:
            edges = self.edges
        else:
            _looked_up = SKELETONS_BY_VERTEX_COUNT.get(len(xy))
            if not _looked_up:
                logger.warning("No skeleton found with %d vertices", len(xy))
                continue
            edges = _looked_up

        for class_a, class_b in edges:
            idx_a = class_a - 1
            idx_b = class_b - 1
            xy_a = xy[idx_a]
            xy_b = xy[idx_b]
            if np.allclose(xy_a, 0) or np.allclose(xy_b, 0):
                continue
            if key_points.visible is not None:
                if (
                    not key_points.visible[detection_index, idx_a]
                    or not key_points.visible[detection_index, idx_b]
                ):
                    continue

            cv2.line(
                img=scene,
                pt1=(int(xy_a[0]), int(xy_a[1])),
                pt2=(int(xy_b[0]), int(xy_b[1])),
                color=self.color.as_bgr(),
                thickness=self.thickness,
            )

    return scene

VertexLabelAnnotator

supervision.key_points.annotators.VertexLabelAnnotator

A class that draws labels of skeleton vertices on images. It uses specified key points to determine the locations where the vertices should be drawn.

Source code in src/supervision/key_points/annotators.py 
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
class VertexLabelAnnotator:
    """
    A class that draws labels of skeleton vertices on images. It uses specified key
    points to determine the locations where the vertices should be drawn.
    """

    def __init__(
        self,
        color: Color | list[Color] = Color.ROBOFLOW,
        text_color: Color | list[Color] = Color.WHITE,
        text_scale: float = 0.5,
        text_thickness: int = 1,
        text_padding: int = 10,
        border_radius: int = 0,
        smart_position: bool = False,
    ):
        """
        Args:
            color: The color to use for each keypoint label. If a list is
                provided, the colors will be used in order for each keypoint.
            text_color: The color to use for the labels. If a list is
                provided, the colors will be used in order for each keypoint.
            text_scale: The scale of the text.
            text_thickness: The thickness of the text.
            text_padding: The padding around the text.
            border_radius: The radius of the rounded corners of the boxes.
                Set to a high value to produce circles.
            smart_position: Spread out the labels to avoid overlap.
        """
        self.border_radius: int = border_radius
        self.color: Color | list[Color] = color
        self.text_color: Color | list[Color] = text_color
        self.text_scale: float = text_scale
        self.text_thickness: int = text_thickness
        self.text_padding: int = text_padding
        self.smart_position = smart_position

    def annotate(
        self,
        scene: ImageType,
        key_points: KeyPoints,
        labels: list[str] | dict[int, list[str]] | None = None,
    ) -> ImageType:
        """
        Draws labels at skeleton vertex positions on the image. Vertices
        marked not visible via ``key_points.visible`` are skipped.

        Args:
            scene: The image where vertex labels will be drawn. `ImageType` is a
                flexible type, accepting either `numpy.ndarray` or `PIL.Image.Image`.
            key_points: A collection of key points where each key point consists of x
                and y coordinates.
            labels: Labels to display at each keypoint. If ``None``, keypoint
                indices are used. A ``list[str]`` applies the same labels to
                every instance. A ``dict[int, list[str]]`` maps ``class_id``
                to per-class label lists, enabling correct labeling for
                datasets with multiple skeleton types.

        Returns:
            The annotated image, matching the type of `scene` (`numpy.ndarray`
                or `PIL.Image.Image`)

        Example:
            Single-skeleton example:

            ```pycon
            >>> import numpy as np
            >>> import supervision as sv
            >>> image = np.zeros((800, 800, 3), dtype=np.uint8)
            >>> key_points = sv.KeyPoints(
            ...     xy=np.array(
            ...         [[[400, 200], [300, 500], [500, 500]]],
            ...         dtype=np.float32,
            ...     ),
            ...     class_id=np.array([0]),
            ...     visible=np.array([[True, True, True]]),
            ... )
            >>> annotator = sv.VertexLabelAnnotator(
            ...     color=sv.Color.ROBOFLOW,
            ...     text_color=sv.Color.WHITE,
            ...     border_radius=5,
            ... )
            >>> result = annotator.annotate(
            ...     scene=image.copy(),
            ...     key_points=key_points,
            ...     labels=["head", "L-foot", "R-foot"],
            ... )

            ```

            Multi-skeleton example with per-class labels:

            ```pycon
            >>> import numpy as np
            >>> import supervision as sv
            >>> image = np.zeros((800, 800, 3), dtype=np.uint8)
            >>> key_points = sv.KeyPoints(
            ...     xy=np.array(
            ...         [[[400, 200], [300, 500], [500, 500]],
            ...          [[700, 300], [650, 500], [0, 0]]],
            ...         dtype=np.float32,
            ...     ),
            ...     class_id=np.array([0, 1]),
            ...     visible=np.array(
            ...         [[True, True, True],
            ...          [True, True, False]],
            ...     ),
            ... )
            >>> annotator = sv.VertexLabelAnnotator(
            ...     color=sv.Color.ROBOFLOW,
            ...     text_color=sv.Color.WHITE,
            ...     border_radius=5,
            ... )
            >>> result = annotator.annotate(
            ...     scene=image.copy(),
            ...     key_points=key_points,
            ...     labels={
            ...         0: ["head", "L-foot", "R-foot"],
            ...         1: ["top", "bottom", "pad"],
            ...     },
            ... )

            ```
        """
        assert isinstance(scene, np.ndarray)
        font = cv2.FONT_HERSHEY_SIMPLEX

        skeletons_count, points_count, _ = key_points.xy.shape
        if skeletons_count == 0:
            return scene

        all_anchors: list[tuple[int, int]] = []
        all_labels: list[str] = []
        all_colors: list[Color] = []
        all_text_colors: list[Color] = []

        for i in range(skeletons_count):
            xy = key_points.xy[i]

            class_id = (
                int(key_points.class_id[i]) if key_points.class_id is not None else None
            )
            instance_labels = self._resolve_labels(labels, points_count, class_id)
            instance_colors = self._resolve_color_list(self.color, points_count)
            instance_text_colors = self._resolve_color_list(
                self.text_color, points_count
            )

            for j in range(points_count):
                if key_points.visible is not None:
                    if not key_points.visible[i, j]:
                        continue
                elif np.allclose(xy[j], 0):
                    continue

                anchor = (int(xy[j][0]), int(xy[j][1]))
                all_anchors.append(anchor)
                all_labels.append(instance_labels[j])
                all_colors.append(instance_colors[j])
                all_text_colors.append(instance_text_colors[j])

        if not all_anchors:
            return scene

        xyxy = np.array(
            [
                self.get_text_bounding_box(
                    text=label,
                    font=font,
                    text_scale=self.text_scale,
                    text_thickness=self.text_thickness,
                    center_coordinates=anchor,
                )
                for anchor, label in zip(all_anchors, all_labels)
            ]
        )
        xyxy_padded = pad_boxes(xyxy=xyxy, px=self.text_padding)

        if self.smart_position:
            xyxy_padded = spread_out_boxes(xyxy_padded)
            xyxy = pad_boxes(xyxy=xyxy_padded, px=-self.text_padding)

        for text, color, text_color, box, box_padded in zip(
            all_labels, all_colors, all_text_colors, xyxy, xyxy_padded
        ):
            draw_rounded_rectangle(
                scene=scene,
                rect=Rect.from_xyxy(box_padded),
                color=color,
                border_radius=self.border_radius,
            )
            cv2.putText(
                img=scene,
                text=text,
                org=(box[0], box[3]),
                fontFace=font,
                fontScale=self.text_scale,
                color=text_color.as_bgr(),
                thickness=self.text_thickness,
                lineType=cv2.LINE_AA,
            )

        return scene

    @staticmethod
    def get_text_bounding_box(
        text: str,
        font: int,
        text_scale: float,
        text_thickness: int,
        center_coordinates: tuple[int, int],
    ) -> tuple[int, int, int, int]:
        text_w, text_h = cv2.getTextSize(
            text=text,
            fontFace=font,
            fontScale=text_scale,
            thickness=text_thickness,
        )[0]
        center_x, center_y = center_coordinates
        return (
            center_x - text_w // 2,
            center_y - text_h // 2,
            center_x + text_w // 2,
            center_y + text_h // 2,
        )

    @staticmethod
    def _resolve_labels(
        labels: list[str] | dict[int, list[str]] | None,
        points_count: int,
        class_id: int | None = None,
    ) -> list[str]:
        """Return the label list for a single instance."""
        if labels is None:
            return [str(j) for j in range(points_count)]

        resolved: list[str]
        if isinstance(labels, dict):
            if class_id is None:
                raise ValueError(
                    "labels is a dict but class_id is None; "
                    "KeyPoints must have class_id set."
                )
            if class_id not in labels:
                raise ValueError(f"No labels defined for class_id={class_id}.")
            resolved = labels[class_id]
        else:
            resolved = labels

        if len(resolved) != points_count:
            raise ValueError(
                f"Number of labels ({len(resolved)}) must match "
                f"number of key points ({points_count})."
            )
        return resolved

    @staticmethod
    def _resolve_color_list(
        colors: Color | list[Color],
        points_count: int,
    ) -> list[Color]:
        """Return a per-keypoint color list for a single instance."""
        if isinstance(colors, list):
            if len(colors) != points_count:
                raise ValueError(
                    f"Number of colors ({len(colors)}) must match "
                    f"number of key points ({points_count})."
                )
            return colors
        return [colors] * points_count

Functions

__init__(color: Color | list[Color] = Color.ROBOFLOW, text_color: Color | list[Color] = Color.WHITE, text_scale: float = 0.5, text_thickness: int = 1, text_padding: int = 10, border_radius: int = 0, smart_position: bool = False)

Parameters:

Name Type Description Default
color
Color | list[Color]

The color to use for each keypoint label. If a list is provided, the colors will be used in order for each keypoint.

 ROBOFLOW
text_color
Color | list[Color]

The color to use for the labels. If a list is provided, the colors will be used in order for each keypoint.

 WHITE
text_scale
float

The scale of the text.

 0.5
text_thickness
int

The thickness of the text.

 1
text_padding
int

The padding around the text.

 10
border_radius
int

The radius of the rounded corners of the boxes. Set to a high value to produce circles.

 0
smart_position
bool

Spread out the labels to avoid overlap.

 False
Source code in src/supervision/key_points/annotators.py 
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
def __init__(
    self,
    color: Color | list[Color] = Color.ROBOFLOW,
    text_color: Color | list[Color] = Color.WHITE,
    text_scale: float = 0.5,
    text_thickness: int = 1,
    text_padding: int = 10,
    border_radius: int = 0,
    smart_position: bool = False,
):
    """
    Args:
        color: The color to use for each keypoint label. If a list is
            provided, the colors will be used in order for each keypoint.
        text_color: The color to use for the labels. If a list is
            provided, the colors will be used in order for each keypoint.
        text_scale: The scale of the text.
        text_thickness: The thickness of the text.
        text_padding: The padding around the text.
        border_radius: The radius of the rounded corners of the boxes.
            Set to a high value to produce circles.
        smart_position: Spread out the labels to avoid overlap.
    """
    self.border_radius: int = border_radius
    self.color: Color | list[Color] = color
    self.text_color: Color | list[Color] = text_color
    self.text_scale: float = text_scale
    self.text_thickness: int = text_thickness
    self.text_padding: int = text_padding
    self.smart_position = smart_position

annotate(scene: ImageType, key_points: KeyPoints, labels: list[str] | dict[int, list[str]] | None = None) -> ImageType

Draws labels at skeleton vertex positions on the image. Vertices marked not visible via key_points.visible are skipped.

Parameters:

Name Type Description Default
scene
ImageType

The image where vertex labels will be drawn. ImageType is a flexible type, accepting either numpy.ndarray or PIL.Image.Image.

 required
key_points
KeyPoints

A collection of key points where each key point consists of x and y coordinates.

 required
labels
list[str] | dict[int, list[str]] | None

Labels to display at each keypoint. If None, keypoint indices are used. A list[str] applies the same labels to every instance. A dict[int, list[str]] maps class_id to per-class label lists, enabling correct labeling for datasets with multiple skeleton types.

 None

Returns:

Type Description
ImageType

The annotated image, matching the type of scene (numpy.ndarray or PIL.Image.Image)
Example

Single-skeleton example:

>>> import numpy as np
>>> import supervision as sv
>>> image = np.zeros((800, 800, 3), dtype=np.uint8)
>>> key_points = sv.KeyPoints(
...     xy=np.array(
...         [[[400, 200], [300, 500], [500, 500]]],
...         dtype=np.float32,
...     ),
...     class_id=np.array([0]),
...     visible=np.array([[True, True, True]]),
... )
>>> annotator = sv.VertexLabelAnnotator(
...     color=sv.Color.ROBOFLOW,
...     text_color=sv.Color.WHITE,
...     border_radius=5,
... )
>>> result = annotator.annotate(
...     scene=image.copy(),
...     key_points=key_points,
...     labels=["head", "L-foot", "R-foot"],
... )

Multi-skeleton example with per-class labels:

>>> import numpy as np
>>> import supervision as sv
>>> image = np.zeros((800, 800, 3), dtype=np.uint8)
>>> key_points = sv.KeyPoints(
...     xy=np.array(
...         [[[400, 200], [300, 500], [500, 500]],
...          [[700, 300], [650, 500], [0, 0]]],
...         dtype=np.float32,
...     ),
...     class_id=np.array([0, 1]),
...     visible=np.array(
...         [[True, True, True],
...          [True, True, False]],
...     ),
... )
>>> annotator = sv.VertexLabelAnnotator(
...     color=sv.Color.ROBOFLOW,
...     text_color=sv.Color.WHITE,
...     border_radius=5,
... )
>>> result = annotator.annotate(
...     scene=image.copy(),
...     key_points=key_points,
...     labels={
...         0: ["head", "L-foot", "R-foot"],
...         1: ["top", "bottom", "pad"],
...     },
... )
Source code in src/supervision/key_points/annotators.py 
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
def annotate(
    self,
    scene: ImageType,
    key_points: KeyPoints,
    labels: list[str] | dict[int, list[str]] | None = None,
) -> ImageType:
    """
    Draws labels at skeleton vertex positions on the image. Vertices
    marked not visible via ``key_points.visible`` are skipped.

    Args:
        scene: The image where vertex labels will be drawn. `ImageType` is a
            flexible type, accepting either `numpy.ndarray` or `PIL.Image.Image`.
        key_points: A collection of key points where each key point consists of x
            and y coordinates.
        labels: Labels to display at each keypoint. If ``None``, keypoint
            indices are used. A ``list[str]`` applies the same labels to
            every instance. A ``dict[int, list[str]]`` maps ``class_id``
            to per-class label lists, enabling correct labeling for
            datasets with multiple skeleton types.

    Returns:
        The annotated image, matching the type of `scene` (`numpy.ndarray`
            or `PIL.Image.Image`)

    Example:
        Single-skeleton example:

        ```pycon
        >>> import numpy as np
        >>> import supervision as sv
        >>> image = np.zeros((800, 800, 3), dtype=np.uint8)
        >>> key_points = sv.KeyPoints(
        ...     xy=np.array(
        ...         [[[400, 200], [300, 500], [500, 500]]],
        ...         dtype=np.float32,
        ...     ),
        ...     class_id=np.array([0]),
        ...     visible=np.array([[True, True, True]]),
        ... )
        >>> annotator = sv.VertexLabelAnnotator(
        ...     color=sv.Color.ROBOFLOW,
        ...     text_color=sv.Color.WHITE,
        ...     border_radius=5,
        ... )
        >>> result = annotator.annotate(
        ...     scene=image.copy(),
        ...     key_points=key_points,
        ...     labels=["head", "L-foot", "R-foot"],
        ... )

        ```

        Multi-skeleton example with per-class labels:

        ```pycon
        >>> import numpy as np
        >>> import supervision as sv
        >>> image = np.zeros((800, 800, 3), dtype=np.uint8)
        >>> key_points = sv.KeyPoints(
        ...     xy=np.array(
        ...         [[[400, 200], [300, 500], [500, 500]],
        ...          [[700, 300], [650, 500], [0, 0]]],
        ...         dtype=np.float32,
        ...     ),
        ...     class_id=np.array([0, 1]),
        ...     visible=np.array(
        ...         [[True, True, True],
        ...          [True, True, False]],
        ...     ),
        ... )
        >>> annotator = sv.VertexLabelAnnotator(
        ...     color=sv.Color.ROBOFLOW,
        ...     text_color=sv.Color.WHITE,
        ...     border_radius=5,
        ... )
        >>> result = annotator.annotate(
        ...     scene=image.copy(),
        ...     key_points=key_points,
        ...     labels={
        ...         0: ["head", "L-foot", "R-foot"],
        ...         1: ["top", "bottom", "pad"],
        ...     },
        ... )

        ```
    """
    assert isinstance(scene, np.ndarray)
    font = cv2.FONT_HERSHEY_SIMPLEX

    skeletons_count, points_count, _ = key_points.xy.shape
    if skeletons_count == 0:
        return scene

    all_anchors: list[tuple[int, int]] = []
    all_labels: list[str] = []
    all_colors: list[Color] = []
    all_text_colors: list[Color] = []

    for i in range(skeletons_count):
        xy = key_points.xy[i]

        class_id = (
            int(key_points.class_id[i]) if key_points.class_id is not None else None
        )
        instance_labels = self._resolve_labels(labels, points_count, class_id)
        instance_colors = self._resolve_color_list(self.color, points_count)
        instance_text_colors = self._resolve_color_list(
            self.text_color, points_count
        )

        for j in range(points_count):
            if key_points.visible is not None:
                if not key_points.visible[i, j]:
                    continue
            elif np.allclose(xy[j], 0):
                continue

            anchor = (int(xy[j][0]), int(xy[j][1]))
            all_anchors.append(anchor)
            all_labels.append(instance_labels[j])
            all_colors.append(instance_colors[j])
            all_text_colors.append(instance_text_colors[j])

    if not all_anchors:
        return scene

    xyxy = np.array(
        [
            self.get_text_bounding_box(
                text=label,
                font=font,
                text_scale=self.text_scale,
                text_thickness=self.text_thickness,
                center_coordinates=anchor,
            )
            for anchor, label in zip(all_anchors, all_labels)
        ]
    )
    xyxy_padded = pad_boxes(xyxy=xyxy, px=self.text_padding)

    if self.smart_position:
        xyxy_padded = spread_out_boxes(xyxy_padded)
        xyxy = pad_boxes(xyxy=xyxy_padded, px=-self.text_padding)

    for text, color, text_color, box, box_padded in zip(
        all_labels, all_colors, all_text_colors, xyxy, xyxy_padded
    ):
        draw_rounded_rectangle(
            scene=scene,
            rect=Rect.from_xyxy(box_padded),
            color=color,
            border_radius=self.border_radius,
        )
        cv2.putText(
            img=scene,
            text=text,
            org=(box[0], box[3]),
            fontFace=font,
            fontScale=self.text_scale,
            color=text_color.as_bgr(),
            thickness=self.text_thickness,
            lineType=cv2.LINE_AA,
        )

    return scene

VertexEllipseAreaAnnotator

supervision.key_points.annotators.VertexEllipseAreaAnnotator

Bases: _BaseVertexEllipseAnnotator

Draws filled semi-transparent covariance ellipses at multiple sigma levels around each keypoint, each ring in a different color. This produces a bullseye-like uncertainty visualization where inner rings represent higher probability density.

Warning

This annotator uses key_points.data["covariance"] with shape (N, K, 2, 2) in pixel coordinates.

Source code in src/supervision/key_points/annotators.py 
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
class VertexEllipseAreaAnnotator(_BaseVertexEllipseAnnotator):
    """
    Draws filled semi-transparent covariance ellipses at multiple sigma levels
    around each keypoint, each ring in a different color.  This produces a
    bullseye-like uncertainty visualization where inner rings represent higher
    probability density.

    !!! warning

        This annotator uses `key_points.data["covariance"]` with shape
        `(N, K, 2, 2)` in pixel coordinates.
    """

    def __init__(
        self,
        sigma: float | Sequence[float] = (1.0, 2.0, 3.0),
        color: Color | Sequence[Color] = (Color.GREEN, Color.YELLOW, Color.RED),
        opacity: float = 0.4,
        max_axis: float | None = None,
    ) -> None:
        """
        Args:
            sigma: Sigma multipliers for each ring, drawn from outermost to
                innermost.  Accepts a single float or a sequence of floats.
                Defaults to ``(1.0, 2.0, 3.0)``.
            color: The color for each sigma level.  Accepts a single
                ``Color`` or a sequence of colors (one per sigma level).
                Defaults to ``(Color.GREEN, Color.YELLOW, Color.RED)``.
            opacity: Opacity of the overlay mask. Must be between ``0`` and
                ``1``.
            max_axis: Optional cap for ellipse semi-axis lengths in pixels.
        """
        super().__init__(sigma=sigma, color=color, max_axis=max_axis)
        self.opacity = opacity

    @ensure_cv2_image_for_class_method
    def annotate(self, scene: ImageType, key_points: KeyPoints) -> ImageType:
        """
        Draws filled semi-transparent covariance ellipses around each keypoint.

        Args:
            scene: The image to annotate. ``ImageType`` accepts either
                ``numpy.ndarray`` or ``PIL.Image.Image``.
            key_points: Key points with covariance data in
                ``key_points.data["covariance"]``.

        Returns:
            The annotated image, matching the type of ``scene``.

        Example:
            ```pycon
            >>> import numpy as np
            >>> import supervision as sv
            >>> image = np.zeros((800, 800, 3), dtype=np.uint8)
            >>> key_points = sv.KeyPoints(
            ...     xy=np.array(
            ...         [[[400, 200], [300, 500], [500, 500]]],
            ...         dtype=np.float32,
            ...     ),
            ...     class_id=np.array([0]),
            ...     visible=np.array([[True, True, True]]),
            ...     data={
            ...         "covariance": np.array(
            ...             [[[[800, 0], [0, 400]],
            ...               [[400, 0], [0, 800]],
            ...               [[600, 0], [0, 600]]]],
            ...             dtype=np.float32,
            ...         )
            ...     },
            ... )
            >>> annotator = sv.VertexEllipseAreaAnnotator(
            ...     sigma=[1.0, 2.0],
            ...     color=[sv.Color.GREEN, sv.Color.RED],
            ... )
            >>> result = annotator.annotate(image.copy(), key_points)

            ```
        """
        assert isinstance(scene, np.ndarray)
        if len(key_points) == 0:
            return scene

        overlay = scene.copy()
        for level in self._iter_ellipse_params(key_points):
            for center, axis_lengths, angle, _sigma, color in level:
                cv2.ellipse(
                    img=overlay,
                    center=center,
                    axes=axis_lengths,
                    angle=angle,
                    startAngle=0,
                    endAngle=360,
                    color=color.as_bgr(),
                    thickness=-1,
                    lineType=cv2.LINE_AA,
                )

        cv2.addWeighted(overlay, self.opacity, scene, 1 - self.opacity, 0, dst=scene)
        return scene

Functions

__init__(sigma: float | Sequence[float] = (1.0, 2.0, 3.0), color: Color | Sequence[Color] = (Color.GREEN, Color.YELLOW, Color.RED), opacity: float = 0.4, max_axis: float | None = None) -> None

Parameters:

Name Type Description Default
sigma
float | Sequence[float]

Sigma multipliers for each ring, drawn from outermost to innermost. Accepts a single float or a sequence of floats. Defaults to (1.0, 2.0, 3.0).

 (1.0, 2.0, 3.0)
color
Color | Sequence[Color]

The color for each sigma level. Accepts a single Color or a sequence of colors (one per sigma level). Defaults to (Color.GREEN, Color.YELLOW, Color.RED).

 (GREEN, YELLOW, RED)
opacity
float

Opacity of the overlay mask. Must be between 0 and 1.

 0.4
max_axis
float | None

Optional cap for ellipse semi-axis lengths in pixels.

 None
Source code in src/supervision/key_points/annotators.py 
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
def __init__(
    self,
    sigma: float | Sequence[float] = (1.0, 2.0, 3.0),
    color: Color | Sequence[Color] = (Color.GREEN, Color.YELLOW, Color.RED),
    opacity: float = 0.4,
    max_axis: float | None = None,
) -> None:
    """
    Args:
        sigma: Sigma multipliers for each ring, drawn from outermost to
            innermost.  Accepts a single float or a sequence of floats.
            Defaults to ``(1.0, 2.0, 3.0)``.
        color: The color for each sigma level.  Accepts a single
            ``Color`` or a sequence of colors (one per sigma level).
            Defaults to ``(Color.GREEN, Color.YELLOW, Color.RED)``.
        opacity: Opacity of the overlay mask. Must be between ``0`` and
            ``1``.
        max_axis: Optional cap for ellipse semi-axis lengths in pixels.
    """
    super().__init__(sigma=sigma, color=color, max_axis=max_axis)
    self.opacity = opacity

annotate(scene: ImageType, key_points: KeyPoints) -> ImageType

Draws filled semi-transparent covariance ellipses around each keypoint.

Parameters:

Name Type Description Default
scene
ImageType

The image to annotate. ImageType accepts either numpy.ndarray or PIL.Image.Image.

 required
key_points
KeyPoints

Key points with covariance data in key_points.data["covariance"].

 required

Returns:

Type Description
ImageType

The annotated image, matching the type of scene.
Example 
>>> import numpy as np
>>> import supervision as sv
>>> image = np.zeros((800, 800, 3), dtype=np.uint8)
>>> key_points = sv.KeyPoints(
...     xy=np.array(
...         [[[400, 200], [300, 500], [500, 500]]],
...         dtype=np.float32,
...     ),
...     class_id=np.array([0]),
...     visible=np.array([[True, True, True]]),
...     data={
...         "covariance": np.array(
...             [[[[800, 0], [0, 400]],
...               [[400, 0], [0, 800]],
...               [[600, 0], [0, 600]]]],
...             dtype=np.float32,
...         )
...     },
... )
>>> annotator = sv.VertexEllipseAreaAnnotator(
...     sigma=[1.0, 2.0],
...     color=[sv.Color.GREEN, sv.Color.RED],
... )
>>> result = annotator.annotate(image.copy(), key_points)
Source code in src/supervision/key_points/annotators.py 
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
@ensure_cv2_image_for_class_method
def annotate(self, scene: ImageType, key_points: KeyPoints) -> ImageType:
    """
    Draws filled semi-transparent covariance ellipses around each keypoint.

    Args:
        scene: The image to annotate. ``ImageType`` accepts either
            ``numpy.ndarray`` or ``PIL.Image.Image``.
        key_points: Key points with covariance data in
            ``key_points.data["covariance"]``.

    Returns:
        The annotated image, matching the type of ``scene``.

    Example:
        ```pycon
        >>> import numpy as np
        >>> import supervision as sv
        >>> image = np.zeros((800, 800, 3), dtype=np.uint8)
        >>> key_points = sv.KeyPoints(
        ...     xy=np.array(
        ...         [[[400, 200], [300, 500], [500, 500]]],
        ...         dtype=np.float32,
        ...     ),
        ...     class_id=np.array([0]),
        ...     visible=np.array([[True, True, True]]),
        ...     data={
        ...         "covariance": np.array(
        ...             [[[[800, 0], [0, 400]],
        ...               [[400, 0], [0, 800]],
        ...               [[600, 0], [0, 600]]]],
        ...             dtype=np.float32,
        ...         )
        ...     },
        ... )
        >>> annotator = sv.VertexEllipseAreaAnnotator(
        ...     sigma=[1.0, 2.0],
        ...     color=[sv.Color.GREEN, sv.Color.RED],
        ... )
        >>> result = annotator.annotate(image.copy(), key_points)

        ```
    """
    assert isinstance(scene, np.ndarray)
    if len(key_points) == 0:
        return scene

    overlay = scene.copy()
    for level in self._iter_ellipse_params(key_points):
        for center, axis_lengths, angle, _sigma, color in level:
            cv2.ellipse(
                img=overlay,
                center=center,
                axes=axis_lengths,
                angle=angle,
                startAngle=0,
                endAngle=360,
                color=color.as_bgr(),
                thickness=-1,
                lineType=cv2.LINE_AA,
            )

    cv2.addWeighted(overlay, self.opacity, scene, 1 - self.opacity, 0, dst=scene)
    return scene

VertexEllipseOutlineAnnotator

supervision.key_points.annotators.VertexEllipseOutlineAnnotator

Bases: _BaseVertexEllipseAnnotator

Draws stroke-only concentric covariance ellipse rings at multiple sigma levels around each keypoint.

Warning

This annotator uses key_points.data["covariance"] with shape (N, K, 2, 2) in pixel coordinates.

Source code in src/supervision/key_points/annotators.py 
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
class VertexEllipseOutlineAnnotator(_BaseVertexEllipseAnnotator):
    """
    Draws stroke-only concentric covariance ellipse rings at multiple sigma
    levels around each keypoint.

    !!! warning

        This annotator uses `key_points.data["covariance"]` with shape
        `(N, K, 2, 2)` in pixel coordinates.
    """

    def __init__(
        self,
        sigma: float | Sequence[float] = (1.0, 2.0, 3.0),
        color: Color | Sequence[Color] = (Color.GREEN, Color.YELLOW, Color.RED),
        thickness: int = 2,
        max_axis: float | None = None,
    ) -> None:
        """
        Args:
            sigma: Sigma multipliers for each ring, drawn from outermost to
                innermost.  Accepts a single float or a sequence of floats.
                Defaults to ``(1.0, 2.0, 3.0)``.
            color: The color for each sigma level.  Accepts a single
                ``Color`` or a sequence of colors (one per sigma level).
                Defaults to ``(Color.GREEN, Color.YELLOW, Color.RED)``.
            thickness: Line thickness of the ellipse outlines.
            max_axis: Optional cap for ellipse semi-axis lengths in pixels.
        """
        super().__init__(sigma=sigma, color=color, max_axis=max_axis)
        self.thickness = thickness

    @ensure_cv2_image_for_class_method
    def annotate(self, scene: ImageType, key_points: KeyPoints) -> ImageType:
        """
        Draws stroke-only covariance ellipse outlines around each keypoint.

        Args:
            scene: The image to annotate. ``ImageType`` accepts either
                ``numpy.ndarray`` or ``PIL.Image.Image``.
            key_points: Key points with covariance data in
                ``key_points.data["covariance"]``.

        Returns:
            The annotated image, matching the type of ``scene``.

        Example:
            ```pycon
            >>> import numpy as np
            >>> import supervision as sv
            >>> image = np.zeros((800, 800, 3), dtype=np.uint8)
            >>> key_points = sv.KeyPoints(
            ...     xy=np.array(
            ...         [[[400, 200], [300, 500], [500, 500]]],
            ...         dtype=np.float32,
            ...     ),
            ...     class_id=np.array([0]),
            ...     visible=np.array([[True, True, True]]),
            ...     data={
            ...         "covariance": np.array(
            ...             [[[[800, 0], [0, 400]],
            ...               [[400, 0], [0, 800]],
            ...               [[600, 0], [0, 600]]]],
            ...             dtype=np.float32,
            ...         )
            ...     },
            ... )
            >>> annotator = sv.VertexEllipseOutlineAnnotator(
            ...     sigma=[1.0, 2.0],
            ...     color=[sv.Color.GREEN, sv.Color.RED],
            ...     thickness=2,
            ... )
            >>> result = annotator.annotate(image.copy(), key_points)

            ```
        """
        assert isinstance(scene, np.ndarray)
        if len(key_points) == 0:
            return scene

        for level in self._iter_ellipse_params(key_points):
            for center, axis_lengths, angle, _sigma, color in level:
                cv2.ellipse(
                    img=scene,
                    center=center,
                    axes=axis_lengths,
                    angle=angle,
                    startAngle=0,
                    endAngle=360,
                    color=color.as_bgr(),
                    thickness=self.thickness,
                    lineType=cv2.LINE_AA,
                )

        return scene

Functions

__init__(sigma: float | Sequence[float] = (1.0, 2.0, 3.0), color: Color | Sequence[Color] = (Color.GREEN, Color.YELLOW, Color.RED), thickness: int = 2, max_axis: float | None = None) -> None

Parameters:

Name Type Description Default
sigma
float | Sequence[float]

Sigma multipliers for each ring, drawn from outermost to innermost. Accepts a single float or a sequence of floats. Defaults to (1.0, 2.0, 3.0).

 (1.0, 2.0, 3.0)
color
Color | Sequence[Color]

The color for each sigma level. Accepts a single Color or a sequence of colors (one per sigma level). Defaults to (Color.GREEN, Color.YELLOW, Color.RED).

 (GREEN, YELLOW, RED)
thickness
int

Line thickness of the ellipse outlines.

 2
max_axis
float | None

Optional cap for ellipse semi-axis lengths in pixels.

 None
Source code in src/supervision/key_points/annotators.py 
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
def __init__(
    self,
    sigma: float | Sequence[float] = (1.0, 2.0, 3.0),
    color: Color | Sequence[Color] = (Color.GREEN, Color.YELLOW, Color.RED),
    thickness: int = 2,
    max_axis: float | None = None,
) -> None:
    """
    Args:
        sigma: Sigma multipliers for each ring, drawn from outermost to
            innermost.  Accepts a single float or a sequence of floats.
            Defaults to ``(1.0, 2.0, 3.0)``.
        color: The color for each sigma level.  Accepts a single
            ``Color`` or a sequence of colors (one per sigma level).
            Defaults to ``(Color.GREEN, Color.YELLOW, Color.RED)``.
        thickness: Line thickness of the ellipse outlines.
        max_axis: Optional cap for ellipse semi-axis lengths in pixels.
    """
    super().__init__(sigma=sigma, color=color, max_axis=max_axis)
    self.thickness = thickness

annotate(scene: ImageType, key_points: KeyPoints) -> ImageType

Draws stroke-only covariance ellipse outlines around each keypoint.

Parameters:

Name Type Description Default
scene
ImageType

The image to annotate. ImageType accepts either numpy.ndarray or PIL.Image.Image.

 required
key_points
KeyPoints

Key points with covariance data in key_points.data["covariance"].

 required

Returns:

Type Description
ImageType

The annotated image, matching the type of scene.
Example 
>>> import numpy as np
>>> import supervision as sv
>>> image = np.zeros((800, 800, 3), dtype=np.uint8)
>>> key_points = sv.KeyPoints(
...     xy=np.array(
...         [[[400, 200], [300, 500], [500, 500]]],
...         dtype=np.float32,
...     ),
...     class_id=np.array([0]),
...     visible=np.array([[True, True, True]]),
...     data={
...         "covariance": np.array(
...             [[[[800, 0], [0, 400]],
...               [[400, 0], [0, 800]],
...               [[600, 0], [0, 600]]]],
...             dtype=np.float32,
...         )
...     },
... )
>>> annotator = sv.VertexEllipseOutlineAnnotator(
...     sigma=[1.0, 2.0],
...     color=[sv.Color.GREEN, sv.Color.RED],
...     thickness=2,
... )
>>> result = annotator.annotate(image.copy(), key_points)
Source code in src/supervision/key_points/annotators.py 
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
@ensure_cv2_image_for_class_method
def annotate(self, scene: ImageType, key_points: KeyPoints) -> ImageType:
    """
    Draws stroke-only covariance ellipse outlines around each keypoint.

    Args:
        scene: The image to annotate. ``ImageType`` accepts either
            ``numpy.ndarray`` or ``PIL.Image.Image``.
        key_points: Key points with covariance data in
            ``key_points.data["covariance"]``.

    Returns:
        The annotated image, matching the type of ``scene``.

    Example:
        ```pycon
        >>> import numpy as np
        >>> import supervision as sv
        >>> image = np.zeros((800, 800, 3), dtype=np.uint8)
        >>> key_points = sv.KeyPoints(
        ...     xy=np.array(
        ...         [[[400, 200], [300, 500], [500, 500]]],
        ...         dtype=np.float32,
        ...     ),
        ...     class_id=np.array([0]),
        ...     visible=np.array([[True, True, True]]),
        ...     data={
        ...         "covariance": np.array(
        ...             [[[[800, 0], [0, 400]],
        ...               [[400, 0], [0, 800]],
        ...               [[600, 0], [0, 600]]]],
        ...             dtype=np.float32,
        ...         )
        ...     },
        ... )
        >>> annotator = sv.VertexEllipseOutlineAnnotator(
        ...     sigma=[1.0, 2.0],
        ...     color=[sv.Color.GREEN, sv.Color.RED],
        ...     thickness=2,
        ... )
        >>> result = annotator.annotate(image.copy(), key_points)

        ```
    """
    assert isinstance(scene, np.ndarray)
    if len(key_points) == 0:
        return scene

    for level in self._iter_ellipse_params(key_points):
        for center, axis_lengths, angle, _sigma, color in level:
            cv2.ellipse(
                img=scene,
                center=center,
                axes=axis_lengths,
                angle=angle,
                startAngle=0,
                endAngle=360,
                color=color.as_bgr(),
                thickness=self.thickness,
                lineType=cv2.LINE_AA,
            )

    return scene

VertexEllipseHaloAnnotator

supervision.key_points.annotators.VertexEllipseHaloAnnotator

Bases: _BaseVertexEllipseAnnotator

Draws filled covariance ellipses with a radial fade: full opacity at the center, smoothly falling off to zero at the ellipse boundary. The falloff follows a power curve controlled by decay, producing a soft glow that is strongest near the keypoint.

Warning

This annotator uses key_points.data["covariance"] with shape (N, K, 2, 2) in pixel coordinates.

Source code in src/supervision/key_points/annotators.py 
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
class VertexEllipseHaloAnnotator(_BaseVertexEllipseAnnotator):
    """
    Draws filled covariance ellipses with a radial fade: full opacity at the
    center, smoothly falling off to zero at the ellipse boundary.  The falloff
    follows a power curve controlled by ``decay``, producing a soft glow that
    is strongest near the keypoint.

    !!! warning

        This annotator uses `key_points.data["covariance"]` with shape
        `(N, K, 2, 2)` in pixel coordinates.
    """

    _DECAY: float = 2.0

    def __init__(
        self,
        sigma: float | Sequence[float] = (1.0, 2.0, 3.0),
        color: Color | Sequence[Color] = (Color.GREEN, Color.YELLOW, Color.RED),
        opacity: float = 0.6,
        max_axis: float | None = None,
    ) -> None:
        """
        Args:
            sigma: Sigma multipliers for each ring, drawn from outermost to
                innermost.  Accepts a single float or a sequence of floats.
                Defaults to ``(1.0, 2.0, 3.0)``.
            color: The color for each sigma level.  Accepts a single
                ``Color`` or a sequence of colors (one per sigma level).
                Defaults to ``(Color.GREEN, Color.YELLOW, Color.RED)``.
            opacity: Peak opacity at the ellipse center. Must be between ``0``
                and ``1``.
            max_axis: Optional cap for ellipse semi-axis lengths in pixels.
        """
        super().__init__(sigma=sigma, color=color, max_axis=max_axis)
        self.opacity = opacity

    @ensure_cv2_image_for_class_method
    def annotate(self, scene: ImageType, key_points: KeyPoints) -> ImageType:
        """
        Draws radially-fading covariance ellipses around each keypoint.

        Args:
            scene: The image to annotate. ``ImageType`` accepts either
                ``numpy.ndarray`` or ``PIL.Image.Image``.
            key_points: Key points with covariance data in
                ``key_points.data["covariance"]``.

        Returns:
            The annotated image, matching the type of ``scene``.

        Example:
            ```pycon
            >>> import numpy as np
            >>> import supervision as sv
            >>> image = np.zeros((800, 800, 3), dtype=np.uint8)
            >>> key_points = sv.KeyPoints(
            ...     xy=np.array(
            ...         [[[400, 200], [300, 500], [500, 500]]],
            ...         dtype=np.float32,
            ...     ),
            ...     class_id=np.array([0]),
            ...     visible=np.array([[True, True, True]]),
            ...     data={
            ...         "covariance": np.array(
            ...             [[[[800, 0], [0, 400]],
            ...               [[400, 0], [0, 800]],
            ...               [[600, 0], [0, 600]]]],
            ...             dtype=np.float32,
            ...         )
            ...     },
            ... )
            >>> annotator = sv.VertexEllipseHaloAnnotator(
            ...     sigma=[1.0, 2.0],
            ...     color=[sv.Color.GREEN, sv.Color.RED],
            ... )
            >>> result = annotator.annotate(image.copy(), key_points)

            ```
        """
        assert isinstance(scene, np.ndarray)
        if len(key_points) == 0:
            return scene

        h, w = scene.shape[:2]
        composite: npt.NDArray[np.float32] = scene.astype(np.float32)

        for level in self._iter_ellipse_params(key_points):
            for center, axis_lengths, angle, _sigma, color in level:
                ax, ay = axis_lengths
                if ax == 0 or ay == 0:
                    continue

                pad = 2
                roi_half_w = ax + pad
                roi_half_h = ay + pad
                cx, cy = center

                x_min = max(cx - roi_half_w, 0)
                x_max = min(cx + roi_half_w, w)
                y_min = max(cy - roi_half_h, 0)
                y_max = min(cy + roi_half_h, h)
                if x_min >= x_max or y_min >= y_max:
                    continue

                ys = np.arange(y_min, y_max, dtype=np.float32) - cy
                xs = np.arange(x_min, x_max, dtype=np.float32) - cx
                grid_x, grid_y = np.meshgrid(xs, ys)

                angle_rad = np.radians(-angle)
                cos_a = np.cos(angle_rad)
                sin_a = np.sin(angle_rad)
                rx = grid_x * cos_a - grid_y * sin_a
                ry = grid_x * sin_a + grid_y * cos_a

                dist_sq = (rx / ax) ** 2 + (ry / ay) ** 2
                inside = dist_sq <= 1.0

                falloff = np.zeros_like(dist_sq)
                falloff[inside] = (1.0 - dist_sq[inside]) ** self._DECAY

                scaled_alpha = falloff * self.opacity

                bgr = np.array(color.as_bgr(), dtype=np.float32)
                roi = composite[y_min:y_max, x_min:x_max]
                alpha_3 = scaled_alpha[:, :, np.newaxis]
                roi[:] = roi * (1 - alpha_3) + bgr * alpha_3

        np.copyto(scene, composite.astype(np.uint8))
        return scene

Functions

__init__(sigma: float | Sequence[float] = (1.0, 2.0, 3.0), color: Color | Sequence[Color] = (Color.GREEN, Color.YELLOW, Color.RED), opacity: float = 0.6, max_axis: float | None = None) -> None

Parameters:

Name Type Description Default
sigma
float | Sequence[float]

Sigma multipliers for each ring, drawn from outermost to innermost. Accepts a single float or a sequence of floats. Defaults to (1.0, 2.0, 3.0).

 (1.0, 2.0, 3.0)
color
Color | Sequence[Color]

The color for each sigma level. Accepts a single Color or a sequence of colors (one per sigma level). Defaults to (Color.GREEN, Color.YELLOW, Color.RED).

 (GREEN, YELLOW, RED)
opacity
float

Peak opacity at the ellipse center. Must be between 0 and 1.

 0.6
max_axis
float | None

Optional cap for ellipse semi-axis lengths in pixels.

 None
Source code in src/supervision/key_points/annotators.py 
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
def __init__(
    self,
    sigma: float | Sequence[float] = (1.0, 2.0, 3.0),
    color: Color | Sequence[Color] = (Color.GREEN, Color.YELLOW, Color.RED),
    opacity: float = 0.6,
    max_axis: float | None = None,
) -> None:
    """
    Args:
        sigma: Sigma multipliers for each ring, drawn from outermost to
            innermost.  Accepts a single float or a sequence of floats.
            Defaults to ``(1.0, 2.0, 3.0)``.
        color: The color for each sigma level.  Accepts a single
            ``Color`` or a sequence of colors (one per sigma level).
            Defaults to ``(Color.GREEN, Color.YELLOW, Color.RED)``.
        opacity: Peak opacity at the ellipse center. Must be between ``0``
            and ``1``.
        max_axis: Optional cap for ellipse semi-axis lengths in pixels.
    """
    super().__init__(sigma=sigma, color=color, max_axis=max_axis)
    self.opacity = opacity

annotate(scene: ImageType, key_points: KeyPoints) -> ImageType

Draws radially-fading covariance ellipses around each keypoint.

Parameters:

Name Type Description Default
scene
ImageType

The image to annotate. ImageType accepts either numpy.ndarray or PIL.Image.Image.

 required
key_points
KeyPoints

Key points with covariance data in key_points.data["covariance"].

 required

Returns:

Type Description
ImageType

The annotated image, matching the type of scene.
Example 
>>> import numpy as np
>>> import supervision as sv
>>> image = np.zeros((800, 800, 3), dtype=np.uint8)
>>> key_points = sv.KeyPoints(
...     xy=np.array(
...         [[[400, 200], [300, 500], [500, 500]]],
...         dtype=np.float32,
...     ),
...     class_id=np.array([0]),
...     visible=np.array([[True, True, True]]),
...     data={
...         "covariance": np.array(
...             [[[[800, 0], [0, 400]],
...               [[400, 0], [0, 800]],
...               [[600, 0], [0, 600]]]],
...             dtype=np.float32,
...         )
...     },
... )
>>> annotator = sv.VertexEllipseHaloAnnotator(
...     sigma=[1.0, 2.0],
...     color=[sv.Color.GREEN, sv.Color.RED],
... )
>>> result = annotator.annotate(image.copy(), key_points)
Source code in src/supervision/key_points/annotators.py 
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
@ensure_cv2_image_for_class_method
def annotate(self, scene: ImageType, key_points: KeyPoints) -> ImageType:
    """
    Draws radially-fading covariance ellipses around each keypoint.

    Args:
        scene: The image to annotate. ``ImageType`` accepts either
            ``numpy.ndarray`` or ``PIL.Image.Image``.
        key_points: Key points with covariance data in
            ``key_points.data["covariance"]``.

    Returns:
        The annotated image, matching the type of ``scene``.

    Example:
        ```pycon
        >>> import numpy as np
        >>> import supervision as sv
        >>> image = np.zeros((800, 800, 3), dtype=np.uint8)
        >>> key_points = sv.KeyPoints(
        ...     xy=np.array(
        ...         [[[400, 200], [300, 500], [500, 500]]],
        ...         dtype=np.float32,
        ...     ),
        ...     class_id=np.array([0]),
        ...     visible=np.array([[True, True, True]]),
        ...     data={
        ...         "covariance": np.array(
        ...             [[[[800, 0], [0, 400]],
        ...               [[400, 0], [0, 800]],
        ...               [[600, 0], [0, 600]]]],
        ...             dtype=np.float32,
        ...         )
        ...     },
        ... )
        >>> annotator = sv.VertexEllipseHaloAnnotator(
        ...     sigma=[1.0, 2.0],
        ...     color=[sv.Color.GREEN, sv.Color.RED],
        ... )
        >>> result = annotator.annotate(image.copy(), key_points)

        ```
    """
    assert isinstance(scene, np.ndarray)
    if len(key_points) == 0:
        return scene

    h, w = scene.shape[:2]
    composite: npt.NDArray[np.float32] = scene.astype(np.float32)

    for level in self._iter_ellipse_params(key_points):
        for center, axis_lengths, angle, _sigma, color in level:
            ax, ay = axis_lengths
            if ax == 0 or ay == 0:
                continue

            pad = 2
            roi_half_w = ax + pad
            roi_half_h = ay + pad
            cx, cy = center

            x_min = max(cx - roi_half_w, 0)
            x_max = min(cx + roi_half_w, w)
            y_min = max(cy - roi_half_h, 0)
            y_max = min(cy + roi_half_h, h)
            if x_min >= x_max or y_min >= y_max:
                continue

            ys = np.arange(y_min, y_max, dtype=np.float32) - cy
            xs = np.arange(x_min, x_max, dtype=np.float32) - cx
            grid_x, grid_y = np.meshgrid(xs, ys)

            angle_rad = np.radians(-angle)
            cos_a = np.cos(angle_rad)
            sin_a = np.sin(angle_rad)
            rx = grid_x * cos_a - grid_y * sin_a
            ry = grid_x * sin_a + grid_y * cos_a

            dist_sq = (rx / ax) ** 2 + (ry / ay) ** 2
            inside = dist_sq <= 1.0

            falloff = np.zeros_like(dist_sq)
            falloff[inside] = (1.0 - dist_sq[inside]) ** self._DECAY

            scaled_alpha = falloff * self.opacity

            bgr = np.array(color.as_bgr(), dtype=np.float32)
            roi = composite[y_min:y_max, x_min:x_max]
            alpha_3 = scaled_alpha[:, :, np.newaxis]
            roi[:] = roi * (1 - alpha_3) + bgr * alpha_3

    np.copyto(scene, composite.astype(np.uint8))
    return scene

Comments