Utils

box_iou_batch

Compute Intersection over Union (IoU) of two sets of bounding boxes - boxes_true and boxes_detection. Both sets of boxes are expected to be in (x_min, y_min, x_max, y_max) format.

Parameters:

Name	Type	Description	Default
boxes_true	ndarray	2D np.ndarray representing ground-truth boxes. shape = (N, 4) where N is number of true objects.	required
boxes_detection	ndarray	2D np.ndarray representing detection boxes. shape = (M, 4) where M is number of detected objects.	required

Returns:

Type	Description
ndarray	np.ndarray: Pairwise IoU of boxes from boxes_true and boxes_detection. shape = (N, M) where N is number of true objects and M is number of detected objects.

Source code in supervision/detection/utils.py

def box_iou_batch(boxes_true: np.ndarray, boxes_detection: np.ndarray) -> np.ndarray:
    """
    Compute Intersection over Union (IoU) of two sets of bounding boxes - `boxes_true` and `boxes_detection`. Both sets
    of boxes are expected to be in `(x_min, y_min, x_max, y_max)` format.

    Args:
        boxes_true (np.ndarray): 2D `np.ndarray` representing ground-truth boxes. `shape = (N, 4)` where `N` is number of true objects.
        boxes_detection (np.ndarray): 2D `np.ndarray` representing detection boxes. `shape = (M, 4)` where `M` is number of detected objects.

    Returns:
        np.ndarray: Pairwise IoU of boxes from `boxes_true` and `boxes_detection`. `shape = (N, M)` where `N` is number of true objects and `M` is number of detected objects.
    """

    def box_area(box):
        return (box[2] - box[0]) * (box[3] - box[1])

    area_true = box_area(boxes_true.T)
    area_detection = box_area(boxes_detection.T)

    top_left = np.maximum(boxes_true[:, None, :2], boxes_detection[:, :2])
    bottom_right = np.minimum(boxes_true[:, None, 2:], boxes_detection[:, 2:])

    area_inter = np.prod(np.clip(bottom_right - top_left, a_min=0, a_max=None), 2)
    return area_inter / (area_true[:, None] + area_detection - area_inter)

non_max_suppression

Perform Non-Maximum Suppression (NMS) on object detection predictions.

Parameters:

Name	Type	Description	Default
predictions	ndarray	An array of object detection predictions in the format of (x_min, y_min, x_max, y_max, score) or (x_min, y_min, x_max, y_max, score, class).	required
iou_threshold	float	The intersection-over-union threshold to use for non-maximum suppression.	0.5

Returns:

Type	Description
ndarray	np.ndarray: A boolean array indicating which predictions to keep after non-maximum suppression.

Raises:

Type	Description
AssertionError	If iou_threshold is not within the closed range from 0 to 1.

Source code in supervision/detection/utils.py

def non_max_suppression(
    predictions: np.ndarray, iou_threshold: float = 0.5
) -> np.ndarray:
    """
    Perform Non-Maximum Suppression (NMS) on object detection predictions.

    Args:
        predictions (np.ndarray): An array of object detection predictions in the format of `(x_min, y_min, x_max, y_max, score)` or `(x_min, y_min, x_max, y_max, score, class)`.
        iou_threshold (float, optional): The intersection-over-union threshold to use for non-maximum suppression.

    Returns:
        np.ndarray: A boolean array indicating which predictions to keep after non-maximum suppression.

    Raises:
        AssertionError: If `iou_threshold` is not within the closed range from `0` to `1`.
    """
    assert 0 <= iou_threshold <= 1, (
        f"Value of `iou_threshold` must be in the closed range from 0 to 1, "
        f"{iou_threshold} given."
    )
    rows, columns = predictions.shape

    # add column #5 - category filled with zeros for agnostic nms
    if columns == 5:
        predictions = np.c_[predictions, np.zeros(rows)]

    # sort predictions column #4 - score
    sort_index = np.flip(predictions[:, 4].argsort())
    predictions = predictions[sort_index]

    boxes = predictions[:, :4]
    categories = predictions[:, 5]
    ious = box_iou_batch(boxes, boxes)
    ious = ious - np.eye(rows)

    keep = np.ones(rows, dtype=bool)

    for index, (iou, category) in enumerate(zip(ious, categories)):
        if not keep[index]:
            continue

        # drop detections with iou > iou_threshold and same category as current detections
        condition = (iou > iou_threshold) & (categories == category)
        keep = keep & ~condition

    return keep[sort_index.argsort()]

polygon_to_mask

Generate a mask from a polygon.

Parameters:

Name	Type	Description	Default
polygon	ndarray	The polygon for which the mask should be generated, given as a list of vertices.	required
resolution_wh	Tuple[int, int]	The width and height of the desired resolution.	required

Returns:

Type	Description
ndarray	np.ndarray: The generated 2D mask, where the polygon is marked with 1's and the rest is filled with 0's.

Source code in supervision/detection/utils.py

def polygon_to_mask(polygon: np.ndarray, resolution_wh: Tuple[int, int]) -> np.ndarray:
    """Generate a mask from a polygon.

    Args:
        polygon (np.ndarray): The polygon for which the mask should be generated, given as a list of vertices.
        resolution_wh (Tuple[int, int]): The width and height of the desired resolution.

    Returns:
        np.ndarray: The generated 2D mask, where the polygon is marked with `1`'s and the rest is filled with `0`'s.
    """
    width, height = resolution_wh
    mask = np.zeros((height, width), dtype=np.uint8)
    cv2.fillPoly(mask, [polygon], color=1)
    return mask

mask_to_xyxy

Converts a 3D np.array of 2D bool masks into a 2D np.array of bounding boxes.

Parameters:

Name	Type	Description	Default
masks	ndarray	A 3D np.array of shape (N, W, H) containing 2D bool masks	required

Returns:

Type	Description
ndarray	np.ndarray: A 2D np.array of shape (N, 4) containing the bounding boxes (x_min, y_min, x_max, y_max) for each mask

Source code in supervision/detection/utils.py

def mask_to_xyxy(masks: np.ndarray) -> np.ndarray:
    """
    Converts a 3D `np.array` of 2D bool masks into a 2D `np.array` of bounding boxes.

    Parameters:
        masks (np.ndarray): A 3D `np.array` of shape `(N, W, H)` containing 2D bool masks

    Returns:
        np.ndarray: A 2D `np.array` of shape `(N, 4)` containing the bounding boxes `(x_min, y_min, x_max, y_max)` for each mask
    """
    n = masks.shape[0]
    bboxes = np.zeros((n, 4), dtype=int)

    for i, mask in enumerate(masks):
        rows, cols = np.where(mask)

        if len(rows) > 0 and len(cols) > 0:
            x_min, x_max = np.min(cols), np.max(cols)
            y_min, y_max = np.min(rows), np.max(rows)
            bboxes[i, :] = [x_min, y_min, x_max, y_max]

    return bboxes

mask_to_polygons

Converts a binary mask to a list of polygons.

Parameters:

Name	Type	Description	Default
mask	ndarray	A binary mask represented as a 2D NumPy array of shape (H, W), where H and W are the height and width of the mask, respectively.	required

Returns:

Type	Description
List[ndarray]	List[np.ndarray]: A list of polygons, where each polygon is represented by a NumPy array of shape (N, 2), containing the x, y coordinates of the points. Polygons with fewer points than MIN_POLYGON_POINT_COUNT = 3 are excluded from the output.

Source code in supervision/detection/utils.py

def mask_to_polygons(mask: np.ndarray) -> List[np.ndarray]:
    """
    Converts a binary mask to a list of polygons.

    Parameters:
        mask (np.ndarray): A binary mask represented as a 2D NumPy array of shape `(H, W)`,
            where H and W are the height and width of the mask, respectively.

    Returns:
        List[np.ndarray]: A list of polygons, where each polygon is represented by a NumPy array of shape `(N, 2)`,
            containing the `x`, `y` coordinates of the points. Polygons with fewer points than `MIN_POLYGON_POINT_COUNT = 3`
            are excluded from the output.
    """

    contours, _ = cv2.findContours(
        mask.astype(np.uint8), cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE
    )
    return [
        np.squeeze(contour, axis=1)
        for contour in contours
        if contour.shape[0] >= MIN_POLYGON_POINT_COUNT
    ]

polygon_to_xyxy

Converts a polygon represented by a NumPy array into a bounding box.

Parameters:

Name	Type	Description	Default
polygon	ndarray	A polygon represented by a NumPy array of shape (N, 2), containing the x, y coordinates of the points.	required

Returns:

Type	Description
ndarray	np.ndarray: A 1D NumPy array containing the bounding box (x_min, y_min, x_max, y_max) of the input polygon.

Source code in supervision/detection/utils.py

def polygon_to_xyxy(polygon: np.ndarray) -> np.ndarray:
    """
    Converts a polygon represented by a NumPy array into a bounding box.

    Parameters:
        polygon (np.ndarray): A polygon represented by a NumPy array of shape `(N, 2)`,
            containing the `x`, `y` coordinates of the points.

    Returns:
        np.ndarray: A 1D NumPy array containing the bounding box `(x_min, y_min, x_max, y_max)` of the input polygon.
    """
    x_min, y_min = np.min(polygon, axis=0)
    x_max, y_max = np.max(polygon, axis=0)
    return np.array([x_min, y_min, x_max, y_max])

filter_polygons_by_area

Filters a list of polygons based on their area.

Parameters:

Name	Type	Description	Default
polygons	List[ndarray]	A list of polygons, where each polygon is represented by a NumPy array of shape (N, 2), containing the x, y coordinates of the points.	required
min_area	Optional[float]	The minimum area threshold. Only polygons with an area greater than or equal to this value will be included in the output. If set to None, no minimum area constraint will be applied.	None
max_area	Optional[float]	The maximum area threshold. Only polygons with an area less than or equal to this value will be included in the output. If set to None, no maximum area constraint will be applied.	None

Returns:

Type	Description
List[ndarray]	List[np.ndarray]: A new list of polygons containing only those with areas within the specified thresholds.

Source code in supervision/detection/utils.py

def filter_polygons_by_area(
    polygons: List[np.ndarray],
    min_area: Optional[float] = None,
    max_area: Optional[float] = None,
) -> List[np.ndarray]:
    """
    Filters a list of polygons based on their area.

    Parameters:
        polygons (List[np.ndarray]): A list of polygons, where each polygon is represented by a NumPy array of shape `(N, 2)`,
            containing the `x`, `y` coordinates of the points.
        min_area (Optional[float]): The minimum area threshold. Only polygons with an area greater than or equal to this value
            will be included in the output. If set to None, no minimum area constraint will be applied.
        max_area (Optional[float]): The maximum area threshold. Only polygons with an area less than or equal to this value
            will be included in the output. If set to None, no maximum area constraint will be applied.

    Returns:
        List[np.ndarray]: A new list of polygons containing only those with areas within the specified thresholds.
    """
    if min_area is None and max_area is None:
        return polygons
    ares = [cv2.contourArea(polygon) for polygon in polygons]
    return [
        polygon
        for polygon, area in zip(polygons, ares)
        if (min_area is None or area >= min_area)
        and (max_area is None or area <= max_area)
    ]