Skip to content

Trackers

ByteTrack

Initialize the ByteTrack object.

Parameters:

Name Type Description Default
track_thresh float

Detection confidence threshold for track activation.

0.25
track_buffer int

Number of frames to buffer when a track is lost.

30
match_thresh float

Threshold for matching tracks with detections.

0.8
frame_rate int

The frame rate of the video.

30
Source code in supervision/tracker/byte_tracker/core.py
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
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
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
class ByteTrack:
    """
    Initialize the ByteTrack object.

    Parameters:
        track_thresh (float, optional): Detection confidence threshold
            for track activation.
        track_buffer (int, optional): Number of frames to buffer when a track is lost.
        match_thresh (float, optional): Threshold for matching tracks with detections.
        frame_rate (int, optional): The frame rate of the video.
    """

    def __init__(
        self,
        track_thresh: float = 0.25,
        track_buffer: int = 30,
        match_thresh: float = 0.8,
        frame_rate: int = 30,
    ):
        self.track_thresh = track_thresh
        self.match_thresh = match_thresh

        self.frame_id = 0
        self.det_thresh = self.track_thresh + 0.1
        self.max_time_lost = int(frame_rate / 30.0 * track_buffer)
        self.kalman_filter = KalmanFilter()

        self.tracked_tracks: List[STrack] = []
        self.lost_tracks: List[STrack] = []
        self.removed_tracks: List[STrack] = []

    def update_with_detections(self, detections: Detections) -> Detections:
        """
        Updates the tracker with the provided detections and
            returns the updated detection results.

        Parameters:
            detections: The new detections to update with.
        Returns:
            Detection: The updated detection results that now include tracking IDs.
        Example:
            ```python
            >>> import supervision as sv
            >>> from ultralytics import YOLO

            >>> model = YOLO(...)
            >>> byte_tracker = sv.ByteTrack()
            >>> annotator = sv.BoxAnnotator()

            >>> def callback(frame: np.ndarray, index: int) -> np.ndarray:
            ...     results = model(frame)[0]
            ...     detections = sv.Detections.from_ultralytics(results)
            ...     detections = byte_tracker.update_with_detections(detections)
            ...     labels = [
            ...         f"#{tracker_id} {model.model.names[class_id]} {confidence:0.2f}"
            ...         for _, _, confidence, class_id, tracker_id
            ...         in detections
            ...     ]
            ...     return annotator.annotate(scene=frame.copy(),
            ...                               detections=detections, labels=labels)

            >>> sv.process_video(
            ...     source_path='...',
            ...     target_path='...',
            ...     callback=callback
            ... )
            ```
        """

        tracks = self.update_with_tensors(
            tensors=detections2boxes(detections=detections)
        )
        detections = Detections.empty()
        if len(tracks) > 0:
            detections.xyxy = np.array(
                [track.tlbr for track in tracks], dtype=np.float32
            )
            detections.class_id = np.array(
                [int(t.class_ids) for t in tracks], dtype=int
            )
            detections.tracker_id = np.array(
                [int(t.track_id) for t in tracks], dtype=int
            )
            detections.confidence = np.array(
                [t.score for t in tracks], dtype=np.float32
            )

        return detections

    def update_with_tensors(self, tensors: np.ndarray) -> List[STrack]:
        """
        Updates the tracker with the provided tensors and returns the updated tracks.

        Parameters:
            tensors: The new tensors to update with.

        Returns:
            List[STrack]: Updated tracks.
        """
        self.frame_id += 1
        activated_starcks = []
        refind_stracks = []
        lost_stracks = []
        removed_stracks = []

        class_ids = tensors[:, 5]
        scores = tensors[:, 4]
        bboxes = tensors[:, :4]

        remain_inds = scores > self.track_thresh
        inds_low = scores > 0.1
        inds_high = scores < self.track_thresh

        inds_second = np.logical_and(inds_low, inds_high)
        dets_second = bboxes[inds_second]
        dets = bboxes[remain_inds]
        scores_keep = scores[remain_inds]
        scores_second = scores[inds_second]

        class_ids_keep = class_ids[remain_inds]
        class_ids_second = class_ids[inds_second]

        if len(dets) > 0:
            """Detections"""
            detections = [
                STrack(STrack.tlbr_to_tlwh(tlbr), s, c)
                for (tlbr, s, c) in zip(dets, scores_keep, class_ids_keep)
            ]
        else:
            detections = []

        """ Add newly detected tracklets to tracked_stracks"""
        unconfirmed = []
        tracked_stracks = []  # type: list[STrack]
        for track in self.tracked_tracks:
            if not track.is_activated:
                unconfirmed.append(track)
            else:
                tracked_stracks.append(track)

        """ Step 2: First association, with high score detection boxes"""
        strack_pool = joint_tracks(tracked_stracks, self.lost_tracks)
        # Predict the current location with KF
        STrack.multi_predict(strack_pool)
        dists = matching.iou_distance(strack_pool, detections)

        dists = matching.fuse_score(dists, detections)
        matches, u_track, u_detection = matching.linear_assignment(
            dists, thresh=self.match_thresh
        )

        for itracked, idet in matches:
            track = strack_pool[itracked]
            det = detections[idet]
            if track.state == TrackState.Tracked:
                track.update(detections[idet], self.frame_id)
                activated_starcks.append(track)
            else:
                track.re_activate(det, self.frame_id, new_id=False)
                refind_stracks.append(track)

        """ Step 3: Second association, with low score detection boxes"""
        # association the untrack to the low score detections
        if len(dets_second) > 0:
            """Detections"""
            detections_second = [
                STrack(STrack.tlbr_to_tlwh(tlbr), s, c)
                for (tlbr, s, c) in zip(dets_second, scores_second, class_ids_second)
            ]
        else:
            detections_second = []
        r_tracked_stracks = [
            strack_pool[i]
            for i in u_track
            if strack_pool[i].state == TrackState.Tracked
        ]
        dists = matching.iou_distance(r_tracked_stracks, detections_second)
        matches, u_track, u_detection_second = matching.linear_assignment(
            dists, thresh=0.5
        )
        for itracked, idet in matches:
            track = r_tracked_stracks[itracked]
            det = detections_second[idet]
            if track.state == TrackState.Tracked:
                track.update(det, self.frame_id)
                activated_starcks.append(track)
            else:
                track.re_activate(det, self.frame_id, new_id=False)
                refind_stracks.append(track)

        for it in u_track:
            track = r_tracked_stracks[it]
            if not track.state == TrackState.Lost:
                track.mark_lost()
                lost_stracks.append(track)

        """Deal with unconfirmed tracks, usually tracks with only one beginning frame"""
        detections = [detections[i] for i in u_detection]
        dists = matching.iou_distance(unconfirmed, detections)

        dists = matching.fuse_score(dists, detections)
        matches, u_unconfirmed, u_detection = matching.linear_assignment(
            dists, thresh=0.7
        )
        for itracked, idet in matches:
            unconfirmed[itracked].update(detections[idet], self.frame_id)
            activated_starcks.append(unconfirmed[itracked])
        for it in u_unconfirmed:
            track = unconfirmed[it]
            track.mark_removed()
            removed_stracks.append(track)

        """ Step 4: Init new stracks"""
        for inew in u_detection:
            track = detections[inew]
            if track.score < self.det_thresh:
                continue
            track.activate(self.kalman_filter, self.frame_id)
            activated_starcks.append(track)
        """ Step 5: Update state"""
        for track in self.lost_tracks:
            if self.frame_id - track.end_frame > self.max_time_lost:
                track.mark_removed()
                removed_stracks.append(track)

        self.tracked_tracks = [
            t for t in self.tracked_tracks if t.state == TrackState.Tracked
        ]
        self.tracked_tracks = joint_tracks(self.tracked_tracks, activated_starcks)
        self.tracked_tracks = joint_tracks(self.tracked_tracks, refind_stracks)
        self.lost_tracks = sub_tracks(self.lost_tracks, self.tracked_tracks)
        self.lost_tracks.extend(lost_stracks)
        self.lost_tracks = sub_tracks(self.lost_tracks, self.removed_tracks)
        self.removed_tracks.extend(removed_stracks)
        self.tracked_tracks, self.lost_tracks = remove_duplicate_tracks(
            self.tracked_tracks, self.lost_tracks
        )
        output_stracks = [track for track in self.tracked_tracks if track.is_activated]

        return output_stracks

update_with_detections(detections)

Updates the tracker with the provided detections and returns the updated detection results.

Parameters:

Name Type Description Default
detections Detections

The new detections to update with.

required

Returns: Detection: The updated detection results that now include tracking IDs. Example:

>>> import supervision as sv
>>> from ultralytics import YOLO

>>> model = YOLO(...)
>>> byte_tracker = sv.ByteTrack()
>>> annotator = sv.BoxAnnotator()

>>> def callback(frame: np.ndarray, index: int) -> np.ndarray:
...     results = model(frame)[0]
...     detections = sv.Detections.from_ultralytics(results)
...     detections = byte_tracker.update_with_detections(detections)
...     labels = [
...         f"#{tracker_id} {model.model.names[class_id]} {confidence:0.2f}"
...         for _, _, confidence, class_id, tracker_id
...         in detections
...     ]
...     return annotator.annotate(scene=frame.copy(),
...                               detections=detections, labels=labels)

>>> sv.process_video(
...     source_path='...',
...     target_path='...',
...     callback=callback
... )

Source code in supervision/tracker/byte_tracker/core.py
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
def update_with_detections(self, detections: Detections) -> Detections:
    """
    Updates the tracker with the provided detections and
        returns the updated detection results.

    Parameters:
        detections: The new detections to update with.
    Returns:
        Detection: The updated detection results that now include tracking IDs.
    Example:
        ```python
        >>> import supervision as sv
        >>> from ultralytics import YOLO

        >>> model = YOLO(...)
        >>> byte_tracker = sv.ByteTrack()
        >>> annotator = sv.BoxAnnotator()

        >>> def callback(frame: np.ndarray, index: int) -> np.ndarray:
        ...     results = model(frame)[0]
        ...     detections = sv.Detections.from_ultralytics(results)
        ...     detections = byte_tracker.update_with_detections(detections)
        ...     labels = [
        ...         f"#{tracker_id} {model.model.names[class_id]} {confidence:0.2f}"
        ...         for _, _, confidence, class_id, tracker_id
        ...         in detections
        ...     ]
        ...     return annotator.annotate(scene=frame.copy(),
        ...                               detections=detections, labels=labels)

        >>> sv.process_video(
        ...     source_path='...',
        ...     target_path='...',
        ...     callback=callback
        ... )
        ```
    """

    tracks = self.update_with_tensors(
        tensors=detections2boxes(detections=detections)
    )
    detections = Detections.empty()
    if len(tracks) > 0:
        detections.xyxy = np.array(
            [track.tlbr for track in tracks], dtype=np.float32
        )
        detections.class_id = np.array(
            [int(t.class_ids) for t in tracks], dtype=int
        )
        detections.tracker_id = np.array(
            [int(t.track_id) for t in tracks], dtype=int
        )
        detections.confidence = np.array(
            [t.score for t in tracks], dtype=np.float32
        )

    return detections

update_with_tensors(tensors)

Updates the tracker with the provided tensors and returns the updated tracks.

Parameters:

Name Type Description Default
tensors ndarray

The new tensors to update with.

required

Returns:

Type Description
List[STrack]

List[STrack]: Updated tracks.

Source code in supervision/tracker/byte_tracker/core.py
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
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
def update_with_tensors(self, tensors: np.ndarray) -> List[STrack]:
    """
    Updates the tracker with the provided tensors and returns the updated tracks.

    Parameters:
        tensors: The new tensors to update with.

    Returns:
        List[STrack]: Updated tracks.
    """
    self.frame_id += 1
    activated_starcks = []
    refind_stracks = []
    lost_stracks = []
    removed_stracks = []

    class_ids = tensors[:, 5]
    scores = tensors[:, 4]
    bboxes = tensors[:, :4]

    remain_inds = scores > self.track_thresh
    inds_low = scores > 0.1
    inds_high = scores < self.track_thresh

    inds_second = np.logical_and(inds_low, inds_high)
    dets_second = bboxes[inds_second]
    dets = bboxes[remain_inds]
    scores_keep = scores[remain_inds]
    scores_second = scores[inds_second]

    class_ids_keep = class_ids[remain_inds]
    class_ids_second = class_ids[inds_second]

    if len(dets) > 0:
        """Detections"""
        detections = [
            STrack(STrack.tlbr_to_tlwh(tlbr), s, c)
            for (tlbr, s, c) in zip(dets, scores_keep, class_ids_keep)
        ]
    else:
        detections = []

    """ Add newly detected tracklets to tracked_stracks"""
    unconfirmed = []
    tracked_stracks = []  # type: list[STrack]
    for track in self.tracked_tracks:
        if not track.is_activated:
            unconfirmed.append(track)
        else:
            tracked_stracks.append(track)

    """ Step 2: First association, with high score detection boxes"""
    strack_pool = joint_tracks(tracked_stracks, self.lost_tracks)
    # Predict the current location with KF
    STrack.multi_predict(strack_pool)
    dists = matching.iou_distance(strack_pool, detections)

    dists = matching.fuse_score(dists, detections)
    matches, u_track, u_detection = matching.linear_assignment(
        dists, thresh=self.match_thresh
    )

    for itracked, idet in matches:
        track = strack_pool[itracked]
        det = detections[idet]
        if track.state == TrackState.Tracked:
            track.update(detections[idet], self.frame_id)
            activated_starcks.append(track)
        else:
            track.re_activate(det, self.frame_id, new_id=False)
            refind_stracks.append(track)

    """ Step 3: Second association, with low score detection boxes"""
    # association the untrack to the low score detections
    if len(dets_second) > 0:
        """Detections"""
        detections_second = [
            STrack(STrack.tlbr_to_tlwh(tlbr), s, c)
            for (tlbr, s, c) in zip(dets_second, scores_second, class_ids_second)
        ]
    else:
        detections_second = []
    r_tracked_stracks = [
        strack_pool[i]
        for i in u_track
        if strack_pool[i].state == TrackState.Tracked
    ]
    dists = matching.iou_distance(r_tracked_stracks, detections_second)
    matches, u_track, u_detection_second = matching.linear_assignment(
        dists, thresh=0.5
    )
    for itracked, idet in matches:
        track = r_tracked_stracks[itracked]
        det = detections_second[idet]
        if track.state == TrackState.Tracked:
            track.update(det, self.frame_id)
            activated_starcks.append(track)
        else:
            track.re_activate(det, self.frame_id, new_id=False)
            refind_stracks.append(track)

    for it in u_track:
        track = r_tracked_stracks[it]
        if not track.state == TrackState.Lost:
            track.mark_lost()
            lost_stracks.append(track)

    """Deal with unconfirmed tracks, usually tracks with only one beginning frame"""
    detections = [detections[i] for i in u_detection]
    dists = matching.iou_distance(unconfirmed, detections)

    dists = matching.fuse_score(dists, detections)
    matches, u_unconfirmed, u_detection = matching.linear_assignment(
        dists, thresh=0.7
    )
    for itracked, idet in matches:
        unconfirmed[itracked].update(detections[idet], self.frame_id)
        activated_starcks.append(unconfirmed[itracked])
    for it in u_unconfirmed:
        track = unconfirmed[it]
        track.mark_removed()
        removed_stracks.append(track)

    """ Step 4: Init new stracks"""
    for inew in u_detection:
        track = detections[inew]
        if track.score < self.det_thresh:
            continue
        track.activate(self.kalman_filter, self.frame_id)
        activated_starcks.append(track)
    """ Step 5: Update state"""
    for track in self.lost_tracks:
        if self.frame_id - track.end_frame > self.max_time_lost:
            track.mark_removed()
            removed_stracks.append(track)

    self.tracked_tracks = [
        t for t in self.tracked_tracks if t.state == TrackState.Tracked
    ]
    self.tracked_tracks = joint_tracks(self.tracked_tracks, activated_starcks)
    self.tracked_tracks = joint_tracks(self.tracked_tracks, refind_stracks)
    self.lost_tracks = sub_tracks(self.lost_tracks, self.tracked_tracks)
    self.lost_tracks.extend(lost_stracks)
    self.lost_tracks = sub_tracks(self.lost_tracks, self.removed_tracks)
    self.removed_tracks.extend(removed_stracks)
    self.tracked_tracks, self.lost_tracks = remove_duplicate_tracks(
        self.tracked_tracks, self.lost_tracks
    )
    output_stracks = [track for track in self.tracked_tracks if track.is_activated]

    return output_stracks