Files
supervision/supervision/tracker/byte_tracker/core.py
T

567 lines
20 KiB
Python

from typing import List, Tuple
import numpy as np
from supervision.detection.core import Detections
from supervision.detection.utils import box_iou_batch
from supervision.tracker.byte_tracker import matching
from supervision.tracker.byte_tracker.basetrack import BaseTrack, TrackState
from supervision.tracker.byte_tracker.kalman_filter import KalmanFilter
from supervision.utils.internal import deprecated_parameter
class STrack(BaseTrack):
shared_kalman = KalmanFilter()
_external_count = 0
def __init__(self, tlwh, score, class_ids, minimum_consecutive_frames):
# wait activate
self._tlwh = np.asarray(tlwh, dtype=np.float32)
self.kalman_filter = None
self.mean, self.covariance = None, None
self.is_activated = False
self.score = score
self.class_ids = class_ids
self.tracklet_len = 0
self.external_track_id = -1
self.minimum_consecutive_frames = minimum_consecutive_frames
def predict(self):
mean_state = self.mean.copy()
if self.state != TrackState.Tracked:
mean_state[7] = 0
self.mean, self.covariance = self.kalman_filter.predict(
mean_state, self.covariance
)
@staticmethod
def multi_predict(stracks):
if len(stracks) > 0:
multi_mean = []
multi_covariance = []
for i, st in enumerate(stracks):
multi_mean.append(st.mean.copy())
multi_covariance.append(st.covariance)
if st.state != TrackState.Tracked:
multi_mean[i][7] = 0
multi_mean, multi_covariance = STrack.shared_kalman.multi_predict(
np.asarray(multi_mean), np.asarray(multi_covariance)
)
for i, (mean, cov) in enumerate(zip(multi_mean, multi_covariance)):
stracks[i].mean = mean
stracks[i].covariance = cov
def activate(self, kalman_filter, frame_id):
"""Start a new tracklet"""
self.kalman_filter = kalman_filter
self.internal_track_id = self.next_id()
self.mean, self.covariance = self.kalman_filter.initiate(
self.tlwh_to_xyah(self._tlwh)
)
self.tracklet_len = 0
self.state = TrackState.Tracked
if frame_id == 1:
self.is_activated = True
if self.minimum_consecutive_frames == 1:
self.external_track_id = self.next_external_id()
self.frame_id = frame_id
self.start_frame = frame_id
def re_activate(self, new_track, frame_id, new_id=False):
self.mean, self.covariance = self.kalman_filter.update(
self.mean, self.covariance, self.tlwh_to_xyah(new_track.tlwh)
)
self.tracklet_len = 0
self.state = TrackState.Tracked
self.frame_id = frame_id
if new_id:
self.internal_track_id = self.next_id()
self.score = new_track.score
def update(self, new_track, frame_id):
"""
Update a matched track
:type new_track: STrack
:type frame_id: int
:type update_feature: bool
:return:
"""
self.frame_id = frame_id
self.tracklet_len += 1
new_tlwh = new_track.tlwh
self.mean, self.covariance = self.kalman_filter.update(
self.mean, self.covariance, self.tlwh_to_xyah(new_tlwh)
)
self.state = TrackState.Tracked
if self.tracklet_len == self.minimum_consecutive_frames:
self.is_activated = True
if self.external_track_id == -1:
self.external_track_id = self.next_external_id()
self.score = new_track.score
@property
def tlwh(self):
"""Get current position in bounding box format `(top left x, top left y,
width, height)`.
"""
if self.mean is None:
return self._tlwh.copy()
ret = self.mean[:4].copy()
ret[2] *= ret[3]
ret[:2] -= ret[2:] / 2
return ret
@property
def tlbr(self):
"""Convert bounding box to format `(min x, min y, max x, max y)`, i.e.,
`(top left, bottom right)`.
"""
ret = self.tlwh.copy()
ret[2:] += ret[:2]
return ret
@staticmethod
def tlwh_to_xyah(tlwh):
"""Convert bounding box to format `(center x, center y, aspect ratio,
height)`, where the aspect ratio is `width / height`.
"""
ret = np.asarray(tlwh).copy()
ret[:2] += ret[2:] / 2
ret[2] /= ret[3]
return ret
def to_xyah(self):
return self.tlwh_to_xyah(self.tlwh)
@staticmethod
def next_external_id():
STrack._external_count += 1
return STrack._external_count
@staticmethod
def reset_external_counter():
STrack._external_count = 0
@staticmethod
def tlbr_to_tlwh(tlbr):
ret = np.asarray(tlbr).copy()
ret[2:] -= ret[:2]
return ret
@staticmethod
def tlwh_to_tlbr(tlwh):
ret = np.asarray(tlwh).copy()
ret[2:] += ret[:2]
return ret
def __repr__(self):
return "OT_{}_({}-{})".format(
self.internal_track_id, self.start_frame, self.end_frame
)
def detections2boxes(detections: Detections) -> np.ndarray:
"""
Convert Supervision Detections to numpy tensors for further computation.
Args:
detections (Detections): Detections/Targets in the format of sv.Detections.
Returns:
(np.ndarray): Detections as numpy tensors as in
`(x_min, y_min, x_max, y_max, confidence, class_id)` order.
"""
return np.hstack(
(
detections.xyxy,
detections.confidence[:, np.newaxis],
detections.class_id[:, np.newaxis],
)
)
class ByteTrack:
"""
Initialize the ByteTrack object.
<video controls>
<source src="https://media.roboflow.com/supervision/video-examples/how-to/track-objects/annotate-video-with-traces.mp4" type="video/mp4">
</video>
Parameters:
track_activation_threshold (float, optional): Detection confidence threshold
for track activation. Increasing track_activation_threshold improves accuracy
and stability but might miss true detections. Decreasing it increases
completeness but risks introducing noise and instability.
lost_track_buffer (int, optional): Number of frames to buffer when a track is lost.
Increasing lost_track_buffer enhances occlusion handling, significantly
reducing the likelihood of track fragmentation or disappearance caused
by brief detection gaps.
minimum_matching_threshold (float, optional): Threshold for matching tracks with detections.
Increasing minimum_matching_threshold improves accuracy but risks fragmentation.
Decreasing it improves completeness but risks false positives and drift.
frame_rate (int, optional): The frame rate of the video.
minimum_consecutive_frames (int, optional): Number of consecutive frames that an object must
be tracked before it is considered a 'valid' track.
Increasing minimum_consecutive_frames prevents the creation of accidental tracks from
false detection or double detection, but risks missing shorter tracks.
""" # noqa: E501 // docs
@deprecated_parameter(
old_parameter="track_buffer",
new_parameter="lost_track_buffer",
map_function=lambda x: x,
warning_message="`{old_parameter}` in `{function_name}` is deprecated and will "
"be remove in `supervision-0.23.0`. Use '{new_parameter}' "
"instead.",
)
@deprecated_parameter(
old_parameter="track_thresh",
new_parameter="track_activation_threshold",
map_function=lambda x: x,
warning_message="`{old_parameter}` in `{function_name}` is deprecated and will "
"be remove in `supervision-0.23.0`. Use '{new_parameter}' "
"instead.",
)
@deprecated_parameter(
old_parameter="match_thresh",
new_parameter="minimum_matching_threshold",
map_function=lambda x: x,
warning_message="`{old_parameter}` in `{function_name}` is deprecated and will "
"be remove in `supervision-0.23.0`. Use '{new_parameter}' "
"instead.",
)
def __init__(
self,
track_activation_threshold: float = 0.25,
lost_track_buffer: int = 30,
minimum_matching_threshold: float = 0.8,
frame_rate: int = 30,
minimum_consecutive_frames: int = 1,
):
self.track_activation_threshold = track_activation_threshold
self.minimum_matching_threshold = minimum_matching_threshold
self.frame_id = 0
self.det_thresh = self.track_activation_threshold + 0.1
self.max_time_lost = int(frame_rate / 30.0 * lost_track_buffer)
self.minimum_consecutive_frames = minimum_consecutive_frames
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.
Args:
detections (Detections): The detections to pass through the tracker.
Example:
```python
import supervision as sv
from ultralytics import YOLO
model = YOLO(<MODEL_PATH>)
tracker = sv.ByteTrack()
bounding_box_annotator = sv.BoundingBoxAnnotator()
label_annotator = sv.LabelAnnotator()
def callback(frame: np.ndarray, index: int) -> np.ndarray:
results = model(frame)[0]
detections = sv.Detections.from_ultralytics(results)
detections = tracker.update_with_detections(detections)
labels = [f"#{tracker_id}" for tracker_id in detections.tracker_id]
annotated_frame = bounding_box_annotator.annotate(
scene=frame.copy(), detections=detections)
annotated_frame = label_annotator.annotate(
scene=annotated_frame, detections=detections, labels=labels)
return annotated_frame
sv.process_video(
source_path=<SOURCE_VIDEO_PATH>,
target_path=<TARGET_VIDEO_PATH>,
callback=callback
)
```
"""
tensors = detections2boxes(detections=detections)
tracks = self.update_with_tensors(tensors=tensors)
if len(tracks) > 0:
detection_bounding_boxes = np.asarray([det[:4] for det in tensors])
track_bounding_boxes = np.asarray([track.tlbr for track in tracks])
ious = box_iou_batch(detection_bounding_boxes, track_bounding_boxes)
iou_costs = 1 - ious
matches, _, _ = matching.linear_assignment(iou_costs, 0.5)
detections.tracker_id = np.full(len(detections), -1, dtype=int)
for i_detection, i_track in matches:
detections.tracker_id[i_detection] = int(
tracks[i_track].external_track_id
)
return detections[detections.tracker_id != -1]
else:
detections = Detections.empty()
detections.tracker_id = np.array([], dtype=int)
return detections
def reset(self):
"""
Resets the internal state of the ByteTrack tracker.
This method clears the tracking data, including tracked, lost,
and removed tracks, as well as resetting the frame counter. It's
particularly useful when processing multiple videos sequentially,
ensuring the tracker starts with a clean state for each new video.
"""
self.frame_id = 0
self.tracked_tracks: List[STrack] = []
self.lost_tracks: List[STrack] = []
self.removed_tracks: List[STrack] = []
BaseTrack.reset_counter()
STrack.reset_external_counter()
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_activation_threshold
inds_low = scores > 0.1
inds_high = scores < self.track_activation_threshold
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, self.minimum_consecutive_frames)
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.minimum_matching_threshold
)
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, self.minimum_consecutive_frames)
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
def joint_tracks(
track_list_a: List[STrack], track_list_b: List[STrack]
) -> List[STrack]:
"""
Joins two lists of tracks, ensuring that the resulting list does not
contain tracks with duplicate internal_track_id values.
Parameters:
track_list_a: First list of tracks (with internal_track_id attribute).
track_list_b: Second list of tracks (with internal_track_id attribute).
Returns:
Combined list of tracks from track_list_a and track_list_b
without duplicate internal_track_id values.
"""
seen_track_ids = set()
result = []
for track in track_list_a + track_list_b:
if track.internal_track_id not in seen_track_ids:
seen_track_ids.add(track.internal_track_id)
result.append(track)
return result
def sub_tracks(track_list_a: List, track_list_b: List) -> List[int]:
"""
Returns a list of tracks from track_list_a after removing any tracks
that share the same internal_track_id with tracks in track_list_b.
Parameters:
track_list_a: List of tracks (with internal_track_id attribute).
track_list_b: List of tracks (with internal_track_id attribute) to
be subtracted from track_list_a.
Returns:
List of remaining tracks from track_list_a after subtraction.
"""
tracks = {track.internal_track_id: track for track in track_list_a}
track_ids_b = {track.internal_track_id for track in track_list_b}
for track_id in track_ids_b:
tracks.pop(track_id, None)
return list(tracks.values())
def remove_duplicate_tracks(tracks_a: List, tracks_b: List) -> Tuple[List, List]:
pairwise_distance = matching.iou_distance(tracks_a, tracks_b)
matching_pairs = np.where(pairwise_distance < 0.15)
duplicates_a, duplicates_b = set(), set()
for track_index_a, track_index_b in zip(*matching_pairs):
time_a = tracks_a[track_index_a].frame_id - tracks_a[track_index_a].start_frame
time_b = tracks_b[track_index_b].frame_id - tracks_b[track_index_b].start_frame
if time_a > time_b:
duplicates_b.add(track_index_b)
else:
duplicates_a.add(track_index_a)
result_a = [
track for index, track in enumerate(tracks_a) if index not in duplicates_a
]
result_b = [
track for index, track in enumerate(tracks_b) if index not in duplicates_b
]
return result_a, result_b