xdobro23/YOLOv8-16bit
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Integrate ByteTracker and BoT-SORT trackers (#788)

Browse Source 
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: Ayush Chaurasia <ayush.chaurarsia@gmail.com>
This commit is contained in:
Laughing
2023-02-16 00:23:03 +08:00
committed by GitHub
parent d99e04daa1
commit ed6c54da7a
24 changed files with 1635 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ultralytics/tracker/trackers/__init__.py Normal file
View File

@ -0,0 +1,2 @@
from .byte_tracker import BYTETracker
from .bot_sort import BOTSORT

52
ultralytics/tracker/trackers/basetrack.py Normal file
View File

@ -0,0 +1,52 @@
import numpy as np
from collections import OrderedDict
class TrackState:
New = 0
Tracked = 1
Lost = 2
Removed = 3
class BaseTrack:
_count = 0
track_id = 0
is_activated = False
state = TrackState.New
history = OrderedDict()
features = []
curr_feature = None
score = 0
start_frame = 0
frame_id = 0
time_since_update = 0
# multi-camera
location = (np.inf, np.inf)
@property
def end_frame(self):
return self.frame_id
@staticmethod
def next_id():
BaseTrack._count += 1
return BaseTrack._count
def activate(self, *args):
raise NotImplementedError
def predict(self):
raise NotImplementedError
def update(self, *args, **kwargs):
raise NotImplementedError
def mark_lost(self):
self.state = TrackState.Lost
def mark_removed(self):
self.state = TrackState.Removed

132
ultralytics/tracker/trackers/bot_sort.py Normal file
View File

@ -0,0 +1,132 @@
from collections import deque
import numpy as np
from ..utils import matching
from ..utils.gmc import GMC
from ..utils.kalman_filter import KalmanFilterXYWH
from .byte_tracker import STrack, BYTETracker
from .basetrack import TrackState
class BOTrack(STrack):
shared_kalman = KalmanFilterXYWH()
def __init__(self, tlwh, score, cls, feat=None, feat_history=50):
super().__init__(tlwh, score, cls)
self.smooth_feat = None
self.curr_feat = None
if feat is not None:
self.update_features(feat)
self.features = deque([], maxlen=feat_history)
self.alpha = 0.9
def update_features(self, feat):
feat /= np.linalg.norm(feat)
self.curr_feat = feat
if self.smooth_feat is None:
self.smooth_feat = feat
else:
self.smooth_feat = self.alpha * self.smooth_feat + (1 - self.alpha) * feat
self.features.append(feat)
self.smooth_feat /= np.linalg.norm(self.smooth_feat)
def predict(self):
mean_state = self.mean.copy()
if self.state != TrackState.Tracked:
mean_state[6] = 0
mean_state[7] = 0
self.mean, self.covariance = self.kalman_filter.predict(mean_state, self.covariance)
def re_activate(self, new_track, frame_id, new_id=False):
if new_track.curr_feat is not None:
self.update_features(new_track.curr_feat)
super().re_activate(new_track, frame_id, new_id)
def update(self, new_track, frame_id):
if new_track.curr_feat is not None:
self.update_features(new_track.curr_feat)
super().update(new_track, frame_id)
@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[2:] / 2
return ret
@staticmethod
def multi_predict(stracks):
if len(stracks) > 0:
multi_mean = np.asarray([st.mean.copy() for st in stracks])
multi_covariance = np.asarray([st.covariance for st in stracks])
for i, st in enumerate(stracks):
if st.state != TrackState.Tracked:
multi_mean[i][6] = 0
multi_mean[i][7] = 0
multi_mean, multi_covariance = BOTrack.shared_kalman.multi_predict(multi_mean, multi_covariance)
for i, (mean, cov) in enumerate(zip(multi_mean, multi_covariance)):
stracks[i].mean = mean
stracks[i].covariance = cov
def convert_coords(self, tlwh):
return self.tlwh_to_xywh(tlwh)
@staticmethod
def tlwh_to_xywh(tlwh):
"""Convert bounding box to format `(center x, center y, width,
height)`.
"""
ret = np.asarray(tlwh).copy()
ret[:2] += ret[2:] / 2
return ret
class BOTSORT(BYTETracker):
def __init__(self, args, frame_rate=30):
super().__init__(args, frame_rate)
# ReID module
self.proximity_thresh = args.proximity_thresh
self.appearance_thresh = args.appearance_thresh
if args.with_reid:
# haven't supported bot-sort(reid) yet
self.encoder = None
# self.gmc = GMC(method=args.cmc_method, verbose=[args.name, args.ablation])
self.gmc = GMC(method=args.cmc_method)
def get_kalmanfilter(self):
return KalmanFilterXYWH()
def init_track(self, dets, scores, cls, img=None):
if len(dets) == 0:
return []
if self.args.with_reid and self.encoder is not None:
features_keep = self.encoder.inference(img, dets)
detections = [BOTrack(xyxy, s, c, f) for (xyxy, s, c, f) in zip(dets, scores, cls, features_keep)]
else:
detections = [BOTrack(xyxy, s, c) for (xyxy, s, c) in zip(dets, scores, cls)]
return detections
def get_dists(self, tracks, detections):
dists = matching.iou_distance(tracks, detections)
dists_mask = (dists > self.proximity_thresh)
# TODO: mot20
# if not self.args.mot20:
dists = matching.fuse_score(dists, detections)
if self.args.with_reid and self.encoder is not None:
emb_dists = matching.embedding_distance(tracks, detections) / 2.0
emb_dists[emb_dists > self.appearance_thresh] = 1.0
emb_dists[dists_mask] = 1.0
dists = np.minimum(dists, emb_dists)
return dists
def multi_predict(self, tracks):
BOTrack.multi_predict(tracks)

338
ultralytics/tracker/trackers/byte_tracker.py Normal file
View File

@ -0,0 +1,338 @@
import numpy as np
from .basetrack import BaseTrack, TrackState
from ..utils import matching
from ..utils.kalman_filter import KalmanFilterXYAH
class STrack(BaseTrack):
shared_kalman = KalmanFilterXYAH()
def __init__(self, tlwh, score, cls):
# wait activate
self._tlwh = np.asarray(self.tlbr_to_tlwh(tlwh[:-1]), dtype=np.float32)
self.kalman_filter = None
self.mean, self.covariance = None, None
self.is_activated = False
self.score = score
self.tracklet_len = 0
self.cls = cls
self.idx = tlwh[-1]
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:
return
multi_mean = np.asarray([st.mean.copy() for st in stracks])
multi_covariance = np.asarray([st.covariance for st in stracks])
for i, st in enumerate(stracks):
if st.state != TrackState.Tracked:
multi_mean[i][7] = 0
multi_mean, multi_covariance = STrack.shared_kalman.multi_predict(multi_mean, multi_covariance)
for i, (mean, cov) in enumerate(zip(multi_mean, multi_covariance)):
stracks[i].mean = mean
stracks[i].covariance = cov
@staticmethod
def multi_gmc(stracks, H=np.eye(2, 3)):
if len(stracks) > 0:
multi_mean = np.asarray([st.mean.copy() for st in stracks])
multi_covariance = np.asarray([st.covariance for st in stracks])
R = H[:2, :2]
R8x8 = np.kron(np.eye(4, dtype=float), R)
t = H[:2, 2]
for i, (mean, cov) in enumerate(zip(multi_mean, multi_covariance)):
mean = R8x8.dot(mean)
mean[:2] += t
cov = R8x8.dot(cov).dot(R8x8.transpose())
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.track_id = self.next_id()
self.mean, self.covariance = self.kalman_filter.initiate(self.convert_coords(self._tlwh))
self.tracklet_len = 0
self.state = TrackState.Tracked
if frame_id == 1:
self.is_activated = True
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.convert_coords(new_track.tlwh))
self.tracklet_len = 0
self.state = TrackState.Tracked
self.is_activated = True
self.frame_id = frame_id
if new_id:
self.track_id = self.next_id()
self.score = new_track.score
self.cls = new_track.cls
self.idx = new_track.idx
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.convert_coords(new_tlwh))
self.state = TrackState.Tracked
self.is_activated = True
self.score = new_track.score
self.cls = new_track.cls
self.idx = new_track.idx
def convert_coords(self, tlwh):
return self.tlwh_to_xyah(tlwh)
@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
@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 f"OT_{self.track_id}_({self.start_frame}-{self.end_frame})"
class BYTETracker:
def __init__(self, args, frame_rate=30):
self.tracked_stracks = [] # type: list[STrack]
self.lost_stracks = [] # type: list[STrack]
self.removed_stracks = [] # type: list[STrack]
self.frame_id = 0
self.args = args
self.max_time_lost = int(frame_rate / 30.0 * args.track_buffer)
self.kalman_filter = self.get_kalmanfilter()
def update(self, results, img=None):
self.frame_id += 1
activated_starcks = []
refind_stracks = []
lost_stracks = []
removed_stracks = []
scores = results.conf
bboxes = results.xyxy
# add index
bboxes = np.concatenate([bboxes, np.arange(len(bboxes)).reshape(-1, 1)], axis=-1)
cls = results.cls
remain_inds = scores > self.args.track_high_thresh
inds_low = scores > self.args.track_low_thresh
inds_high = scores < self.args.track_high_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]
cls_keep = cls[remain_inds]
cls_second = cls[inds_second]
detections = self.init_track(dets, scores_keep, cls_keep, img)
""" Add newly detected tracklets to tracked_stracks"""
unconfirmed = []
tracked_stracks = [] # type: list[STrack]
for track in self.tracked_stracks:
if not track.is_activated:
unconfirmed.append(track)
else:
tracked_stracks.append(track)
""" Step 2: First association, with high score detection boxes"""
strack_pool = self.joint_stracks(tracked_stracks, self.lost_stracks)
# Predict the current location with KF
self.multi_predict(strack_pool)
if hasattr(self, "gmc"):
warp = self.gmc.apply(img, dets)
STrack.multi_gmc(strack_pool, warp)
STrack.multi_gmc(unconfirmed, warp)
dists = self.get_dists(strack_pool, detections)
matches, u_track, u_detection = matching.linear_assignment(dists, thresh=self.args.match_thresh)
for itracked, idet in matches:
track = strack_pool[itracked]
det = detections[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)
""" Step 3: Second association, with low score detection boxes"""
# association the untrack to the low score detections
detections_second = self.init_track(dets_second, scores_second, cls_second, img)
r_tracked_stracks = [strack_pool[i] for i in u_track if strack_pool[i].state == TrackState.Tracked]
# TODO
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 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 = self.get_dists(unconfirmed, 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.args.new_track_thresh:
continue
track.activate(self.kalman_filter, self.frame_id)
activated_starcks.append(track)
""" Step 5: Update state"""
for track in self.lost_stracks:
if self.frame_id - track.end_frame > self.max_time_lost:
track.mark_removed()
removed_stracks.append(track)
self.tracked_stracks = [t for t in self.tracked_stracks if t.state == TrackState.Tracked]
self.tracked_stracks = self.joint_stracks(self.tracked_stracks, activated_starcks)
self.tracked_stracks = self.joint_stracks(self.tracked_stracks, refind_stracks)
self.lost_stracks = self.sub_stracks(self.lost_stracks, self.tracked_stracks)
self.lost_stracks.extend(lost_stracks)
self.lost_stracks = self.sub_stracks(self.lost_stracks, self.removed_stracks)
self.removed_stracks.extend(removed_stracks)
self.tracked_stracks, self.lost_stracks = self.remove_duplicate_stracks(self.tracked_stracks, self.lost_stracks)
output = [
track.tlbr.tolist() + [track.track_id, track.score, track.cls, track.idx] for track in self.tracked_stracks
if track.is_activated]
return np.asarray(output, dtype=np.float32)
def get_kalmanfilter(self):
return KalmanFilterXYAH()
def init_track(self, dets, scores, cls, img=None):
return [STrack(xyxy, s, c) for (xyxy, s, c) in zip(dets, scores, cls)] if len(dets) else [] # detections
def get_dists(self, tracks, detections):
dists = matching.iou_distance(tracks, detections)
# TODO: mot20
# if not self.args.mot20:
dists = matching.fuse_score(dists, detections)
return dists
def multi_predict(self, tracks):
STrack.multi_predict(tracks)
@staticmethod
def joint_stracks(tlista, tlistb):
exists = {}
res = []
for t in tlista:
exists[t.track_id] = 1
res.append(t)
for t in tlistb:
tid = t.track_id
if not exists.get(tid, 0):
exists[tid] = 1
res.append(t)
return res
@staticmethod
def sub_stracks(tlista, tlistb):
stracks = {t.track_id: t for t in tlista}
for t in tlistb:
tid = t.track_id
if stracks.get(tid, 0):
del stracks[tid]
return list(stracks.values())
@staticmethod
def remove_duplicate_stracks(stracksa, stracksb):
pdist = matching.iou_distance(stracksa, stracksb)
pairs = np.where(pdist < 0.15)
dupa, dupb = [], []
for p, q in zip(*pairs):
timep = stracksa[p].frame_id - stracksa[p].start_frame
timeq = stracksb[q].frame_id - stracksb[q].start_frame
if timep > timeq:
dupb.append(q)
else:
dupa.append(p)
resa = [t for i, t in enumerate(stracksa) if i not in dupa]
resb = [t for i, t in enumerate(stracksb) if i not in dupb]
return resa, resb