# ****************************************************************************** # Copyright (c) 2022. Kneron Inc. All rights reserved. * # ****************************************************************************** import numpy as np from .kalman_filter import KalmanFilter from . import matching from .basetrack import BaseTrack, TrackState class STrack(BaseTrack): shared_kalman = KalmanFilter() def __init__(self, tlwh, score): # 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.tracklet_len = 0 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 = 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 # NOTE is activated is not triggered def activate(self, kalman_filter, frame_id): # new-> track """Start a new tracklet""" self.kalman_filter = kalman_filter self.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: # only frame 1 self.is_activated = True #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): # lost-> track 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.is_activated = True self.frame_id = frame_id if new_id: self.track_id = self.next_id() self.score = new_track.score def update(self, new_track, frame_id): # track-> track """ Update a matched track :type new_track: STrack :type frame_id: int :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 self.is_activated = True self.score = new_track.score @property # @jit(nopython=True) 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 # @jit(nopython=True) 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 @property # @jit(nopython=True) def center(self): """Convert bounding box to center """ ret = self.tlwh.copy() return ret[:2] + (ret[2:]/2) @staticmethod # @jit(nopython=True) 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 # @jit(nopython=True) def tlbr_to_tlwh(tlbr): ret = np.asarray(tlbr).copy() ret[2:] -= ret[:2] return ret @staticmethod # @jit(nopython=True) def tlwh_to_tlbr(tlwh): ret = np.asarray(tlwh).copy() ret[2:] += ret[:2] return ret def __repr__(self): return 'OT_{}_({}-{})'.format(self.track_id, self.start_frame, self.end_frame) class BYTETracker(object): # """ YTE tracker :track_thresh: tau_high as defined in ByteTrack paper, this value separates the high/low score for tracking, : set to 0.6 in original paper, but for demo is set to 0.5 : This value also has an impact on the det_thresh :match_thresh: set to 0.9 in original paper, but for demo is set to 0.8 :frame_rate : frame rate of input sequences :track_buffer: how long we shall buffer the track :max_time_lost: number of frames that keep in lost state, after that state: Lost-> Removed :max_per_image: max number of output objects """ def __init__(self, track_thresh = 0.6, match_thresh = 0.9, frame_rate=30, track_buffer = 120): self.tracked_stracks = [] # type: list[STrack] self.lost_stracks = [] # type: list[STrack] self.removed_stracks = [] # type: list[STrack] self.frame_id = 0 self.track_thresh = track_thresh self.match_thresh = match_thresh self.det_thresh = track_thresh + 0.1 self.buffer_size = int(frame_rate / 30.0 * track_buffer) self.max_time_lost = self.buffer_size self.mot20 = False #may open if high surveilance scenarios? (no fuse score) self.kalman_filter = KalmanFilter() def update(self, output_results): ''' dets: list of bbox information [x, y, w, h, score, class] ''' self.frame_id += 1 activated_starcks = [] refind_stracks = [] lost_stracks = [] removed_stracks = [] dets = [] dets_second = [] if len(output_results) > 0: output_results = np.array(output_results) #if output_results.ndim == 2: scores = output_results[:, 4] bboxes = output_results[:, :4] ''' Step 1: get detections ''' remain_inds = scores > self.track_thresh inds_low = scores > 0.1 # tau_Low inds_high = scores < self.track_thresh inds_second = np.logical_and(inds_low, inds_high) dets_second = bboxes[inds_second] #D_low dets = bboxes[remain_inds] #D_high scores_keep = scores[remain_inds] #D_high_score scores_second = scores[inds_second] #D_low_score if len(dets) > 0: '''Detections''' detections = [STrack(tlwh, s) for (tlwh, s) in zip(dets, scores_keep)] else: detections = [] ''' 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 = joint_stracks(tracked_stracks, self.lost_stracks) # Predict the current location with KF STrack.multi_predict(strack_pool) # for fairmot, it is with embedding distance and fuse_motion (kalman filter gating distance) # for bytetrack, the distance is computed with IOU * detection scores # which mean the matching dists = matching.iou_distance(strack_pool, detections) if not self.mot20: 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(tlwh, s) for (tlwh, s) in zip(dets_second, scores_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) if not self.mot20: 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_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 = joint_stracks(self.tracked_stracks, activated_starcks) self.tracked_stracks = joint_stracks(self.tracked_stracks, refind_stracks) self.lost_stracks = sub_stracks(self.lost_stracks, self.tracked_stracks) self.lost_stracks.extend(lost_stracks) self.lost_stracks = sub_stracks(self.lost_stracks, self.removed_stracks) self.removed_stracks.extend(removed_stracks) self.tracked_stracks, self.lost_stracks = remove_duplicate_stracks(self.tracked_stracks, self.lost_stracks) # get scores of lost tracks output_stracks = [track for track in self.tracked_stracks if track.is_activated] return output_stracks def postprocess_(dets, tracker, min_box_area = 120, **kwargs): ''' return: frame with bboxs ''' online_targets = tracker.update(dets) online_tlwhs = [] online_ids = [] for t in online_targets: tlwh = t.tlwh tid = t.track_id #vertical = tlwh[2] / tlwh[3] > 1.6 #if tlwh[2] * tlwh[3] > min_box_area and not vertical: online_tlwhs.append(np.round(tlwh, 2)) online_ids.append(tid) return online_tlwhs, online_ids 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 # remove tlisb items from tlist a def sub_stracks(tlista, tlistb): stracks = {} for t in tlista: stracks[t.track_id] = t for t in tlistb: tid = t.track_id if stracks.get(tid, 0): del stracks[tid] return list(stracks.values()) def remove_duplicate_stracks(stracksa, stracksb): # remove track overlap with 85 % pdist = matching.iou_distance(stracksa, stracksb) pairs = np.where(pdist < 0.15) dupa, dupb = list(), list() 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 not i in dupa] resb = [t for i, t in enumerate(stracksb) if not i in dupb] return resa, resb