File size: 15,158 Bytes
7734d5b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
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
from collections import deque
import torch
import numpy as np
from utils.kalman_filter import KalmanFilter
from utils.log import logger
from models import *
from tracker import matching
from .basetrack import BaseTrack, TrackState


class STrack(BaseTrack):

    def __init__(self, tlwh, score):

        # wait activate
        self._tlwh = np.asarray(tlwh, dtype=np.float)
        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, kalman_filter):
        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.kalman_filter.multi_predict(multi_mean, multi_covariance)
            multi_mean, multi_covariance = kalman_filter.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 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.tlwh_to_xyah(self._tlwh))

        self.tracklet_len = 0
        self.state = TrackState.Tracked
        #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.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()

    def update(self, new_track, frame_id, update_feature=True):
        """
        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
        self.is_activated = True

        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 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.track_id, self.start_frame, self.end_frame)


class BYTETracker(object):
    def __init__(self, opt, frame_rate=30):
        self.opt = opt
        self.model = Darknet(opt.cfg, nID=14455)
        # load_darknet_weights(self.model, opt.weights)
        self.model.load_state_dict(torch.load(opt.weights, map_location='cpu')['model'], strict=False)
        self.model.cuda().eval()

        self.tracked_stracks = []  # type: list[STrack]
        self.lost_stracks = []  # type: list[STrack]
        self.removed_stracks = []  # type: list[STrack]

        self.frame_id = 0
        self.det_thresh = opt.conf_thres
        self.init_thresh = self.det_thresh + 0.2
        self.low_thresh = 0.3
        self.buffer_size = int(frame_rate / 30.0 * opt.track_buffer)
        self.max_time_lost = self.buffer_size

        self.kalman_filter = KalmanFilter()

    def update(self, im_blob, img0):
        """
        Processes the image frame and finds bounding box(detections).

        Associates the detection with corresponding tracklets and also handles lost, removed, refound and active tracklets

        Parameters
        ----------
        im_blob : torch.float32
                  Tensor of shape depending upon the size of image. By default, shape of this tensor is [1, 3, 608, 1088]

        img0 : ndarray
               ndarray of shape depending on the input image sequence. By default, shape is [608, 1080, 3]

        Returns
        -------
        output_stracks : list of Strack(instances)
                         The list contains information regarding the online_tracklets for the recieved image tensor.

        """

        self.frame_id += 1
        activated_starcks = []      # for storing active tracks, for the current frame
        refind_stracks = []         # Lost Tracks whose detections are obtained in the current frame
        lost_stracks = []           # The tracks which are not obtained in the current frame but are not removed.(Lost for some time lesser than the threshold for removing)
        removed_stracks = []

        t1 = time.time()
        ''' Step 1: Network forward, get detections & embeddings'''
        with torch.no_grad():
            pred = self.model(im_blob)
        # pred is tensor of all the proposals (default number of proposals: 54264). Proposals have information associated with the bounding box and embeddings
        pred = pred[pred[:, :, 4] > self.low_thresh]
        # pred now has lesser number of proposals. Proposals rejected on basis of object confidence score
        if len(pred) > 0:
            dets = non_max_suppression(pred.unsqueeze(0), self.low_thresh, self.opt.nms_thres)[0].cpu()
            # Final proposals are obtained in dets. Information of bounding box and embeddings also included
            # Next step changes the detection scales
            scale_coords(self.opt.img_size, dets[:, :4], img0.shape).round()
            '''Detections is list of (x1, y1, x2, y2, object_conf, class_score, class_pred)'''
            # class_pred is the embeddings.

            dets = dets.numpy()
            remain_inds = dets[:, 4] > self.det_thresh
            inds_low = dets[:, 4] > self.low_thresh
            inds_high = dets[:, 4] < self.det_thresh
            inds_second = np.logical_and(inds_low, inds_high)
            dets_second = dets[inds_second]
            dets = dets[remain_inds]

            detections = [STrack(STrack.tlbr_to_tlwh(tlbrs[:4]), tlbrs[4]) for
                          tlbrs in dets[:, :5]]
        else:
            detections = []
            dets_second = []

        t2 = time.time()
        # print('Forward: {} s'.format(t2-t1))

        ''' Add newly detected tracklets to tracked_stracks'''
        unconfirmed = []
        tracked_stracks = []  # type: list[STrack]
        for track in self.tracked_stracks:
            if not track.is_activated:
                # previous tracks which are not active in the current frame are added in unconfirmed list
                unconfirmed.append(track)
                # print("Should not be here, in unconfirmed")
            else:
                # Active tracks are added to the local list 'tracked_stracks'
                tracked_stracks.append(track)

        ''' Step 2: First association, with embedding'''
        # Combining currently tracked_stracks and lost_stracks
        strack_pool = joint_stracks(tracked_stracks, self.lost_stracks)
        # Predict the current location with KF
        STrack.multi_predict(strack_pool, self.kalman_filter)
        dists = matching.iou_distance(strack_pool, detections)
        # The dists is the list of distances of the detection with the tracks in strack_pool
        matches, u_track, u_detection = matching.linear_assignment(dists, thresh=0.8)
        # The matches is the array for corresponding matches of the detection with the corresponding strack_pool

        for itracked, idet in matches:
            # itracked is the id of the track and idet is the detection
            track = strack_pool[itracked]
            det = detections[idet]
            if track.state == TrackState.Tracked:
                # If the track is active, add the detection to the track
                track.update(detections[idet], self.frame_id)
                activated_starcks.append(track)
            else:
                # We have obtained a detection from a track which is not active, hence put the track in refind_stracks list
                track.re_activate(det, self.frame_id, new_id=False)
                refind_stracks.append(track)

        # association the untrack to the low score detections
        if len(dets_second) > 0:
            detections_second = [STrack(STrack.tlbr_to_tlwh(tlbrs[:4]), tlbrs[4]) for
                                 tlbrs in dets_second[:, :5]]
        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=0.4)
        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)
        # If no detections are obtained for tracks (u_track), the tracks are added to lost_tracks list and are marked lost

        '''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)
        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])

        # The tracks which are yet not matched
        for it in u_unconfirmed:
            track = unconfirmed[it]
            track.mark_removed()
            removed_stracks.append(track)

        # after all these confirmation steps, if a new detection is found, it is initialized for a new track
        """ Step 4: Init new stracks"""
        for inew in u_detection:
            track = detections[inew]
            if track.score < self.init_thresh:
                continue
            track.activate(self.kalman_filter, self.frame_id)
            activated_starcks.append(track)

        """ Step 5: Update state"""
        # If the tracks are lost for more frames than the threshold number, the tracks are removed.
        for track in self.lost_stracks:
            if self.frame_id - track.end_frame > self.max_time_lost:
                track.mark_removed()
                removed_stracks.append(track)
        # print('Remained match {} s'.format(t4-t3))

        # Update the self.tracked_stracks and self.lost_stracks using the updates in this step.
        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 = [t for t in self.lost_stracks if t.state == TrackState.Lost]  # type: list[STrack]
        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]

        logger.debug('===========Frame {}=========='.format(self.frame_id))
        logger.debug('Activated: {}'.format([track.track_id for track in activated_starcks]))
        logger.debug('Refind: {}'.format([track.track_id for track in refind_stracks]))
        logger.debug('Lost: {}'.format([track.track_id for track in lost_stracks]))
        logger.debug('Removed: {}'.format([track.track_id for track in removed_stracks]))
        # print('Final {} s'.format(t5-t4))
        return output_stracks

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

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):
    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