RT-ODLab/models/tracker/byte_tracker/byte_tracker.py

import numpy as np
import os
import os.path as osp

from .kalman_filter import KalmanFilter
from .matching import iou_distance, fuse_score, linear_assignment
from .basetrack import BaseTrack, TrackState


class STrack(BaseTrack):
    shared_kalman = KalmanFilter()
    def __init__(self, xywh, score):

        # wait activate
        self._xywh = np.asarray(xywh, 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):
        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

    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.xywh_to_cxcyah(self._xywh))

        self.tracklet_len = 0
        self.state = TrackState.Tracked
        if frame_id == 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):
        self.mean, self.covariance = self.kalman_filter.update(
            self.mean, self.covariance, self.xywh_to_cxcyah(new_track.xywh)
        )
        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):
        """
        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_xywh = new_track.xywh
        self.mean, self.covariance = self.kalman_filter.update(
            self.mean, self.covariance, self.xywh_to_cxcyah(new_xywh))
        self.state = TrackState.Tracked
        self.is_activated = True

        self.score = new_track.score

    @property
    # @jit(nopython=True)
    def xywh(self):
        """Get current position in bounding box format `(top left x, top left y,
                width, height)`.
        """
        if self.mean is None:
            return self._xywh.copy()
        ret = self.mean[:4].copy()
        ret[2] *= ret[3]
        ret[:2] -= ret[2:] / 2
        return ret


    @property
    # @jit(nopython=True)
    def xyxy(self):
        """Convert bounding box to format `(min x, min y, max x, max y)`, i.e.,
        `(top left, bottom right)`.
        """
        ret = self.xywh.copy()
        ret[2:] += ret[:2]
        return ret


    @staticmethod
    # @jit(nopython=True)
    def xywh_to_cxcyah(xywh):
        """[x1, y1, w, h] -> [cx, cy, aspect ratio, h], 
        where the aspect ratio is `width / height`.
        """
        ret = np.asarray(xywh).copy()
        ret[:2] += ret[2:] / 2
        ret[2] /= ret[3]
        return ret


    @staticmethod
    # @jit(nopython=True)
    def xyxy_to_xywh(xyxy):
        """ [x1, y1, x2, y2] -> [x1, y1, w, h]"""
        ret = np.asarray(xyxy).copy()
        ret[2:] -= ret[:2]
        return ret


    @staticmethod
    # @jit(nopython=True)
    def xywh_to_xyxy(xywh):
        ret = np.asarray(xywh).copy()
        ret[2:] += ret[:2]
        return ret


    def to_cxcyah(self):
        return self.xywh_to_cxcyah(self.xywh)


    def __repr__(self):
        return 'OT_{}_({}-{})'.format(self.track_id, self.start_frame, self.end_frame)


class ByteTracker(object):
    def __init__(self, track_thresh=0.6, track_buffer=30, frame_rate=30, match_thresh=0.9, mot20=False):
        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.track_buffer = track_buffer
        self.det_thresh = track_thresh + 0.1
        self.match_thresh = match_thresh

        self.buffer_size = int(frame_rate / 30.0 * track_buffer)
        self.max_time_lost = self.buffer_size
        self.kalman_filter = KalmanFilter()

        self.mot20 = mot20


    def update(self, scores, bboxes, labels):
        self.frame_id += 1
        activated_starcks = []
        refind_stracks = []
        lost_stracks = []
        removed_stracks = []

        # process outputs
        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)

        # high score detections
        dets = bboxes[remain_inds]
        scores_keep = scores[remain_inds]

        # second detections
        dets_second = bboxes[inds_second]
        scores_second = scores[inds_second]

        if len(dets) > 0:
            '''Detections'''
            detections = [STrack(STrack.xyxy_to_xywh(xyxy), s) for
                          (xyxy, 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)
        dists = iou_distance(strack_pool, detections)
        if not self.mot20:
            dists = fuse_score(dists, detections)
        matches, u_track, u_detection = 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.xyxy_to_xywh(xyxy), s) for
                          (xyxy, 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 = iou_distance(r_tracked_stracks, detections_second)
        matches, u_track, u_detection_second = 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 = iou_distance(unconfirmed, detections)
        if not self.mot20:
            dists = fuse_score(dists, detections)
        matches, u_unconfirmed, u_detection = 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 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 = 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