Integrate ByteTracker and BoT-SORT trackers (#788)

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>

ultralytics/tracker/trackers/bot_sort.py

@@ -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)