─░├žeri─če ge├ž

Referans i├žin ultralytics/trackers/bot_sort.py

Not

Bu dosya https://github.com/ultralytics/ultralytics/blob/main/ ultralytics/trackers/bot_sort .py adresinde mevcuttur. Bir sorun tespit ederseniz l├╝tfen bir ├çekme ─░ste─či ­čŤá´ŞĆ ile katk─▒da bulunarak d├╝zeltilmesine yard─▒mc─▒ olun. Te┼čekk├╝rler ­čÖĆ!



ultralytics.trackers.bot_sort.BOTrack

├ťsler: STrack

YOLOv8 i├žin STrack s─▒n─▒f─▒n─▒n nesne izleme ├Âzellikleri ekleyen geni┼čletilmi┼č bir s├╝r├╝m├╝.

Nitelikler:

─░sim Tip A├ž─▒klama
shared_kalman KalmanFilterXYWH

BOTrack'in t├╝m ├Ârnekleri i├žin payla┼č─▒lan bir Kalman filtresi.

smooth_feat ndarray

D├╝zle┼čtirilmi┼č ├Âzellik vekt├Âr├╝.

curr_feat ndarray

Ge├žerli ├Âzellik vekt├Âr├╝.

features deque

Taraf─▒ndan tan─▒mlanan maksimum uzunlu─ča sahip ├Âzellik vekt├Ârlerini depolamak i├žin bir deque feat_history.

alpha float

├ľzelliklerin ├╝stel hareketli ortalamas─▒ i├žin yumu┼čatma fakt├Âr├╝.

mean ndarray

Kalman filtresinin ortalama durumu.

covariance ndarray

Kalman filtresinin kovaryans matrisi.

Y├Ântemler:

─░sim A├ž─▒klama
update_features

├ľzellikler vekt├Âr├╝n├╝ g├╝ncelleyin ve ├╝stel hareketli ortalama kullanarak d├╝zeltin.

predict

Kalman filtresi kullanarak ortalama ve kovaryans─▒ tahmin eder.

re_activate

G├╝ncellenmi┼č ├Âzellikler ve iste─če ba─čl─▒ olarak yeni kimlik ile bir par├žay─▒ yeniden etkinle┼čtirir.

update

YOLOv8 ├Ârne─čini yeni par├ža ve ├žer├ževe kimli─či ile g├╝ncelleyin.

tlwh

Ge├žerli konumu tlwh bi├žiminde alan ├Âzellik (top left x, top left y, width, height).

multi_predict

Payla┼č─▒lan Kalman filtresini kullanarak ├žoklu nesne izlerinin ortalamas─▒n─▒ ve kovaryans─▒n─▒ tahmin eder.

convert_coords

tlwh s─▒n─▒rlay─▒c─▒ kutu koordinatlar─▒n─▒ xywh format─▒na d├Ân├╝┼čt├╝r├╝r.

tlwh_to_xywh

S─▒n─▒rlay─▒c─▒ kutuyu xywh bi├žimine d├Ân├╝┼čt├╝rme (center x, center y, width, height).

Kullan─▒m

bo_track = BOTrack(tlwh, score, cls, feat) bo_track.predict() bo_track.update(new_track, frame_id)

Kaynak kodu ultralytics/trackers/bot_sort.py
class BOTrack(STrack):
    """
    An extended version of the STrack class for YOLOv8, adding object tracking features.

    Attributes:
        shared_kalman (KalmanFilterXYWH): A shared Kalman filter for all instances of BOTrack.
        smooth_feat (np.ndarray): Smoothed feature vector.
        curr_feat (np.ndarray): Current feature vector.
        features (deque): A deque to store feature vectors with a maximum length defined by `feat_history`.
        alpha (float): Smoothing factor for the exponential moving average of features.
        mean (np.ndarray): The mean state of the Kalman filter.
        covariance (np.ndarray): The covariance matrix of the Kalman filter.

    Methods:
        update_features(feat): Update features vector and smooth it using exponential moving average.
        predict(): Predicts the mean and covariance using Kalman filter.
        re_activate(new_track, frame_id, new_id): Reactivates a track with updated features and optionally new ID.
        update(new_track, frame_id): Update the YOLOv8 instance with new track and frame ID.
        tlwh: Property that gets the current position in tlwh format `(top left x, top left y, width, height)`.
        multi_predict(stracks): Predicts the mean and covariance of multiple object tracks using shared Kalman filter.
        convert_coords(tlwh): Converts tlwh bounding box coordinates to xywh format.
        tlwh_to_xywh(tlwh): Convert bounding box to xywh format `(center x, center y, width, height)`.

    Usage:
        bo_track = BOTrack(tlwh, score, cls, feat)
        bo_track.predict()
        bo_track.update(new_track, frame_id)
    """

    shared_kalman = KalmanFilterXYWH()

    def __init__(self, tlwh, score, cls, feat=None, feat_history=50):
        """Initialize YOLOv8 object with temporal parameters, such as feature history, alpha and current features."""
        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):
        """Update features vector and smooth it using exponential moving average."""
        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):
        """Predicts the mean and covariance using Kalman filter."""
        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):
        """Reactivates a track with updated features and optionally assigns a new ID."""
        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):
        """Update the YOLOv8 instance with new track and 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):
        """Predicts the mean and covariance of multiple object tracks using shared Kalman filter."""
        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][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):
        """Converts Top-Left-Width-Height bounding box coordinates to X-Y-Width-Height format."""
        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

tlwh property

Ge├žerli konumu s─▒n─▒rlay─▒c─▒ kutu bi├žiminde al─▒r (top left x, top left y, width, height).

__init__(tlwh, score, cls, feat=None, feat_history=50)

YOLOv8 nesnesini ├Âzellik ge├žmi┼či, alfa ve mevcut ├Âzellikler gibi zamansal parametrelerle ba┼člat─▒n.

Kaynak kodu ultralytics/trackers/bot_sort.py
def __init__(self, tlwh, score, cls, feat=None, feat_history=50):
    """Initialize YOLOv8 object with temporal parameters, such as feature history, alpha and current features."""
    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

convert_coords(tlwh)

├ťst-Sol-Geni┼člik-Y├╝kseklik s─▒n─▒rlay─▒c─▒ kutu koordinatlar─▒n─▒ X-Y-Geni┼člik-Y├╝kseklik bi├žimine d├Ân├╝┼čt├╝r├╝r.

Kaynak kodu ultralytics/trackers/bot_sort.py
def convert_coords(self, tlwh):
    """Converts Top-Left-Width-Height bounding box coordinates to X-Y-Width-Height format."""
    return self.tlwh_to_xywh(tlwh)

multi_predict(stracks) staticmethod

Payla┼č─▒lan Kalman filtresini kullanarak ├žoklu nesne izlerinin ortalamas─▒n─▒ ve kovaryans─▒n─▒ tahmin eder.

Kaynak kodu ultralytics/trackers/bot_sort.py
@staticmethod
def multi_predict(stracks):
    """Predicts the mean and covariance of multiple object tracks using shared Kalman filter."""
    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][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

predict()

Kalman filtresi kullanarak ortalama ve kovaryans─▒ tahmin eder.

Kaynak kodu ultralytics/trackers/bot_sort.py
def predict(self):
    """Predicts the mean and covariance using Kalman filter."""
    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)

re_activate(new_track, frame_id, new_id=False)

Bir par├žay─▒ g├╝ncellenmi┼č ├Âzelliklerle yeniden etkinle┼čtirir ve iste─če ba─čl─▒ olarak yeni bir kimlik atar.

Kaynak kodu ultralytics/trackers/bot_sort.py
def re_activate(self, new_track, frame_id, new_id=False):
    """Reactivates a track with updated features and optionally assigns a new ID."""
    if new_track.curr_feat is not None:
        self.update_features(new_track.curr_feat)
    super().re_activate(new_track, frame_id, new_id)

tlwh_to_xywh(tlwh) staticmethod

S─▒n─▒rlay─▒c─▒ kutuyu bi├žime d├Ân├╝┼čt├╝rme (center x, center y, width, height).

Kaynak kodu ultralytics/trackers/bot_sort.py
@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

update(new_track, frame_id)

YOLOv8 ├Ârne─čini yeni par├ža ve ├žer├ževe kimli─či ile g├╝ncelleyin.

Kaynak kodu ultralytics/trackers/bot_sort.py
def update(self, new_track, frame_id):
    """Update the YOLOv8 instance with new track and frame ID."""
    if new_track.curr_feat is not None:
        self.update_features(new_track.curr_feat)
    super().update(new_track, frame_id)

update_features(feat)

├ľzellikler vekt├Âr├╝n├╝ g├╝ncelleyin ve ├╝stel hareketli ortalama kullanarak d├╝zeltin.

Kaynak kodu ultralytics/trackers/bot_sort.py
def update_features(self, feat):
    """Update features vector and smooth it using exponential moving average."""
    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)



ultralytics.trackers.bot_sort.BOTSORT

├ťsler: BYTETracker

ReID ve GMC algoritmas─▒ ile nesne izleme i├žin tasarlanm─▒┼č YOLOv8 i├žin BYTETracker s─▒n─▒f─▒n─▒n geni┼čletilmi┼č bir s├╝r├╝m├╝.

Nitelikler:

─░sim Tip A├ž─▒klama
proximity_thresh float

─░zler ve tespitler aras─▒ndaki uzamsal yak─▒nl─▒k (IoU) i├žin e┼čik.

appearance_thresh float

─░zler ve tespitler aras─▒ndaki g├Âr├╝n├╝m benzerli─či (ReID kat─▒┼čt─▒rmalar─▒) i├žin e┼čik.

encoder object

ReID kat─▒┼čt─▒rmalar─▒n─▒ i┼člemek i├žin nesne, ReID etkinle┼čtirilmemi┼čse Yok olarak ayarlan─▒r.

gmc GMC

Veri ili┼čkilendirmesi i├žin GMC algoritmas─▒n─▒n bir ├Ârne─či.

args object

─░zleme parametreleri i├žeren ayr─▒┼čt─▒r─▒lm─▒┼č komut sat─▒r─▒ arg├╝manlar─▒.

Y├Ântemler:

─░sim A├ž─▒klama
get_kalmanfilter

Nesne izleme i├žin bir KalmanFilterXYWH ├Ârne─či d├Ând├╝r├╝r.

init_track

─░zi tespitler, puanlar ve s─▒n─▒flarla ba┼člat─▒n.

get_dists

IoU ve (iste─če ba─čl─▒ olarak) ReID kullanarak izler ve tespitler aras─▒ndaki mesafeleri al─▒n.

multi_predict

YOLOv8 modeli ile birden fazla nesneyi tahmin edin ve izleyin.

Kullan─▒m

bot_sort = BOTSORT(args, frame_rate) bot_sort.init_track(dets, scores, cls, img) bot_sort.multi_predict(tracks)

Not

S─▒n─▒f, YOLOv8 nesne alg─▒lama modeliyle ├žal─▒┼čmak ├╝zere tasarlanm─▒┼čt─▒r ve yaln─▒zca args arac─▒l─▒─č─▒yla etkinle┼čtirilirse ReID'yi destekler.

Kaynak kodu ultralytics/trackers/bot_sort.py
class BOTSORT(BYTETracker):
    """
    An extended version of the BYTETracker class for YOLOv8, designed for object tracking with ReID and GMC algorithm.

    Attributes:
        proximity_thresh (float): Threshold for spatial proximity (IoU) between tracks and detections.
        appearance_thresh (float): Threshold for appearance similarity (ReID embeddings) between tracks and detections.
        encoder (object): Object to handle ReID embeddings, set to None if ReID is not enabled.
        gmc (GMC): An instance of the GMC algorithm for data association.
        args (object): Parsed command-line arguments containing tracking parameters.

    Methods:
        get_kalmanfilter(): Returns an instance of KalmanFilterXYWH for object tracking.
        init_track(dets, scores, cls, img): Initialize track with detections, scores, and classes.
        get_dists(tracks, detections): Get distances between tracks and detections using IoU and (optionally) ReID.
        multi_predict(tracks): Predict and track multiple objects with YOLOv8 model.

    Usage:
        bot_sort = BOTSORT(args, frame_rate)
        bot_sort.init_track(dets, scores, cls, img)
        bot_sort.multi_predict(tracks)

    Note:
        The class is designed to work with the YOLOv8 object detection model and supports ReID only if enabled via args.
    """

    def __init__(self, args, frame_rate=30):
        """Initialize YOLOv8 object with ReID module and GMC algorithm."""
        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.gmc_method)

    def get_kalmanfilter(self):
        """Returns an instance of KalmanFilterXYWH for object tracking."""
        return KalmanFilterXYWH()

    def init_track(self, dets, scores, cls, img=None):
        """Initialize track with detections, scores, and classes."""
        if len(dets) == 0:
            return []
        if self.args.with_reid and self.encoder is not None:
            features_keep = self.encoder.inference(img, dets)
            return [BOTrack(xyxy, s, c, f) for (xyxy, s, c, f) in zip(dets, scores, cls, features_keep)]  # detections
        else:
            return [BOTrack(xyxy, s, c) for (xyxy, s, c) in zip(dets, scores, cls)]  # detections

    def get_dists(self, tracks, detections):
        """Get distances between tracks and detections using IoU and (optionally) ReID embeddings."""
        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):
        """Predict and track multiple objects with YOLOv8 model."""
        BOTrack.multi_predict(tracks)

    def reset(self):
        """Reset tracker."""
        super().reset()
        self.gmc.reset_params()

__init__(args, frame_rate=30)

YOLOv8 nesnesini ReID mod├╝l├╝ ve GMC algoritmas─▒ ile ba┼člat─▒n.

Kaynak kodu ultralytics/trackers/bot_sort.py
def __init__(self, args, frame_rate=30):
    """Initialize YOLOv8 object with ReID module and GMC algorithm."""
    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.gmc_method)

get_dists(tracks, detections)

IoU ve (iste─če ba─čl─▒ olarak) ReID kat─▒┼čt─▒rmalar─▒n─▒ kullanarak izler ve alg─▒lamalar aras─▒ndaki mesafeleri al─▒n.

Kaynak kodu ultralytics/trackers/bot_sort.py
def get_dists(self, tracks, detections):
    """Get distances between tracks and detections using IoU and (optionally) ReID embeddings."""
    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

get_kalmanfilter()

Nesne izleme i├žin bir KalmanFilterXYWH ├Ârne─či d├Ând├╝r├╝r.

Kaynak kodu ultralytics/trackers/bot_sort.py
def get_kalmanfilter(self):
    """Returns an instance of KalmanFilterXYWH for object tracking."""
    return KalmanFilterXYWH()

init_track(dets, scores, cls, img=None)

─░zi tespitler, puanlar ve s─▒n─▒flarla ba┼člat─▒n.

Kaynak kodu ultralytics/trackers/bot_sort.py
def init_track(self, dets, scores, cls, img=None):
    """Initialize track with detections, scores, and classes."""
    if len(dets) == 0:
        return []
    if self.args.with_reid and self.encoder is not None:
        features_keep = self.encoder.inference(img, dets)
        return [BOTrack(xyxy, s, c, f) for (xyxy, s, c, f) in zip(dets, scores, cls, features_keep)]  # detections
    else:
        return [BOTrack(xyxy, s, c) for (xyxy, s, c) in zip(dets, scores, cls)]  # detections

multi_predict(tracks)

YOLOv8 modeli ile birden fazla nesneyi tahmin edin ve izleyin.

Kaynak kodu ultralytics/trackers/bot_sort.py
def multi_predict(self, tracks):
    """Predict and track multiple objects with YOLOv8 model."""
    BOTrack.multi_predict(tracks)

reset()

─░zleyiciyi s─▒f─▒rla.

Kaynak kodu ultralytics/trackers/bot_sort.py
def reset(self):
    """Reset tracker."""
    super().reset()
    self.gmc.reset_params()





Created 2023-11-12, Updated 2024-06-02
Authors: glenn-jocher (5), Burhan-Q (1), Laughing-q (1)