सामग्री पर जाएं

के लिए संदर्भ ultralytics/trackers/byte_tracker.py

नोट

यह फ़ाइल यहाँ उपलब्ध है https://github.com/ultralytics/ultralytics/बूँद/मुख्य/ultralytics/ट्रैकर्स/byte_tracker.py का उपयोग करें। यदि आप कोई समस्या देखते हैं तो कृपया पुल अनुरोध का योगदान करके इसे ठीक करने में मदद करें 🛠️। 🙏 धन्यवाद !



ultralytics.trackers.byte_tracker.STrack

का रूप: BaseTrack

एकल ऑब्जेक्ट ट्रैकिंग प्रतिनिधित्व जो राज्य अनुमान के लिए कलमैन फ़िल्टरिंग का उपयोग करता है।

यह वर्ग व्यक्तिगत ट्रैकलेट के बारे में सभी जानकारी संग्रहीत करने के लिए जिम्मेदार है और राज्य अपडेट करता है और कलमैन फ़िल्टर पर आधारित भविष्यवाणियां।

विशेषताएँ:

नाम प्रकार या क़िस्‍म
shared_kalman KalmanFilterXYAH

साझा कलमैन फ़िल्टर जो भविष्यवाणी के लिए सभी STrack उदाहरणों में उपयोग किया जाता है।

_tlwh ndarray

शीर्ष-बाएँ कोने निर्देशांक और बाउंडिंग बॉक्स की चौड़ाई और ऊंचाई को स्टोर करने के लिए निजी विशेषता।

kalman_filter KalmanFilterXYAH

इस विशेष ऑब्जेक्ट ट्रैक के लिए उपयोग किए जाने वाले कलमैन फ़िल्टर का उदाहरण।

mean ndarray

मतलब राज्य अनुमान वेक्टर।

covariance ndarray

राज्य के अनुमान का सहप्रसरण।

is_activated bool

बूलियन ध्वज दर्शाता है कि क्या ट्रैक सक्रिय किया गया है।

score float

ट्रैक का कॉन्फिडेंस स्कोर।

tracklet_len int

ट्रैकलेट की लंबाई।

cls any

ऑब्जेक्ट के लिए क्लास लेबल।

idx int

ऑब्जेक्ट के लिए अनुक्रमणिका या पहचानकर्ता.

frame_id int

वर्तमान फ़्रेम ID.

start_frame int

फ़्रेम जहां ऑब्जेक्ट का पहली बार पता चला था।

विधियाँ:

नाम या क़िस्‍म
predict

Kalman फिल्टर का उपयोग वस्तु के अगले राज्य की भविष्यवाणी.

multi_predict

कई पटरियों के लिए अगले राज्यों की भविष्यवाणी करें।

multi_gmc

होमोग्राफी मैट्रिक्स का उपयोग करके कई ट्रैक राज्यों को अपडेट करें।

activate

एक नया ट्रैकलेट सक्रिय करें।

re_activate

पहले से खोए हुए ट्रैकलेट को पुनः सक्रिय करें।

update

मेल खाने वाले ट्रैक की स्थिति अपडेट करें।

convert_coords

बाउंडिंग बॉक्स को x-y-aspect-height प्रारूप में कनवर्ट करें।

tlwh_to_xyah

tlwh बाउंडिंग बॉक्स को xyah प्रारूप में बदलें।

में स्रोत कोड ultralytics/trackers/byte_tracker.py
class STrack(BaseTrack):
    """
    Single object tracking representation that uses Kalman filtering for state estimation.

    This class is responsible for storing all the information regarding individual tracklets and performs state updates
    and predictions based on Kalman filter.

    Attributes:
        shared_kalman (KalmanFilterXYAH): Shared Kalman filter that is used across all STrack instances for prediction.
        _tlwh (np.ndarray): Private attribute to store top-left corner coordinates and width and height of bounding box.
        kalman_filter (KalmanFilterXYAH): Instance of Kalman filter used for this particular object track.
        mean (np.ndarray): Mean state estimate vector.
        covariance (np.ndarray): Covariance of state estimate.
        is_activated (bool): Boolean flag indicating if the track has been activated.
        score (float): Confidence score of the track.
        tracklet_len (int): Length of the tracklet.
        cls (any): Class label for the object.
        idx (int): Index or identifier for the object.
        frame_id (int): Current frame ID.
        start_frame (int): Frame where the object was first detected.

    Methods:
        predict(): Predict the next state of the object using Kalman filter.
        multi_predict(stracks): Predict the next states for multiple tracks.
        multi_gmc(stracks, H): Update multiple track states using a homography matrix.
        activate(kalman_filter, frame_id): Activate a new tracklet.
        re_activate(new_track, frame_id, new_id): Reactivate a previously lost tracklet.
        update(new_track, frame_id): Update the state of a matched track.
        convert_coords(tlwh): Convert bounding box to x-y-aspect-height format.
        tlwh_to_xyah(tlwh): Convert tlwh bounding box to xyah format.
    """

    shared_kalman = KalmanFilterXYAH()

    def __init__(self, xywh, score, cls):
        """Initialize new STrack instance."""
        super().__init__()
        # xywh+idx or xywha+idx
        assert len(xywh) in {5, 6}, f"expected 5 or 6 values but got {len(xywh)}"
        self._tlwh = np.asarray(xywh2ltwh(xywh[:4]), dtype=np.float32)
        self.kalman_filter = None
        self.mean, self.covariance = None, None
        self.is_activated = False

        self.score = score
        self.tracklet_len = 0
        self.cls = cls
        self.idx = xywh[-1]
        self.angle = xywh[4] if len(xywh) == 6 else None

    def predict(self):
        """Predicts mean and covariance using Kalman filter."""
        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):
        """Perform multi-object predictive tracking using Kalman filter for given stracks."""
        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][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

    @staticmethod
    def multi_gmc(stracks, H=np.eye(2, 3)):
        """Update state tracks positions and covariances using a homography matrix."""
        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])

            R = H[:2, :2]
            R8x8 = np.kron(np.eye(4, dtype=float), R)
            t = H[:2, 2]

            for i, (mean, cov) in enumerate(zip(multi_mean, multi_covariance)):
                mean = R8x8.dot(mean)
                mean[:2] += t
                cov = R8x8.dot(cov).dot(R8x8.transpose())

                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.convert_coords(self._tlwh))

        self.tracklet_len = 0
        self.state = TrackState.Tracked
        if frame_id == 1:
            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):
        """Reactivates a previously lost track with a new detection."""
        self.mean, self.covariance = self.kalman_filter.update(
            self.mean, self.covariance, self.convert_coords(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
        self.cls = new_track.cls
        self.angle = new_track.angle
        self.idx = new_track.idx

    def update(self, new_track, frame_id):
        """
        Update the state of a matched track.

        Args:
            new_track (STrack): The new track containing updated information.
            frame_id (int): The ID of the current frame.
        """
        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.convert_coords(new_tlwh)
        )
        self.state = TrackState.Tracked
        self.is_activated = True

        self.score = new_track.score
        self.cls = new_track.cls
        self.angle = new_track.angle
        self.idx = new_track.idx

    def convert_coords(self, tlwh):
        """Convert a bounding box's top-left-width-height format to its x-y-aspect-height equivalent."""
        return self.tlwh_to_xyah(tlwh)

    @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 xyxy(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

    @property
    def xywh(self):
        """Get current position in bounding box format (center x, center y, width, height)."""
        ret = np.asarray(self.tlwh).copy()
        ret[:2] += ret[2:] / 2
        return ret

    @property
    def xywha(self):
        """Get current position in bounding box format (center x, center y, width, height, angle)."""
        if self.angle is None:
            LOGGER.warning("WARNING ⚠️ `angle` attr not found, returning `xywh` instead.")
            return self.xywh
        return np.concatenate([self.xywh, self.angle[None]])

    @property
    def result(self):
        """Get current tracking results."""
        coords = self.xyxy if self.angle is None else self.xywha
        return coords.tolist() + [self.track_id, self.score, self.cls, self.idx]

    def __repr__(self):
        """Return a string representation of the BYTETracker object with start and end frames and track ID."""
        return f"OT_{self.track_id}_({self.start_frame}-{self.end_frame})"

result property

वर्तमान ट्रैकिंग परिणाम प्राप्त करें।

tlwh property

बाउंडिंग बॉक्स प्रारूप में वर्तमान स्थिति प्राप्त करें (शीर्ष बाएं x, शीर्ष बाएं y, चौड़ाई, ऊंचाई)।

xywh property

बाउंडिंग बॉक्स प्रारूप (केंद्र एक्स, केंद्र वाई, चौड़ाई, ऊंचाई) में वर्तमान स्थिति प्राप्त करें।

xywha property

बाउंडिंग बॉक्स प्रारूप (केंद्र x, केंद्र y, चौड़ाई, ऊंचाई, कोण) में वर्तमान स्थिति प्राप्त करें।

xyxy property

बाउंडिंग बॉक्स को प्रारूप में कनवर्ट करें (न्यूनतम x, न्यूनतम y, अधिकतम x, अधिकतम y), यानी, (ऊपर बाएँ, नीचे दाएँ)।

__init__(xywh, score, cls)

नया STrack इंस्टेंस इनिशियलाइज़ करें।

में स्रोत कोड ultralytics/trackers/byte_tracker.py
def __init__(self, xywh, score, cls):
    """Initialize new STrack instance."""
    super().__init__()
    # xywh+idx or xywha+idx
    assert len(xywh) in {5, 6}, f"expected 5 or 6 values but got {len(xywh)}"
    self._tlwh = np.asarray(xywh2ltwh(xywh[:4]), dtype=np.float32)
    self.kalman_filter = None
    self.mean, self.covariance = None, None
    self.is_activated = False

    self.score = score
    self.tracklet_len = 0
    self.cls = cls
    self.idx = xywh[-1]
    self.angle = xywh[4] if len(xywh) == 6 else None

__repr__()

प्रारंभ और अंत फ्रेम और ट्रैक आईडी के साथ BYTETracker ऑब्जेक्ट का एक स्ट्रिंग प्रतिनिधित्व लौटाएं।

में स्रोत कोड ultralytics/trackers/byte_tracker.py
def __repr__(self):
    """Return a string representation of the BYTETracker object with start and end frames and track ID."""
    return f"OT_{self.track_id}_({self.start_frame}-{self.end_frame})"

activate(kalman_filter, frame_id)

एक नया ट्रैकलेट शुरू करें।

में स्रोत कोड ultralytics/trackers/byte_tracker.py
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.convert_coords(self._tlwh))

    self.tracklet_len = 0
    self.state = TrackState.Tracked
    if frame_id == 1:
        self.is_activated = True
    self.frame_id = frame_id
    self.start_frame = frame_id

convert_coords(tlwh)

एक बाउंडिंग बॉक्स के ऊपरी-बाएं-चौड़ाई-ऊंचाई प्रारूप को उसके x-y-पहलू-ऊंचाई समकक्ष में कनवर्ट करें।

में स्रोत कोड ultralytics/trackers/byte_tracker.py
def convert_coords(self, tlwh):
    """Convert a bounding box's top-left-width-height format to its x-y-aspect-height equivalent."""
    return self.tlwh_to_xyah(tlwh)

multi_gmc(stracks, H=np.eye(2, 3)) staticmethod

अद्यतन राज्य एक होमोग्राफी मैट्रिक्स का उपयोग करके पदों और सहप्रसरण को ट्रैक करता है।

में स्रोत कोड ultralytics/trackers/byte_tracker.py
@staticmethod
def multi_gmc(stracks, H=np.eye(2, 3)):
    """Update state tracks positions and covariances using a homography matrix."""
    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])

        R = H[:2, :2]
        R8x8 = np.kron(np.eye(4, dtype=float), R)
        t = H[:2, 2]

        for i, (mean, cov) in enumerate(zip(multi_mean, multi_covariance)):
            mean = R8x8.dot(mean)
            mean[:2] += t
            cov = R8x8.dot(cov).dot(R8x8.transpose())

            stracks[i].mean = mean
            stracks[i].covariance = cov

multi_predict(stracks) staticmethod

दिए गए stracks के लिए Kalman फिल्टर का उपयोग कर बहु वस्तु भविष्य कहनेवाला ट्रैकिंग प्रदर्शन.

में स्रोत कोड ultralytics/trackers/byte_tracker.py
@staticmethod
def multi_predict(stracks):
    """Perform multi-object predictive tracking using Kalman filter for given stracks."""
    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][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

predict()

Kalman फिल्टर का उपयोग करके माध्य और सहप्रसरण की भविष्यवाणी करता है।

में स्रोत कोड ultralytics/trackers/byte_tracker.py
def predict(self):
    """Predicts mean and covariance using Kalman filter."""
    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)

re_activate(new_track, frame_id, new_id=False)

एक नई पहचान के साथ पहले से खोए हुए ट्रैक को पुनः सक्रिय करता है।

में स्रोत कोड ultralytics/trackers/byte_tracker.py
def re_activate(self, new_track, frame_id, new_id=False):
    """Reactivates a previously lost track with a new detection."""
    self.mean, self.covariance = self.kalman_filter.update(
        self.mean, self.covariance, self.convert_coords(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
    self.cls = new_track.cls
    self.angle = new_track.angle
    self.idx = new_track.idx

tlwh_to_xyah(tlwh) staticmethod

बाउंडिंग बॉक्स को प्रारूप (केंद्र x, केंद्र y, पहलू अनुपात, ऊंचाई) में कनवर्ट करें, जहां पहलू अनुपात चौड़ाई / पराकाष्‍ठा।

में स्रोत कोड ultralytics/trackers/byte_tracker.py
@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

update(new_track, frame_id)

मेल खाने वाले ट्रैक की स्थिति अपडेट करें।

पैरामीटर:

नाम प्रकार या क़िस्‍म चूक
new_track STrack

अद्यतन जानकारी वाला नया ट्रैक।

आवश्यक
frame_id int

वर्तमान फ़्रेम की ID.

आवश्यक
में स्रोत कोड ultralytics/trackers/byte_tracker.py
def update(self, new_track, frame_id):
    """
    Update the state of a matched track.

    Args:
        new_track (STrack): The new track containing updated information.
        frame_id (int): The ID of the current frame.
    """
    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.convert_coords(new_tlwh)
    )
    self.state = TrackState.Tracked
    self.is_activated = True

    self.score = new_track.score
    self.cls = new_track.cls
    self.angle = new_track.angle
    self.idx = new_track.idx



ultralytics.trackers.byte_tracker.BYTETracker

BYTETracker: के शीर्ष पर निर्मित एक ट्रैकिंग एल्गोरिथ्म YOLOv8 वस्तु का पता लगाने और ट्रैकिंग के लिए।

कक्षा एक वीडियो में पता लगाई गई वस्तुओं के लिए पटरियों को प्रारंभ करने, अपडेट करने और प्रबंधित करने के लिए जिम्मेदार है अनुक्रम। यह फ्रेम पर ट्रैक किए गए, खोए हुए और हटाए गए ट्रैक की स्थिति को बनाए रखता है, कलमैन फ़िल्टरिंग का उपयोग करता है नए ऑब्जेक्ट स्थानों की भविष्यवाणी करना, और डेटा एसोसिएशन करना।

विशेषताएँ:

नाम प्रकार या क़िस्‍म
tracked_stracks list[STrack]

सफलतापूर्वक सक्रिय पटरियों की सूची।

lost_stracks list[STrack]

खोए हुए ट्रैक की सूची।

removed_stracks list[STrack]

हटाए गए ट्रैक की सूची।

frame_id int

वर्तमान फ़्रेम ID.

args namespace

आदेश-पंक्ति तर्क.

max_time_lost int

एक ट्रैक के लिए अधिकतम फ्रेम को 'खोया' माना जाता है।

kalman_filter object

Kalman फ़िल्टर ऑब्जेक्ट।

विधियाँ:

नाम या क़िस्‍म
update

नए डिटेक्शन के साथ ऑब्जेक्ट ट्रैकर अपडेट करता है।

get_kalmanfilter

बाउंडिंग बॉक्स को ट्रैक करने के लिए एक कलमैन फ़िल्टर ऑब्जेक्ट लौटाता है।

init_track

डिटेक्शन के साथ ऑब्जेक्ट ट्रैकिंग प्रारंभ करें।

get_dists

पटरियों और पता लगाने के बीच की दूरी की गणना करता है।

multi_predict

पटरियों के स्थान की भविष्यवाणी करता है।

reset_id

STrack का ID काउंटर रीसेट करता है।

joint_stracks

स्ट्रैक्स की दो सूचियों को जोड़ती है।

sub_stracks

पहली सूची से दूसरी सूची में मौजूद स्ट्रैक को फ़िल्टर करता है।

remove_duplicate_stracks

IoU के आधार पर डुप्लिकेट ट्रैक को हटाता है।

में स्रोत कोड ultralytics/trackers/byte_tracker.py
class BYTETracker:
    """
    BYTETracker: A tracking algorithm built on top of YOLOv8 for object detection and tracking.

    The class is responsible for initializing, updating, and managing the tracks for detected objects in a video
    sequence. It maintains the state of tracked, lost, and removed tracks over frames, utilizes Kalman filtering for
    predicting the new object locations, and performs data association.

    Attributes:
        tracked_stracks (list[STrack]): List of successfully activated tracks.
        lost_stracks (list[STrack]): List of lost tracks.
        removed_stracks (list[STrack]): List of removed tracks.
        frame_id (int): The current frame ID.
        args (namespace): Command-line arguments.
        max_time_lost (int): The maximum frames for a track to be considered as 'lost'.
        kalman_filter (object): Kalman Filter object.

    Methods:
        update(results, img=None): Updates object tracker with new detections.
        get_kalmanfilter(): Returns a Kalman filter object for tracking bounding boxes.
        init_track(dets, scores, cls, img=None): Initialize object tracking with detections.
        get_dists(tracks, detections): Calculates the distance between tracks and detections.
        multi_predict(tracks): Predicts the location of tracks.
        reset_id(): Resets the ID counter of STrack.
        joint_stracks(tlista, tlistb): Combines two lists of stracks.
        sub_stracks(tlista, tlistb): Filters out the stracks present in the second list from the first list.
        remove_duplicate_stracks(stracksa, stracksb): Removes duplicate stracks based on IoU.
    """

    def __init__(self, args, frame_rate=30):
        """Initialize a YOLOv8 object to track objects with given arguments and frame rate."""
        self.tracked_stracks = []  # type: list[STrack]
        self.lost_stracks = []  # type: list[STrack]
        self.removed_stracks = []  # type: list[STrack]

        self.frame_id = 0
        self.args = args
        self.max_time_lost = int(frame_rate / 30.0 * args.track_buffer)
        self.kalman_filter = self.get_kalmanfilter()
        self.reset_id()

    def update(self, results, img=None):
        """Updates object tracker with new detections and returns tracked object bounding boxes."""
        self.frame_id += 1
        activated_stracks = []
        refind_stracks = []
        lost_stracks = []
        removed_stracks = []

        scores = results.conf
        bboxes = results.xywhr if hasattr(results, "xywhr") else results.xywh
        # Add index
        bboxes = np.concatenate([bboxes, np.arange(len(bboxes)).reshape(-1, 1)], axis=-1)
        cls = results.cls

        remain_inds = scores >= self.args.track_high_thresh
        inds_low = scores > self.args.track_low_thresh
        inds_high = scores < self.args.track_high_thresh

        inds_second = inds_low & inds_high
        dets_second = bboxes[inds_second]
        dets = bboxes[remain_inds]
        scores_keep = scores[remain_inds]
        scores_second = scores[inds_second]
        cls_keep = cls[remain_inds]
        cls_second = cls[inds_second]

        detections = self.init_track(dets, scores_keep, cls_keep, img)
        # 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 = self.joint_stracks(tracked_stracks, self.lost_stracks)
        # Predict the current location with KF
        self.multi_predict(strack_pool)
        if hasattr(self, "gmc") and img is not None:
            warp = self.gmc.apply(img, dets)
            STrack.multi_gmc(strack_pool, warp)
            STrack.multi_gmc(unconfirmed, warp)

        dists = self.get_dists(strack_pool, detections)
        matches, u_track, u_detection = matching.linear_assignment(dists, thresh=self.args.match_thresh)

        for itracked, idet in matches:
            track = strack_pool[itracked]
            det = detections[idet]
            if track.state == TrackState.Tracked:
                track.update(det, self.frame_id)
                activated_stracks.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
        detections_second = self.init_track(dets_second, scores_second, cls_second, img)
        r_tracked_stracks = [strack_pool[i] for i in u_track if strack_pool[i].state == TrackState.Tracked]
        # TODO
        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_stracks.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 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 = self.get_dists(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_stracks.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.args.new_track_thresh:
                continue
            track.activate(self.kalman_filter, self.frame_id)
            activated_stracks.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 = self.joint_stracks(self.tracked_stracks, activated_stracks)
        self.tracked_stracks = self.joint_stracks(self.tracked_stracks, refind_stracks)
        self.lost_stracks = self.sub_stracks(self.lost_stracks, self.tracked_stracks)
        self.lost_stracks.extend(lost_stracks)
        self.lost_stracks = self.sub_stracks(self.lost_stracks, self.removed_stracks)
        self.tracked_stracks, self.lost_stracks = self.remove_duplicate_stracks(self.tracked_stracks, self.lost_stracks)
        self.removed_stracks.extend(removed_stracks)
        if len(self.removed_stracks) > 1000:
            self.removed_stracks = self.removed_stracks[-999:]  # clip remove stracks to 1000 maximum

        return np.asarray([x.result for x in self.tracked_stracks if x.is_activated], dtype=np.float32)

    def get_kalmanfilter(self):
        """Returns a Kalman filter object for tracking bounding boxes."""
        return KalmanFilterXYAH()

    def init_track(self, dets, scores, cls, img=None):
        """Initialize object tracking with detections and scores using STrack algorithm."""
        return [STrack(xyxy, s, c) for (xyxy, s, c) in zip(dets, scores, cls)] if len(dets) else []  # detections

    def get_dists(self, tracks, detections):
        """Calculates the distance between tracks and detections using IoU and fuses scores."""
        dists = matching.iou_distance(tracks, detections)
        # TODO: mot20
        # if not self.args.mot20:
        dists = matching.fuse_score(dists, detections)
        return dists

    def multi_predict(self, tracks):
        """Returns the predicted tracks using the YOLOv8 network."""
        STrack.multi_predict(tracks)

    @staticmethod
    def reset_id():
        """Resets the ID counter of STrack."""
        STrack.reset_id()

    def reset(self):
        """Reset tracker."""
        self.tracked_stracks = []  # type: list[STrack]
        self.lost_stracks = []  # type: list[STrack]
        self.removed_stracks = []  # type: list[STrack]
        self.frame_id = 0
        self.kalman_filter = self.get_kalmanfilter()
        self.reset_id()

    @staticmethod
    def joint_stracks(tlista, tlistb):
        """Combine two lists of stracks into a single one."""
        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

    @staticmethod
    def sub_stracks(tlista, tlistb):
        """DEPRECATED CODE in https://github.com/ultralytics/ultralytics/pull/1890/
        stracks = {t.track_id: t for t in tlista}
        for t in tlistb:
            tid = t.track_id
            if stracks.get(tid, 0):
                del stracks[tid]
        return list(stracks.values())
        """
        track_ids_b = {t.track_id for t in tlistb}
        return [t for t in tlista if t.track_id not in track_ids_b]

    @staticmethod
    def remove_duplicate_stracks(stracksa, stracksb):
        """Remove duplicate stracks with non-maximum IoU distance."""
        pdist = matching.iou_distance(stracksa, stracksb)
        pairs = np.where(pdist < 0.15)
        dupa, dupb = [], []
        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 i not in dupa]
        resb = [t for i, t in enumerate(stracksb) if i not in dupb]
        return resa, resb

__init__(args, frame_rate=30)

एक YOLOv8 दिए गए तर्कों और फ्रेम दर के साथ वस्तुओं को ट्रैक करने के लिए ऑब्जेक्ट।

में स्रोत कोड ultralytics/trackers/byte_tracker.py
def __init__(self, args, frame_rate=30):
    """Initialize a YOLOv8 object to track objects with given arguments and frame rate."""
    self.tracked_stracks = []  # type: list[STrack]
    self.lost_stracks = []  # type: list[STrack]
    self.removed_stracks = []  # type: list[STrack]

    self.frame_id = 0
    self.args = args
    self.max_time_lost = int(frame_rate / 30.0 * args.track_buffer)
    self.kalman_filter = self.get_kalmanfilter()
    self.reset_id()

get_dists(tracks, detections)

IoU का उपयोग करके पटरियों और डिटेक्शन के बीच की दूरी की गणना करता है और स्कोर को फ़्यूज़ करता है।

में स्रोत कोड ultralytics/trackers/byte_tracker.py
def get_dists(self, tracks, detections):
    """Calculates the distance between tracks and detections using IoU and fuses scores."""
    dists = matching.iou_distance(tracks, detections)
    # TODO: mot20
    # if not self.args.mot20:
    dists = matching.fuse_score(dists, detections)
    return dists

get_kalmanfilter()

बाउंडिंग बॉक्स को ट्रैक करने के लिए एक कलमैन फ़िल्टर ऑब्जेक्ट लौटाता है।

में स्रोत कोड ultralytics/trackers/byte_tracker.py
def get_kalmanfilter(self):
    """Returns a Kalman filter object for tracking bounding boxes."""
    return KalmanFilterXYAH()

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

STrack एल्गोरिथम का उपयोग करके डिटेक्शन और स्कोर के साथ ऑब्जेक्ट ट्रैकिंग को इनिशियलाइज़ करें।

में स्रोत कोड ultralytics/trackers/byte_tracker.py
def init_track(self, dets, scores, cls, img=None):
    """Initialize object tracking with detections and scores using STrack algorithm."""
    return [STrack(xyxy, s, c) for (xyxy, s, c) in zip(dets, scores, cls)] if len(dets) else []  # detections

joint_stracks(tlista, tlistb) staticmethod

स्ट्रैक की दो सूचियों को एक ही में मिलाएं।

में स्रोत कोड ultralytics/trackers/byte_tracker.py
@staticmethod
def joint_stracks(tlista, tlistb):
    """Combine two lists of stracks into a single one."""
    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

multi_predict(tracks)

का उपयोग करके अनुमानित ट्रैक लौटाता है YOLOv8 नेटवर्क।

में स्रोत कोड ultralytics/trackers/byte_tracker.py
def multi_predict(self, tracks):
    """Returns the predicted tracks using the YOLOv8 network."""
    STrack.multi_predict(tracks)

remove_duplicate_stracks(stracksa, stracksb) staticmethod

गैर-अधिकतम IoU दूरी के साथ डुप्लिकेट स्ट्रैक निकालें।

में स्रोत कोड ultralytics/trackers/byte_tracker.py
@staticmethod
def remove_duplicate_stracks(stracksa, stracksb):
    """Remove duplicate stracks with non-maximum IoU distance."""
    pdist = matching.iou_distance(stracksa, stracksb)
    pairs = np.where(pdist < 0.15)
    dupa, dupb = [], []
    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 i not in dupa]
    resb = [t for i, t in enumerate(stracksb) if i not in dupb]
    return resa, resb

reset()

ट्रैकर रीसेट करें।

में स्रोत कोड ultralytics/trackers/byte_tracker.py
def reset(self):
    """Reset tracker."""
    self.tracked_stracks = []  # type: list[STrack]
    self.lost_stracks = []  # type: list[STrack]
    self.removed_stracks = []  # type: list[STrack]
    self.frame_id = 0
    self.kalman_filter = self.get_kalmanfilter()
    self.reset_id()

reset_id() staticmethod

STrack का ID काउंटर रीसेट करता है।

में स्रोत कोड ultralytics/trackers/byte_tracker.py
@staticmethod
def reset_id():
    """Resets the ID counter of STrack."""
    STrack.reset_id()

sub_stracks(tlista, tlistb) staticmethod

DEPRECATED CODE in https://github.com/ultralytics/ultralytics/pull/1890/ stracks = {t.track_id: t for t in tlista} for t in tlistb: tid = t.track_id if stracks.get(tid, 0): del stracks[tid] return list(stracks.values())

में स्रोत कोड ultralytics/trackers/byte_tracker.py
@staticmethod
def sub_stracks(tlista, tlistb):
    """DEPRECATED CODE in https://github.com/ultralytics/ultralytics/pull/1890/
    stracks = {t.track_id: t for t in tlista}
    for t in tlistb:
        tid = t.track_id
        if stracks.get(tid, 0):
            del stracks[tid]
    return list(stracks.values())
    """
    track_ids_b = {t.track_id for t in tlistb}
    return [t for t in tlista if t.track_id not in track_ids_b]

update(results, img=None)

नए डिटेक्शन के साथ ऑब्जेक्ट ट्रैकर को अपडेट करता है और ट्रैक किए गए ऑब्जेक्ट बाउंडिंग बॉक्स लौटाता है।

में स्रोत कोड ultralytics/trackers/byte_tracker.py
def update(self, results, img=None):
    """Updates object tracker with new detections and returns tracked object bounding boxes."""
    self.frame_id += 1
    activated_stracks = []
    refind_stracks = []
    lost_stracks = []
    removed_stracks = []

    scores = results.conf
    bboxes = results.xywhr if hasattr(results, "xywhr") else results.xywh
    # Add index
    bboxes = np.concatenate([bboxes, np.arange(len(bboxes)).reshape(-1, 1)], axis=-1)
    cls = results.cls

    remain_inds = scores >= self.args.track_high_thresh
    inds_low = scores > self.args.track_low_thresh
    inds_high = scores < self.args.track_high_thresh

    inds_second = inds_low & inds_high
    dets_second = bboxes[inds_second]
    dets = bboxes[remain_inds]
    scores_keep = scores[remain_inds]
    scores_second = scores[inds_second]
    cls_keep = cls[remain_inds]
    cls_second = cls[inds_second]

    detections = self.init_track(dets, scores_keep, cls_keep, img)
    # 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 = self.joint_stracks(tracked_stracks, self.lost_stracks)
    # Predict the current location with KF
    self.multi_predict(strack_pool)
    if hasattr(self, "gmc") and img is not None:
        warp = self.gmc.apply(img, dets)
        STrack.multi_gmc(strack_pool, warp)
        STrack.multi_gmc(unconfirmed, warp)

    dists = self.get_dists(strack_pool, detections)
    matches, u_track, u_detection = matching.linear_assignment(dists, thresh=self.args.match_thresh)

    for itracked, idet in matches:
        track = strack_pool[itracked]
        det = detections[idet]
        if track.state == TrackState.Tracked:
            track.update(det, self.frame_id)
            activated_stracks.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
    detections_second = self.init_track(dets_second, scores_second, cls_second, img)
    r_tracked_stracks = [strack_pool[i] for i in u_track if strack_pool[i].state == TrackState.Tracked]
    # TODO
    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_stracks.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 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 = self.get_dists(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_stracks.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.args.new_track_thresh:
            continue
        track.activate(self.kalman_filter, self.frame_id)
        activated_stracks.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 = self.joint_stracks(self.tracked_stracks, activated_stracks)
    self.tracked_stracks = self.joint_stracks(self.tracked_stracks, refind_stracks)
    self.lost_stracks = self.sub_stracks(self.lost_stracks, self.tracked_stracks)
    self.lost_stracks.extend(lost_stracks)
    self.lost_stracks = self.sub_stracks(self.lost_stracks, self.removed_stracks)
    self.tracked_stracks, self.lost_stracks = self.remove_duplicate_stracks(self.tracked_stracks, self.lost_stracks)
    self.removed_stracks.extend(removed_stracks)
    if len(self.removed_stracks) > 1000:
        self.removed_stracks = self.removed_stracks[-999:]  # clip remove stracks to 1000 maximum

    return np.asarray([x.result for x in self.tracked_stracks if x.is_activated], dtype=np.float32)





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