FPh/!ddlmZddlZddlmZddlmZmZddl m Z ddl m Z ddl mZGd d eZGd d eZy) )dequeN) TrackState) BYTETrackerSTrack)matching)GMCKalmanFilterXYWHceZdZdZeZd fd ZdZdZd fd Z fdZ e dZ e dZd Ze d ZxZS) BOTrackaI 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) ct||||d|_d|_||j |t g||_d|_y)zgInitialize YOLOv8 object with temporal parameters, such as feature history, alpha and current features.N)maxleng?)super__init__ smooth_feat curr_featupdate_featuresrfeaturesalpha)selftlwhscoreclsfeat feat_history __class__s hC:\Users\daisl\Desktop\realtime-object-detection\venv\Lib\site-packages\ultralytics/trackers/bot_sort.pyrzBOTrack.__init__,sL uc*     &b6  c|tjj|z}||_|j||_n1|j |jzd|j z |zz|_|j j||xjtjj|jzc_y)zFUpdate features vector and smooth it using exponential moving average.Nr)nplinalgnormrrrrappend)rrs rrzBOTrack.update_features7s  t$$    ##D #zzD,<,<<DJJRV?VVD  T" BIINN4+;+;<<rc|jj}|jtjk7r d|d<d|d<|j j ||j\|_|_y)z5Predicts the mean and covariance using Kalman filter.rN)meancopystaterTracked kalman_filterpredict covariance)r mean_states rr-zBOTrack.predictBs[YY^^% ::++ +JqMJqM%)%7%7%?%? DOO%\" 4?rcv|j|j|jt| |||y)zJReactivates a track with updated features and optionally assigns a new ID.N)rrr re_activate)r new_trackframe_idnew_idrs rr1zBOTrack.re_activateKs4    *  !4!4 5 Ix8rct|j|j|jt| ||y)z7Update the YOLOv8 instance with new track and frame ID.N)rrrupdate)rr2r3rs rr6zBOTrack.updateQs1    *  !4!4 5 y(+rc|j|jjS|jddj}|ddxxx|dddz zccc|S)zVGet current position in bounding box format `(top left x, top left y, width, height)`.N)r(_tlwhr))rrets rrz BOTrack.tlwhWsV 99 ::??$ $iim  " BQ3qr7Q; rc6t|dkrytj|Dcgc]}|jj c}}tj|Dcgc]}|j c}}t |D]3\}}|jtjk7s$d||d<d||d<5tjj||\}}t t||D]\}\}}|||_|||_ycc}wcc}w)zVPredicts the mean and covariance of multiple object tracks using shared Kalman filter.rNr&r')lenr!asarrayr(r)r. enumerater*rr+r shared_kalman multi_predictzip)stracksst multi_meanmulti_covarianceir(covs rrAzBOTrack.multi_predict`s w<1  ZZ' B'B' BC ::w&Gwr}}w&GHw'EArxx:---#$ 1 a #$ 1 a ((/'<'<'J'J:Wg'h$ $'J8H(IJNA{c"GAJO$'GAJ !K!C&Gs !DDc$|j|S)zSConverts Top-Left-Width-Height bounding box coordinates to X-Y-Width-Height format.) tlwh_to_xywh)rrs rconvert_coordszBOTrack.convert_coordsps  &&rcttj|j}|ddxxx|dddz z ccc|S)zEConvert bounding box to format `(center x, center y, width, height)`.Nr9)r!r>r))rr;s rrJzBOTrack.tlwh_to_xywhts:jj##% BQ3qr7Q; r)N2)F)__name__ __module__ __qualname____doc__r r@rrr-r1r6propertyr staticmethodrArKrJ __classcell__rs@rr r sm6%&M  =]9 ,  ( ('rr c>eZdZdZdfd ZdZddZdZdZxZ S) BOTSORTa 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. ct||||j|_|j|_|jrd|_t |j|_y)z>DLdoo.rctS)zI 99  4<<#; LL223=MBEdFTWYfBghBgaAGD!Q*Bgh hrs9!-1kfk\F&kF&r