hh TddlZddlZddlmZddlmZmZ ddlZejsJ ddejdedefd Zd ed ed ejfd Zddededed ejfdZdejded ejfdZy#e e e f$rddl mZedddlZY{wxYw)N)cdist) batch_probioubbox_ioa)check_requirementsz lap>=0.5.12 cost_matrixthreshuse_lapc |jdk(r\tjdtt t |j dt t |j dfS|rytj|d|\}}}t|Dcgc]\}}|dk\s ||g}}}tj|dkd} tj|dkd} nctjj|\}}tjt t|D cgc]} ||| || f|ks|| || gc} }t|dk(rWt!tj"|j d} t!tj"|j d} nt!t%tj"|j dt%|dddfz } t!t%tj"|j dt%|dddfz } || | fScc}}wcc} w)a Perform linear assignment using either the scipy or lap.lapjv method. Args: cost_matrix (np.ndarray): The matrix containing cost values for assignments, with shape (N, M). thresh (float): Threshold for considering an assignment valid. use_lap (bool): Use lap.lapjv for the assignment. If False, scipy.optimize.linear_sum_assignment is used. Returns: matched_indices (np.ndarray): Array of matched indices of shape (K, 2), where K is the number of matches. unmatched_a (np.ndarray): Array of unmatched indices from the first set, with shape (L,). unmatched_b (np.ndarray): Array of unmatched indices from the second set, with shape (M,). Examples: >>> cost_matrix = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]]) >>> thresh = 5.0 >>> matched_indices, unmatched_a, unmatched_b = linear_assignment(cost_matrix, thresh, use_lap=True) r)rdtypeT) extend_cost cost_limitN)sizenpemptyinttuplerangeshapelaplapjv enumeratewherescipyoptimizelinear_sum_assignmentasarraylenlistarange frozenset) rrr _xyixmxmatches unmatched_a unmatched_bis a/var/www/html/dev/engine/venv/lib/python3.12/site-packages/ultralytics/trackers/utils/matching.pylinear_assignmentr.s&1xxc*E% 8I8I!8L2M,NPUV[\g\m\mno\pVqPrrr))KTfM1a*3A,BB"'B8BBhhq1uoa( hhq1uoa( ~~33K@1**E#a&Mgq[QRSTQUWXYZW[Q[E\`fEfqtQqTlgh w<1 ryy):):1)=>?Kryy):):1)=>?Ky;3D3DQ3G)HIIV]^_ab^bVcLddeKy;3D3DQ3G)HIIV]^_ab^bVcLddeK K ,,Chs I&I.I Iatracksbtracksreturnc|rt|dtjs|r"t|dtjr|}|}nb|Dcgc]&}|j |jn |j (}}|Dcgc]&}|j |jn |j (}}tj t|t|ftj}t|rt|rt|ddk(rvt|ddk(rettj|tjtj|tjj}d|z Sttj|tjtj|tjd}d|z Scc}wcc}w)a Compute cost based on Intersection over Union (IoU) between tracks. Args: atracks (List[STrack] | List[np.ndarray]): List of tracks 'a' or bounding boxes. btracks (List[STrack] | List[np.ndarray]): List of tracks 'b' or bounding boxes. Returns: (np.ndarray): Cost matrix computed based on IoU with shape (len(atracks), len(btracks)). Examples: Compute IoU distance between two sets of tracks >>> atracks = [np.array([0, 0, 10, 10]), np.array([20, 20, 30, 30])] >>> btracks = [np.array([5, 5, 15, 15]), np.array([25, 25, 35, 35])] >>> cost_matrix = iou_distance(atracks, btracks) rr T)iour) isinstancerndarrayanglexywhaxyxyzerosr float32rascontiguousarraynumpyr)r/r0atlbrsbtlbrstrackiouss r- iou_distancerB@sn":gaj"**5ZPWXYPZ\^\f\fEgV]^U!8%++ejjH^^V]^U!8%++ejjH^^ 88S[#f+.bjj AD 6{s6{ vay>Q 3vay>Q#6 $$V2::>$$V2::>eg  t8O $$V2::>$$V2::>D t8O!_^s +G9+Gtracks detectionsmetricctjt|t|ftj}|jdk(r|Stj |Dcgc]}|j c}tj}tj |Dcgc]}|jc}tj}tjdt|||}|Scc}wcc}w)a Compute distance between tracks and detections based on embeddings. Args: tracks (List[STrack]): List of tracks, where each track contains embedding features. detections (List[BaseTrack]): List of detections, where each detection contains embedding features. metric (str): Metric for distance computation. Supported metrics include 'cosine', 'euclidean', etc. Returns: (np.ndarray): Cost matrix computed based on embeddings with shape (N, M), where N is the number of tracks and M is the number of detections. Examples: Compute the embedding distance between tracks and detections using cosine metric >>> tracks = [STrack(...), STrack(...)] # List of track objects with embedding features >>> detections = [BaseTrack(...), BaseTrack(...)] # List of detection objects with embedding features >>> cost_matrix = embedding_distance(tracks, detections, metric="cosine") r rg) rr:r r;rr curr_feat smooth_featmaximumr)rCrDrErr@ det_featurestrack_featuress r-embedding_distancerLhs&((CKZ9LK1::JG5uGrzzZLZZ Gu!2!2 GrzzZN**S% f"MNK  H!Hs C(C-c|jdk(r|Sd|z }tj|Dcgc]}|jc}}tj|dj |j dd}||z}d|z Scc}w)a Fuse cost matrix with detection scores to produce a single similarity matrix. Args: cost_matrix (np.ndarray): The matrix containing cost values for assignments, with shape (N, M). detections (List[BaseTrack]): List of detections, each containing a score attribute. Returns: (np.ndarray): Fused similarity matrix with shape (N, M). Examples: Fuse a cost matrix with detection scores >>> cost_matrix = np.random.rand(5, 10) # 5 tracks and 10 detections >>> detections = [BaseTrack(score=np.random.rand()) for _ in range(10)] >>> fused_matrix = fuse_score(cost_matrix, detections) rr)axis)rrarrayscore expand_dimsrepeatr)rrDiou_simdet det_scoresfuse_sims r- fuse_scorerWs"1+oG ;399;res (= ???)-2::)-u)-t)-X%$%%"**%PtsRTR\R\<BJJDRZZs ^^4;}% sB B'&B'