3jSSKJr SSKrSSKrSSKrSSKJr SSKJrJ r J r SSK r SSK J r SSKJrJr SSKJr SSKJr SS KJr SS KJr S /r\R4"\5r"S S 5rg) ) annotationsN)Path)AnyOptionalUnion) kornia_config)ObjectDetectorRTDETRDetectorBuilder)boxmot)numpy)tensor_to_image) write_image BoxMotTrackerc^\rSrSr%SrSrS\S'S S U4SjjjrS SjrSSSjjr SSS jjr S r U=r $)r(a-BoxMotTracker is a module that wraps a detector and a tracker model. This module uses BoxMot library for tracking. Args: detector: The detector model. tracker_model_name: The name of the tracker model. Valid options are: - "BoTSORT" - "DeepOCSORT" - "OCSORT" - "HybridSORT" - "ByteTrack" - "StrongSORT" - "ImprAssoc" tracker_model_weights: Path to the model weights for ReID (Re-Identification). device: Union[str, torch.device, None] on which to run the model (e.g., 'cpu' or 'cuda'). fp16: Whether to use half-precision (fp16) for faster inference on compatible devices. per_class: Whether to perform per-class tracking. track_high_thresh: High threshold for detection confidence. Detections above this threshold are used in the first association round. track_low_thresh: Low threshold for detection confidence. Detections below this threshold are ignored. new_track_thresh: Threshold for creating a new track. Detections above this threshold will be considered as potential new tracks. track_buffer: Number of frames to keep a track alive after it was last detected. match_thresh: Threshold for the matching step in data association. proximity_thresh: Threshold for IoU (Intersection over Union) distance in first-round association. appearance_thresh: Threshold for appearance embedding distance in the ReID module. cmc_method: Method for correcting camera motion. Options include "sof" (simple optical flow). frame_rate: Frame rate of the video being processed. Used to scale the track buffer size. fuse_first_associate: Whether to fuse appearance and motion information during the first association step. with_reid: Whether to use ReID (Re-Identification) features for association. Note: To use this tracker, load image tensors (shape: ``(1, C, H, W)``) and call ``model.update(image)`` for at least 4 frames before calling ``model.save(image)``. .. note:: At least 4 frames are needed to initialize the tracking position. boxmot_trackerstrnamec >[TU]5 [U[5(a:UR S5(a[ R "US9nO[SUS35eXl[R"[RS3SS9 [[U5"S [[R R#[RS3U55UUS.UD6Ulg) Nrtdetr) model_namez Detector `zA` not available. You may pass an ObjectDetector instance instead.z/boxmotTexist_ok) model_weightsdevicefp16)super__init__ isinstancer startswithr build ValueErrordetectorosmakedirsrhub_models_dirgetattrr rpathjointracker)selfr$tracker_model_nametracker_model_weightsrrkwargs __class__s W/home/wildlama/miniconda3/lib/python3.13/site-packages/kornia/contrib/boxmot_tracker.pyrBoxMotTracker.__init__Us  h $ $""8,,066(K   *kl!  }334G".%<  ,    #          4":H8 99r3) __future__rrYloggingr%pathlibrtypingrrrrP kornia.configrkornia.contrib.object_detectionr r kornia.core.externalr r r@kornia.image.utilsr kornia.ior__all__ getLoggerrkr_rrr3r1r~sU$# '' 'Q',.!     8 $N9N9r3