![]() ![]() The original Track.to_* methods for retrieving bounding box values returns only the Kalman predicted values. Getting bounding box of original detection Look into deep_sort_realtime/deepsort_tracker.py for more hyperparameters which you can tune to suit your use-case.is_confirmed (): continue track_id = track. update_tracks ( bbs, embeds = embeds ) # bbs expected to be a list of detections, each in tuples of (, confidence, detection_class ), also, no need to give frame as your chips has already been embedded for track in tracks : if not track. detect ( frame ) # your own object detection object_chips = chipper ( frame, bbs ) # your own logic to crop frame based on bbox values embeds = embedder ( object_chips ) # your own embedder to take in the cropped object chips, and output feature vectors tracks = tracker. To add project-specific logic into the Track class, you can make a subclass (of Track) and pass it in ( override_track_class argument) when instantiating DeepSort.Įxample with your own embedder/ReID model:įrom deep_sort_epsort_tracker import DeepSort tracker = DeepSort ( max_age = 5 ) bbs = object_detector. update_tracks ( bbs, frame = frame ) # bbs expected to be a list of detections, each in tuples of (, confidence, detection_class ) for track in tracks : if not track. whl file in this repo's releasesĮxample usage: from deep_sort_epsort_tracker import DeepSort tracker = DeepSort ( max_age = 5 ) bbs = object_detector. or, clone this repo & install deep-sort-realtime as a python package using pip or as an editable package if you like ( -e flag).from PyPI via pip3 install deep-sort-realtime. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |