Hi guys
I am new to computer vision and tracking on PyTorch. I am using YOLO-Pose for animal pose estimation. YOLO estimates both bounding boxes and key points of the animal’s body.
In each frame, there may be one or more animals, so I need to assign a unique ID to each using a tracker. Everything works fine when there is only one animal in the frame. However, when a second animal enters the frame, the model detects two animals, and I don’t know how to correctly arrange these detections and match them with the correct tracker IDs.
Any advice would be really appreciated
Do you have a git repo you could share / code? This would help others help you!