Use this repo to only use tracking: https://github.com/yasarniyazoglu/YoloV5-and-DeepSort-Custom-Dataset
Thanks to: https://github.com/mikel-brostrom/Yolov5_DeepSort_Pytorch
This repository contains a two-stage-tracker. The detections generated by YOLOv5, a family of object detection architectures and models pretrained on the COCO dataset, are passed to a Deep Sort algorithm which tracks the objects. It can track and draw the heatmap of any object that your Yolov5 model was trained to detect. In my case I used only person to draw the heatmap.
- Clone the repository recursively:
git clone https://github.com/rukon-uddin/Yolov5-DeepSort-Heatmap.git
- Run:
pip install -r requirements.txt
Tracking can be run on most video formats
python track.py --source ... --show-vid
- Video:
--source file.mp4, *.avi
- Webcam:
--source 0
- RTSP stream:
--source rtsp://170.93.143.139/rtplive/470011e600ef003a004ee33696235daa
- HTTP stream:
--source http://wmccpinetop.axiscam.net/mjpg/video.mjpg
There is a clear trade-off between model inference speed and accuracy. In order to make it possible to fulfill your inference speed/accuracy needs you can select a Yolov5 family model for automatic download
$ python track.py --source 0 --yolo_weights yolov5s.pt --img 640
yolov5m.pt
yolov5l.pt
yolov5x.pt --img 1280
By default the tracker tracks and draws heatmap of all MS COCO classes. But its very convenient to only draw heatmap of a single class, for example you want to check the car intensity on the road, or person intensity on a street.
If you only want to track persons I recommend you to get these weights for increased performance
python3 track.py --source 0 --yolo_weights yolov5/weights/crowdhuman_yolov5m.pt --classes 0 # tracks persons, only
If you want to track a subset of the MS COCO classes, add their corresponding index after the classes flag
python3 track.py --source 0 --yolo_weights yolov5s.pt --classes 16 17 # tracks cats and dogs, only
Here is a list of all the possible objects that a Yolov5 model trained on MS COCO can detect. Notice that the indexing for the classes in this repo starts at zero.