forked from {https://github.com/mikel-brostrom/Yolov5_DeepSort_Pytorch} and made changes based on our own dataset.
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 any object that your Yolov5 model was trained to detect.
- Clone the repository:
git clone https://github.com/unmannedlab/UWB_Dataset.git
- Make sure that you fulfill all the requirements: Python 3.8 or later with all requirements.txt dependencies installed, including torch>=1.7. To install, run:
pip install -r ~/UWB_Dataset/benchmarks/requirements.txt
Tracking can be run on most video formats
$ python track.py --source 0 # webcam
img.jpg # image
vid.mp4 # video
path/ # directory
path/*.jpg # glob
'https://youtu.be/Zgi9g1ksQHc' # YouTube
'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP stream
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_model yolov5n.pt --img 640
yolov5s.pt
yolov5m.pt
yolov5l.pt
yolov5x.pt --img 1280
...
Choose a ReID model based on your needs from this ReID model zoo
$ python track.py --source 0 --deep_sort_model osnet_x1_0
nasnsetmobile
resnext101_32x8d
...
By default the tracker tracks all MS COCO classes.
If you only want to track persons I recommend you to get these weights for increased performance
python3 track.py --source 0 --yolo_model 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_model 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.
Can be saved to your experiment folder track/expN
by
python3 track.py --source ... --save-txt
python3 track.py --source path_to_output.mp4 --save-txt --save-vid --evaluate --yolo_model yolov5/weights/crowdhuman_yolov5m.pt --classes 0 --imgsz 728 1296
Note: remember to change the path to output.mp4 video, for example ~/Document/output.mp4
mv ~/UWB_Dataset/benchmarks/runs/track/exp/* \
~/benchmarks/MOT16_eval/TrackEval/data/trackers/mot_challenge/MOT16-train/ch_yolov5m_deep_sort/data/
python ~/UWB_Dataset/benchmarks/MOT16_eval/TrackEval/scripts/run_mot_challenge.py --BENCHMARK MOT16 \
--TRACKERS_TO_EVAL ch_yolov5m_deep_sort --SPLIT_TO_EVAL train --METRICS CLEAR Identity HOTA \
--USE_PARALLEL False --NUM_PARALLEL_CORES 4
If you find this repo useful in your research, please also cite:
@misc{yolov5deepsort2020,
title={Real-time multi-object tracker using YOLOv5 and deep sort},
author={Mikel Broström},
howpublished = {\url{https://github.com/mikel-brostrom/Yolov5_DeepSort_Pytorch}},
year={2020}
}