Skip to content

The YOLOv8-SORT-Human-Tracking repository demonstrates human tracking using YOLOv8 and the SORT algorithm, showcasing results of using YOLOv8 alone versus the combined method.

License

Notifications You must be signed in to change notification settings

dev-jinwoohong/YOLOv8-SORT-Human-Tracking

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

29 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

facebook_cover_photo_2

                    Python GitHub Issues Contributions welcome License

Prerequisites

1. Download Required Files

sudo snap install yt-dlp
yt-dlp https://youtu.be/2SATljljXCY?si=y8Lbldme2RhQADCP -f "bestvideo[ext=mp4]+bestaudio[ext=m4a]/mp4" --download-sections "*00:00:00-00:00:17" -o ./resource/sample.mp4

2. Install Required Libraries

Run the following command to install the necessary libraries:

pip install -r requirements.txt

3. Run

  1. Inference using yolov8 only.
python yolov8.py
  1. Inference using yolov8 + sort.
python yolov8_sort.py

4. Result

You can see the inference results during execution or check them in the result folder.

My YOLO+SORT implementation shows promising object tracking, maintaining IDs across frames. However, ID switches still occur during occlusions.

  • YOLOv8 Result

yolov8_result.gif

  • YOLOv8 + SORT Result

yolov8_result.gif

I plan to implement Deep SORT in future updates to improve tracking stability, especially in challenging scenarios.

About

The YOLOv8-SORT-Human-Tracking repository demonstrates human tracking using YOLOv8 and the SORT algorithm, showcasing results of using YOLOv8 alone versus the combined method.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages