https://github.com/quzanh1130/object_tracking_trackline
This project utilizes YOLOv9 and DeepSORT for object tracking, combined with a line-drawing feature to visualize the path of tracked objects.
https://github.com/quzanh1130/object_tracking_trackline
deep-sort object-tracking yolo yolov9-object-tracking
Last synced: 12 months ago
JSON representation
This project utilizes YOLOv9 and DeepSORT for object tracking, combined with a line-drawing feature to visualize the path of tracked objects.
- Host: GitHub
- URL: https://github.com/quzanh1130/object_tracking_trackline
- Owner: quzanh1130
- License: mit
- Created: 2024-05-03T17:37:42.000Z (about 2 years ago)
- Default Branch: master
- Last Pushed: 2024-12-06T08:46:55.000Z (over 1 year ago)
- Last Synced: 2025-04-08T15:52:41.773Z (about 1 year ago)
- Topics: deep-sort, object-tracking, yolo, yolov9-object-tracking
- Language: Python
- Homepage:
- Size: 57.4 MB
- Stars: 3
- Watchers: 1
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Object Tracking with Trackline
This project utilizes YOLOv9 and DeepSORT for object tracking, combined with a line-drawing feature to visualize the path of tracked objects.
## Reproductbility
### 1. Clone this project
```bash
git clone https://github.com/quzanh1130/Object_tracking_trackline.git
cd Object_tracking_trackline
```
### 2. Install package
```bash
pip install -r setup.txt
```
### 3. Run this project
- `--weights`: model path or triton URL
- `--source`: file/dir/URL/glob/screen/0(webcam)
- `--device`: cuda device, i.e. 0 or 0,1,2,3 or cpu
- `--mode`: mode show line or not. 0: not show, 1: show line
``` bash
python object_tracking.py --weights weight\yolov9-c-converted.pt --source data_ext/test.mp4 --device cuda --mode 1
```