<h1 align="center"><span>YOLOv9 + ByteTracker</span></h1>
This project integrates YOLOv9 and ByteTracker for real-time, TensorRT-optimized object detection and tracking, extending the existing implementation.
<p align="center" margin: 0 auto;>
<img src="assets/demo.gif" width="360px" />
<img src="assets/highway.gif" width="360px" />
</p>
## Usage
- CPP(TensorRT):
``` shell
cd build/release
yolov9-bytetrack-trt.exe yolov9-c.engine test.mp4 # the video path
```
- Python(ONNX):
``` shell
cd python
python yolov9_bytetrack.py --model yolov9-c-converted.onnx --video_path test_video.mp4 --output_video_path result.mp4
```
## What is next?
- [ ] Python(TensorRT)
## Setup
**Python:**
``` shell
cd python
pip install -r requirement.txt
```
**CPP:**
Refer to our [docs/INSTALL.md](https://github.com/spacewalk01/yolov9-bytetrack-tensorrt/blob/main/docs/INSTALL.md) for detailed installation instructions. Note that Bytetracker is directly integrated without any modification.
## Requirement
- TensorRT
- CUDA, CudaNN
- Eigen 3.3
- C++ compiler with C++17 or higher support
- CMake 3.14 or higher
- OpenCV
跟踪算法_使用YOLOv9+ByteTracker实现目标跟踪算法_优质算法项目实战.zip （36个子文件） 
跟踪算法_使用YOLOv9+ByteTracker实现目标跟踪算法_优质算法项目实战 
CMakeLists.txt 1KB assets 
highway.gif 8.56MB demo.gif 5.83MB src 
yolov9.cpp 4KB macros.h 1KB preprocess.h 308B cuda_utils.h 1KB preprocess.cu 4KB logging.h 16KB yolov9.h 1KB main.cpp 4KB docs INSTALL.md 2KB bytetrack lapjv.h 126B Object.h 229B BYTETracker.h 3KB KalmanFilter.cpp 3KB KalmanFilter.h 1KB STrack.cpp 3KB Object.cpp 212B STrack.h 1KB BYTETracker.cpp 18KB Rect.cpp 3KB Rect.h 976B lapjv.cpp 8KB reparameterize.py 4KB python tracker kalman_filter.py 9KB __init__.py 173B basetrack.py 951B matching.py 6KB boxes.py 4KB byte_tracker.py 12KB yolov9_bytetrack.py 7KB requirement.txt 25B README.md 834B visualize.py 5KB README.md 1KB资源评论
