A Libtorch implementation of the SiamRPN tracker algorithm described in paper High Performance Visual Tracking with Siamese Region Proposal Network. This project is inspired by the pytorch version, I rewritten it with C++.
- LibTorch v1.0.0
- CUDA
- OpenCV
If you want to compile and run the project, you can create a build folder first, and set CMAKE_PREFIX_PATH as /Path/to/pytorch/torch/share/cmake, then run the command:
mkdir build;
cd build;
cmake ..;
make;
- Download traced model files detect.pt and template.pt from Baidu Yun or Google Drive , and put the file under path/to/SiamRPNTracker/model.
- run
./siamrpn_tracker
Li, Bo, et al. "High performance visual tracking with siamese region proposal network." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018.