Skip to content
Robust Tracking Using Region Proposal Networks
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.
dataset/VOT/2016/bag initial commit. Jun 2, 2017
external/_caffe Update: Jun 10, 2017
gen_norm initial commit. Jun 2, 2017
models initial commit. Jun 2, 2017
tracking minor update. Jun 2, 2017
train_small_rpn initial commit. Jun 2, 2017
utils initial commit. Jun 2, 2017
.gitignore CREATE .gitignore Jun 10, 2017
LICENSE fixed a typo Jun 10, 2017


Robust Tracking Using Region Proposal Networks


RPN2T tracker achieved state-of-the-art results on several large scale benchmarks including OTB50, OTB100 and VOT2016.

Detailed description of the system is provided by our paper(

This software is implemented using Caffe and part of Faster_rcnn.


If you're using this code in a publication, please cite our paper.

  title={Robust Tracking Using Region Proposal Networks},  
  author={Ren, Jimmy and Yu, Zhiyang and Liu, Jianbo and Zhang, Rui and Sun, Wenxiu and Pang, Jiahao and Chen, Xiaohao and Yan, Qiong},  
  journal={arXiv preprint arXiv:1705.10447},  

System Requirements

This code is tested on 64 bit Linux (Ubuntu 14.04 LTS).


  1. MATLAB (tested with R2014b)
  2. Caffe (included in this repository external/_caffe/)
  3. For GPU support, a GPU, CUDA toolkit and cuDNN will be needed. We have tested in GTX TitanX(MAXWELL) with CUDA7.5+cuDNNv5 and GTX 1080 with CUDA8.0+cuDNNv5.1.


Compile Caffe according to the installation guideline.

cd $(RPN2T_ROOT)
cd external/_caffe
# Adjust Makefile.config (For example, the path of MATLAB.)
make all -j8
make matcaffe

Online Tracking using RPN2T


Run 'tracking/demo_tracking.m'.

You can’t perform that action at this time.