Code for the paper 'ROI Pooled Correlation Filters for Visual Tracking'
-
Clone the GIT repository
-
Compile the source code in the ./caffe directory and the matlab interface following the installation instruction of caffe.
-
Download the VGG_ILSVRC_16_layers.caffemodel (553.4 MB) from https://gist.github.com/ksimonyan/211839e770f7b538e2d8, and put the caffemodel file under the ./model directory.
-
Download imagenet-vgg-m-2048 (345 MB) from http://www.vlfeat.org/matconvnet/pretrained/, and put the file into ./networks .
-
Compile matconvnet in the ./external_libs folders.
-
Run the demo code demo_RPCF.m to test the code. You can customize your own test sequences following this example.
-
Modify the configSeq.m to your OTB dataset path, then run run_RPCF.m on all 100 datasets.
- RESULTS (Extracted code: 2cdc )
The above link includes the results of OTB-100、VOT-2018 datasets.
Please cite if you find the paper is helpful to your research :)
@inproceedings{sun2019roi,
title={ROI Pooled Correlation Filters for Visual Tracking},
author={Sun, Yuxuan and Sun, Chong and Wang, Dong and He, You and Lu, Huchuan},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages={5783--5791},
year={2019}
}
Ubuntu 14.04
MATLAB R2017a
Nvidia 1080 GPU
CUDA 8.0
CUDNN 6.0