guapizyq / rpt

a tracker based on reliable patches

Reliable Patch Trackers: Robust Visual Tracking by Exploiting Reliable Patches (RPT)

This is the research code of our RPT tracker. It is implemented in matlab code and aimed to academical purpose. Details can be found in our CVPR paper. Please cite our publication if you use the code

@InProceedings{Li_2015_CVPR,
author = {Li, Yang and Zhu, Jianke and Hoi, Steven C.H.},
title = {Reliable Patch Trackers: Robust Visual Tracking by Exploiting Reliable Patches},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2015}
}

Instructions

• 1. Modify the base_path in "run_tracker.m" with your own setting if needed.
• 2. Run the "run_tracker.m" script in MATLAB.
• 3. Choose sequence.

Dependencies

Our work employs KCF[1] as the base tracker.

[1] J. F. Henriques, R. Caseiro, P. Martins, J. Batista. "High-Speed Tracking with Kernelized Correlation Filters." TPAMI - IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015

Contact:

Yang Li, [email protected] ihpdep.github.io

Jianke Zhu [email protected] jkzhu.github.io

Our Lab website