Optimized Correlation Output Filters Toolset (OCOFTools)

A software package is now offered for those intersted in experimenting with David Bolme's Optimized Correlation Output Filters. This work is summarized in David Bolme's Dissertation as well as two papers:

D. S. Bolme, J. R. Beveridge, B. A. Draper, and Y. M. Lui. Visual Object Tracking using Adaptive Correlation Filters. Computer Vision and Pattern Recognition. June 2010 (PDF) (Online Video)

D.S. Bolme, B.A. Draper, and J.R. Beveridge.Average of Synthetic Exact Filters. Computer Vision and Pattern Recognition. June 2009 (PDF)

The software is made available in two ways. The easier with which to get started is encapsulated within a Virtual Box Virtual Machine (VM). The source code itself may also be downloaded directly. There is a link below to a download page where both options are available. Here is a link to the distribution's README document. Before downloading the software, we will ask that you kindly provide us your name, an email address and instiution if applicable. Please do provide us this information, it is extremely helpfu for us to know who is experimenting and using our software. If you have questions, please correspond with either Ross Beveridge or David Bolme, or both of us.

Be aware that Colorado State University has Patent US8520956, Optimized Correlation Filters for Signal Processing, covering the filter construction technique implemented in the software and we ask you please reveiw the Colorado State University Software Evaluation License Agreement . This license, in essence, grants license to use this software for research, teaching, and other non-commerical activities. License is not granted for commerical use, and anyone seeking to utilize it or its underlying filter construction technology for commerical purposes must comminicate with Colorado State University and negotiate a license to do so.

Download the OCOFTools.