This page contains links to training and test data, source code and evaluation programs, provided by members of our lab. The goal is to promote the scientific use of our work and help advance research in computer vision and pattern recognition. Please feel free to contact individual authors or members of our labs if you have questions or suggestions.
Description: We have developed a robust and fast lattice detection algorithm using a probabilistic graph model that has a better detection rate and is approximately 10 times faster than current state-of-the-art algorithms.
Project Page: [Deformed Lattice Detection]
Source Code/Binaries: Lattice Detection Code for MATLAB
Description: Papercutting is a widespread and ancient artform which, as far as we could tell, had no previous computational treatment. We developed algorithms to analyze the symmetry of papercut patterns and produce efficient folding and cutting plans.
Source Code/Binaries: Binary executables are available upon request. Please email the listed contact(s).
Sketch: SIGGRAPH 2005 Sketch
Description: This database contains textures from completely regular to completely irregular patterns, with a focus on near-regular textures. It also includes video of near-regular textures in motion. Also available: groundtruth for translation, rotation and reflection/glide-reflection symmetry detection algorithms.
PSU HUB Dataset
Description: Ground truth trajectory and grouping information for pedestrians walking in the PSU student union building. This is dataset "SU2" described in the paper: Weina Ge, Robert Collins, and Barry Ruback, "Vision-based Analysis of Small Groups in Pedestrian Crowds" IEEE Transactions on Pattern Analysis and Machine Intelligence, to appear, May 2012. We ask that you refer to that paper if you use this dataset in your own research publications.
Readme: README file
Contact: Robert Collins