Return to Complete List of Publications

Rate-efficient Visual Correspondences Using Random Projections
(Chuohao Yeo, Parvez Ahammad, Kannan Ramchandran) [BibTex] [pdf]
Proceedings of the IEEE International Conference on Image Processing  (ICIP) - 2008.

Abstract:  We consider the problem of establishing visual correspondences in a distributed and rate-efficient fashion by broadcasting compact descriptors. Establishing visual correspondences is a critical task before other vision tasks can be performed in a camera network. We use coarsely quantized random projections of descriptors to build binary hashes, and use the hamming distance between binary hashes as a matching criterion. In this work, we show that the hamming distance between the binary hashes has a binomial distribution, with parameters that are a function of the number of random projections and the euclidean distance between the original descriptors. We present experimental results that verify our result, and show that for the task of finding visual correspondences, sending binary hashes is more rate-efficient than prior approaches.

Keywords: camera networks, rate or bandwidth constraints, visual correspondence, random projections