Scalable Active Matching

Abstract

In matching tasks in computer vision, and particularly in real-time tracking from video, there are generally strong priors available on absolute and relative correspondence locations thanks to motion and scene models. While these priors are often partially used post-hoc to resolve matching consensus in algorithms like RANSAC, it was recently shown that fully integrating them in an ‘Active Matching’ (AM) approach permits efficient guided image processing withrigorous decisions guided by InformationTheory. AM’s weakness was that the overhead induced by intermediate Bayesian updates required meant poor scaling to caseswheremanycorrespondencesweresought. Inthispaperweshowthatrelaxationoftherigidprobabilisticmodel ofAM,whereeveryfeaturemeasurementdirectlyaffectsthe prediction of every other, permits dramatically more scalable