Motion Models that Only Work SometimesOverviewIt is too often that tracking algorithms lose track of interest points in image sequences. This persistent problem is difficult because the pixels around an interest point change in appearance or move in unpredictable ways. In this project we explore how classifying videos into categories of camera motion improves the tracking of interest points, by selecting the right specialist motion model for each video. As a proof of concept, we enumerate a small set of simple categories of camera motion and implement their corresponding specialized motion models. We evaluate the strategy of predicting the most appropriate motion model for each test sequence. Within the framework of a standard Bayesian tracking formulation, we compare this strategy to two standard motion models. Our tests on challenging real-world sequences show a significant improvement in tracking robustness, achieved with different kinds of supervision at training time.Publications
Data and CodeIf you find the following useful, please cite our BMVC paper (a journal version is in submission).Motion Model Selection DatasetThe videos are in avi format, compressed with HuffYUV. They are separated into folders accoding to manual inspection-based labels, as explained in the paper.
Matlab code for recreating the experimentsContact: cristina.garcia_cifuentes.09 (at) alumni.ucl.ac.uk Last updated: June 2013 |
