Motion models that only work sometimes

It 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 paper we explore how classifying videos into categories of camera motion improves the tracking of interest points, by se-lecting 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 cor-responding 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 mod-els. Our tests on challenging real-world sequences show a significant improvement in tracking robustness, achieved with different kinds of supervision at training time. frame 0 frame 10 frame 20 Figure 1: Example sequence with overlaid box showing the output of our specialized “for-ward ” motion model, where the velocity and scale of objects approaching the camera tend to increase. Neither Brownian nor constant-velocity motion models are as successful at track-ing interest points here. c © 2012. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms