INCREMENTAL LEARNING AND VALIDATION OF SEQUENTIAL PREDICTORS IN VIDEO BROWSING APPLICATION
David Hurych, Tomáš Svoboda · 2010
Loss-of-track detection (tracking validation) and automatic tracker adaptation to new object appearances are attractive topics in computer vision. We apply very efficient learnable sequential predictors in order to address both issues. Validation is done by clustering of the sequential predictor responses. No aditional object model for validation is needed. The paper also proposes an incremental learning procedure that accommodates changing object appearance, which mainly improves the recall of the tracker/detector. Exemplars for the incremental learning are collected automatically, no user interaction is required. The aditional training examples are selected automatically using the tracker stability computed for each potential aditional training example. Coupled with a sparsely applied SIFT or SURF based detector the method is employed for object localization in videos. Our Matlab implementation scans videosequences up to eight times faster than the actual frame rate. A standard-length movie can be thus searched through in terms of minutes.