Abstract. A tracking-by-detection framework is proposed that combines nearest-neighbor classification of bags of features, efficient subwindow search, and a novel feature selection...
Abstract Kernel-based object tracking refers to computing the translation of an isotropic object kernel from one video frame to the next. The kernel is commonly chosen as a primiti...
We study from a theoretical standpoint the ambiguities that occur when tracking a generic deformable surface under monocular perspective projection given 3?D to 2?D correspondence...
MAP estimation of Gaussian mixtures through maximisation of penalised likelihoods was used to learn models of spatial context. This enabled prior beliefs about the scale, orientat...
Detecting car taillights at night is a task which can nowadays be accomplished very fast on cheap hardware. We rely on such detections to build a vision-based system that, couplin...