This paper extends the classical warping-based optical flow method to achieve accurate flow in the presence of spatially-varying motion blur. Our idea is to parameterize the app...
Previous pixel-level change detection methods either contain a background updating step that is costly for moving cameras (background subtraction) or can not locate object positio...
We present a model based approach to the integration of multiple cues for tracking high degree of freedom articulated motions and model refinement. We then apply it to the problem...
Shan Lu, Dimitris N. Metaxas, Dimitris Samaras, Jo...
Abstract. We present a method for learning feature descriptors using multiple images, motivated by the problems of mobile robot navigation and localization. The technique uses the ...
Jason Meltzer, Ming-Hsuan Yang, Rakesh Gupta, Stef...
Principal ComponentAnalysis (PCA) has been successfully applied to construct linear models of shape, graylevel, and motion. In particular, PCA has been widely used to model the var...