The likelihood models used in probabilistic visual tracking applications are often complex non-linear and/or nonGaussian functions, leading to analytically intractable inference. ...
In this work, we present an approach to jointly segment a rigid object in a 2D image and estimate its 3D pose, using the knowledge of a 3D model. We naturally couple the two proces...
Samuel Dambreville, Romeil Sandhu, Anthony J. Yezz...
A monocular vision based location algorithm is presented to detect and track rear vehicles for lane change assist. The algorithm uses the shadow underneath the vehicle to extract ...
Wei Liu, Chunyan Song, Pengyu Fu, Nan Wang, Huai Y...
We present a new method for multi-object segmentation in a maximum a posteriori estimation framework. Our method is motivated by the observation that neighboring or coupling objec...
We introduce two fourth-order regularization methods that remove geometric noise without destroying significant geometric features. These methods leverage ideas from image denoisi...