We describe a method for generating N-best configurations from part-based models, ensuring that they do not overlap according to some user-provided definition of overlap. We ext...
Abstract— Mobile robots need maps or other forms of geometric information about the environment to navigate. The mobility sensors (LADAR, stereo, etc.) on these robotic vehicles ...
Bart C. Nabbe, Derek Hoiem, Alexei A. Efros, Marti...
We present a new approach to iteratively estimate both
high-quality depth map and alpha matte from a single image
or a video sequence. Scene depth, which is invariant
to illumin...
Jiejie Zhu (University of Kentucky), Miao Liao (Un...
Many existing human detection systems are based on sub-window classification, namely detection is done by enumerating rectangular sub-images in the 2D image space. Detection rate...
View plus depth` is a 3D video representation where a single color video channel is augmented with per-pixel depth information in the form of gray-scale video sequence. This repre...
Sergey Smirnov, Atanas P. Gotchev, Karen O. Egiaza...