In this paper we present a framework for semantic scene parsing and object recognition based on dense depth maps. Five viewindependent 3D features that vary with object class are e...
Next-best-view (NBV) planning is an important aspect for three-dimensional (3D) reconstruction within controlled environments, such as a camera mounted on a robotic arm. NBV metho...
Michael Trummer, Christoph Munkelt, Joachim Denzle...
We present a novel approach for detecting global behaviour
anomalies in multiple disjoint cameras by learning
time delayed dependencies between activities cross camera
views. Sp...
Recently SVMs using spatial pyramid matching (SPM)
kernel have been highly successful in image classification.
Despite its popularity, these nonlinear SVMs have a complexity
O(n...
Jianchao Yang, Kai Yu, Yihong Gong, Thomas S. Huan...
While traditional face recognition is typically based on still images, face recognition from video sequences has become popular recently. In this paper, we propose to use adaptive...