We present a system that constructs "implicit shape models" for classes of rigid 3D objects and utilizes these models to estimating the pose of class instances in single...
This paper presents a unified framework for object detection,
segmentation, and classification using regions. Region
features are appealing in this context because: (1) they enco...
Chunhui Gu, Joseph J. Lim, Pablo Arbelaez, Jitendr...
This paper presents a method for capturing and computing 3D parallax. 3D parallax, as used here, refers to vertical offset from the ground plane, height. The method is based on an...
The paper presents a fusion-tracker and pedestrian classifier for color and thermal cameras. The tracker builds a background model as a multi-modal distribution of colors and temp...
The medial surface of a volumetric object is of significant interest for shape analysis. However, its numerical computation can be subtle. Methods based on Voronoi techniques prese...