A common practice when carrying out self-calibration of a camera from one or more views is to start with a guess at the principal point. The general belief is that inaccuracies in...
We present a method to learn object class models from unlabeled and unsegmented cluttered scenes for the purpose of visual object recognition. We focus on a particular type of mode...
The omnidirectional image sensor named HyperOmniVision, is composed of hyperboloidal mirror and conventional video camera. It can observt: 360 degree field of view and can transfo...
We address the problem of automatic object classification for traffic scene surveillance, which is very challenging for the low resolution videos, large intraclass variations and ...
In this paper, a novel multi-cue collaborative kernel tracking algorithm is proposed. A new constraint based on the property of cross ratio invariant enables tracking of objects i...