In this paper, a new learning framework?probabilistic boosting-tree (PBT), is proposed for learning two-class and multi-class discriminative models. In the learning stage, the pro...
Virtually all structured light methods assume that the scene and the sources are immersed in pure air and that light is neither scattered nor absorbed. Recently, however, structur...
Srinivasa G. Narasimhan, Shree K. Nayar, Bo Sun, S...
Learning visual models of object categories notoriously requires thousands of training examples; this is due to the diversity and richness of object appearance which requires mode...
This paper presents an algorithm that matches interest points detected on a pair of grey level images taken from arbitrary points of view. First matching hypotheses are generated ...
The motion of a planar surface between two camera views induces a homography. The homography depends on the cameraintrinsic and extrinsic parameters, as well as on the 3D plane pa...