This paper introduces a new feature-based technique for implicitly modelling objects in visual surveillance. Previous work has generally employed background subtraction and other ...
We propose a new unsupervised learning method to obtain a layered pictorial structure (LPS) representation of an articulated object from video sequences. It will be seen that this...
M. Pawan Kumar, Philip H. S. Torr, Andrew Zisserma...
While low-dimensional image representations have been very popular in computer vision, they suffer from two limitations: (i) they require collecting a large and varied training se...
In this paper, there is introduced an approach to surface reconstruction of an object captured by one grayscale camera with a small resolution. The proposed solution expects a rec...
To reconstruct the shape of objects from incomplete point sets or noisy images, robust and accurate reconstruction methods are required. This paper presents a physics-based approa...