This paper presents work we have done in detecting moving shadows in the context of an outdoor traffic scene for visual surveillance purposes. The algorithm just exploits some for...
Reconstruction of 3D structures from uncalibrated image sequences has a wealthy history. Most work has been focused on rigid objects or static scenes. This paper studies the probl...
According to the recent theory of compressed sensing, accurate reconstruction is possible even from data samples dramatically smaller than Nyquist sampling limit as long as the un...
This paper addresses the problem of automatically extracting frequently used pedestrian pathways from video sequences of natural outdoor scenes. Path models are learnt from the ac...
This paper presents a technique to enable deformable objects to be matched throughout video sequences based on the information provided by multi-scale Gaussian derivative filter ba...