We address the problem of localizing and obtaining high-resolution footage of the people present in a scene. We propose a biologically-inspired solution combining pre-attentive, lo...
James H. Elder, Simon J. D. Prince, Yuqian Hou, Mi...
Abstract. We present a new method to simultaneously estimate optical flow fields and parameters of dynamic processes, violating the standard brightness change constraint equation...
Horst W. Haussecker, Christoph S. Garbe, Hagen Spi...
Current state-of-the-art image-based scene reconstruction
techniques are capable of generating high-fidelity 3D
models when used under controlled capture conditions.
However, th...
Jean-Yves Guillemaut, Joe Kilner and Adrian Hilton
A novel framework for anomaly detection in crowded scenes is presented. Three properties are identified as important for the design of a localized video representation suitable f...
Abstract. The exploitation of video data requires to extract information at a rather semantic level, and then, methods able to infer "concepts" from low-level video featu...