We propose a novel system-level error tolerance approach specifically targeted for multimedia compression algorithms. In particular we focus on the motion estimation process perf...
This paper presents a novel technique for 2D human motion estimation using a single non calibrated camera. The user’s five crucial human features (head, hands and feet) are ext...
Pedro Correa, Jacek Czyz, Toshiyuki Umeda, Ferran ...
Motion Estimation (ME) is the most computationally intensive and the most power consuming part of video compression and video enhancement systems. In this paper, we propose a nove...
Caglar Kalaycioglu, Onur C. Ulusel, Ilker Hamzaogl...
Estimating relative camera motion from two views is a classical problem in computer vision. The minimal case for such problem is the so-called five-point-problem, for which the st...
In this paper we propose a new motion estimator for image sequences depicting fluid flows. The proposed estimator is based on the Helmholtz decomposition of vector fields. This ...