In this work, we propose an unsupervised Bayesian model for the detection of moving objects from dynamic scenes. This unsupervised solution is a three-step approach that uses a st...
In this paper, we propose a 2D visual motion estimation method which can be exploited to achieve a dynamic positioning (eg. by gaze control) with respect to a sea-bottom area of i...
State-of-the-art motion estimation algorithms suffer from three major problems: Poorly textured regions, occlusions and small scale image structures. Based on the Gestalt principle...
The estimation and detection of occlusion boundaries and moving bars are important and challenging problems in image sequence analysis. Here, we model such motion features as line...
This paper gives a practical and accurate algorithm for the computation of the quadrifocal tensor and extraction of camera matrices from it. Previous methods for using the quadrifo...