We propose semantic texton forests, efficient and powerful new low-level features. These are ensembles of decision trees that act directly on image pixels, and therefore do not ne...
This paper deals with motion estimation and segmentation in video sequences. Some methods of motion computation between two consecutive frames of a video sequence are based on the...
Ariane Herbulot, Sylvain Boltz, Eric Debreuve, Mic...
We propose a new approach to estimate gait kinematics from image sequences taken by a monocular uncalibrated camera. This approach involves two generative models for gait represen...
This paper presents a dynamic conditional random field (DCRF) model to integrate contextual constraints for object segmentation in image sequences. Spatial and temporal dependenci...
We propose a methodology for improved segmentation of images in a Bayesian framework by fusion of color, texture and gradient information. The proposed algorithm is initialized by...