Integration of Conditionally Dependent Object Features for Robust Figure/Background Segmentation

We propose a new technique for fusing multiple cues to robustly segment an object from its background in video sequences that suffer from abrupt changes of both illumination and position of the target. Robustness is achieved by the integration of appearance and geometric object features and by their description using particle filters. Previous approaches assume independence of the object cues or apply the particle filter formulation to only one of the features, and assume a smooth change in the rest, which can prove is very limiting, especially when the state of some features needs to be updated using other cues or when their dynamics follow non-linear and unpredictable paths. Our technique offers a general framework to model the probabilistic relationship between features. The proposed method is analytically justified and applied to develop a robust tracking system that adapts online and simultaneously the colorspace where the image points are represented, the color distributions, an...

• Type: Conference
• Year: 2005
• Where: ICCV
• Authors: Francesc Moreno-Noguer, Alberto Sanfeliu, Dimitris Samaras
• Keywords: Approaches Assume Independence, Computer Vision, Geometric Object Features, ICCV 2005, Object Cues, Particle Filter Formulation, Real Video Sequences