Fusion of a multiple hypotheses color model and deformable contours for figure ground segmentation in dynamic environments

In this paper we propose a new technique to perform figure-ground segmentation in image sequences of moving objects under varying illumination conditions. Unlike most of the algorithms that adapt color, the assumption of smooth change of the viewing conditions is no longer needed. To cope with this, in this work we introduce a technique that formulates multiple hypotheses about the next state of the color distribution (some of these hypotheses take into account small and gradual changes in the color model and others consider more abrupt and unexpected variations) and the hypothesis that generates the best object segmentation is used to remove noisy edges from the image. This simplifies considerably the final step of fitting a deformable contour to the object boundary, thus allowing a standard snake formulation to successfully track nonrigid contours. Reciprocally, the contour estimation is used to correct the color model. The integration of color and shape is done in a stage denominated 'sample concentration', that has been introduced as a final step to the well-known CONDENSATION algorithm.