A region-based particle filter for generic object tracking and segmentation

In this work we present a region-based particle filter for generic object tracking and segmentation. The representation of the object in terms of regions homogeneous in color allows the proposed algorithm to robustly track the object and accurately segment its shape along the sequence. Moreover, this segmentation provides a mechanism to update the target model and allows the tracker to deal with color and shape variations of the object. The performance of the algorithm has been tested using the LabelMe Video public database. The experiments show satisfactory results in both tracking and segmentation of the object without an important increase of the computational time due to an efficient computation of the image partition.