Morphological operators for segmentation of color sequences

This paper presents a technique for the segmentation of moving objects in color image sequences. The technique is based on Beucher-Meyer paradigm, with markers detected by a morphological operator designed by computational learning (or, equivalently, statistical optimization). Objects in some frames of the video are marked manually and used to train the markers detector. Then, the operator designed is used to mark the objects in the other frames and the paradigm is applied to all frames marked by the detector. Two real world examples illustrate the application of the proposed technique