Spatio-temporal shape building from image sequences using lateral interaction in accumulative computation

To be able to understand the motion of non-rigid objects, techniques in image processing and computer vision are essential for motion analysis. Lateral interaction in accumulative computation for extracting non-rigid shapes from an image sequence has recently been presented, as well as its application to segmentation from motion. In this paper, we introduce a modi4ed version of the 4rst multi-layer architecture. This version uses the basic parameters of the LIAC model to spatio-temporally build up to the desired extent the shapes of all moving objects present in a sequence of images. The in5uences of LIAC model parameters are explained in this paper, and we 4nally show some examples of the usefulness of the model proposed. ? 2002 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.