Visual object tracking and segmentation in a closed loop
HOME RESEARCH/DEMOS PROJECTS ACTIVITIES PUBLICATIONS CITATIONS COURSES STUDENTS LINKS RESTRICTED	Brief description We introduce a new method for integrated tracking and segmentation of a single non-rigid object in a monocular video, captured by a possibly moving camera. A closed-loop interaction between EM-like color-histogram-based tracking and Random Walker-based image segmentation is proposed, which results in reduced tracking drifts and in fine object segmentation. More specifically, pixel-wise spatial and color image cues are fused using Bayesian inference to guide object segmentation. The spatial properties and the appearance of the segmented objects are exploited to initialize the tracking algorithm in the next step, closing the loop between tracking and segmentation. As confirmed by experimental results on a variety of image sequences, the proposed approach efficiently tracks and segments previously unseen objects of varying appearance and shape, under challenging environmental conditions. The outline of the method The outline of the method with sample intermediate results Sample results · Book video (deforming book, static camera, very simple background) · Face video (moving head, static camera, typical background) · Hand video I (articulated object, static camera, simple background) · Hand video II (articulated object, moving camera, cluttered background) Contributors Konstantinos Papoutsakis, Antonis Argyros. This work was partially supported by the IST-FP7-IP-215821 project GRASP. Relevant publications · K. Papoutsakis, A.A. Argyros, “Object tracking and segmentation in a closed loop”, in Proceedings of the International Symposium on Visual Computing, ISVC’2010, Advances in Visual Computing, Lecture Notes in Computer Science, Volume 6453, pp. 405-416, Las Vegas, USA, Nov 29-Dec 1, 2010. The electronic versions of the above publications can be downloaded from my publications page.
Last update:	19 October 2010, Antonis Argyros, argyros@ics.forth.gr