Multiple Genetic Snakes for People Segmentation in Video Sequences
In this paper we propose a method for finding people and segmenting their body parts in video image sequences. We propose the use of Genetic Snakes, that are active contour models, also known as snakes, with an energy minimization procedure based on Genetic Algorithms (GA). Genetic Snakes have been proposed to overcome some limits of the classical snakes, as initialization and existence of multiple minima, and have been successfully applied to images from different domains. We extend the formulation of Genetic Snakes in two ways, by adding an elastic force that couples multiple contours together and by applying them to color images. Experimental results, carried out on images acquired in our lab, are described.
KeywordsGenetic Algorithm Video Sequence Active Contour Elastic Force Deformable Model
- 12.Xu, C., Pham, D.L., Prince, J.L.: Image segmentation using deformable models. In Sonka, M., Fitzpatrick, J.M., eds.: Handbook of Medical Imaging. Volume 2. SPIE Press (2000) 129–174Google Scholar
- 17.MacEachern, L.A., Manku, T.: Genetic algorithms for active contour optimization. In: Proc. IEEE International Symposium on Circuits and Systems. Volume 4. (1998) 229–232Google Scholar
- 18.Tanatipanond, T., Covavisaruch, N.: An improvement of multiscale approach to deformable contour for brain MR images by genetic algorithms. In: Proc. IEEE International Symposium on Intelligent Signal Processing and Communication Systems, Phucket, Thailand (1999) 677–680Google Scholar
- 19.Ooi, C., Liatsis, P.: Co-evolutionary-based active contour models in tracking of moving obstacles. In: Proc. International Conference on Advanced Driver Assistance Systems. (2001) 58–62Google Scholar
- 20.Schraudolph, N.N., Grefenstette, J.J.: A user’s guide to GAucsd 1.4. Technical Report CS92-249, Computer Science and Engineering Department, University of California, San Diego, La Jolla, CA (1992)Google Scholar