An Improved Real-Time Contour Tracking Algorithm Using Fast Level Set Method
Human contour provides important information in high level vision tasks such as activity recognition and human computer interaction where detailed analysis of shape deformation is required. In this paper, a real time region-based contour tracking algorithm is presented. The main advantage of our algorithm is the ability of tracking nonrigid objects such as human using an adaptive external speed function with fast level set method. The weighting parameter, λ i is adjusted to accommodate the situations in which the object being tracked and the background have similar intensity. Experimental results show the better performance of the proposed algorithm with adaptive weights.
KeywordsActive Contour Active Contour Model Subsequent Frame Speed Function Geodesic Active Contour
Unable to display preview. Download preview PDF.
- 1.Yilmaz, A., Li, X., Shah, M.: Contour-based tracking with occlusion handling in video acquired using mobile cameras. IEEE Trans. on Pattern Analysis and Machine Intelligence 26(11) (November 2004)Google Scholar
- 2.Besson, S., Barlaund, M., Aubert, G.: Detection and trackign of moving objects using a new level set based method. In: Proc. International Conference on Pattern Recognition, September 2000, vol. 3, pp. 1100–1105 (2000)Google Scholar
- 3.Stauffer, C., Grimson, W.E.L.: Adaptive background mixture models for real-time tracking. In: IEEE Comptuer Society Conference on Computer Vision and Pattern Recognition, vol. 2 (1999)Google Scholar
- 5.Cremers, D.: Dynamical statistical shape priors for level set based tracking. IEEE Trans. on Pattern Analysis and Machine Intelligence (2006)Google Scholar
- 9.Paragios, N., Deriche, R.: Unifying boundary and region-based information for geodesic active tracking. In: IEEE Conference on Computer Vision and Pattern Recognition, Colorado, USA (1999)Google Scholar
- 11.Shi, Y., Clem Karl, W: Real-time tracking using level sets. Computer Vision and Pattern Recognition (June 2005)Google Scholar