Contour tracking based on a synergistic approach of geodesic active contours and conditional random fields

• Published in: 2010 IEEE International Conference on Image Processing pp. 2801 - 2804
• Main Authors: Jiading Gai, Stevenson, R L
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.09.2010
• Subjects: 3D conditional random field; Active contours; belief propagation; Contour tracking; Deformable models; geodesic active contours; Level set; level set methods; motion detection; Pixel; Target tracking; Three dimensional displays; variational inference
• ISBN: 9781424479924; 1424479924
• ISSN: 1522-4880
• DOI: 10.1109/ICIP.2010.5651053

This paper presents a new general framework for contour tracking based on the synergy of two powerful segmentation tools, namely, spatial temporal conditional random fields (CRFs) and geodesic active contours (GACs). The contours of targets are modeled using a level set representation. The evolution of the level sets toward the target contours is formulated as one of the joint region-based (CRF) and boundary-based (GAC) segmentations under a unified Bayesian framework. A variational inference technique is used to solve this otherwise intractable inference problem, leading to approximate MAP solutions of both the new 3D spatial temporal CRF and the GAC model. The tracking result of the previous frame is used to initialize the curve in the current frame. Typical contour tracking problems are considered and experimental results are given to illustrate the robustness of the method against noise and its accurate performance in moving objects boundary localization.