Shape Tracking with Occlusions via Coarse-to-Fine Region-Based Sobolev Descent

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 37; no. 5; pp. 1053 - 1066
• Main Authors: Yanchao Yang, Sundaramoorthi, Ganesh
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.05.2015; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: deformable templates; Joints; Manifolds; Object segmentation from video; object tracking; occlusions; optical flow; Optical imaging; Optimization; Shape; shape metrics; Tracking; Object segmentation from video; object tracking; shape metrics; optical flow; deformable templates; occlusions

We present a method to track the shape of an object from video. The method uses a joint shape and appearance model of the object, which is propagated to match shape and radiance in subsequent frames, determining object shape. Self-occlusions and dis-occlusions of the object from camera and object mo...