Translator Disclaimer
14 February 2013 Efficient occlusion reasoning for articulated tracking in monocular views
Author Affiliations +
Pose estimation and tracking of articulated objects like humans is particularly difficult due to the complex occlusions among the articulated parts. Without the benefit of multiple views, resolution of occlusions becomes both increasingly valuable and challenging. We propose a method for articulated 3D pose estimation from monocular video which uses nonparametric belief propagation and employs a novel and efficient approach to occlusion reasoning. We present a human tracking application, and evaluate results using the HumanEva II data set.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Landis M. Huffman and Ilya Pollak "Efficient occlusion reasoning for articulated tracking in monocular views", Proc. SPIE 8657, Computational Imaging XI, 86570L (14 February 2013);

Back to Top