Monocular reconstruction of human motion by qualitative selection
2004 (English)In: SIXTH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION, PROCEEDINGS, LOS ALAMITOS: IEEE COMPUTER SOC , 2004, 863-868 p.Conference paper (Refereed)
One of the main difficulties when reconstructing human motion from monocular video is the depth ambiguity. Achieving a reconstruction, given the projection of the joints, can be regarded as a search-problem, where the objective is to find the most likely configuration. One inherent problem in such a formulation is the definition of "most likely". In this work we will pick the configuration that best complies with a set of training-data in a qualitative sense. The reason for doing this is to allow for large individual variation within the class of motions, and avoid an extreme bias towards the training-data. In order to capture the qualitative constraints, we have used a set of 3D motion capture data of walking people. The method is tested on orthographic projections of motion capture data, in order to compare the achieved reconstruction with the original motion.
Place, publisher, year, edition, pages
LOS ALAMITOS: IEEE COMPUTER SOC , 2004. 863-868 p.
Computer and Information Science
IdentifiersURN: urn:nbn:se:kth:diva-44735DOI: 10.1109/AFGR.2004.1301642ISI: 000222059800140ScopusID: 2-s2.0-4544268045ISBN: 0-7695-2122-3OAI: oai:DiVA.org:kth-44735DiVA: diva2:451499
6th IEEE International Conference on Automatic Face and Gesture Recognition Location: Seoul, SOUTH KOREA Date: MAY 17-19, 2004
QC 201110262011-10-262011-10-252012-01-20Bibliographically approved