Tracking Generic Human Motion via Fusion of Low- and High-Dimensional Approaches

• Published in: IEEE transactions on systems, man, and cybernetics. Systems Vol. 43; no. 4; pp. 996 - 1002
• Main Authors: Cui, Jinshi, Liu, Ye, Xu, Yuandong, Zhao, Huijing, Zha, Hongbin
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.07.2013; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Applied sciences; Artificial intelligence; Computational modeling; Computer science; control theory; systems; Cybernetics; Exact sciences and technology; High-dimensional methods; Human motion; human motion tracking; Humans; Learning; Learning and adaptive systems; Legged locomotion; low-dimensional methods; Pattern recognition. Digital image processing. Computational geometry; probabilistic fusion; Probabilistic logic; Probabilistic methods; Probability theory; Robustness; Sampling; Studies; Tracking; Training data; Performance evaluation; Computer vision; Tracking; probabilistic fusion; Probabilistic approach; Motion estimation; State space method; Modeling; Experimental result; low-dimensional methods; Multidimensional analysis; Surveillance; Efficiency; human motion tracking; High-dimensional methods; Data fusion; Robustness; Data models; Sampling; Artificial intelligence
• ISSN: 2168-2216; 2168-2232
• DOI: 10.1109/TSMCA.2012.2223670

Tracking generic human motion is highly challenging due to its high-dimensional state space and the various motion types involved. In order to deal with these challenges, a fusion formulation which integrates low- and high-dimensional tracking approaches into one framework is proposed. The low-dimensional approach successfully overcomes the high-dimensional problem of tracking the motions with available training data by learning motion models, but it only works with specific motion types. On the other hand, although the high-dimensional approach may recover the motions without learned models by sampling directly in the pose space, it lacks robustness and efficiency. Within the framework, the two parallel approaches, low- and high-dimensional, are fused via a probabilistic approach at each time step. This probabilistic fusion approach ensures that the overall performance of the system is improved by concentrating on the respective advantages of the two approaches and resolving their weak points. The experimental results, after qualitative and quantitative comparisons, demonstrate the effectiveness of the proposed approach in tracking generic human motion.