TY - GEN
T1 - A language modeling approach to atomic human action recognition
AU - Liang, Yu Ming
AU - Shih, Sheng Wen
AU - Shih, Arthur Chun Chieh
AU - Liao, Hong Yuan Mark
AU - Lin, Cheng-Chung
PY - 2007/12/1
Y1 - 2007/12/1
N2 - Visual analysis of human behavior has generated considerable interest in the field of computer vision because it has a wide spectrum of potential applications. Atomic human action recognition is an important part of a human behavior analysis system. In this paper, we propose a language modeling framework for this task. The framework is comprised of two modules: a posture labeling module, and an atomic action learning and recognition module. A posture template selection algorithm is developed based on a modified shape context matching technique. The posture templates form a codebook that is used to convert input posture sequences into training symbol sequences or recognition symbol sequences. Finally, a variable-length Markov model technique is applied to learn and recognize the input symbol sequences of atomic actions. Experiments on real data demonstrate the efficacy of the proposed system.
AB - Visual analysis of human behavior has generated considerable interest in the field of computer vision because it has a wide spectrum of potential applications. Atomic human action recognition is an important part of a human behavior analysis system. In this paper, we propose a language modeling framework for this task. The framework is comprised of two modules: a posture labeling module, and an atomic action learning and recognition module. A posture template selection algorithm is developed based on a modified shape context matching technique. The posture templates form a codebook that is used to convert input posture sequences into training symbol sequences or recognition symbol sequences. Finally, a variable-length Markov model technique is applied to learn and recognize the input symbol sequences of atomic actions. Experiments on real data demonstrate the efficacy of the proposed system.
KW - Human behavior analysis
KW - Language modeling
KW - Posture template selection
KW - Variable-lenth Markov mode
UR - http://www.scopus.com/inward/record.url?scp=48149091737&partnerID=8YFLogxK
U2 - 10.1109/MMSP.2007.4412874
DO - 10.1109/MMSP.2007.4412874
M3 - Conference contribution
AN - SCOPUS:48149091737
SN - 1424412749
SN - 9781424412747
T3 - 2007 IEEE 9Th International Workshop on Multimedia Signal Processing, MMSP 2007 - Proceedings
SP - 288
EP - 291
BT - 2007 IEEE 9Th International Workshop on Multimedia Signal Processing, MMSP 2007 - Proceedings
Y2 - 1 October 2007 through 3 October 2007
ER -