標題: Learning Atomic Human Actions Using Variable-Length Markov Models
作者: Liang, Yu-Ming
Shih, Sheng-Wen
Shih, Arthur Chun-Chieh
Liao, Hong-Yuan Mark
Lin, Cheng-Chung
資訊工程學系
Department of Computer Science
關鍵字: Atomic action learning;atomic action recognition;human behavior analysis;variable-length Markov models (VLMMs)
公開日期: 1-二月-2009
摘要: Visual analysis of human behavior has generated considerable interest in the field of computer vision because of its wide spectrum of potential applications. Human behavior can be segmented into atomic actions, each of which indicates a basic and complete movement. Learning and recognizing atomic human actions are essential to human behavior analysis. In this paper, we propose a framework for handling this task using variable-length Markov models (VLMMs). The framework is comprised of the following two modules: a posture labeling module and a VLMM atomic action learning and recognition module. First, a posture template selection algorithm, based on a modified shape context matching technique, is developed. The selected posture templates form a codebook that is used to convert input posture sequences into discrete symbol sequences for subsequent processing. Then, the VLMM technique is applied to learn the training symbol sequences of atomic actions. Finally, the constructed VLMMs are transformed into hidden Markov models (HMMs) for recognizing input atomic actions. This approach combines the advantages of the excellent learning function of a VLMM and the fault-tolerant recognition ability of an HMM. Experiments on realistic data demonstrate the efficacy of the proposed system.
URI: http://dx.doi.org/10.1109/TSMCB.2008.2005643
http://hdl.handle.net/11536/7674
ISSN: 1083-4419
DOI: 10.1109/TSMCB.2008.2005643
期刊: IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS
Volume: 39
Issue: 1
起始頁: 268
結束頁: 280
顯示於類別:期刊論文


文件中的檔案:

  1. 000262562700023.pdf

若為 zip 檔案,請下載檔案解壓縮後,用瀏覽器開啟資料夾中的 index.html 瀏覽全文。