<link rel="stylesheet" href="styles.cf390c6bfbe7555f.css">

學術出版;;Publications

Permanent URI for this communityhdl:11536/1

收集所有交通大學研究人員與學生個人或團體所發表之各項學術著作，涵蓋期刊論文、教師專書、學位論文等項。;;Collections of Publications of NCTU Researchers and Students Like Journal Papers and Thesis.

Browse

Filters

2006 - 20092

Settings

🏛️國立陽明交通大學機構典藏

Access type: Metadata onlyAuthor: search.filters.author.Liang, Yu-Ming

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item type:Item,
    Understanding human behavior using a language modeling approach
    (2006)
    Liang, Yu-Ming
    ;
    Shih, Sheng-Wen
    ;
    Shih, Arthur Chun-Chieh
    ;
    Liao, Hong-Yuan Mark
    ;
    資訊工程學系
    Visual analysis of human behavior has generated considerable interest in the field of computer vision because of the wide spectrum of potential applications. In this paper, we present a language modeling framework for understanding human behavior. The proposed framework consists of two modules: the key posture selection module, and the variable-length Markov model (VLMM) behavior recognition module. A key posture selection algorithm is developed based on the shape context matching technique. A codebook is then constructed with the computed key postures and used to convert input image sequences into training symbol sequences or recognition symbol sequences. Finally, a VLMM is applied to learn and recognize the constructed symbol sequences corresponding to human behavior patterns. Experiments on real data demonstrate the efficacy of the proposed system.
  • Thumbnail Image
    Item type:Item,
    Unsupervised Analysis of Human Behavior Based on Manifold Learning
    (2009)
    Liang, Yu-Ming
    ;
    Shih, Sheng-Wen
    ;
    Shih, Arthur Chun-Chieh
    ;
    Liao, Hong-Yuan Mark
    ;
    Lin, Cheng-Chung
    In this paper, we propose a framework for unsupervised analysis of human behavior based on manifold learning. First, a pairwise human posture distance matrix is calculated from a training action sequence. Then, the isometric feature mapping (Isomap) algorithm is applied to construct a low-dimensional structure from the distance matrix. The data points in the Isomap space are consequently represented as a time-series of low-dimensional points. A temporal segmentation technique is then applied to segment the time series into subseries corresponding to atomic actions. Next, a dynamic time warping (DTW) approach is applied for clustering atomic action sequences. Finally, we use the clustering results to learn and classify atomic actions using the nearest neighbor rule. Experiments conducted on real data demonstrate the efficacy of the proposed method.