Browsing by Author "Shih, Arthur Chun-Chieh"

Now showing 1 - 4 of 4

A language modeling approach to atomic human action recognition
(2007)
Liang, Yu-Ming
;
Shih, Sheng-Wen
;
Shih, Arthur Chun-Chieh
;
Liao, Hong-Yuan Mark
;
Lin, Cheng-Chung
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.
Learning Atomic Human Actions Using Variable-Length Markov Models
(2009-02-01)
Liang, Yu-Ming
;
Shih, Sheng-Wen
;
Shih, Arthur Chun-Chieh
;
Liao, Hong-Yuan Mark
;
Lin, Cheng-Chung
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.
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.
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.