Recognizing human action in time-sequential images using hidden Markov model

J. Yamato, Jun Ohya, K. Ishii

研究成果: Conference contribution

997 被引用数 (Scopus)

抄録

A human action recognition method based on a hidden Markov model (HMM) is proposed. It is a feature-based bottom-up approach that is characterized by its learning capability and time-scale invariability. To apply HMMs, one set of time-sequential images is transformed into an image feature vector sequence, and the sequence is converted into a symbol sequence by vector quantization. In learning human action categories, the parameters of the HMMs, one per category, are optimized so as to best describe the training sequences from the category. To recognize an observed sequence, the HMM which best matches the sequence is chosen. Experimental results for real time-sequential images of sports scenes show recognition rates higher than 90%. The recognition rate is improved by increasing the number of people used to generate the training data, indicating the possibility of establishing a person-independent action recognizer.

本文言語English
ホスト出版物のタイトルProceedings CVPR 1992 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition
出版社IEEE Computer Society
ページ379-385
ページ数7
ISBN(電子版)0818628553
DOI
出版ステータスPublished - 1992 1月 1
外部発表はい
イベント1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 1992 - Champaign, United States
継続期間: 1992 6月 151992 6月 18

出版物シリーズ

名前Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
1992-June
ISSN(印刷版)1063-6919

Conference

Conference1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 1992
国/地域United States
CityChampaign
Period92/6/1592/6/18

ASJC Scopus subject areas

  • ソフトウェア
  • コンピュータ ビジョンおよびパターン認識

フィンガープリント

「Recognizing human action in time-sequential images using hidden Markov model」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル