Action recognition using three-way cross-correlations feature of local motion attributes

Tetsu Matsukawa, Takio Kurita

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

7 被引用数 (Scopus)

抄録

This paper proposes a spatio-temporal feature using three-way cross-correlations of local motion attributes for action recognition. Recently, the cubic higher-order local auto-correlations (CHLAC) feature has been shown high classification performances for action recognition. In previous researches, CHLAC feature was applied to binary motion image sequences that indicates moving or static points. However, each binary motion image lost informations about the type of motion such as timing of change or motion direction. Therefore, we can improve the classification accuracy further by extending CHLAC to multivalued motion image sequences that considered several types of local motion attributes. The proposed method is also viewed as an extension of popular bag-of-features approach. Experimental results using two datasets shows proposed method outperformed CHLAC features and bag-of-features approach.

本文言語英語
ホスト出版物のタイトルProceedings - 2010 20th International Conference on Pattern Recognition, ICPR 2010
ページ1731-1734
ページ数4
DOI
出版ステータス出版済み - 11 18 2010
外部発表はい
イベント2010 20th International Conference on Pattern Recognition, ICPR 2010 - Istanbul, トルコ
継続期間: 8 23 20108 26 2010

出版物シリーズ

名前Proceedings - International Conference on Pattern Recognition
ISSN(印刷版)1051-4651

その他

その他2010 20th International Conference on Pattern Recognition, ICPR 2010
Countryトルコ
CityIstanbul
Period8/23/108/26/10

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

フィンガープリント 「Action recognition using three-way cross-correlations feature of local motion attributes」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