Interactive activity recognition using articulated-pose features on spatio-temporal relation
  • Huynh-The, Thien
  • Bui, Dinh-Mao
  • Lee, Sungyoung
  • Yoon, Yongik
Citations

WEB OF SCIENCE

0
Citations

SCOPUS

0

초록

A success progress of pose estimation approaches motivates the activity recognition used in CCTV-based surveillance systems. In this paper, a method is proposed for recognizing interactive activities between two human objects. Based on articulated joint coordinates obtained from a pose estimation algorithm, the distance and direction feature are extracted from objects to describe both the spatial and temporal relation. The multiclass Support Vector Machine is finally employed for activity classification task. Compared with existing methods using the public interaction dataset, the proposed method outperforms in overall classification accuracy.

키워드

Articulated-pose featureInteractive activity recognitionSpatio-temporal relationClassification (of information)Motion estimationPattern recognitionActivity classificationsActivity recognitionArticulated-pose featureClassification accuracyInteractive activitiesMulti-class support vector machinesPose estimation algorithmSpatio-temporal relationsImage recognition
제목
Interactive activity recognition using articulated-pose features on spatio-temporal relation
저자
Huynh-The, ThienBui, Dinh-MaoLee, SungyoungYoon, Yongik
DOI
10.1007/978-981-10-0281-6_50
발행일
2015-12
유형
Article
저널명
Lecture Notes in Electrical Engineering
373
페이지
345 ~ 351