Human action segmentation and recognition via motion and shape analysis

Ling Shao, Ling Ji, Yan Liu, Jianguo Zhang

Research output: Journal article publicationJournal articleAcademic researchpeer-review

92 Citations (Scopus)

Abstract

In this paper, we present an automated video analysis system which addresses segmentation and detection of human actions in an indoor environment, such as a gym. The system aims at segmenting different movements from the input video and recognizing the action types simultaneously. Two action segmentation techniques, namely color intensity based and motion based, are proposed. Both methods can efficiently segment periodic human movements into temporal cycles. We also apply a novel approach for human action recognition by describing human actions using motion and shape features. The descriptor contains both the local shape and its spatial layout information, therefore is more effective for action modeling and is suitable for detecting and recognizing a variety of actions. Experimental results show that the proposed action segmentation and detection algorithms are highly effective.
Original languageEnglish
Pages (from-to)438-445
Number of pages8
JournalPattern Recognition Letters
Volume33
Issue number4
DOIs
Publication statusPublished - 1 Mar 2012

Keywords

  • Human action recognition
  • Human action segmentation
  • Motion analysis
  • Motion history image
  • PCOG

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this