Modeling and recognizing action contexts in persons using sparse representation

Hui Fen Chiang*, Jun-Wei Hsieh, Chi Hung Chuang, Kai Ting Chuang, Yilin Yan

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

Abstract This paper proposes a novel dynamic sparsity-based classification scheme to analyze various interaction actions between persons. To address the occlusion problem, this paper represents an action in an over-complete dictionary to makes errors (caused by lighting changes or occlusions) sparsely appear in the training library if the error cases are well collected. Because of this sparsity, it is robust to occlusions and lighting changes. In addition, a novel Hamming distance classification (HDC) scheme is proposed to classify action events to various types. Because the nature of Hamming code is highly tolerant to noise, the HDC scheme is also robust to environmental changes. The difficulty of complicated action modeling can be easily tackled by adding more examples to the over-complete dictionary. More importantly, the HDC scheme is very efficient and suitable for real-time applications because no minimization process is involved to calculate the reconstruction error.

Original languageEnglish
Article number1515
Pages (from-to)252-265
Number of pages14
JournalJournal of Visual Communication and Image Representation
Volume30
DOIs
StatePublished - 1 Jul 2015

Keywords

  • Keywords Sparse coding Sparse reconstruction error Occlusions R transform Interaction action analysis Behavior analysis Person-to-person action recognition Person-to-object action recognition

Fingerprint

Dive into the research topics of 'Modeling and recognizing action contexts in persons using sparse representation'. Together they form a unique fingerprint.

Cite this