Action-02MCF: A robust space-time correlation filter for action recognition in clutter and adverse lighting conditions

Anwaar Ul-Haq, Xiaoxia Yin, Yunchan Zhang, Iqbal Gondal

Research output: Book chapter/Published conference paperConference paperpeer-review

2 Citations (Scopus)

Abstract

Human actions are spatio-temporal visual events and recognizing human actions in different conditions is still a challenging computer vision problem. In this paper, we introduce a robust feature based space-time correlation filter, called Action-02MCF (0’zero-aliasing’ 2M’ Maximum Margin’) for recognizing human actions in video sequences. This filter combines (i) the sparsity of spatio-temporal feature space, (ii) generalization of maximum margin criteria, (iii) enhanced aliasing free localization performance of correlation filtering using (iv) rich context of maximally stable space-time interest points into a single classifier. Its rich multi-objective function provides robustness, generalization and recognition as a single package. Action-02MCF can simultaneously localize and classify actions of interest even in clutter and adverse imaging conditions. We evaluate the performance of our proposed filter for challenging human action datasets. Experimental results verify the performance potential of our action-filter compared to other correlation filtering based action recognition approaches.
Original languageEnglish
Title of host publicationAdvanced concepts for intelligent vision systems
Subtitle of host publication17th international conference, ACIVS 2016, proceedings
EditorsJacques Blanc-Talon, Cosimo Distante, Wilfried Philips, Dan Popescu, Paul Scheunders
Place of PublicationCham, Switzerland
PublisherSpringer
Pages465-476
Number of pages12
ISBN (Electronic)9783319486802
ISBN (Print)9783319486796
DOIs
Publication statusPublished - 2016
Event17th International Conference on Advanced Concepts for Intelligent Vision Systems 2016: ACIVS 2016 - Patria Palace Hotel, Lecce, Italy
Duration: 24 Oct 201627 Oct 2016
http://acivs.org/acivs2016/ (Conference webpage)
https://link.springer.com/book/10.1007/978-3-319-48680-2 (Proceedings)
https://link.springer.com/content/pdf/bfm%3A978-3-319-48680-2%2F1 (Front matter)

Publication series

NameLecture notes in computer science
PublisherSpringer
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference17th International Conference on Advanced Concepts for Intelligent Vision Systems 2016
Country/TerritoryItaly
CityLecce
Period24/10/1627/10/16
OtherAcivs 2016 is a conference focusing on techniques for building adaptive, intelligent, safe and secure imaging systems. Acivs 2016 consists of four days of lecture sessions, both regular (25 minutes) and invited presentations, and poster sessions. The proceedings of Acivs 2016 will be published by Springer in the Lecture Notes in Computer Science series and are listed in the ISI proceedings index.
Internet address

Fingerprint

Dive into the research topics of 'Action-02MCF: A robust space-time correlation filter for action recognition in clutter and adverse lighting conditions'. Together they form a unique fingerprint.

Cite this