Tampere University of Technology

TUTCRIS Research Portal

Stereoscopic video description for human action recognition

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Details

Original languageEnglish
Title of host publicationIEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIMSIVP 2014: 2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing, Proceedings
PublisherThe Institute of Electrical and Electronics Engineers, Inc.
ISBN (Print)9781479945047
DOIs
Publication statusPublished - 16 Jan 2015
Publication typeA4 Article in a conference publication
Event2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing, CIMSIVP 2014 - Orlando, United States
Duration: 9 Dec 201412 Dec 2014

Conference

Conference2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing, CIMSIVP 2014
CountryUnited States
CityOrlando
Period9/12/1412/12/14

Abstract

In this paper, a stereoscopic video description method is proposed that indirectly incorporates scene geometry information derived from stereo disparity, through the manipulation of video interest points. This approach is flexible and able to cooperate with any monocular low-level feature descriptor. The method is evaluated on the problem of recognizing complex human actions in natural settings, using a publicly available action recognition database of unconstrained stereoscopic 3D videos, coming from Hollywood movies. It is compared both against competing depth-aware approaches and a state-of-the-art monocular algorithm. Experimental results denote that the proposed approach outperforms them and achieves state-of-the-art performance.