Spatiotemporal salient points for visual recognition of human actions.

Full Abstract

This paper addresses the problem of human-action recognition by introducing a sparse representation of image sequences as a collection of spatiotemporal events that are localized at points that are salient both in space and time. The spatiotemporal salient points are detected by measuring the variations in the information content of pixel neighborhoods not only in space but also in time. An appropriate distance metric between two collections of spatiotemporal salient points is introduced, which is based on the chamfer distance and an iterative linear time-warping technique that deals with time expansion or time-compression issues. A classification scheme that is based on relevance vector machines and on the proposed distance measure is proposed. Results on real image sequences from a small database depicting people performing 19 aerobic exercises are presented.

Learn Faster Today Improve your study skills

Author information

Author/s: Oikonomopoulos, Antonios (A); Patras, Ioannis (I); Pantic, Maja (M);

Journal and publication information

Publication Type: Letter; Research Support, Non-U.S. Gov't

Journal: IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society (IEEE Trans Syst Man Cybern B Cybern), published in United States. (Language: eng)

Reference: 2006-Jun; vol 36 (issue 3) : pp 710-9

Dates: Created 2006/06/09; Completed 2006/07/07; Revised 2006/11/15;

PMID: 16761823, status: MEDLINE (last retrieval date: 12/26/2008)

Sourced from the National Library of Medicine. Abstract text and other information may be subject to copyright.

External Links for this article (including full text providers, if available):

Click Electronic Full-text Provider Links to see options for finding the electronic full text links to this article. Note there may be a subscription or fee required for access to the full text. See our FAQ for information on finding FREE full text articles.

This article may also be located in paper journal collections available in many libraries. Use the Journal and Publication Information above to find the full article.

MeSH headings (categories)

This article was linked to the MESH Headings shown below.

Algorithms
Artificial Intelligence
Computer Simulation
Humans
Image Interpretation, Computer-Assisted - methods
Models, Biological

Movement
Pattern Recognition, Automated - methods
Subtraction Technique
Task Performance and Analysis
Time Factors
Video Recording - methods

These are the highest related articles currently in the database:

Discriminant locally linear embedding with high-order tensor data. 30 Mar 2008
Geometric observers for dynamically evolving curves. 30 May 2008
Tracking the visual focus of attention for a varying number of wandering people. 29 Jun 2008
Robust shape tracking with multiple models in ultrasound images. 28 Feb 2008
Fixation precision in high-speed noncontact eye-gaze tracking. 30 Mar 2008
Infinite hidden Markov models for unusual-event detection in video. 29 Apr 2008
Motion segmentation and depth ordering using an occlusion detector. 29 Jun 2008
Segmentation and tracking of multiple humans in crowded environments. 29 Jun 2008
State-based modeling and object extraction from echocardiogram video. 29 Apr 2008
Constraint integration for efficient multiview pose estimation with self-occlusions. 28 Feb 2008

See 100+ related articles.