Article

A Probabilistic Sensor for the Perception and Recognition of Activities

Authors:

Olivier Chomat,

James L. CrowleyAuthors Info & Claims

ECCV '00: Proceedings of the 6th European Conference on Computer Vision-Part I

Pages 487 - 503

Published: 26 June 2000 Publication History

Abstract

This paper presents a new technique for the perception and recognition of activities using statistical descriptions of their spatio-temporal properties. A set of motion energy receptive fields is designed in order to sample the power spectrum of a moving texture. Their structure relates to the spatio-temporal energy models of Adelson and Bergen where measures of local visual motion information are extracted by comparing the outputs of a triad of Gabor energy filters. Then the probability density function required for Bayes rule is estimated for each class of activity by computing multi-dimensional histograms from the outputs from the set of receptive fields. The perception of activities is achieved according to Bayes rule. The result at each instant of time is the map of the conditional probabilities that each pixel belongs to each one of the activities of the training set. Since activities are perceived over a short integration time, a temporal analysis of outputs is done using Hidden Markov Models.

The approach is validated with experiments in the perception and recognition of activities of people walking in visual surveillance scenari. The presented work is in progress and preliminary results are encouraging, since recognition is robust to variations in illumination conditions, to partial occlusions and to changes in texture. It is shown that it constitute a powerful early vision tool for human behaviors analysis for smart-environnements.

References

[1]

E.H. Adelson and J.R. Bergen. Spatio-temporal energy models for the perception of motion. Optical Society of America, 2(2):284-299, 1985.

[2]

E.H. Adelson and J.R. Bergen. Computational Models of Visual Processing , chapter The Plenoptic function and the elements of early vision. M. Landy and J.A. Movshons, Cambridge, 1991. MIT Press.

[3]

C. Biernacki, G. Celeux, and G. Govaert. Assessing a mixture model for clustering eith integrated classification likelihood. Technical report, October 1998.

[4]

A. Bobick and J. Davis. An appearence based representation of action. In Proc. Int. Conference on Pattern Recognition, pages 307-312, 1996.

[5]

A.M. Baumberg and D.C. Hogg. Learning spatiotemporal models from training examples. Technical Report 95.9, School of Computer Studies, Division of Artificial Intelligence, University of Leeds, March 1995.

[6]

M.J. Black and A.D. Jepson. Eigentracking: Robust matching and tracking of articulated objects using a view-based representation. In European Conference on Computer Vision, pages 329-342, 1996.

[7]

V. Colin de Verdière and J.L. Crowley. Visual recognition using local appearance. In European Conference on Computer Vision, pages 640- 654, 1998.

[8]

T.F. Cootes, C.J. Taylor, A. Lanitis, D.H. Cooper, and J. Graham. Building and using flexible models incorporating gray-level information. In International Conference on Computer Vision, pages 242-246, May 1993.

[9]

D.J. Heeger. Optical flow using spatio-temporal filters. International Journal of Computer Vision, pages 279-302, 1988.

[10]

J.J. Koenderink and A.J. van Doorn. Generic neighborhood operators. Pattern Analysis and Machine Intelligence, 14(6):597-605, june 1992.

[11]

T. Lindeberg. Feature detection with automatic scale selection. International Journal of Computer Vision, 30(2):79-116, 1998.

[12]

H. Murase and S.K. Nayar. Visual learning and recognition of 3-d objects from appearance. International Journal of Computer Vision, 14:5-24, 1995.

[13]

B. Schiele. Object Recognition Using Multidimentional Receptive Field Histograms. PhD thesis, Institut National Polytechnique de Grenoble, july 1997.

[14]

A. Spinei, D. Pellerin, and J. Herault. Spatio-temporal energy-based method for velocity estimation. Signal Processing, 65:347-362, 1998.

[15]

C. Wren, A. Azarbayejani, T. Darrel, and A. Pentland. Pfinder: Real-time tracking of the human body. In International Conference on Automatic face and Gesture Recognition, pages 51-56, 1996.

[16]

Y. Yacoob and M.J. Black. Parameterized modeling and recognition of activities. In International Conference on Computer Vision, 1998.

Cited By

Bang-Jensen JYeo A(2014)The complexity of multicut and mixed multicut problems in (di)graphsTheoretical Computer Science10.1016/j.tcs.2013.10.022520(87-96)Online publication date: 1-Feb-2014
https://dl.acm.org/doi/10.1016/j.tcs.2013.10.022
Sokol DTojeira J(2014)Speeding up the detection of tandem repeats over the edit distanceTheoretical Computer Science10.1016/j.tcs.2013.04.021525(103-110)Online publication date: 1-Mar-2014
https://dl.acm.org/doi/10.1016/j.tcs.2013.04.021
Gryn JWildes RTsotsos J(2009)Detecting motion patterns via direction maps with application to surveillanceComputer Vision and Image Understanding10.1016/j.cviu.2008.10.006113:2(291-307)Online publication date: 1-Feb-2009
https://dl.acm.org/doi/10.1016/j.cviu.2008.10.006
Show More Cited By

A Probabilistic Sensor for the Perception and Recognition of Activities
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision tasks

Recommendations

A Probabilistic Sensor for the Perception of Activities
FG '00: Proceedings of the Fourth IEEE International Conference on Automatic Face and Gesture Recognition 2000

This paper presents a new technique for the perception of activities using statistical description of spatio-temporal properties. With this approach, the probability of an activity in a spatio-temporal image sequence is computed by applying Bayes rule ...
Recognition of coupling-paired activities in daily life
HCCE '12: Proceedings of the 2012 Joint International Conference on Human-Centered Computer Environments

Recognition of daily activities is one of major focuses in health care systems. But limited number of studies has been done on recognition of complex human activities in daily life. Therefore in this work an attempt has been done to recognize complex ...
Recognition of Continuous Activities
IBERAMIA 2002: Proceedings of the 8th Ibero-American Conference on AI: Advances in Artificial Intelligence

The recognition of continuous human activities performed with several limbs is still an open problem. We propose a novel approach for recognition of continuous activities, which considers the direction change between frames to track the motion of ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Guide Proceedings

ECCV '00: Proceedings of the 6th European Conference on Computer Vision-Part I

June 2000

930 pages

ISBN:3540676856

Editor:
David Vernon

Publisher

Springer-Verlag

Berlin, Heidelberg

Publication History

Published: 26 June 2000

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

9
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 14 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Bang-Jensen JYeo A(2014)The complexity of multicut and mixed multicut problems in (di)graphsTheoretical Computer Science10.1016/j.tcs.2013.10.022520(87-96)Online publication date: 1-Feb-2014
https://dl.acm.org/doi/10.1016/j.tcs.2013.10.022
Sokol DTojeira J(2014)Speeding up the detection of tandem repeats over the edit distanceTheoretical Computer Science10.1016/j.tcs.2013.04.021525(103-110)Online publication date: 1-Mar-2014
https://dl.acm.org/doi/10.1016/j.tcs.2013.04.021
Gryn JWildes RTsotsos J(2009)Detecting motion patterns via direction maps with application to surveillanceComputer Vision and Image Understanding10.1016/j.cviu.2008.10.006113:2(291-307)Online publication date: 1-Feb-2009
https://dl.acm.org/doi/10.1016/j.cviu.2008.10.006
Gorelick LBlank MShechtman EIrani MBasri R(2007)Actions as Space-Time ShapesIEEE Transactions on Pattern Analysis and Machine Intelligence10.1109/TPAMI.2007.7071129:12(2247-2253)Online publication date: 1-Dec-2007
https://dl.acm.org/doi/10.1109/TPAMI.2007.70711
Shechtman EIrani M(2007)Space-Time Behavior-Based Correlation—OR—How to Tell If Two Underlying Motion Fields Are Similar Without Computing Them?IEEE Transactions on Pattern Analysis and Machine Intelligence10.1109/TPAMI.2007.111929:11(2045-2056)Online publication date: 1-Nov-2007
https://dl.acm.org/doi/10.1109/TPAMI.2007.1119
Andrade NBrasileiro FCirne WMowbray M(2007)Automatic grid assembly by promoting collaboration in peer-to-peer gridsJournal of Parallel and Distributed Computing10.1016/j.jpdc.2007.04.01167:8(957-966)Online publication date: 1-Aug-2007
https://dl.acm.org/doi/10.1016/j.jpdc.2007.04.011
Laptev ICaputo BSchüldt CLindeberg T(2007)Local velocity-adapted motion events for spatio-temporal recognitionComputer Vision and Image Understanding10.1016/j.cviu.2006.11.023108:3(207-229)Online publication date: 1-Dec-2007
https://dl.acm.org/doi/10.1016/j.cviu.2006.11.023
Laptev ILindeberg T(2004)Local descriptors for spatio-temporal recognitionProceedings of the First international conference on Spatial Coherence for Visual Motion Analysis10.1007/11676959_8(91-103)Online publication date: 15-May-2004
https://dl.acm.org/doi/10.1007/11676959_8
Laptev ILindeberg T(2003)Interest point detection and scale selection in space-timeProceedings of the 4th international conference on Scale space methods in computer vision10.5555/1764717.1764753(372-387)Online publication date: 10-Jun-2003
https://dl.acm.org/doi/10.5555/1764717.1764753

View Options

View options

Media

Figures

Other

Tables

View Table of Contents