Article

Top-down, bottom-up multivalued default reasoning for identity maintenance

Authors:

Larry S. DavisAuthors Info & Claims

VSSN '06: Proceedings of the 4th ACM international workshop on Video surveillance and sensor networks

Pages 79 - 86

https://doi.org/10.1145/1178782.1178795

Published: 27 October 2006 Publication History

Abstract

Persistent tracking systems require the capacity to track individuals by maintaining identity across visibility gaps caused by occlusion events. In traditional computer vision systems, the flow of information is typically bottom-up. The low level image processing modules take video input, perform early vision tasks such as background subtraction and object detection,and pass this information to the high level reasoning module. This paper describes the architecture of a system that uses top-down information flow to perform identity maintenance across occlusion events. This system uses the high level reasoning module to provide control feedback to the low level image processing module to perform forensic analysis of archival video and actively acquire information required to arrive at identity decisions. This functionality is in addition to traditional bottom-up reasoning about identity, employing contextual cues and appearance matching, within the multivalued default logic framework proposed in [18]. This framework, in addition to bestowing upon the system the property of nonmonotonicity, also allows for it to qualitatively encode its confidence in the identity decisions it takes.

References

[1]

C. BenAbdelkader, R. Cutler,and L. Davis. Motion-based recognition of people in eigengait space. In Proc of Intl. Conf. on Auto Face and Gesture Recogtn page 267, 2002.

Digital Library

[2]

G. J. Brostowand I. A. Essa. Motionbased decompositing of video. IEEE International Conference on Computer Vision 2001.

[3]

D. Comaniciu, V. Ramesh, and P. Meer. Real-time tracking of non-rigid objects using mean shift. IEEE Computer Vision and Pattern Recognition 2:142--149, 2000.

[4]

M. L. Ginsberg. Multi-valued logics: a uniform approach to reasoning in artificial intelligence. Computational Intelligence 4:265--316, 1988.

[5]

I. Haritaoglu, D. Harwood, and L. Davis. W4: A real time system for detecting and tracking people. IEEE Computer Vision and Pattern Recognition page 962, 1998.

Digital Library

[6]

S. S. Intille and A. F. Bobick. Closed-world tracking. IEEE International Conference on Computer Vision pages 672--678,1995.

Digital Library

[7]

M. Isard and J. MacCormick. Bramble: A bayesian multiple-blob tracker. IEEE International Conference on Computer Vision pages 34--41, 2001.

[8]

A. D. Jepson, D. J. Fleet, and T. F. El-Maraghi. Robust online appearance models for visual tracking. IEEE Trans. Pattern Analysis and Machine Intelligence 25:1296--1311, 2003.

Digital Library

[9]

N. Jojic and B. Frey. Learning flexible sprites in video layers. IEEE Computer Vision and Pattern Recognition 2001.

[10]

K. Kim, T. H. Chalidabhongse, D. Harwood, and L. Davis. Background modeling and subtraction by codebook construction. IEEE International Conference on Image Processing 2004.

[11]

D. Koller, J. Weber, and J. Malik. Robust multiple car tracking with occlusion reasoning. European Conference on Computer Vision pages 189--196, 1994.

Digital Library

[12]

J. Krumm, S. Harris, B. Meyers, B. Brumitt, M. Hale, and S. Shafer. Multi-camera multi-person tracking for easyliving. Proc. 3rd IEEE Intl Workshop on Visual Surveillance 2000.

Digital Library

[13]

S. J. McKenna, S. Jabri, Z. Duric, A. Rosenfeld, and H. Wechsler. Tracking groups of people. Computer Vision and Image Understanding 80:42--56, 2000.

Digital Library

[14]

C. Nakajima, M. Pontil, B. Heisele, and T. Poggio. Full-body person recognition system. Pattern Recognition 36(9):1997--2006, 2003.

[15]

J. Rehg and T. Kanade. Model-based tracking of self-occluding articulated objects. IEEE International Conference on Computer Vision 1995.

Digital Library

[16]

R. Reiter. A logic for default reasoning. Readings in nonmonotonic reasoning pages 68--93, 1987.

Digital Library

[17]

A. Senior, A. Hampapur,Y.-L. Tian, L. Brown, S. Pankanti, and R. Bolle. Appearance models for occlusion handling. In IEEE Workshop on Performance Evaluation of Tracking and Surveillance 2001.

[18]

V. Shet, D. Harwood, and L. Davis. Multivalued Default Logic for Identity Maintenance in Visual Surveillance. European Conference on Computer Vision IV:119--132, 2006.

Digital Library

[19]

H. Tao, H. S. Sawhney, and R. Kumar. Object tracking with bayesian estimation of dynamic layer representations. IEEE Trans. on Pattern Analysis and Machine Intelligence 24(1):75--89, 2002.

Digital Library

[20]

G. Wei, V. Petrushin, and A. Gershman. Multiple-camera people localization in a cluttered environment. The 5th International Workshop on Multimedia Data Mining 2004.

[21]

C. Wren, A. Azarbayejani, T. Darrell, and A. Pentland. P finder: Real-time tracking of the human body. IEEE Trans. Pattern Analysis and Machine Intelligence 19(7):780--85, 1997.

Digital Library

[22]

K. Yoon, D. Harwood, and L. Davis. Appearance-based person recognition using color-path/length profile. Unpublished work.

[23]

S. Zhou, V. Krueger, and R. Chellappa. Probabilistic recognition of human faces from video.Comput. Vis. Image Underst. 91(1-2):214--245, 2003.

Digital Library

Cited By

Ray KPaul SSaha D(2018)Preorder-based triangle: a modified version of bilattice-based triangle for belief revision in nonmonotonic reasoningJournal of Experimental & Theoretical Artificial Intelligence10.1080/0952813X.2018.1467493(1-26)Online publication date: 18-May-2018
https://doi.org/10.1080/0952813X.2018.1467493
Han SStechele W(2013)Default Reasoning for Forensic Visual Surveillance Based on Subjective Logic and its Comparison with L-Fuzzy Set Based ApproachesMultimedia Data Engineering Applications and Processing10.4018/978-1-4666-2940-0.ch004(51-94)Online publication date: 2013
https://doi.org/10.4018/978-1-4666-2940-0.ch004
Han SStechele W(2011)Default Reasoning for Forensic Visual Surveillance based on Subjective Logic and Its Comparison with L-Fuzzy Set Based ApproachesInternational Journal of Multimedia Data Engineering and Management10.4018/jmdem.20110101032:1(38-86)Online publication date: Jan-2011
https://doi.org/10.4018/jmdem.2011010103
Show More Cited By

Index Terms

Top-down, bottom-up multivalued default reasoning for identity maintenance
1. Computing methodologies
  1. Artificial intelligence
    1. Philosophical/theoretical foundations of artificial intelligence

Recommendations

Preferential reasoning in the perspective of Poole default logic
Complexity of argument-based default reasoning with specificity

In this paper we investigate the complexity of Dung and Son's approach to default reasoning with specificity. We show that the three decision problems: existence of extensions, brave reasoning and cautious reasoning are generally complete for the second ...
A tutorial on default logics

Default logic is one of the most prominent approaches to nonmonotonic reasoning, and allows one to make plausible conjectures when faced with incomplete information about the problem at hand. Default rules prevail in many application domains such as ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

VSSN '06: Proceedings of the 4th ACM international workshop on Video surveillance and sensor networks

October 2006

230 pages

ISBN:1595934960

DOI:10.1145/1178782

General Chairs:
Jake K. Aggarwal
University of Texas
,
Rita Cucchiara
University of Modena and Reggio Emilia, Italy
,
Program Chair:
Andrea Prati
University of Modena and Reggio Emilia, Italy

Copyright © 2006 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 27 October 2006

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Article

Conference

MM06

Sponsor:

MM06: The 14th ACM International Conference on Multimedia 2006

October 27, 2006

California, Santa Barbara, USA

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

5
Total Citations
View Citations
254
Total Downloads

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

Reflects downloads up to 30 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Ray KPaul SSaha D(2018)Preorder-based triangle: a modified version of bilattice-based triangle for belief revision in nonmonotonic reasoningJournal of Experimental & Theoretical Artificial Intelligence10.1080/0952813X.2018.1467493(1-26)Online publication date: 18-May-2018
https://doi.org/10.1080/0952813X.2018.1467493
Han SStechele W(2013)Default Reasoning for Forensic Visual Surveillance Based on Subjective Logic and its Comparison with L-Fuzzy Set Based ApproachesMultimedia Data Engineering Applications and Processing10.4018/978-1-4666-2940-0.ch004(51-94)Online publication date: 2013
https://doi.org/10.4018/978-1-4666-2940-0.ch004
Han SStechele W(2011)Default Reasoning for Forensic Visual Surveillance based on Subjective Logic and Its Comparison with L-Fuzzy Set Based ApproachesInternational Journal of Multimedia Data Engineering and Management10.4018/jmdem.20110101032:1(38-86)Online publication date: Jan-2011
https://doi.org/10.4018/jmdem.2011010103
Han SKoo BStechele W(2010)Subjective Logic Based Approach to Modeling Default Reasoning for Visual SurveillanceProceedings of the 2010 IEEE Fourth International Conference on Semantic Computing10.1109/ICSC.2010.55(112-119)Online publication date: 22-Sep-2010
https://dl.acm.org/doi/10.1109/ICSC.2010.55
Li YYin Y(2009)Towards Suspicious Behavior Discovery in Video Surveillance SystemProceedings of the 2009 Second International Workshop on Knowledge Discovery and Data Mining10.1109/WKDD.2009.22(539-541)Online publication date: 23-Jan-2009
https://dl.acm.org/doi/10.1109/WKDD.2009.22

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents