skip to main content
10.1145/2510650.2510657acmconferencesArticle/Chapter ViewAbstractPublication PagesmmConference Proceedingsconference-collections
research-article

Cross-domain traffic scene understanding by motion model transfer

Published: 21 October 2013 Publication History

Abstract

This paper proposes a novel framework for cross-domain traffic scene understanding. Existing learning-based outdoor wide-area scene interpretation models suffer from requiring long term data collection in order to acquire statistically sufficient model training samples for every new scene. This makes installation costly, prevents models from being easily relocated, and from being used in UAVs with continuously changing scenes. In contrast, our method adopts a geometrical matching approach to relate motion models learned from a database of source scenes (source domains) with a handful sparsely observed data in a new target scene (target domain). This framework is capable of online ''sparse-shot'' anomaly detection and motion event classification in the unseen target domain, without the need for extensive data collection, labelling and offline model training for each new target domain. That is, trained models in different source domains can be deployed to a new target domain with only a few unlabelled observations and without any training in the new target domain. Crucially, to provide cross-domain interpretation without risk of dramatic negative transfer, we introduce and formulate a scene association criterion to quantify transferability of motion models from one scene to another. Extensive experiments show the effectiveness of the proposed framework for cross-domain motion event classification, anomaly detection and scene association.

References

[1]
D. H. Douglas and T. K. Peucker. Algorithms for the reduction of the number of points required to represent a digitized line or its caricature. Cartographica: The International Journal for Geographic Information and Geovisualization, 10(2):112--122, Oct. 1973.
[2]
Federal Highway Administration. Next generation simulation (ngsim) dataset. http://ops.fhwa.dot.gov/trafficanalysistools/ngsim.htm.
[3]
A. Goshtasby. Image registration by local approximation methods. Image Vision Comput., 6(4):255--261, 1988.
[4]
J. Hershey and P. Olsen. Approximating the kullback leibler divergence between gaussian mixture models. In ICASSP, 2007.
[5]
T. Hospedales, S. Gong, and T. Xiang. Video behaviour mining using a dynamic topic model. International Journal of Computer Vision, 98:303--323, 2012.
[6]
W. Hu, X. Xiao, Z. Fu, D. Xie, T. Tan, and S. J. Maybank. A system for learning statistical motion patterns. IEEE Transaction on Pattern Analysis and Machine Intelligence, 28(9):1450--1464, 2006.
[7]
S. Khokhar, I. Saleemi, and M. Shah. Similarity invariant classification of events by kl divergence minimization. In ICCV, 2011.
[8]
J. F. Kooij, G. Englebienne, and D. M. Gavrila. A non-parametric hierarchical model to discover behavior dynamics from tracks. In ECCV, 2012.
[9]
H. Kuhn. The Hungarian method for the assignment problem. Naval research logistics quarterly, 2(1--2):83--97, 1955.
[10]
J. Li, S. Gong, and T. Xiang. Learning behavioural context. International Journal of Computer Vision, 97(3):276--304, 2012.
[11]
J. Lin. Divergence measures based on the shannon entropy. IEEE Transactions on Information Theory, 37(1):145--151, 1991.
[12]
R. Mehran, A. Oyama, and M. Shah. Abnormal crowd behavior detection using social force model. In CVPR, 2009.
[13]
B. T. Morris and M. M. Trivedi. Learning and classification of trajectories in dynamic scenes: A general framework for live video analysis. In AVSS, 2008.
[14]
B. T. Morris and M. M. Trivedi. A survey of vision-based trajectory learning and analysis for surveillance. IEEE Transaction on Circuits and Systems for Video Technology, 18(8):1114--1127, 2008.
[15]
J. Nocedal and S. Wright. Numerical optimization. Springer-Verlag, 2nd edition, 2006.
[16]
S. J. Pan and Q. Yang. A survey on transfer learning. IEEE Transsaction on Knowledge and Data Engineering, 22(10):1345--1359, Oct. 2010.
[17]
J. Prokaj, X. Zhao, and G. G. Medioni. Tracking many vehicles in wide area aerial surveillance. In CVPR Workshops, 2012.
[18]
I. Saleemi, L. Hartung, and M. Shah. Scene understanding by statistical modeling of motion patterns. In CVPR, 2010.
[19]
A. Sodemann, M. Ross, and B. Borghetti. A review of anomaly detection in automated surveillance. IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, 42(6):1257--1272, 2012.
[20]
O. Tuzel, F. Porikli, and P. Meer. Region covariance: A fast descriptor for detection and classification. In ECCV, 2006.
[21]
X. Wang, X. Ma, and E. Grimson. Unsupervised activity perception by hierarchical bayesian models. In CVPR, 2007.
[22]
L. Zelnik-Manor and P. Perona. Self-tuning spectral clustering. In NIPS, 2004.
[23]
G. Zen, E. Ricci, and N. Sebe. Exploiting sparse representations for robust analysis of noisy complex video scenes. In ECCV, 2012.

Cited By

View all
  • (2020)Transferring fashion to surveillance with weak labelsNeural Computing and Applications10.1007/s00521-020-05528-935:18(13021-13035)Online publication date: 23-Nov-2020
  • (2017)Discovery of Shared Semantic Spaces for Multiscene Video Query and SummarizationIEEE Transactions on Circuits and Systems for Video Technology10.1109/TCSVT.2016.253271927:6(1353-1367)Online publication date: Jun-2017
  • (2017)A transfer learning framework for traffic video using neuro-fuzzy approachSādhanā10.1007/s12046-017-0705-x42:9(1431-1442)Online publication date: 4-Aug-2017

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
ARTEMIS '13: Proceedings of the 4th ACM/IEEE international workshop on Analysis and retrieval of tracked events and motion in imagery stream
October 2013
94 pages
ISBN:9781450323932
DOI:10.1145/2510650
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: 21 October 2013

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. anomaly detection
  2. gaussian mixtures
  3. transfer learning
  4. visual surveillance

Qualifiers

  • Research-article

Conference

MM '13
Sponsor:
MM '13: ACM Multimedia Conference
October 21, 2013
Barcelona, Spain

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)2
  • Downloads (Last 6 weeks)0
Reflects downloads up to 23 Jan 2025

Other Metrics

Citations

Cited By

View all
  • (2020)Transferring fashion to surveillance with weak labelsNeural Computing and Applications10.1007/s00521-020-05528-935:18(13021-13035)Online publication date: 23-Nov-2020
  • (2017)Discovery of Shared Semantic Spaces for Multiscene Video Query and SummarizationIEEE Transactions on Circuits and Systems for Video Technology10.1109/TCSVT.2016.253271927:6(1353-1367)Online publication date: Jun-2017
  • (2017)A transfer learning framework for traffic video using neuro-fuzzy approachSādhanā10.1007/s12046-017-0705-x42:9(1431-1442)Online publication date: 4-Aug-2017

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Media

Figures

Other

Tables

Share

Share

Share this Publication link

Share on social media