Observe locally, infer globally: A space-time MRF for detecting abnormal activities with incremental updates

@article{Kim2009ObserveLI,
  title={Observe locally, infer globally: A space-time MRF for detecting abnormal activities with incremental updates},
  author={Jaechul Kim and Kristen Grauman},
  journal={2009 IEEE Conference on Computer Vision and Pattern Recognition},
  year={2009},
  pages={2921-2928}
}
We propose a space-time Markov random field (MRF) model to detect abnormal activities in video. The nodes in the MRF graph correspond to a grid of local regions in the video frames, and neighboring nodes in both space and time are associated with links. To learn normal patterns of activity at each local node, we capture the distribution of its typical optical flow with a mixture of probabilistic principal component analyzers. For any new optical flow patterns detected in incoming video clips… CONTINUE READING
Highly Influential
This paper has highly influenced 67 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 406 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 242 extracted citations

Collective Representation for Abnormal Event Detection

Journal of Computer Science and Technology • 2017
View 11 Excerpts
Highly Influenced

Video Anomaly Search in Crowded Scenes via Spatio-Temporal Motion Context

IEEE Transactions on Information Forensics and Security • 2013
View 10 Excerpts
Highly Influenced

Abnormal event detection in indoor video using feature coding

2017 Artificial Intelligence and Signal Processing Conference (AISP) • 2017
View 10 Excerpts
Highly Influenced

Computer Analysis of Images and Patterns

Lecture Notes in Computer Science • 2017
View 10 Excerpts
Highly Influenced

406 Citations

0204060'10'12'14'16'18
Citations per Year
Semantic Scholar estimates that this publication has 406 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 19 references

Robust Real-Time Unusual Event Detection using Multiple Fixed-Location Monitors

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2008
View 5 Excerpts
Highly Influenced

Incremental and adaptive abnormal behaviour detection

Computer Vision and Image Understanding • 2008
View 5 Excerpts
Highly Influenced

Unsupervised Activity Perception by Hierarchical Bayesian Models

2007 IEEE Conference on Computer Vision and Pattern Recognition • 2007
View 4 Excerpts
Highly Influenced

Detecting unusual activity in video

Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004. • 2004
View 4 Excerpts
Highly Influenced

Learning object motion patterns for anomaly detection and improved object detection

2008 IEEE Conference on Computer Vision and Pattern Recognition • 2008
View 3 Excerpts

Incremental Learning for Robust Visual Tracking

International Journal of Computer Vision • 2007
View 2 Excerpts

Spatio-Temporal Markov Random Field for Video Denoising

2007 IEEE Conference on Computer Vision and Pattern Recognition • 2007
View 1 Excerpt

A system for learning statistical motion patterns

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2006
View 2 Excerpts

Similar Papers

Loading similar papers…