Unsupervised Bayesian Detection of Independent Motion in Crowds

@article{Brostow2006UnsupervisedBD,
  title={Unsupervised Bayesian Detection of Independent Motion in Crowds},
  author={Gabriel J. Brostow and Roberto Cipolla},
  journal={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
  year={2006},
  volume={1},
  pages={594-601}
}
While crowds of various subjects may offer applicationspecific cues to detect individuals, we demonstrate that for the general case, motion itself contains more information than previously exploited. This paper describes an unsupervised data driven Bayesian clustering algorithm which has detection of individual entities as its primary goal. We track simple image features and probabilistically group them into clusters representing independently moving entities. The numbers of clusters and the… CONTINUE READING
Highly Influential
This paper has highly influenced 24 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 432 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.

Citations

Publications citing this paper.
Showing 1-10 of 268 extracted citations

Computational Science and Its Applications – ICCSA 2017

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

Counting Vehicles from Semantic Regions

IEEE Transactions on Intelligent Transportation Systems • 2013
View 8 Excerpts
Highly Influenced

Modeling Collective Crowd Behaviors in Video

2012
View 9 Excerpts
Highly Influenced

Vision-Based Analysis of Small Groups in Pedestrian Crowds

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2012
View 5 Excerpts
Highly Influenced

Hierarchical detection of moving targets on moving platforms

2009 IEEE Intelligent Vehicles Symposium • 2009
View 8 Excerpts
Highly Influenced

Detecting Dominant Motions in Dense Crowds

IEEE Journal of Selected Topics in Signal Processing • 2008
View 4 Excerpts
Highly Influenced

Fast Detection of Independent Motion in Crowds Guided by Supervised Learning

2007 IEEE International Conference on Image Processing • 2007
View 8 Excerpts
Highly Influenced

432 Citations

02040'08'11'14'17
Citations per Year
Semantic Scholar estimates that this publication has 432 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 32 references

Tracking of Multiple, Partially Occluded Humans based on Static Body Part Detection

2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06) • 2006
View 4 Excerpts
Highly Influenced

Tracking multiple humans in complex situations

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2004
View 4 Excerpts
Highly Influenced

Tracking multiple humans in crowded environment

Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004. • 2004
View 6 Excerpts
Highly Influenced

Visual motion perception.

Scientific American • 1975
View 1 Excerpt
Highly Influenced

Detection of multiple, partially occluded humans in a single image by Bayesian combination of edgelet part detectors

Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 • 2005
View 1 Excerpt

Pedestrian detection in crowded scenes

2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) • 2005
View 1 Excerpt

Simultaneous estimation of segmentation and shape

2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) • 2005

Similar Papers

Loading similar papers…