Finding Coherent Motions and Semantic Regions in Crowd Scenes: A Diffusion and Clustering Approach

@inproceedings{Wang2014FindingCM,
  title={Finding Coherent Motions and Semantic Regions in Crowd Scenes: A Diffusion and Clustering Approach},
  author={Weiyue Wang and Weiyao Lin and Yuanzhe Chen and Jianxin Wu and Jingdong Wang and Bin Sheng},
  booktitle={ECCV},
  year={2014}
}
This paper addresses the problem of detecting coherent motions in crowd scenes and subsequently constructing semantic regions for activity recognition. We first introduce a coarse-to-fine thermal-diffusionbased approach. It processes input motion fields (e.g., optical flow fields) and produces a coherent motion filed, named as thermal energy field. The thermal energy field is able to capture both motion correlation among particles and the motion trends of individual particles which are helpful… CONTINUE READING
Highly Cited
This paper has 53 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 27 extracted citations

Simulating Crowds in Egress Scenarios

View 5 Excerpts
Highly Influenced

Crowd behavior identification

2016 IEEE International Conference on Image Processing (ICIP) • 2016
View 5 Excerpts
Highly Influenced

Crowd Behavior Analysis via Curl and Divergence of Motion Trajectories

International Journal of Computer Vision • 2017
View 4 Excerpts
Highly Influenced

Adaptive Discrete Hypergraph Matching

IEEE Transactions on Cybernetics • 2018
View 1 Excerpt

54 Citations

0102020152016201720182019
Citations per Year
Semantic Scholar estimates that this publication has 54 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 26 references

LIBSVM: A library for support vector machines

ACM TIST • 2011
View 3 Excerpts
Highly Influenced

Motion Competition: A Variational Approach to Piecewise Parametric Motion Segmentation

International Journal of Computer Vision • 2004
View 4 Excerpts
Highly Influenced

Adaptive diffusion flow active contours for image segmentation

Computer Vision and Image Understanding • 2013
View 7 Excerpts
Highly Influenced

Measuring Crowd Collectiveness

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2013
View 9 Excerpts
Highly Influenced

Crowd Motion Partitioning in a Scattered Motion Field

IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) • 2012
View 8 Excerpts
Highly Influenced

Multi-camera activity correlation analysis

2009 IEEE Conference on Computer Vision and Pattern Recognition • 2009
View 5 Excerpts
Highly Influenced

A Lagrangian Particle Dynamics Approach for Crowd Flow Segmentation and Stability Analysis

2007 IEEE Conference on Computer Vision and Pattern Recognition • 2007
View 10 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…