Crowd Density as Dynamic Texture: Behavior Estimation and Classification

Extracting crowd feature is a key step for crowd density estimation. This paper proposes a simple and novel approach of preprocessing and extraction of crowd feature. A 5 × 5 mask is defined for finding isolated components in the image, which proved very efficient for classification of crowd density. SVM classifier is used for classifying the crowd in five different levels. The proposed method is powerful to understand crowd behavior such as crowd coming toward camera and exiting from the camera site. The results are analyzed for PETS dataset and are very promising for images that have bright sunlight and shadow frames too. This method can be used for intelligent surveillance system in public places.

[1]  Robert Sabourin,et al.  “One Against One” or “One Against All”: Which One is Better for Handwriting Recognition with SVMs? , 2006 .

[2]  Xiaojuan Wu,et al.  A new approach of crowd density estimation , 2010, TENCON 2010 - 2010 IEEE Region 10 Conference.

[3]  A. Marana,et al.  On the efficacy of texture analysis for crowd monitoring , 1998, Proceedings SIBGRAPI'98. International Symposium on Computer Graphics, Image Processing, and Vision (Cat. No.98EX237).

[4]  A. N. Marana,et al.  Real-Time Crowd Density Estimation Using Images , 2005, ISVC.

[5]  Hong Liu,et al.  Crowd Density Estimation Based on Local Binary Pattern Co-Occurrence Matrix , 2012, 2012 IEEE International Conference on Multimedia and Expo Workshops.

[6]  Xuran Zhao,et al.  Crowd density analysis using subspace learning on local binary pattern , 2013, 2013 IEEE International Conference on Multimedia and Expo Workshops (ICMEW).

[7]  Yuanyuan Liu,et al.  A crowd flow estimation method based on dynamic texture and GRNN , 2012, 2012 7th IEEE Conference on Industrial Electronics and Applications (ICIEA).

[8]  Jean-Luc Dugelay,et al.  A new multiclass SVM algorithm and its application to crowd density analysis using LBP features , 2013, 2013 IEEE International Conference on Image Processing.

[9]  A. Marana,et al.  Estimation of crowd density using image processing , 1997 .

[10]  Hua Yang,et al.  The large-scale crowd density estimation based on sparse spatiotemporal local binary pattern , 2011, 2011 IEEE International Conference on Multimedia and Expo.

[11]  Tshilidzi Marwala,et al.  Image Classification Using SVMs: One-against-One Vs One-against-All , 2007, ArXiv.

[12]  Luciano da Fontoura Costa,et al.  Automatic estimation of crowd density using texture , 1998 .