K-means based segmentation for real-time zenithal people counting

The paper presents an efficient and reliable approach to automatic people segmentation, tracking and counting, designed for a system with an overhead mounted (zenithal) camera. Upon the initial block-wise background subtraction, k-means clustering is used to enable the segmentation of single persons in the scene. The number of people in the scene is estimated as the maximal number of clusters with acceptable inter-cluster separation. Tracking of segmented people is addressed as a problem of dynamic cluster assignment between two consecutive frames and it is solved in a greedy fashion. Systems for people counting are applied to people surveillance and management and lately within the ambient intelligence solutions. Experimental results suggest that the proposed method is able to achieve very good results in terms of counting accuracy and execution speed.

[1]  Carlo S. Regazzoni,et al.  Advanced image-processing tools for counting people in tourist site-monitoring applications , 2001, Signal Process..

[2]  M. Rossi,et al.  Tracking and counting moving people , 1994, Proceedings of 1st International Conference on Image Processing.

[3]  Yang Wang,et al.  A dynamic conditional random field model for foreground and shadow segmentation , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Senem Velipasalar,et al.  Automatic Counting of Interacting People by using a Single Uncalibrated Camera , 2006, 2006 IEEE International Conference on Multimedia and Expo.

[5]  Horst Bischof,et al.  Human Tracking by Fast Mean Shift Mode Seeking , 2006, J. Multim..

[6]  Narciso García,et al.  DCT based segmentation applied to a scalable zenithal people counter , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[7]  Fernando Boto,et al.  Real-Time People Counting Using Multiple Lines , 2008, 2008 Ninth International Workshop on Image Analysis for Multimedia Interactive Services.

[8]  W. Eric L. Grimson,et al.  Adaptive background mixture models for real-time tracking , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[9]  T. J. Stonham,et al.  A system for counting people in video images using neural networks to identify the background scene , 1996, Pattern Recognit..

[10]  Liang-Gee Chen,et al.  Fast video segmentation algorithm with shadow cancellation, global motion compensation, and adaptive threshold techniques , 2004, IEEE Transactions on Multimedia.

[11]  Tommy W. S. Chow,et al.  A People-Counting System Using a Hybrid RBF Neural Network , 2004, Neural Processing Letters.

[12]  Christian Micheloni,et al.  Video security for ambient intelligence , 2005, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.