Single-pixel approach for fast people counting and direction estimation

In recent years, people detection and counting has attracted a lot of attention in visual surveillance and security. However, it remains a challenging and complex task for cases where occlusions, varying illumination and weather conditions are experienced. In order to bypass and resolve these challenges, a two-part method based on feature extraction is proposed. In the first part, a single-pixel method for background segmentation is proposed, and in the second part, a virtual-line direction-estimation method is proposed where the direction in which the person is moving is estimated before counting. This method aims to overcome the shortcomings of people detecting, tracking and counting methods.

[1]  Ramakant Nevatia,et al.  Segmentation and Tracking of Multiple Humans in Crowded Environments , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Osama Masoud,et al.  Estimating pedestrian counts in groups , 2008, Comput. Vis. Image Underst..

[3]  Chabane Djeraba,et al.  Spatio-Temporal Optical Flow Analysis for People Counting , 2010, 2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance.

[4]  Cheng Wang,et al.  A Heuristic Information Based System for People Counting , 2011, 2011 Third International Conference on Intelligent Human-Machine Systems and Cybernetics.

[5]  Norbert Brändle,et al.  Pedestrian Detection and Tracking for Counting Applications in Crowded Situations , 2006, 2006 IEEE International Conference on Video and Signal Based Surveillance.

[6]  Shihong Lao,et al.  Robust crowd counting using detection flow , 2011, 2011 18th IEEE International Conference on Image Processing.

[7]  Grantham Pang,et al.  People Counting and Human Detection in a Challenging Situation , 2011, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[8]  Nuno Vasconcelos,et al.  Privacy preserving crowd monitoring: Counting people without people models or tracking , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Lei Meng,et al.  A people counting system based on head-shoulder detection and tracking in surveillance video , 2010, 2010 International Conference On Computer Design and Applications.

[10]  José Luis Lázaro,et al.  Embedded Vision Modules for Tracking and Counting People , 2009, IEEE Transactions on Instrumentation and Measurement.

[11]  Antonio Albiol,et al.  Real-time high density people counter using morphological tools , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[12]  Peter H. Tu,et al.  Detecting and counting people in surveillance applications , 2005, IEEE Conference on Advanced Video and Signal Based Surveillance, 2005..