Research on People Counting Based on Stereo Vision

Abstract:

In both industrial field and office building, the accurate statistic of people who enter or leave the elevator has important practical meaning in security and analysis of passenger flow. We present a binocular vision system to count the people pass by. The camera is set in the height of 2.45 meters to monitor the people overhead in order to reduce the overlap of pedestrians. The object segment and tracking method proposed in this paper show good result with the disparity map gained by the dual-camera. Dynamic promotion of threshold is used in the object segmentation. Feature matching is used to track the moving objects. The system can get the number of people accurate and timely. Experiment results show that our system has good performance under relatively complex circumstance.

• Periodical: Applied Mechanics and Materials (Volumes 373-375)
• Pages: 619-623
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.373-375.619
• Online since: August 2013
• Authors: Yun Zhou Zhang, Shou Shuai Xu, Liang Gao, Shan Bao Yang, Xiao Lin Su
• Keywords: Binocular Vision, Disparity Map, Feature Matching, Object Tracking, People Counting

References

[1] Hou Zhi-Qiang, Han Chong-Zhao. A Survey of Visual Tracking. Acta Automatica Sinica, 2006 7(4): 603-617.

[2] Schreiber, D. ; Rauter, M. A CPU-GPU hybrid people counting system forreal-world airport scenarios using arbitrary obliqueview cameras. Computer Vision and Pattern Recognition Workshops (CVPRW), 2012 IEEE Computer Society Conference, 2012: 83-88.

DOI: 10.1109/cvprw.2012.6238899

[3] Jorge García, Alfredo Gardel, Ignacio Bravo, José Luis Lázaro, Miguel Martínez, David Rodríguez. Directional People Counter Based on Head Tracking. IEEE Trans. Industrial Electronics, 2011, 60(9): 3991-4000.

DOI: 10.1109/tie.2012.2206330

[4] Jin Haiyan, Xiong Qingyu, Wang Kai, Shi Weiren. Study of a Counting Method for the number of People in the Elevator based on Image Processing Technology. Chinese Journal of Scientific Instrument, 2011, 32(6): 161-165.

[5] DI Hongwei, CHAI Ying, LI Kui. A Fast Binocular Vision Stereo Matching Algorithm. Acta Optica Sinica, 2009, 29(8): 2180-2184.

DOI: 10.3788/aos20092908.2180

[6] PENG Xionghong, ZHANG Cui, WANG Zhenzhi. A Method of Binocular Matching Based on Cell Dynamics. Journal of National University of Defense Technology, 1999, 21(6): 93-97.

[7] K. Terada, D. Yoshida, S. Oe J. Yamaguchi . A Counting Method of the Number of Passing People Using a Stereo Camera. The 25th Annual Conference of the IEEE , 1999: 1318-1323.

DOI: 10.1109/iecon.1999.819402

[8] Daniel Scharstein, Richard Szeliski. A Taxonomy and Evaluation of Dense Two-Fame Stereo Correspondence Algorithms. Stereo and Multi-Baseline Vision, 2001: 131-140.

DOI: 10.1109/smbv.2001.988771

[9] Cottini, N. De Nicola, M. Gottardi, M. Manduchi, R. A Low-Power Stereo Vision System Based on a Custom CMOS Imager with Positional Data Coding[C]. Research in Microelectronics and Electronics (PRIME), 2011: 161-164.

DOI: 10.1109/prime.2011.5966242

[10] ZHU Qiuyu, TANG Li, JIANG Yiping. A Novel Approach of Counting People Based on Stereovision and DSP. 2010 The 2nd International Conference of Computer and Automation Engineering (ICCAE), 2010: 81-84.

DOI: 10.1109/iccae.2010.5451996