行人計數是很多影像監視系統中重要的應用之一。在這篇論文當中，我們提出了藉由背景消除法以及團塊跟蹤的方式來達到自動化行人計數。背景消除法能夠取出團塊，使得團塊能以聯通成分的形式表示，而每一個團塊的質心則是用來做跟蹤的使用以達到正確的計數。我們使用單一的攝影機去錄製不同的場景下行人經過的影片以作為實驗，實驗的結果也顯示我們的方法能夠達到非常高的準確率。

People counting is one of many important applications of video surveillance systems. We propose an automatic people counting system by applying background subtraction and blob tracking on video camera output. Background subtraction identifies blobs in the form of connected components. Centroid of blobs is used to track blobs for counting. We capture video using a single overhead-mounted camera for experiment. Experimental results show that our method achieves very high accuracy.

[1] B. Antic’, D. Letic’, D. C’ulibrk, and V. Crnojevic, “K-means Based Segmentation for Real-time Zenithal People Counting,” IEEE International Conference on Image Processing, pp. 2565-2568, 2009.
[2] G. J. Brostow, R. Cipolla, “Unsupervised Bayesian Detection of Independent Motion in Crowds,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 594–601, 2006.
[3] F. Chang, C. Chen, and C. Lu, “A Linear-Time Component-Labeling Algorithm Using Contour Tracing Technique,” Journal of Computer Vision and Image Understanding, vol. 93, pp. 206-229, 2004.
[4] T. Chen, C. Ho, D. Wang, and Y. Kuo, “A People Counting System Based on Face-Detection,” IEEE International Conference on Genetic and Evolutionary Computing, pp. 699-702, 2010.
[5] N. Dalal and B. Triggs, “Histograms of Oriented Gradients for Human Detection,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 886-893, 2005.
[6] H. Goldstein, “People Counting Using Image Processing,” Technical Report, Advanced Programming Lab B. Department of Computer Science, Technion-Israel Institute of Technology, 1999.
[7] D. Kong, D. Gray, and H. Tao, “Counting Pedestrians in Crowds Using Viewpoint Invariant Training,” British Conference on Machine Vision, pp. 63.1-63.10, 2005.
[8] P. Kilambi, E. Ribnick, A. J. Joshi, O. Masoud, and N. Papanikolopoulos, ”Estimating Pedestrian Counts in Group,” Journal of Computer vision and Image Understanding, vol. 110, pp. 43-59, 2008.
[9] J. Li, L. Huang, and C. Liu, “Robust People Counting in Video Surveillance: Dataset and System,” IEEE International Conference on Advanced Video and Signal-Based Surveillance, pp. 54-59, 2011.
[10] M. Li, Z. Zhang, K. Huang, and T. Tan, "Estimating the Number of People in Crowded Scenes by MID Based Foreground Segmentation and Head-shoulder Detection," IEEE International Conference on Pattern Recognition, pp. 1-4, 2008.
[11] D. Merad, K. E. Aziz, and N. Thome, “Fast People Counting Using Head Detection From Skeleton Graph,” IEEE International Conference Advanced Video and Signal Based Surveillance, pp. 233-240, 2010.
[12] O. Masoud, N. P. Papanikolopoulos, “A Novel Method for Tracking and Counting Pedestrians in Real-time Using a Single Camera,” IEEE Transactions on Vehicular Technology, vol. 50, pp. 1267-1278, 2001.
[13] H. Ma and C. Zeng, “A Reliable People Counting System via Multiple Cameras,” Journal of ACM Transactions on Intelligent Systems and Technology, vol. 3, no. 2, article 31, 2012.
[14] Open Source Computer Vision (OpenCV), available at http://opencv.org.
[15] C. Stauffer and W. Grimson, “Adaptive Background Mixture Models for Real-time Tracking,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 246-252, 1999.
[16] K. Terada, D. Yoshida, S. Oe, and J. Yamaguchi, “A Counting Method of the Number of Passing People Using a Stereo Camera,” IEEE Industrial Electronics Conference, vol. 3, pp. 1318-1323, 1999.
[17] P. Viola and M. Jones, “Robust Real Time Object Detection,” Journal of Computer Vision, vol. 57, no.2, pp. 137-154, 2004.
[18] H. Xu and L. Meng, “A People Counting System Based on Head-shoulder Detection and Tracking in Surveillance Video,” IEEE International Conference on Computer Design and Applications, vol. 1, pp. 394-398, 2010.
[19] F. Zhu, X. Yang, J. Gu, and R. Yang, “A New Method for People-Counting Based on Support Vector Machine,” IEEE Second International Conference on Intelligent Networks and Intelligent Systems, pp. 342-345, 2009.