人流計數系統提供許多資訊，可被使用於監控保全、客流分析等許多不同的用途。本論文提出一種由垂直架設的TOF深度攝影機進行感測，並基於深度資訊進行人流計數的系統。在行人偵測部分，首先利用背景相減法取出移動的前景部分，接著藉由分割機制由前景部分獲得行人資訊。針對每個已被偵測到的行人建立深度直方圖，並且分析深度直方圖，將頭部以外的區域濾除，並使用均值漂移演算法進行追蹤。最後，由獲取的行人資訊，利用人流計數有限狀態機進行人流計數。實驗的部分，我們針對五種不同的情景進行正確率的測試，結果顯示出本系統具備高正確率及低執行時間的兩種特性。

Counting the people flow passing a door or a gate can provide many useful information. This paper describes a depth-based people counting method. Firstly, the people passing through the field-of-view of a zenithal time-of-flight sensor is detected by motion object detection, and counted by a split algorithm. Moving people is tracked by mean shift algorithm. However, merge-split and touching situation may cause to tracking failure. To improve the accuracy, a depth-based head histogram is introduced to the mean shift algorithm. The experimental results show that a high accuracy, low cost people counting system can be achieved using the purposed method.

[1] B. Antic, D. Letic, D. Culibrk and V. Crnojevic, “K-Means Based Segmentation for Real-Time Zenithal People Counting,” IEEE International Conference on Image Processing, pp.2565-2568, 2009.
[2] J. Barandiaran, B. Murguia, and F. Boto, “Real-time People Counting using Multiple Lines,” IEEE Ninth International Workshop on Image Analysis for Multimedia Interactive Services, pp. 159–162, 2008.
[3] F. Bartolini, V. Cappellini and A. Mecocci, “Counting People Getting In and Out Of a Bus by Real Time Image-sequence Processing,” Image and Vision Computing, Vol.12, No.1, pp. 36-41, Jan. 1994.
[4] T.H. Chen, T.Y. Chen, and Z.X Chen, “An Intelligent People-flow Counting Method for Passing through a Gate,” Robotics, Automation and Mechatronics, IEEE Conference on, pp.1-6, 2006.
[5] T.H. Chen & C.W. Hsu, “An Automatic Bi-Directional Passing-People Counting Method Based on Color Image Processing,” Security Technology, IEEE Conference on, p. 200-207, 2003
[6] T. Darrell, G. Gordon, J. Woodfill, and M. Harville, “Integrated Person Tracking using Stereo, Color, and Pattern Detection," International Journal of Computer Vision Vol.37, No.2, pp. 175-185, 2000.
[7] A.C. Davies, J.H. Yin, and S.A. Velastin, “Crowd monitoring using image processing,” Electronics & Communication Engineering Journal Vol.7, No.1, pp.37-47, 1995.
[8] D. Demirdjian and T. Darrell, “3-d articulated pose tracking for untethered diectic reference,” Proceedings of the 4th IEEE International Conference on Multimodal Interfaces , pp.267, 2002.
[9] A. Elgammal, H. David, and L. Davis, “Non-parametric model for background subtraction,” Computer Vision—ECCV 2000. Springer Berlin Heidelberg, pp. 751-767, 2000.
[10] S.B. Gokturk, and C. Tomasi, “3D head tracking based on recognition and interpolation using a time-of-flight depth sensor,” Computer Vision and Pattern Recognition, IEEE Conference on. Vol.2, pp.211-217, 2004.
[11] P. Kilambi, O. Masoud, and N. Papanikolopoulos, “Crowd analysis at mass transit sites,” Intelligent Transportation Systems Conference, 2006.
[12] J.W. Kim, et al. “Real–time Vision–based People Counting System for the Security Door,” International Technical Conference on Circuits/Systems Computers and Communications, 2002.
[13] D. Koller, et al. “Towards Robust Automatic Traffic Scene Analysis in Real-time,” Pattern Recognition, Pattern Recognition, Conference A: Computer Vision & Image Processing, Proceedings of the 12th IAPR International Conference on, Vol.1, 1994
[14] D. Kong, D. Gray, and H. Tao, “A viewpoint invariant approach for crowd counting,” Pattern Recognition, 2006. ICPR 2006. 18th International Conference on. Vol. 3. IEEE, 2006.
[15] D. Maio, and D. Maltoni. “Real-time face location on gray-scale static images,” Pattern Recognition Vol.33, No.9, pp.1525-1539, 2000.
[16] M. Rossi and A. Bozzoli, “Tracking and Counting Moving People,” Image Processing, 1994. Proceedings. ICIP-94., IEEE International Conference. Vol. 3, 1994.
[17] G. Sexton, et al. “Advances in automated pedestrian counting,” European Convention on. IET, 1995.
[18] K. Terada, D. Yoshida, S. Oe and J. Yamaguchi, “A Method of Counting the Passing People by Using the Stereo Images,” Image Processing, International Conference on, IEEE, Vol.2, 1999.
[19] C. Tomasi and T. Kanade, “Detection and tracking of point features,” Pittsburgh: School of Computer Science, Carnegie Mellon Univ., 1991.
[20] B. Wu and R. Nevatia, “Detection and tracking of multiple, partially occluded humans by bayesian combination of edgelet based part detectors,” International Journal of Computer Vision, Vol.75, No.2, pp.247-266, 2007.
[21] K. Wu, E. Otoo, and K. Suzuki, “Optimizing Two-pass Connected-Component Labeling Algorithms,” Pattern Analysis and Applications, Vol.12, No.2, pp.117-135, 2009.
[22] L. Xia, C.C. Chen, and J.K. Aggarwal, “Human Detection using Depth Information by Kinect,” Computer Vision and Pattern Recognition Workshops (CVPRW), IEEE Computer Society Conference on, 2011.
[23] H.D. Yang and S.W. Lee, “Reconstruction of 3D Human Body Pose from Stereo Image Sequences based on Top-down Learning,” Pattern Recognition, Vol.40, No.11, pp.3120-3131, 2007.
[24] S. Yu, et al. “A Robust Method for Detecting and Counting People,” Audio, Language and Image Processing, 2008. International Conference on. IEEE, 2008.
[25] X. Zhang and G. Sexton, “Automatic human head location for pedestrian counting,” pp.535-540, 1997.
[26] T. Zhao, R. Nevatia, and B. Wu, “Segmentation and tracking of multiple humans in crowded environments,” Pattern Analysis and Machine Intelligence, IEEE Transactions on, Vol.30, No.7, pp.1198-1211, 2008.
[27] T. Zhao and R. Nevatia, “Tracking multiple humans in complex situations,” Pattern Analysis and Machine Intelligence, IEEE Transactions on, Vol.26, No.9, pp.1208-1221, 2004.
[28] A.G. Vicente, I.B. Munoz, P. J. Molina, J.L.L. Galilea, “Embedded Vision Modules for Tracking and Counting People,” Instrumentation and Measurement, IEEE Transactions on Vol.58, No.9, pp.3004-3011, 2009.
[29] Y. Kobayashi, D. Sugimura, K. Hirasawa, N. Suzuki, H. Kage, Y. Sato, and A. Sugimoto, “3D Head Tracking using the Particle Filter with Cascaded Classifiers,” BMVC, pp. 37-46, 2006.
[30] http://www.iosh.gov.tw/wSite/lp?ctNode=665&mp=11