影像處理技術在諸多科技應用中扮演舉足輕重的角色，與「安全」相關的應用是近幾年影像處理很重要的研究方向，「行人檢出」為其中甚為重要的一環。早期多以擷取動態影像並利用其與背景影像之差異檢出行人，之後的研究以背景模型取代背景影像以增加行人檢出率。近期研究則以行人輪廓為基礎進行檢出，具有不需擷取動態影像、檢出範圍不侷限固定場景及可直接區分場景中行人與其他物體等優點。
　　利用小波轉換多解析度的特性以及Haar函數頗佳的運算效率，擷取行人輪廓並建立小波行人樣板（wavelet pedestrian template）。Förstner特徵運算元（Förstner interest operator）可擷取行人頭部圓形輪廓之圓心。本研究整合小波轉換及Förstner特徵運算元進行行人檢出。經實驗證明，相較於文獻[11]僅以小波轉換及樣板比對所得之52.7%行人檢出率，本方法之檢出率可達65.06%。

Security and monitoring are significant research topics in digital image processing. Among these, pedestrian detection is the crucial part. Over the years, a variety of techniques has been developed for pedestrian detection. Most pedestrian detection systems employed temporal differencing or background subtraction techniques in early years. In the near future, the pedestrian shape-based approach has been proposed to detect pedestrians, which is more convenient and effective since it can discriminate pedestrians from other objects without using image sequence and limited to some specific scenes.
Wavelet transform with Haar function has been employed in getting pedestrian contour to build wavelet pedestrian template because of the multiresolution characteristic and been simple since Förstner interest operator can detect the center of pedestrian’s head. We integrate the wavelet transform and Förstner interest operator in our pedestrian detection system to improve the detection rate up to 65.06% as compared to 52.7% in the literature [11].

[1] N. Paragios and C. Tziritas, “Detection and location of moving objects using deterministic relaxation algorithms,” Proceedings of the 13th International Conference on Pattern Recognition, pp.201-205, vol.1, 25-29 Aug. 1996.
[2] A.C. Davies, J.Y. Yin and S.A. Velastin, “Crowd Monitoring using Image Processing,” Transaction of the IEE Electronics and Communications Engineering Journal, vol. 7, no. 1, pp. 37-47, Feb. 1995.
[3] C. Stauffer and W.E.L. Grimson, “Adaptive background mixture models for real-time tracking,” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 252, 23-25 June 1999.
[4] S. Huwer and H. Niemann, “Adaptive change detection for real-time surveillance applications,” Proceedings of the Third IEEE International Workshop on Visual Surveillance, pp. 37-46, 1 July 2000.
[5] Xidong Yuan, Yean-Jye Lu and S. Sarraf, “A Computer Vision System for Measurement of Pedestrian Volume,” Proceedings of the 1993 IEEE Region 10 Conference (TENCON ‘93) on Computer, Communication, Control and Power Engineering, pp. 1046-1049, 19-21 Oct. 1993.
[6] H. Mori, N. M. Charkari and T. Matsushita, “On-line vehicle and pedestrian detections based on sign patterns,” IEEE Transaction on Industrial Electronics, vol. 41, no. 4, pp. 384-390, Aug. 1994.
[7] S. Yasutomi and H. Mori, “A method for discriminating of pedestrian based on rhythm,” Proceedings of the IEEE/RSJ/GI International Conference on Intelligent Robots and Systems '94. 'Advanced Robotic Systems and the Real World', vol. 2, pp. 988 -995, 12-16 Sept. 1994.
[8] P. Vannoorenberghe, C. Motamed, J.-M. Blosseville and J.-G. Postaire, “Monitoring pedestrians in a uncontrolled urban environment by matching low-level features,” Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics, vol. 3, pp. 2259-2264, 14-17 Oct. 1996.
[9] O. Masoud and 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, no. 5, pp. 1267-1278, Sept. 2001.
[10] D. Hogg, “Model-based vision: A program to see a walking person,” Image and Vision Computing, vol. 1, no. 1, pp. 5–20, Feb. 1983.
[11] M. Oren, C. Papageorgiou, P. Sinha, E. Osuna and T. Poggio, “Pedestrian detection using wavelet templates,” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 193 – 19, 17-19 June 1997.
[12] C. Papageorgiou and T. Poggio, “Trainable pedestrian detection,” Proceedings of International Conference on Image Processing, vol. 4, pp. 35-39, 24-28 Oct. 1999.
[13] D.M. Gavrila and V. Philomin, “Real-time object detection for smart vehicles,” Proceedings of the Seventh IEEE International Conference on Computer Vision, vol. 1, pp. 87-93, 20-27 Sept. 1999.
[14] D.M. Gavrila and J. Giebel, “Shape-based pedestrian detection and tracking,” Proceedings of the IEEE Intelligent Vehicle Symposium, vol. 1, pp. 8-14, 17-21 June 2002.
[15] A. Mohan, C. Papageorgiou and T. Poggio, “Example-based object detection in images by components,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 4, April 2001.
[16] A. Broggi, M. Bertozzi, A. Fascioli and M.Sechi, “Shape-based pedestrian detection,” Proceedings of the IEEE Intelligent Vehicles Symposium 2000, pp. 215-220, 3-5 Oct. 2000.
[17] C. Curio, J. Edelbrunner, T. Kalinke, C. Tzomakas and W. von Seelen, ” Walking pedestrian recognition,” IEEE Transactions on Intelligent Transportation Systems, vol. 1, no. 3, pp. 155-163, Sept. 2000.
[18] M. Yasuno, N. Yasuda and M. Aoki, “Pedestrian Detection and Tracking in Far Infrared Images,” Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, pp. 125, 27-02 June 2004.
[19] M. Bertozzi, A. Broggi, A. Lasagni, M.D. Rose, “Infrared stereo vision-based pedestrian detection,” Proceedings of the IEEE Intelligent Vehicles Symposium, pp. 24-29, 6-8 June 2005.
[20] Fang Yajun, K. Yamada, Y. Ninomiya, B.K.P. Horn and I. Masaki, “A shape-independent method for pedestrian detection with far-infrared images,” IEEE Transactions on Vehicular Technology, vol. 53, no. 6, pp. 1679-1697, Nov. 2004.
[21] Haralick, R.M., Shapiro, L.G., Computer and Robot Vision II, Addison-Wesley, pp. 289-379, 1993.
[22] R. Jain, R.Kasturi and B. Schunk, Machine Vision, McGraw Hill, 1995.
[23] 2006 IPPR技術競賽影像資料 http://www.ippr.org.tw/
[24] 王俊明, 陳世旺, “漸進背景影像的建構,” 師大學報:數理與科技類, vol. 47, no. 2, pp. 43-54, 2002.
[25] A.H.S. Lai and N.H.C. Yung, “A fast and accurate scoreboard algorithm for estimating stationary backgrounds in an image sequence,” Proceedings of the 1998 IEEE International Symposium on Circuits and Systems, vol. 4, pp. 241-244, 1998.
[26] Dae-Woon Lim, Sung-Hoon Choi and Joon-Suk Jun, “Automated detection of all kinds of violations at a street intersection using real time individual vehicle tracking,” Proceedings of Fifth IEEE Southwest Symposium on Image Analysis and Interpretation, pp. 126-129, 2002.
[27] M. Weber, M. Welling and P. Perona, “Unsupervised learning of models for recognition,” Proceedings of the Sixth European Conference on Computer Vision, pp. 18-32, 2000.
[28] A. Elgammal, R. Duraiswami, D. Harwood and L. S. Davis, “Background and foreground modeling using nonparametric kernel density estimation for visual surveillance,” Proceedings of the IEEE, vol. 90, no. 7, pp.1151-1163, July 2002.
[29] Y. Wand and B. Yuan, “A novel approach for human face detection from color images under complex background,” Pattern Recognition, vol. 34, no. 10, pp. 1983-1992, 2001.
[30] A. Boggess and F. J. Narcowich, A First Course in Wavalets with Fourier Analysis, Prentice Hall, 2000.
[31] A. Grossman and J. Morlet, “Decomposition of Hardy functions into square integrable wavelets of constant shape,” SIAM J. Appl. Math., pp. 723-773, June 1984.
[32] http://en.wikipedia.org/wiki/Wavelet
[33] S. Mallat, “A compact multiresolution representation: the wavelet model,” Proceeding of IEEE Computer Society Workshop on Computer Vision, pp. 2-7, 1987.
[34] S. Mallat, “A theory for multiresolution signal decomposition: The wavelet representation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 11, no. 7, pp. 674-693, July 1989.
[35] A. Haar, “Zur Theorie der Orthogonalen Funktionensysteme,” Mathematical Annals, vol. 69, pp. 331-371, 1910.
[36] H.P. Moravec, “Toward Automatic Visual Obstacle Avoidance,” International Joint Conference of Artificial Intelligent, vol. 1, pp. 584, 1977.
[37] W. Förstner, “Quality assessment of Object Location and Point Transfer Using Digital Image Correlation,” International Archives of Photogrammetry and Remote Sensing, vol. 25-Ⅲ, pp. 197-219, 1984.
[38] Yan Lue “Interest Operator and Fast Implementation,” International Archives of Photogrammetry and Remote Sensing, vol. 27-Ⅱ, pp. 491-500, 1988.
[39] Lin and Lee, “A Simple, Fast, and Accurate Method for Image Registration,” Research Report for National Science Council, Taiwan, 1995.
[40] 洪偉嘉, 自動化影像套和之研究, 國立交通大學土木工程研究所碩士論文, 1999。
[41] R. Jain, R. Kasturi and B.G. Schunck, Machine Vision, McGraw-Hill, 1995.
[42] L. G. Roberts, “Machine Perception of Three-Dimensional Solids,” Proceeding in Optical and Electro-Optical Information, Tippet, J. T(ed.), MIT Press, 1965.
[43] 鍾國亮, 影像處理與電腦視覺第二版, 東華書局, 2004.