本論文提出以嵌入式平台為基礎的大空間人數估測與上下樓人員計數兩大系統，期望應用於調節大空間燈光、空調與增加樓梯使用率以達到節能省電目的。大空間人數估測系統乃透過攝影機架設高度與角度，求出用於修正當前環境影像形變的權重模型，再透過此模型，估測影像中的人數有多少，接著將估測數據回傳給人機介面並儲存於資料庫中，用以分析當前環境中人數與出現時間之關係，期望能應用在調節大空間的燈光或空調開關，以達節能目的；上下樓人員計數系統則可讓系統管理者計數上下樓人數，並回傳給人機介面統計各樓層人員數量。此系統可應用於大賣場或捷運站上，當上樓人數達中獎設定時，便顯示中獎人正面影像並回傳給系統管理者比對。藉此獎勵機制達到鼓勵行人多走樓梯少搭電扶梯之節能減碳目的。經由多次實驗證實，本論文人數估測與人員計數結果皆有滿意的可靠度。

This study proposes two embedded platform based systems as follows, one is a people number estimation system in a large space and the other is a people counting system for those people going up and down stairs. Both systems can be applied to save energy in adjusting the switches of lighting and air conditioner in large space and in increasing the utilization rate of escalators, respectively. The first system can give a weighting model for each person in the image based on the height and angle values of the camera. The weighting model is used to adjust the people shape so that the number of people in the image can be estimated. Then, the estimated result is shown in the user interface and is stored in the database. Therefore, based on the number of people in the current space, the lighting and air conditioner in the space can be adjusted to achieve energy saving in real time. The second system can count the number of people going down stair or going up stair. The counting result is shown in the user interface. The counted result can be applied to calculate the people number in each floor of a shopping mall or be applied to calculate the going stair people number in MRT station. If the people number of going upstairs is accumulated to a specified number, the last one person can be selected as the winner who can win a prize. Furthermore, the system will frame the face image of the winner in the monitor and inform the winner to get the prize. Therefore, people will be encouraged to use stairs instead of escalators so that the energy saving will be achieved. According to a series of experiments, we are satisfied with the results of the two systems.

[1] X. C. Li, L. Zhao, and S. H. Zhao, “The establishment and application of based on DSP image processing dynamic multi-threshold template,” in Proceedings of IEEE International Conference on Future Computer and Communication, Wuhan, China, May 2010, pp. 828-832.
[2] C. Yin and D. Zhao, “The research on target recognition and image tracking system based on high-speed DSP,” in Proceedings of IEEE International Conference on Computer Science and Education, Nanning, China, July 2009, pp. 721-726.
[3] R. Zhou, D. Li, and Z. Li, “Design and implementation of the video detecting and recording system on DSP,” in Proceedings of IEEE International Conference on Computer Research and Development, Beijing, China, March 2011, pp. 139-143.
[4] K. Li, Y. Zhu, and Y. Tian, “Implementation and optimization of a weed identification algorithm on the DSP with C64+ core,” in Proceedings of IEEE International Conference on Intelligent Signal Processing and Communication Systems, Chengdu, China, December 2010, pp. 1-4.
[5] W. Lu, Y. Ma, Q. Wang, L. Zhang, Y. Zhang, and S. Ma, “A detection system for the vehicle queue length of crossroad based on DSP image processing,” in Proceedings of IEEE International Conference on Electrical and Control Engineering, Wuhan, China, June 2010, pp. 35-38.
[6] S. F. Lin, J. Y. Chen, and H. X. Chao, “Estimation of number of people in crowded scenes using perspective transformation,” IEEE Transactions on Systems, Man and Cybernetics, Part A: Systems and Humans, vol. 31, pp. 645-654, 2001.
[7] A. G. Vicente, I. B. Munoz, P. J. Molina, and J. L. L. Galilea, “Embedded vision modules for tracking and counting people,” IEEE Transactions on Instrumentation and Measurement, vol. 58, pp. 3004-3011, 2009.
[8] T. Zhao, R. Nevatia, and B. Wu, “Segmentation and tracking of multiple humans in crowded environments,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 30, pp. 1198-1211, 2008.
[9] C. C. Chen, H. H. Lin, and O. T. C. Chen, “Tracking and counting people in visual surveillance systems,” in Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, Prague, Czech Republic, May 2011, pp. 1425-1428.
[10] D. Ryan, S. Denman, C. Fookes, and S. Sridharan, “Crowd counting using group tracking and local features,” in Proceedings of IEEE International Conference on Advanced Video and Signal Based Surveillance, Boston, USA, August 2010, pp. 218-224.
[11] A. B. Chan and N. Vasconcelos, “Counting people with low-level features and bayesian regression,” IEEE Transactions on Image Processing, vol. 21, pp. 2160-2177, 2012.
[12] Y. L. Hou and G. K. H. Pang, “People counting and human detection in a challenging situation,” IEEE Transactions on Systems, Man and Cybernetics, Part A: Systems and Humans, vol. 41, pp. 24-33, 2011.
[13] D. Kong, D. Gray, and H. Tao, “A viewpoint invariant approach for crowd counting,” in Proceedings of IEEE International Conference on Pattern Recognition, Hong Kong, China, August 2009, pp. 1187-1190.

[14] Q. Zhu, L. Tang, Y. Jiang, and W. J. Deng, “Novel approach of counting people based on stereovision and DSP,” in Proceedings of IEEE International Conference on Computer and Automation Engineering, Singapore, February 2010, pp. 81-84.
[15] A. Albiol, I. Mora, and V. Naranjo, “Real-time high density people counter using morphological tools,” IEEE Transactions on Intelligent Transportation Systems, vol. 2, pp. 204-218, 2001.
[16] C. H. Chen, Y. C. Chang, T. Y. Chen, and D. J. Wang, “People counting system for getting in/out of a bus based on video processing,” in Proceedings of IEEE International Conference on Intelligent Systems Design and Applications, Kaohsiung, Taiwan, November 2008, pp. 565-569.
[17] 羅安鈞(陳世旺教授指導)，俯視型行人計數系統，國立臺灣師範大學資訊工程研究所碩士論文，2008年5月。
[18] B. Antic´, D. Letic´, D. C´ulibrk, and V. Crnojevic´, “K-means based segmentation for real-time zenithal people counting,” in Proceedings of IEEE International Conference on Image Processing, Cairo, Egypt, November 2009, pp. 2565-2568.
[19] T. H. Chen, T. Y. Chen, and Z. X. Chen, “An intelligent people-flow counting method for passing through a gate,” in Proceedings of IEEE International Conference on Robotics, Automation and Mechatronics, Bangkok, Thailand, June 2006, pp. 1-6.
[20] J. Barandiaran, B. Murguia, and F. Boto, “Real-time people counting using multiple lines,” in Proceedings of IEEE International Conference on Image Analysis for Multimedia Interactive Services, Klagenfurt, Austria, May 2008, pp. 159-162.

[21] 嵌入式平台DM6437EVM相關網站，
http://c6000.spectrumdigital.com/evmdm6437/reve/，2013年6月。
[22] 郭宗勝、謝瑛之、曲建仲，雙核心嵌入式系統開發DaVinci Soc平台架構及實作演練，全華圖書股份有限公司，2010年。
[23] 陳宏宇，DSP程式設計，文魁資訊股份有限公司，2004年。
[24] 林黃淳(蔡宗漢教授指導)，以數位信號處理器實現H.264/SVC解碼器及其最佳化演算法設計，國立中央大學電機工程研究所碩士論文，2009年10月。
[25] HIN232晶片相關網站，
http://www.datasheetcatalog.com/datasheets_pdf/H/I/N/2/HIN232.shtml，2013年6月。
[26] CCD靶面規格相關網站，
http://baike.baidu.com/view/18579.htm，2013年6月。
[27] 2005至2008台灣居民平均體位相關網站，
http://www.bhp.doh.gov.tw/BHPNet/Web/Easy/FormCenterShow.aspx?No=201111030003，2013年6月。
[28] Z. Yin, Y. He, C. Xiong, and R. Zhong, “The design of moving objects detection system based on DM6437,” in Proceedings of IEEE International Conference on Computer Science and Service System, Nanjing, China, June 2011, pp. 4100-4103.
[29] 賴岱佑，數位影像分析之智慧型監視系統，文魁資訊股份有限公司，2008年。
[30] 吳怡明(蔡超人教授指導)，手勢辯識應用於遙控音樂撥放系統，國立台灣科技大學電機工程系碩士學位論文，2009年1月。
[31] 黃識翰(王文俊教授指導)，手勢及聲音遙控家電技術，國立中央大學電機工程研究所碩士論文，2011年7月。