隨著高科技和高齡化的到來，居家安全監控逐漸受到重視，然而一般監控系統多為定點錄影監控，當發生意外時無法即時通知監護人員，所以本論文以開發獨立式居家安全即時監控系統為目的。數位訊號處理器(Digital Signal Processor, DSP)具體積小、高速率以及獨立運作的優點，因此本系統採用德州儀器(Texas Instrument)之TMS320DM642 DSP為開發平台，搭配雙攝影機架構組合成智慧型居家照護系統，在雙攝影機中的場景攝影機做為大範圍偵測用，而PTZ(Pan/Tilt/Zoom)攝影機實現旋轉與縮放，可達到目標物追蹤之目的。首先透過前景萃取法找出連續輸入影像中的目標物，並建立其姿態骨架，接著由此骨架與事先建立的各姿態碼本進行比對後得到姿態辨識之結果，然後由連續的姿態結果判斷目標物之連動姿態，最後將影像透過網際網路傳送至遠端監控者，使監控者可使用電腦和智慧型手機觀看目前畫面，以達到智慧型居家照護之安全警訊偵測系統。

Video recording based surveillance system have been used in health care and home care areas. When an accident occurs, guardianship person cannot be informed immediately. Therefore, this thesis presents a stand-alone system for home care by recognizing six postures and four actions. The system combines TMS320DM642 Digital Signal Processor (DSP) and dual-camera module. In dual-camera module, the field camera is used for detecting a preliminary target. Another one is PTZ camera used for tracking the target. At first, we extract the target person from input image and establish its posture skeleton. Secondly, the posture is recognized by computing similarity between posture skeleton and posture codebook which is established previously. The change in posture of continuously is used for analyzing action. Finally, we can transmit the image to remote computer, and the monitoring personnel can use computer and smart phone to watch current image. According to the research result, the accuracy of posture recognition and action analysis is larger than 90%. The warning message detection of intelligent home care system could successfully monitor and send warning message.

[1] I. Haritaoglu, D. Harwood and L. S. Davis, “W4: Real-Time Surveillance of People and Their Activities,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 22, No. 8, pp. 809-830, 2000.
[2] C. R. Wren, A. Azarbayejani, T. Darrell and A. Pentland. “Pfinder: Real-Time Tracking of the Human Body,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 19, pp. 780-785, 1997.
[3] W. Lu and Y.-P Tan, “A Color Histogram Based People Tracking System,” Proceedings of the IEEE International Symposium on Circuit and Systems 2, pp. 137-140, 2001.
[4] Y. H. Liang, S. Guo, Z. Y. Wang, X. W. Xu and X. Y. Cao, “A Robust and Fast Motion Segmentation Method for Video Sequences,” Proceedings of the IEEE International Conference on Automation and Logistics, ICAL 2007, pp. 2952-2957, 2007.
[5] R. C. Gonzalez and R. E. Woods, Digital Image Processing, Prentice-Hall, New Jersey, pp. 116-123, 2002.
[6] A. Prati, I. Mikic, M. M. Trivedi and R. Cucchiara, “Detecting Moving Shadows: Algorithms and Evaluation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 25, No. 7, pp. 918-923, 2003.
[7] L. D. Stefano and A. Bulgarelli, “A Simple and Efficient Connected Components Labeling Algorithm,” Proceedings of 10th International Conference on Image Analysis, pp. 322-327, 1999.
[8] L. Wang, T. Tan, H. Nig and W. Hu, “Silhouette Analysis-Based Gait Recognition for Human Identification,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 25, No. 12, pp. 1505-1508, 2003.
[9] H. S. Chen, H. T. Chen, Y. W. Chen and S. Y. Lee, “Human Action Recognition Using Star Skeleton,” Proceedings of the ACM International Multimedia Conference and Exhibition, pp. 171-178, 2006.
[10] K. Takahashi and M. Naemura, “Remarks on Real-Time Human Posture Estimation from Silhouette Image Using Neural Network,” Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, pp. 370-375, 2004.
[11] J. Y. Chang, J. J. Shyu and C.W. Cho, “Fuzzy Rule Inference Based Human Activity Recognition”, Proceedings of the IEEE International Conference on Control Application and Intelligent Control, pp. 211-215, 2009.
[12] X. Yuan and X. Yang, “A Robust Human Action Recognition System using Single Camera,” Proceedings of the IEEE International Conference on Computational Intelligence and Software Engineering, pp.1-4, 2009.
[13] R. Cucchiara, C. Grana, M. Piccardi and A. Prati, “Detecting Moving Objects, Ghosts, and Shadows in Video Streams,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 25, No. 10, pp. 1337-1342, 2003.
[14] J. P. Serra, Image Analysis and Mathematical Morphology, Academic Press, pp. 115-130, 1982.
[15] Y. S. Huang and F. H. Cheng, “Object-Oriented Foreground Image Extraction,” Second International Conference on Innovative Computing, Information and Control, pp. 407,2007.
[16] A. Bevilacqua, L. D. Stefano and P. Azzari, “An Effective Real-time Mosaicing Algorithm Apt to Detect Motion Through Background Subtraction Using a PTZ Camera,” IEEE Conference on Advanced Video and Signal Based Surveillance, pp. 511-516, 2005.
[17] R. Poppe, “Vision-Based Human Motion Analysis: An Overview,”Computer Vision and Image Understanding, Vol. 108, pp. 4-18, 2007.
[18] J. Ben-Arie, Z. Wang, P. Pandit and S. Rajaram,“Human Activity Recognition Using Multidimensional Indexing,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24, No. 8, pp. 1091-1104, 2002.
[19] A. Rosenfield and M. Thurston, “Edge and Curve Detection for Visual Scene Analysis,” IEEE Transactions Computation, Vol. C-20, pp. 562-569, 1971.
[20] J. Canny, “Computational Approach to Edge Detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. PAMI-8, No. 6, pp. 679-698, 1986.
[21] S. R. Gunn, “On the Discrete Representation of the Laplacian of a Gaussian,” Pattern Recognition, Vol. 32, No. 8, pp. 1463-2472, 1999.
[22] B. Liu and H. Zhou, “Using Object Classification to Improve Urban Traffic Monitoring System,” IEEE International Conference on Neural Networks and Signal Processing, Vol. 2, pp. 1155-1159, 2003.
[23] Sony Corporation, Color Video Camera Technical Manual, 2003.
[24] D-Link Corporation, User Manual DWR-113, 2011
[25] Texas Instruments Inc., TMS320C6000 Chip Support Library API Reference Guide, April 2004.
[26] 郭青曉, “獨立式老人居家安全即時監控系統之研製,” 國立臺灣科技大學電機工程系, pp. 15-95, 2009.