監視系統應用在今日社會已逐漸扮演著重要的角色，例如：社區保全的應用、交通流量的監控、車輛牌照的自動識別與機械視覺相關的應用等。從社區保全的應用，我們發現許多刑案裡，犯罪者大都使用手持武器犯案；因此在此研究中，我們針對此現象提出一個有無手持物品的偵測技術，於監視畫面中分析目標物(人)是否持物，以期在事件可能發生前，提出一警告訊息給監視系統使用人員。在本研究中，我們提出一偵測有無手持物品的技術，並以手持槍支這類的影像為實驗例子。本技術是以色彩資訊為基礎，首先利用攝影機(camera)取得一連串的彩色影像，進行移動物體偵測；再者針對所偵測到的物體，使用三個特徵：人體長寬比、頭跟身體所佔面積比例與人體膚色，來判斷出移動物體是否為人；最後經由肢態分析找出手部位置，並透過區塊分析來比對出是否有手持物品。在文章的最後，我們以實驗的結果來證明本方法的可靠性與強健性。目前影像處理技術相關文獻中，尚無針對手持物品偵測技術這方面的探討和應用，因此本研究是全新的研究題目。

The applications of surveillance system play important roles today. Such applications have traffic control, community security monitor, license plate recognition (LPR) and machine vision processing, etc. From applications of community security monitor, we observed that criminals always took weapons when criminal cases happened. However, in previous work, researchers have paid little attention and given few discussions to the intended detection of taking weapon. Thus, we propose a novel method in the case of the gun weapon to detect the situation if the human has taken the things (weapons). This method, which is based up on color information, utilizes the video information to detect the moving objects and analyzes it for detecting if the human has taken things. The method can give an early warning to safeguards when any “customer” or “intruder” takes any things with an obvious action. It includes four processes: motion detection, geometric analysis, gesture analysis and hand region analysis. At first, the motion detection is used to find the moving object from video frame. Next, we recognize the moving object by geometric analysis. Then, the position of hand is located by gesture analysis. At last, we judge that if the human has taken the things by hand region analysis. Experimental results show the performance and reliability of the proposed technology.

1. Horn, B. K. P. and B. G. Schunck, “Determining optical flow,” Artificial Intelligence, Vol.17, No.1-3, pp.185-203(1981).
2. Fuh, C. S. and P. Maragos, “Region-based optical flow estimation,” Proc. of 1989 IEEE Conference on Computer Vision and Patter Recognition, San Diego, CA, pp. 130-133(1989).
3. Iannizzotto, G. and L. Vita, “On-line object tracking for colour video analysis,” Real-Time Imaging, Vol.8, No.2, pp. 145-155(2002).
4. Shi, J. and C. Tomasi, “Good features to track,” Proc. of 1994 IEEE Conference on Computer Vision and Pattern Recognition, Seattle, pp. 593-600(1994).
5. Tomasi, C. and T. Kanade, “Shape and motion from image streams: a factorization method -- part 3: detection and tracking of point features. Technical Report,” Technical Report CMU-CS-91-132, Computer Science Department, Carnegie Mellon University, Pittsburgh, PA(1991).
6. Tommasini, T., A. Fusiello, E. Trucco and V. Roberto, “Making Good Features Track Better,” Proc. of the 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp.178(1998).
7. Azarbayejani, A. and A. P. Pentland,, “Recursive Estimation of Motion, Structure, and Focal Length,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.17, No.6, pp.562-575(1995).
8. Paragios, N. and G. Tziritas, “Adaptive detection and localization of moving objects in image sequences,” Signal Processing: Image Communication, Vol.14, No.4, pp.277-296(1999).
9. Neumann, U. and S. You, “Natural feature tracking for augmented reality,” IEEE Transactions on Multimedia1, Vol.1, No.1, pp.53-64(1999).
10. Li, Y., S.D. Ma and H. Lu, “Human Posture Recognition Using Multi-Scale Morphological Method and Kalman Motion Estimation,” Proc. of the 14th International Conference on Pattern Recognition, Vol.1, No.1, pp.175(1998).
11. Gavrila, D.M. and L.S. Davis, “Towards 3-d model-based tracking and recognition of human movement: a multi-view approach,” International Workshop on Face and Gesture Recognition, Zurich(1995).
12. Hager, G.D. and P.N, Belhumeur, “Real-time tracking of image regions with changes in geometry and illumination,” Proc. of 1996 IEEE Conference on Computer Vision and Pattern Recognition, pp.403(1996).
13. Raja, Y., S.J. McKenna and S. Gong, “Tracking and segmenting people in varying lighting conditions using colour,” Proc. of the 3rd. International Conference on Face and Gesture Recognition, Japan, Nara(1998).
14. Sung, K. K. and S. Poggio, ”Learning a distribution-based face model for human face detection,” Neural Networks for Signal Processing, Processing of the 1995 IEEE Workshop, pp. 398-406(1995)
15. Leung, T. K., M. C. Burl and P. Perona, ”Finding faces in clustered scenes using random labeled graph matching,” Proc. Computer Vision and Pattern Recognition, pp. 637-644(1995).
16. Donato, G., M. S. Bartlett, J. C. Hager, P. Ekman and T. J. Sejnowski,“Classifying Facial Actions”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 21, No.10, pp. 974-989(2000).
17. Essa, I.A. and A. Pentland, “Facial Expression Recognition Using a Dynamic Model and Motion Energy”, Proc. Fifth IEEE International Conference on Computer Vision, Cambridge, MA, pp. 360-367(1995).
18. Fujiyoshi, H., A. J. Lipton, “Real-time Human Motion Analysis by Image Skeletonization,” Proc. of the 4th IEEE Workshop on Applications of Computer Vision, pp.15(1998)
19. Park, J. and J. Yi “Efficient Fingertrip Tracking and Mouse Pointer Control for a Human Mouse,” International Conference on Computer Vision System 2003, pp. 88-97(2003)
20. 張世鵬，「人體計測資料庫測量方法之探討」，元培學報，第六期，第9-25頁，民國八十九年。
21. Wang, Y. 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).
22. 鍾國亮，「影像處理與電腦視覺」，東華書局，第7頁，民國九十三年。
23. Gonzalez, R. C. and R. E. Woods, Digital Image Processing, Prentice Hall, pp.299(2001).
24. Jain, R., R. Kasturi, and B. G. Schunck, Machine Vision, McGraw-Hill, pp.147(1995)
25. Yu, Y., A. Samal and S. C. Seth, “A system for recognizing a large class of engineering drawings”, IEEE Transactions on Pattern Analysis and Machines Intelligence, Vol.19, No.8, pp. 868-890(1997).
26. Otsu, N.,“A threshold selection method from gray level histogram” IEEE Transactions On Systems, Man and Cybernetics, SMC-8, pp. 62-66(1978).
27. Kapur, J. N., P. K. Sahoo and A. K. C. Wong, “A new method for gray-level picture thresholding using the entropy of the histogram”, Computer Vision, Graphics, and Image Processing, Vol.29, pp. 273-285(1985).
28. Chang, F. and C.J. Chen, “A component-labeling algorithm using contour tracing technique”, Proc. of Seventh International Conference, Document Analysis and Recognition, pp. 741-745(2003).