現今社會中，人們追求更安全的生活環境，因此電腦影像技術應用於監控系統成為目前熱門的領域，在我們生活周遭中，無論商業用途、公共安全、交通運輸或自動控制方面上，已經有許多以偵測行人動作及行為的電腦視覺研究，例如出入口行人計數、遺留物偵測、人臉表情及年齡辨識等，而本論文所探討之攜帶物偵測同樣可運用於這些領域中，可實際應用於倉儲管理、機密檔案室、機場及限制消費者攜帶大容量攜帶物進入之賣場或購物中心入口等重要區域，其應用範圍十分廣泛，本系統核心作法為利用電腦影像處理技術，模擬人類視覺的判定程序及條件，達成行人攜帶物偵測及追蹤，未來可結合監控系統，降低人力監視的成本，增加監控的處理速度，提供高效率的系統性能及準確度。
系統架構主要分為移動行人偵測模組，其包含背景建構、移運目標提取與及行人偵測，完成行人前景影像後做攜帶物偵測，利用膚色偵測找出臉部及手部位置，除了用於判定行人特徵外，也可幫助攜帶物定位及提取，我們利用彩色和人形輪廓(灰階影像)兩種輸入影像來做攜帶物的偵測，針對彩色影像部分，我們使用色彩分割，透過分水嶺演算法將前景影像將人身上不同顏色的區塊切割；在分水嶺過程中需要建立一梯度影像，為強化攜帶物與人體軀幹切割，融合人形輪廓作對稱分析，找出其非對稱區塊，該區塊即為攜帶物區塊，將非對稱區塊加入梯度影像，目的在於增強其攜帶物區域的梯度強度，避免攜帶物上具有對比強烈的色彩因而被分割為二或是攜帶物和軀幹顏色相近無法分割，接著輸入梯度影像和前景影像於分水嶺演算法作色彩分割，最後將偵測攜帶物定位整合。本系統之優點在於提取行人所攜帶之物品，有別於傳統的作法只能找到攜帶物位置或是攜帶物凸出身體軀幹的區塊，本系統可找到完整之攜帶物輪廓。
實驗結果顯示，本論文所實現的系統能偵測行人之攜帶物，並偵測出該攜帶物面積、輪廓及位置，進而可知其性質(手持物品、後背或是手拖物品)，在執行速度上平均執行速度為225ms/per fame，偵測成功率為84%，攜帶物成功定位率為95%，分別測試不同攜帶物情況，可分為前、後、下方攜帶物及未具有攜帶物，針對不同攜帶物體積、形狀及顏色和行人作搭配。

Automatic detection of carried objects by persons in video is an important step to be used for security monitoring, crime detection, and anti-terrorist surveillance. We propose a novel method using color segmentation to extract carried objects from pedestrians. We can detect not only position of objects but also their integral shapes. First of all, we can extract the pedestrian from each foreground image and further detecting pedestrian feature by taking advantage of skin detection and silhouettes symmetry analysis. After we obtain features of pedestrian, we present new watershed-based color segmentation to the extracted pedestrian target image. The goal of color image segmentation is to partition person image into several homogenous regions with similar properties. We use a new gradient image approach which combines edge detection with morphology and pedestrian features for the improvement of watershed algorithm. The gradient image achieves better color region segmentation in foreground image. We then extract region of carried objects from pedestrian using features which is detected before. Experimental results demonstrate that the proposed method is robust and accurate in detecting the shape, property and position of carried objects. Compared with other related thesis that we surveyed, our approach has better accuracy in the shape of carried object not an approximate position without shape information. Our method obtains a correct detection rate of 84% and also detect explicit region of carried object.

參考文獻
[1]C. Stauffer, and W. E. L. Grimson, “Adaptive background mixture models for real-time tracking,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR '99), vol. 2, pp. 2246-2252, 1999.
[2]P. KaewTraKulPong, and R. Bowden, “An improved adaptive background mixture model for real-time tracking with shadow detection,” 2nd European Workshop on Advanced Video-based Surveillance Systems(AVB 01), 2001.
[3]鄭士奇, “以高斯混合模型為基礎並使用陰影濾除之動態背景影像模型建立,” 電機與控制工程系所, 國立交通大學, 新竹市, 2005.
[4]B. Decann, and A. Ross, "Gait curves for human recognition, backpack detection, and silhouette correction in a nighttime environment," SPIE Conference on Biometric Technology for Human Identification VII, Orlando, USA, 2010.
[5]袁凱群, “限制區域非法進入者之偵測,” 資訊工程研究所, 國立中央大學, 桃園縣, 2005.
[6]D. Damen, and D. Hogg, “Detecting carried objects in short video sequences,” European Conference on Computer Vision(ECCV 08), vol. 3, no. , pp. 154-167, 2008.
[7]T. Senst, R. H. Evangelio, and T. Sikora, “Detecting people carrying objects based on an optical flow motion model,” IEEE Workshop on Applications of Computer Vision (WACV 11) pp. 301-306, 2011.
[8]C. Benabdelkader, and L. S. Davis, “Detection of people carrying objects : a motion-based recognition approach,” IEEE International Conference on Automatic Face and Gesture Recognition, pp. 378-383, 2002.
[9]Q. Yue, H. Guo-Chang, and W. Yun-Hong, “Carrying object detection and tracking based on body main axis,” International Conference on Wavelet Analysis and Pattern Recognition(ICWAPR 07), pp. 1237-1240, 2007.
[10]C.-S. Lee, and A. M. Elgammal, “Carrying object detection using pose preserving dynamic shape models,” Articulated Motion and Deformable Objects(AMBO 06), pp. 315-325, 2006.
[11]曾芳梅, “應用視訊於攜帶武器之人體物件自動偵測研究,” 資訊工程研究所, 中原大學, 桃園縣, 2010.
[12]C. Garcia, and G. Tziritas, “Face detection using quantized skin color regions merging and wavelet packet analysis,” IEEE Transactions on Multimedia, vol. 1, no. 3, pp. 264-277, 1999.
[13]莊啟宏, “肢體分析與異常事件分析在視訊中之應用,” 資訊工程研究所, 國立中央大學, 桃園縣, 2009.
[14]劉冠廷, “基於運動歷史影像實現行人追蹤與計數系統,” 電子工程系, 國立臺灣科技大學, 台北市, 2010.
[15]I. Haritaoglu, R. Cutler, D. Harwood, and L. S. Davis, “Backpack: detection of people carrying objects using silhouettes,” Computer Vision and Image Understanding, vol. 81, no. 3, pp. 385-397, 2001.
[16]K. Kim, T. H. Chalidabhongse, D. Harwood, and L. S. Davis, “Background modeling and subtraction by codebook construction,” International Conference on Image Processing, vol. 5, pp. 3061-3064, 2004.
[17]L. Vincent, and P. Soille, “Watersheds in digital spaces: an efficient algorithm based on immersion simulations,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 13, no. 6, pp. 583-598, 1991.
[18]S. Pumrin, “A framework for dynamically measuring mean vehicle speed using un-calibrated cameras,” Technical report UWEETR-2002-0005, Univ. Washington Dept. of Elect. Engr., 2002
[19]Z. Yi, and F. Liangzhong, “Moving object detection based on running average background and temporal difference,” Intelligent Systems and Knowledge Engineering (ISKE), pp. 270-272, 2010
[20]B. Shoushtarian, and H. E. Bez, “A practical adaptive approach for dynamic background subtraction using an invariant color model and object tracking,” Pattern Recognition Letters, vol. 26, no. 1, pp. 5-26, 2005.
[21]B. K. P. Horn, and B. G. Schunck, “Determining optical flow,” AI Memo 572. Massachusetts Institute of Technology, 1980.
[22]T. Kohonen, “Improved versions of learning vector quantization,” International Joint Conference on Neural Networks(IJCNN '90), vol. 1, pp. 545-550 1990.
[23]Y. Deng, B. S. Manjunath, and H. Shin, “Color image segmentation,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CPVR '99), vol. 2, pp. 446-451, 1999.
[24]F. Meyer, “Color image segmentation,” International Conference on Image Processing and its Applications, pp. 303-306, 1992.
[25]戴安琦, “以分水嶺分割法為基礎的彩色分割研究,” 資訊工程學系, 淡江大學, 新北市, 2003.
[26]鐘國亮, "影像處理與電腦視覺," 東華書局, 台北, 2006.
[27]Wikipedia. "RGB Colorcube," http://upload.wikimedia.org/wikipedia/commons/0/03/RGB_Colorcube_Corner_White.png.
[28]J. R. Parker, "Algorithms for Image Processing and Computer Vision," 2nd Edition, wiley Publishing, Inc., New York, 2010.
[29]E. R. Davies, "Machine Vision: Theory, Algorithms, Practicalities," 3rd Edition, Morgan Kaufmann, San Francisco, 2005.
[30]J. Canny, “A computational approach to edge detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-8, no. 6, pp. 679-698, 1986.
[31]A. B. Huguet, M. C. de Andrade, R. L. Carceroni, and A. A. Araujo, “Color-based watershed segmentation of low-altitude aerial images,” 17th Brazilian Symposium on Computer Graphics and Image Processing, pp. 138-145, 2004.
[32]紀肇育, “以分水嶺演算法為基礎之彩色影像切割,” 電機工程研究所, 國立成功大學, 台南市, 2004.
[33]陳柏豪, “連續影像中人體及手持物品偵測之研究,” 高分子工程系, 國立台灣科技大學, 台北市, 2005.