目前監控系統幾乎已廣泛架設於各式各樣的公共環境，提供交通監控、治安維護及保全等多樣功能，然而大部分的監控系統僅忠實地記錄影像，卻無法自動且有效地偵測特殊事件，往往必須由監控人員同步監看或事後過濾，方能擷取出有意義的關鍵影像，無法達到即時偵測及警示的功能。近年來，學者們針對複雜背景下的遺留物偵測與判斷提出許多研究方法，目的在提升監控系統效能，透過即時偵測技術，降低人力資源浪費。
本論文針對複雜場景下的背景建構演算法進行研究，選擇Codebook 演算法為本系統背景建構模型，然後提出一個基於精簡碼簿模型之遺留物偵測演算法，透過Codebook 演算法參數精簡來降低記憶體需求，並利用YCbCr 色彩空間實現陰影濾除，進而獲取前景及背景區域分離結果，最後，透過演算法偵測條件判斷遺留物位置並紀錄關鍵影像，達成遺留物體即時偵測、紀錄及警告的目標。

Nowadays, video-based surveillance systems have been commonly installed in a wide range of public environments, providing traffic monitoring and security maintenance. Nevertheless, most of the surveillance systems can only record the video, but cannot detect special events automatically and effectively. Security guards have to monitor on-line and may mis-detect the special events when it happened. These systems cannot achieve real-time detection and cannot function as an alarm as events take place.
In order to upgrade the system performance and reduce the cost of human power, several research methods are proposed for the detection of abandoned object in the complex environments. In this thesis, we build a background model based on Codebook algorithm and combine a shadow removal algorithm in YCbCr colorspace, and the system uses compact Codebook algorithm to reduce the memory requirement. Our experiments show that our system can effectively detect the area of the abandoned object, record the key image and make an alarm.

[1] 劉瑞禎、于仕琪，OpenCV 教程－基礎篇，北京航空航天大學出版社，北京，
2007。
[2] Pakorn Kaewtrakulpong, and Richard Bowden, “An Improved Adaptive
Background Mixture Model for Real-time Tracking with Shadow Detection,”
Proc. 2nd European Workshop on Advanced Video Based Surveillance Systems,
AVBS01,Video Based Surveillance Systems: Computer Vision and Distributed
Processing, (2001)
[3] 鐘國亮，影像處理與電腦視覺第三版，東華書局，台北（2006）。
[4] Kyungnam Kim, Thanarat H. Chalidabhongse, David Harwood, Larry Davis,
“Real-time foreground-background segmentation using codebook model.
Real-Time Imaging 11(3), pp. 167-256(2005)
[5] Lei Geng, ZhiTao Xiao, “Real Time Foreground-Background Segmentation
Using Two-Layer Codebook Model,” International Conference on Control,
Automation and Systems Engineering - CASE , pp. 99-103（2011）.
[6] Qi Li, Chunfu Shao, Hao Yue, Juan Li, “Real-time foreground-background
segmentation based on improved Codebook model,” Congress on Image and
Signal Processing – CISP,pp. 269-273（2010）.
[7] Jiu XU, Ning JIANG, Satoshi GOTO, “Block-based Codebook Model with
Oriented-Gradient Feature for Real-time Foreground Detection,” IEEE
International Workshop on Multimedia Signal Processing(MMSP),pp. 360-365
（2011）.
[8] Jing-Ming Guo, “Hierarchical Method for Foreground Detection Using
Codebook Model,” IEEE Transactions on Circuits and Systems for Video
- 55 -
Technology, VOL. 21, NO. 6, pp.804-815（2011）.
[9] 徐誌笙，「以碼簿模型為基礎之階層式背景濾除」，碩士論文，國立台灣科技
大學電子工程系，台北（2010）。
[10] Chris Stauffer and W. Eric L. Grimson, “Adaptive background mixture models
for real-time tracking,” Proceedings of the IEEE Computer Vision and Pattern
Recognition, vol. 2, pp. 2246-2252（1999）.
[11] Elena Stringa and Carlo S. Regazzoni, “Real-time video-shot detection for scene
surveillance applications,” IEEE Transactions on Image Processing, Vol. 9, No. 1,
pp. 69-79（2000）.
[12] Carlo S. Regazzoni, Andrea Teschioni and Elena Slringa, “A Long Term Change
Detection Method for Surveillance Applications,” Proceedings of the 9th
International Conference on Image Analysis and Processing, pp. 485-492
（1997）.
[13] Chuan-Yu Cho, Wei-Hao Tung, and Jia-Shung Wang, “A Crowd-Filter for
Detection of Abandoned Objects in Crowded Area,” IEEE Sensing Technology,
pp. 581-584（2008）.
[14] Ying-Li Tian, Max Lu, and Arun Hampapur, “Robust and Efficient Foreground
Analysis for Real-time Video Surveillance”, IEEE Computer Society Conference
on Computer Vision and Pattern Recognition (CVPR’05), Vol. 1, pp. 1182-1187
（2005）.
[15] Ying-Li Tian, Rogerio Feris, and Arun Hampapur, “Real-time detection of
abandoned and removed objects in complex environments,” The Eighth
International Workshop on Visual Surveillance - VS2008,（2008）.
[16] Ying-Li Tian, Rogerio Feris, Haowei Liu, and Ming-Ting Sun, "Robust
Detection of Abandoned and Removed Objects in Complex Surveillance
- 56 -
Videos," IEEE Transactions on Systems, Man, and Cybernetics, Part C:
Applications and Reviews, vol.41, Issue 5, pp. 565-576（2011）.
[17] Jagdish Lai Raheja, Chaitanya Malireddy, Aniket Singh and I Solanki,
“Detection of Abandoned Objects in Real Time,” International Conference on
Electronic Computer Technology - ICECT , pp. 199-203（2011）.
[18] I-Ting Sun, “A Hybrid Codebook Background Model for Background
Subtraction,” IEEE International Workshop on Signal Processing System, pp.
96-101（2011）.
[19] 祝珮軒，「遺留物及持有人自動偵測並具關鍵影像提供能力之視訊監控系統」，
碩士論文，國立中央大學資訊工程研究所，桃園（2006）。
[20] A. Singh, S. Sawan, Madasu Hanmandlu, Vamsi Krishna, and Brian Lovell, “An
abandoned object detection system based on dual background segmentation,”
Proc. Int. Conf. Advanced Video, Signal Based Surveillance, pp. 352-357
（2009）.
[21] Qiujie Li, Yaobin Mao, Zhiquan Wang, Wenbo Xiang, “Robust Real-Time
Detection of Abandoned and Removed Objects, ” pp. 156-161（2009）.
[22] 呂博琪，「應用姿態分析於遺留物品與人關聯性之研究」，碩士論文，國立台
灣科技大學電子工程系，台北（2006）。
[23] 劉冠廷，「基於運動歷史影像實現行人追蹤與計數系統」，碩士論文，國立台
灣科技大學電子工程系，台北（2010）。
[24] 聶政邦，「光影變化環境中的背景切割技術」，碩士論文，國立交通大學資訊
科學與工程研究所，新竹（2006）。
[25] 溫致絹，「利用外形及紋理特徵做入侵者偵測」，碩士論文，國立中央大學資
訊工程研究所，桃園（2009）。
[26] 林珏汝，「實作codebook 背景模型辨別連續影像前背景」，專題報告，東海
- 57 -
大學資訊工程系，台中（2009）。
[27] Stephen J. McKenna, Sumer Jabri, Zoran Duric, HarryWechsler, and Azriel
Rosenfeld, “Tracking Groups of People,” Computer Vision and Image
Understanding, pp. 42-56,(2000).
[28] Rita Cucchiara , Costantino Grana , Massimo Piccardi , Andrea Prati , Stefano
Sirotti, “Improving shadow suppression in moving object detection with HSV
color information,” IEEE Intelligent Transportation Systems Conference
Proceedings, pp.334-339(2001).
[29] 林恩宇，「在HSV 色彩空間中以VQ 編碼為基礎之移動物體偵測」，碩士論
文，私立逢甲大學資訊工程研究所，台中（2009）。
[30] 鄧亞麗，「一種有效的圖像陰影自動去除演算法」，Signal Processing，Vol 27，
No 11(2011).
[31] Huiyuan Fu, “Abandoned Object Detection in Highway Scene,” International
Conference on Pervasive Computing and Applications (ICPCA), pp.
117-121(2011).