建立出一套智慧型監控系統，其能自動地分析影像來偵測出在無人注意的環境之中所被置放的監控品物是否遭竊取，並且亦能夠自動地發送簡訊給監控者的手機，使其能在第一時間到現場處理。 本篇論文將系統分為四個主要部份，第一部份利用樣板比對找出前場景中所監控的物品並萃取ROI。第二部份是追踪入侵者並記錄其移動區塊。第三部份是對ROI區塊結合邊緣資訊、顏色資訊、監控目標物外形特徵去偵測是否消失或移動。當偵測出場景有人入侵並且監控目標物被移動或是消失，若同時有兩種警訊觸發，系統才會進入後第四部份，系統會透過手機或GSM模組發送多媒體簡訊(MMS)或簡訊(SMS)來發出警訊，使相關人員提高警覺或採取相關反應措施。 Recently, video surveillance and monitoring (VSAM) has become an important research topic. In this thesis, we implement an intelligent video-based surveillance system for detecting the targets in the unattended environment. The proposed system is composed of four main parts. The first part is Region of Interest (ROI) setting. Template matching operation is manipulated on original background to extract the ROI location and information. The second part is moving object detection and record motion segmentation. The third part is analysis of missing objects. The fourth part is reporting of alarms. In addition to all of the above modules, we develop reporting module for reporting Short Messaging Service (SMS) and Multimedia Messaging Service (MMS) to response the alarms. The system will alert the monitor and provide users the keyframe by MMS. The experimental results show that our system is a real time system with high detection accuracy.
