- 學位論文
在複雜監視場景下遺失物與遺留物之智慧型偵測
Intelligent Detection of Missing and Unattended Objects in Complex Scene of Surveillance Videos
摘要
以往在重要場所都會安排保安人員，遺失物與遺留物偵測可以幫助保安人員監控重要場所的安全，而無須派駐大量的保安人員巡邏勘查。本論文發展一套在視訊監控的環境下，自動地偵測出目標物體被移出監控範圍和不明物體停留在監控範圍之MUD (Missing and Unattended object Detection)系統。研究中採用時間漸進式背景萃取出前景物件，再搭配物件質心(CoM，Center of Mass)，過濾掉不可信賴的疑似遺失遺留物件，透過物件邊緣與新進影像邊緣差異度與匹配度的計算，判斷出靜態前景物件為遺失物或遺留物。MUD系統改善不規則且相似顏色的大範圍遺留物誤判，環境預設在任何複雜的環境當中，無論室內室外，人數多寡，例如：捷運出口、車站。利用MUD系統，可以準確地判斷出遺失物與遺留物，並且排除掉不合理的遺失物與遺留物。
並列摘要
In the past, security personnel were arranged to guard on all important occasions. Missing and unattended objects of detection could help security personnel monitor an important place of safety, and it did not require a large number of security personnel to guard these places. This study develops a MUD (Missing and Unattended object Detection) system to detect and mark the target object removed from the monitoring scene and the unknown object left in the monitoring scene. The identifying of the center of mass (CoM) was compared with the objects, thus, the unreliable pixels were filtered out. By the foreground object was compared with the current frame and the background, an object detection rule is developed to determine whether the foreground object is missing object or unattended object. MUD system can be applied to any complex environment, both indoors and outdoors, such as the subway station, where is thronged with people. Using MUD system can determine the missing and unattended object accurately and the unreasonable object is excluded in video surveillance system.