主動式監控攝影機破壞偵測以及物件追蹤實現於Android平台

Active Tampering Detection and Objects Tracking of Surveillance Camera and Implementation on Android Platform

吳忠翰(Chung-Han, Wu)

指導教授 ： 林道通

國立臺北大學/電機資訊學院/電機工程研究所/碩士(2012年)

摘要

主動的攝影機破壞偵測對於監控系統越來越重要，尤其在大量安裝監控系統的場所。一般監控攝影機在錄影時無法檢測是否有被人為破壞的狀況發生。通常事情發生後才會回撥錄影畫面，證明許多監控系統經常無人看管，因此即時的檢測攝影機是否有被破壞相當重要。本論文介紹了一種新的攝影機破壞偵測演算法，提出的方法主要辨識邊緣上的差異，以及灰階直方圖的比較，最後結合攝影機破壞偵測以及物件追蹤演算法並實現於BeagleBoard-xM嵌入式系統平台(德州儀器OMAP3系列)。此方法可以提高監控系統的真實性以及可靠性。在實驗結果中可以追蹤物件以及檢測各種破壞情況。

關鍵字

攝影機破壞偵測 ； 攝影機遮蔽 ； 攝影機轉向 ； 攝影機失焦 ； 物件追蹤

並列摘要

Active and automatic camera tampering detection is more and more important, especially for wide area surveillance systems with large amounts of video cameras installed. Generally, a camera functions for video recording and lacks the ability to detect whether tampering has occurred. Most tampering solutions are passive, as evidenced by many surveillance systems frequently left unattended. Tampering detection of real-time automated cameras is thus of priority concern important for timely operator warning. This thesis describes a novel algorithm for camera tampering detection, and the proposed approach identifies camera tampering by detecting large edge differences and grayscale histogram comparisons between current and previous frames. Furthermore, the proposed camera tampering detection is integrated with an object tracking algorithm developed from a previou study. We then combine the resulting algorithm the camera tampering detection and the object tracking algorithms and implemented on BeagleBoard-xM (Texas Instruments OMAP3 device family). The resultant embedded system improves the system reliability and is ready to incorporate with the existing surveillance system. Experimental results indicate that the proposed approach can detect object tracking and various tampering cases.

並列關鍵字

Camera tampering detection ； Camera occlusion ； Camera motion ； Camera defocusing ； Object tracking ； Android platform ； BeagleBoard-xM

參考文獻

analysis for video surveillance. In Advanced Video and Signal Based Surveillance, 2007.

tection of camera tampering. In Video and Signal Based Surveillance, 2006. AVSS'06.

N. Enomoto, O. Hasegawa, P. Burt, et al. A system for video surveillance and moni-

toring. Carnegie Mellon University, the Robotics Institute, 2000.

[4] A. Saglam and A. Temizel. Real-time adaptive camera tamper detection for video