多攝影機協同視訊監控系統

A Cooperative Video Surveillance System by Using Multiple Cameras

楊棣華(Ti-Hua Yang)

指導教授 ： 張厥煒

國立臺北科技大學/電資學院/資訊工程系研究所/碩士(2007年)

https://doi.org/10.6841/NTUT.2007.00287

摘要

2001年美國911事件後，第三代保全監控系統已成為全球監控業發展趨勢，其中最主要的概念在於以「全數位化」的角度來設計保全監控系統。然而，在全面數位化後的結果，大部分的監控系統，仍然採用傳統沒效率的人工方式來監督是否發生異常事件，且由於缺乏定義多攝影機彼此在空間上的關係，導致手動追蹤可疑人物時常有見樹不見林的缺點。另外，一旦變動攝影機架設位置或分佈時，會直接影響整個監控系統運作時的複雜度，造成牽一髮而動全身的不便。本研究之目的，是引用圖形理論，設計一個多攝影機協同偵測視訊物件之監控系統。在多個時間點對不同空間狀態的識別、提升物件偵測與追蹤效能、單一主機統籌管理多支攝影機、由使用者自行定義監控場景範圍、以及即時且有效的異常事件通報等功能，提出一套具體可行的作法。
經實驗後顯示，藉由設計完成的空間關係圖形拓撲，可使得監控系統具備彈性及適應性；不會因為變動攝影機架設位置或分佈，而需提昇監控系統複雜度；藉由局部偵測區域可減少全畫面大量比對的計算量，由此可加快偵測及追蹤物件之速度；藉由條件路徑與警戒區域的搭配偵測，可掌握第一時間發送警報的時機，減少監控人力負擔；透過有效率地事件查詢方式，可大幅降低回放搜尋時間。此研究將可提供未來多點視訊監控保全系統，一個具有彈性及適應性之基本架構。

關鍵字

視訊監控 ； 多攝影機同步協調 ； 空間關係圖形拓撲 ； 物件偵測與追蹤 ； 異常事件偵測

並列摘要

The third generation surveillance system had become trends in the surveillance industry after the 911 in 2001. The key concept of it is the fully digitization of the surveillance system. However, it is still using the traditional manner to observe the output by human. Since the spatial relationship between the multi-cameras has not been defined, there will be a defect that the security officer can only watch the individual scene of each camera, but not the overall view for whole monitoring area. Furthermore, once the distribution of the multi-cameras are changed, the work complexity of the surveillance system will increase.
Therefore, the purpose of our research is to design a multi-cameras cooperative video surveillance system which can improve the defects mentioned above. We propose a novel model building a graph topology with spatial relationship into our surveillance system, which improves the performance while detecting and tracking an object; controls multi-cameras by one central station; alerts the inspectors for the abnormal events immediately and effectively.
After a series of experiments, we can show that the graph topology with spatial relationship in the surveillance system is not only more adaptive for the indoor space but also more flexible for the detection region. Our design provides a basic architecture for multi-points surveillance system in the future.

並列關鍵字

Video Surveillance ； Multi-Camera Cooperative ； Graph Topology with Spatial Relationship ； Object Detection and Tracking ； Abnormal Event Detection

參考文獻

[27] 張傑閩，羽球場中球員位置偵測與追蹤方法，碩士論文，國立臺北科技大學資訊工程研究所，台北，2006。

[1] I. K Sethi, R. Jain, “Finding trajectories of feature points in monocular image sequences” IEEE Trans. On PAMI, Jan 1987.

[2] M. Fathy and M. Y. Siyal, “An Image Detection Technique Based on Morphological Edge Detection and Background Difference for Real-time Traffic Analysis,” Pattern Recognition Letters, Vol.16, No.12, pp. 1321-1330, 1995.

[3] C. A. Christopoulos and W. Philips, ”Segmented Image Coding：Techniques and Experimental Results,” Signal Processing: Image Communication, Vol. 11,　pp. 63-80, 1997.

[4] C. Kim. and J. N. Hwang, “Fast and Automatic Video Object Segmentation and Tracking for Content-Based Applications,” IEEE Trans. on Circuits System Video Technology, Vol. 12,pp.122-129. 1999.