利用前景運動資訊之異常行為定位偵測

Anomaly Detection Localization via Foreground Motion Information

王逸辰(Yi-Chen Wang)

指導教授 ： 鄭士康

國立臺灣大學/電機資訊學院/電機工程學研究所/碩士(2012年)

https://doi.org/10.6342/NTU.2012.10688

摘要

監視攝影機系統現在已經廣泛使用在全世界。本研究藉由電腦強大的運算能
力，對一段影像做一個初始的處理－也稱為冷開始－，找出影片當中使用者，例
如警方可能會有興趣的片段藉以減少人力資源耗費。本研究提出了以物體當作基
礎，再以光學流動來推測前後幾張畫面物體的運動趨勢，就物體時間以及空間上
面的關係進行預測，並且以物體的運動行為當作特性，以機率模型加以描述，再
分析不同物體之間的差異性，以找出影片都中可疑的片段。經過實驗之後，證明
本研究在異常行為定位上面有優異的表現。此外，本研究在未來有許多實際的應
用，例如偵測搶案、丟棄物品以及行人跌倒等異常行為。

關鍵字

監視攝影機系 ； 冷開始 ； 異常行為 ； 光學流動 ； 機率模型

並列摘要

Surveillance system is pervasive all over the world. In our research, We exploit
powerful computation intelligence to preprocess the video clips, also called cold-start,
to filter out the clips which users, the police for example, might be interested in, in order
to reduce the human resource cost. Object-based method is proposed, and optical flow is
used to estimate the motion tendency in consecutive frames, to increase the
spatio-temporal relations. We use motion as features, which are described using
probability model. And we analyze the differences between blobs to filter out the
suspicious clips in the video. Through experiments, our method has excellent
performance on anomaly detection localization. Besides, in the future, some practical
applications are expected, such as detection of robbery, abandoned objects and
human-falling-down.

並列關鍵字

Surveillance system ； cold-start ； anomaly ； optical flow ； probability model

參考文獻

[2]P. Antonakaki, D. Kosmopoulos, and S. J. Perantonis. “Detecting abnormal human behaviour using multiple cameras,” Signal Processing, vol. 89, issue 9: pp. 1723 – 1738, 2009.

[4]A. Shen, R. Tong, Y. Deng. “Application of Classification Models on Credit Card Fraud Detection,” Intl. Conf. Service Systems and Service Management, pp. 1–4, June 2007.

[6]V. Saligrama, J. Konrad, Pierre-Marc Jodoin, “Video Anomaly Identification,” IEEE Signal Processing Magazine, vol. 27, issue: 5, pp. 18 – 33, 2010.

[7]C. Brax, L. Niklasson, and M. Smedberg. “Finding behavioural anomalies in public areas using video surveillance data,” Conf. International Conference on Information Fusion, pp.1 –8, 2008.

[8]S. Calderara, C. Alaimo, A. Prati, and R. Cucchiara. “A real-time system for abnormal path detection,” Conf. Imaging for Crime Detection and Prevention (ICDP), pp. 1–6, 2009.