以視覺為基礎之公共場所抽煙異常事件偵測系統

Vision-based Detection System of Smoking Event

葉信逸(Hsing-Yi Yeh)

指導教授 ： 謝君偉

元智大學/電機通訊學院/電機工程學系/碩士(2009年)

摘要

近年來健康養生觀念不斷地在提升與推廣，而抽煙行為對於自身的健康有著相當的危害，政府亦於今年初開始實施菸害新法，明訂不得於吸煙區之外的場所抽煙，因此，我們於此篇論文中嘗試以視覺為基礎配合使用一般的監視系統設計一套抽煙行為偵測系統，主動監控異常的抽煙行為。
本系統建構於人臉偵測系統之下，再利用顏色特徵與抽煙事件中的各種特性來偵測香煙，最後配合手部動作與香煙之間的關連性與此行為本身的連續性加以分析辨識是否有異常行為發生。
由實驗結果得知，我們所建構的抽煙異常事件偵測系統對於抽煙行為的判斷有著不錯的效果。

關鍵字

抽煙 ； 菸 ； 行為分析 ； 異常事件

並列摘要

In recently years, the concept of health is popularized and promoted unceasingly. Smoking is harmful to our health seriously. The government had put the new “Tobacco Hazards Prevention and Control Act” into practice this year. It stipulates that smoking in the public places is prohibited except in the designated smoking areas. Thereby, we propose a vision-based system and operate this system in coordination with general camera to detect smoking event.
Our system is based on face detection. We make use of color feature and various characteristics of smoking event to detect cigarette. And then, we analyze the correlation between cigarette and hands and the continuity of smoking event to recognize the behavior. Experimental results reveal that the performance of proposed system is well.

並列關鍵字

smoking ； cigarette ； behavior analysis ； event

參考文獻

[1] Haiyuan Wu, Qian Chen, and Masahiko Yachida, “Face Detection from Color Images Using a Fuzzy Pattern Matching Method,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.21, no.6, pp.557-563, June 1999.

[3] C. Chen and S.-P. Chiang, “Detection of Human Faces in Colour Images,” IEE. Proceedings on Vision, Image and Signal Processing, vol.144, no.6, pp.384-388, Dec. 1997.

[5] B. Menser and F. Muller, “Face Detection in Color Images Using Principal Components Analysis,” International Conference on Image Processing and Its Applications, (Conf. Publ. No. 465) vol.2, 13-15, pp.620-624, July 1999.

[8] Chin-Chuan Han, Hong-Yuan Mark Liao, Kuo-Chung Yu, and Liang-Hua Chen, “Fast Face Detection Via Morphology-based Pre-processing,” Pattern Recognition, Vol.33, no.10, pp.1701-1712, 2000.

[10] M. Fleury and A. F. Clark, “Karhunen-Loeve Transform: An Exercise in Simple Image-processing Parallel Pipelines,” Third International Euro-Par Conference, Passau, Germany, August 1997.