植基於紅外線影像分析技術之居家廚房火災偵測系統

House-Fire Detection System Using Infrared Image Analyzing Technique

陳柏志(Chen Po-Chih)

指導教授 ： 曾煥雯

國立臺灣師範大學/科技學院/工業教育學系/碩士(2009年)

摘要

由於火災的發生不僅危害到人們的生活品質，也嚴重影響到經濟與生態上的損失，根據內政部消防署的統計，台灣平均每年有5千多件火災意外。在美國，73%-83%的家庭火災源於廚房起火，而其中72%-77%的廚房火災是因為烹飪時起火，所以高溫烹煮及不正確的使用炊具都增加了廚房火災的發生機率。本文提出一套應用於監視居家環境火災偵測系統，旨在及時對居家熱源進行監視及不明熱源提出警報，避免造成火災、危害鄰近居家安全。

本論文不同於一般火災辨識，而是一套居家熱源監視，藉由紅外線熱像監視居家環境，數位影像由影像卡擷取後，進行各種火源的分析，如發展趨勢判斷、可靠熱源登錄、警示與警報等，即時對於居家環境中，固定或是變動的熱源進行偵測等防護。

本論文透過Visual C++6.0來開發火災監視系統，可讓居家用戶結合專家系統知識庫進行火災知識推論，經由特徵值擷取及時推論是否有發生火災的可能，就此達到熱源監視防護。

關鍵字

紅外線 ； 火災偵測 ； 專家系統 ； 火源分析 ； 熱源登錄

並列摘要

The emergence of the fire not merely endangers to people's quality of the life, but also influens losses on the economy and ecology seriously, according to statistics of Fire Service Department of Ministry of Internal Affairs, there is more than 5,000 pieces of fire accident every year on average in Taiwan. In U.S.A., 73%-83% of the family fire comes from the kitchen on firely, and among them 72% -77% kitchen in the fire because when not cooking the on fire, so boil high temperature and using cooking utensil not to be increased emergence probability, kitchen of fire of incorrect. This text proposes one set is applied to monitor at home the environmental fire detects the system of examining, aim at carrying on controlling and unidentified heat source and putting forward the alarm to the heat source at home in time, avoid causing the fire, danger near the security of the house.
This thesis is different from the general fire to distinguish, but a set of heat source at home is controlled, with monitoring the environment of the house of hot picture of infrared ray, after several images are picked and fetch by the image card, carry on the analysis of different fire sources, for instance calculating in the position, development trend judging, reliable heat source log-in, warning with the alarm, etc ., to the environment of the house immediately, the heat source of the regular or change detects and examines etc. protecting.
This thesis develops the monitoring system of the fire through Visual C ++6.0, can let users at home combine the knowledge base of expert system and carry on the knowledge inference of the fire, value is picked and fetched in time the inference is possible to fire takes place via the characteristic, reach the heat source to control and protect at this point.

並列關鍵字

Infrared ； Fire Detect ； Expert System ； Fire Analyze ； Heart Source Log-in

參考文獻

[5] U. Meis, W. Ritter, and H. Neumann, “Detection and Classification of Obstacles in Night Vision Traffic Scenes Based on Infrared Imagery,” IEEE International Intelligent Transportation Systems, vol.2, pp. 1140-1144, Oct. 2003.

[6] J. W. Davis and M. A. Keck, “A Two-Stage Template Approach to Person Detection in Thermal Imagery,” IEEE International Workshop on Applications of Computer Vision, vol.1, pp. 364-369, January 2005.

[7] H. Nanda and L. Davis, “Probabilistic Template Based Pedestrian Detection in Infrared Videos,” IEEE Intelligent Vehicles Symposium, pp. 15-20, June 2002.

[10] J. Davis and V. Sharma, “Robust Background-Subtraction for Person Detection in Thermal Imagery,” IEEE International Workshop on Object Tracking and Classification Beyond the Visible Spectrum, July 2004.

[11] S. J. Krotosky, M. M. Trivedi, “On Color-, Infrared-, and Multimodal-Stereo Approaches to Pedestrian Detection,” Intelligent Transportation Systems, IEEE Transactions, Volume 8, Issue 4, pp.619 – 629, Dec. 2007.