Efficient Forest Fire Detection using Rule-Based Multi-color Space and Correlation Coefficient for Application in Unmanned Aerial Vehicles

• DOI: 10.3837/tiis.2022.02.002
• Publication Date: 2022-03-08T02:43:07Z
• Authors: Nguyễn Đức; Pham Van Thanh; Doan Lap; Nguyễn Ngọc Khai; Tran Van An; Duc–Tan Tran; Nguyen Huu; Dang Nhu Dinh; Nhu Dang
• Keywords: 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology

Forest fires inflict great losses of human lives and serious damages to ecological systems.Hence, numerous fire detection methods have been proposed, one which is based on sensors.However, these reveal several limitations when applied in large spaces like forests such as high cost, level false alarm, limited battery capacity, other problems.In this research, we propose a novel forest method image processing correlation coefficient.Firstly, two conditions are RGB color space distinguish between pixels the background.Secondly, converted from YCbCr with being space.Finally, coefficient used objects fire-like colors.Our proposed algorithm tested evaluated eleven non-fire videos collected internet achieves up 95.87% 97.89% F-score accuracy respectively performance evaluation.