EARLY FOREST FIRE DETECTION USING TEXTURE, BLOB THRESHOLD, AND MOTION ANALYSIS OF PRINCIPAL COMPONENTS

• Main Author: Moussa, Georges Fouad, Mr.
• Format: Others
• Published: DigitalCommons@CalPoly 2012
• Subjects: Signal Processing
• Online Access: https://digitalcommons.calpoly.edu/theses/881; https://digitalcommons.calpoly.edu/cgi/viewcontent.cgi?article=1931&context=theses

Forest fires constantly threaten ecological systems, infrastructure and human lives. The purpose behind this study is minimizing the devastating damage caused by forest fires. Since it is impossible to completely avoid their occurrences, it is essential to accomplish a fast and appropriate intervention to minimize their destructive consequences. The most traditional method for detecting forest fires is human based surveillance through lookout towers. However, this study presents a more modern technique. It utilizes land-based real-time multispectral video processing to identify and determine the possibility of fire occurring within the camera’s field of view. The temporal, spectral, and spatial signatures of the fire are exploited. The methods discussed include: (1) Range filtering followed by entropy filtering of the infrared (IR) video data, and (2) Principal Component Analysis of visible spectrum video data followed by motion analysis and adaptive intensity threshold. The two schemes presented are tailored to detect the fire core, and the smoke plume, respectively. Cooled Midwave Infrared (IR) camera is used to capture the heat distribution within the field of view. The fire core is then isolated using texture analysis techniques: first, range filtering applied on two consecutive IR frames, and then followed by entropy filtering of their absolute difference. Since smoke represents the earliest sign of fire, this study also explores multiple techniques for detecting smoke plumes in a given scene. The spatial and temporal variance of smoke plume is captured using temporal Principal Component Analysis, PCA. The results show that a smoke plume is readily segmented via PCA applied on the visible Blue band over 2 seconds sampled every 0.2 seconds. The smoke plume exists in the 2nd principal component, and is finally identified, segmented, and isolated, using either motion analysis or adaptive intensity threshold. Experimental results, obtained in this study, show that the proposed system can detect smoke effectively at a distance of approximately 832 meters with a low false-alarm rate and short reaction time. Applied, such system would achieve early forest fire detection minimizing fire damage. Keywords: Image Processing, Principal Component Analysis, PCA, Principal Component, PC, Texture Analysis, Motion Analysis, Multispectral, Visible, Cooled Midwave Infrared, Smoke Signature, Gaussian Mixture Model.