SVM based forest fire detection using static and dynamic features

Abstract

A novel approach is proposed in this paper for automatic forest fire detection from video. Based on 3D point cloud of the collected sample fire pixels, Gaussian mixture model is built and helps segment some possible flame regions in single image. Then the new specific flame pattern is defined for forest, and three types of fire colors are labeled accordingly. With 11 static features including color distributions, texture parameters and shape roundness, the static SVM classifier is trained and filters the segmented results. Using defined overlapping degree and varying degree, the remained candidate regions are matched among consecutive frames. Subsequently the variations of color, texture, roundness, area, contour are computed, then the average and the mean square deviation of them are obtained. Together with the flickering frequency from temporal wavelet based Fourier descriptors analysis of flame contour, 27 dynamic features are used to train the dynamic SVM classifier, which is applied for final decision. Our approach has been tested with dozens of video clips, and it can detect forest fire while recognize the fire like objects, such as red house, bright light and flying flag. Except for the acceptable accuracy, our detection algorithm performs in real time, which proves its value for computer vision based forest fire surveillance.

Contour Points based P2P Algorithm for Shape Matching and Image Retrieval

“…Since our method is based on the obtained object contour and thus contour extraction is not the focus point of our work, we did not pay attention to those state-of-the-arts while very complex algorithms [19,20,21,22] of contour extraction, such as active contour model, level set method, interactive image segmenting, etc. Instead, a simple algorithm has been developed to extract contours from image with the help of some related functions from OpenCV, and the procedure is described as follows.…”

GIS based real time assessment of wildfire and other changes in a forest: A review

“…For forest environment, the whole scene does not keep still due to waving trees, changing weather, varying light, moving shadow, shaking camera, and so on. Therefore, compared with moving estimation, color based segmentation is more suitable for forest fire extraction [16]. Celik et al…”

“…The threshold values along R, G and B axis can be used to define a rough space for fire color. To build a more precise color model, 3D shape of the point cloud is represented by Gaussian mixture model (GMM), and the pixel whose color within the range of the GMM distribution model can be taken as a candidate fire pixel [16].…”

Hierarchical detection of wildfire flame video from pixel level to semantic level

“…In 2006, Toreyin, Dedeoglu, Gudukbay, and Cetin (2006) presented a new method extracting flame flicker by computing the spatial wavelet transform of moving fire-colored regions. Flicker features based on methods proposed (Chen, Wu, Ju, & Jain, 2011;Dedeoglu, Toreyin, Gudukbay, & Cetin, 2005;Marbach, Loepfe, & Brupbacher, 2006;Toreyin et al, 2006;Zhang et al, 2008;Zhao et al, 2011) are compared and their capability to discriminate flames from moving non-flame objects are evaluated in the literature (Anton, Tjark, & Klaus, 2014).…”