Continuous wavelet transform based gene optimized fuzzy C-Means clustering for forest fire detection

Abstract

Fire detection is an important aspect of disaster preparedness, to reduce loss of lives and property damage. Conventionally, many techniques have been designed so far, to discover the forest fires through input videos. But, clustering performance of conventional fire detection techniques was not sufficient. To overcome the above limitations, Continuous Wavelet Transform Based Gene Optimized Fuzzy C-Means Clustering (CWT-GOFCC) technique is proposed. The proposed CWT-GOFCC technique takes number of video files from FIRESENSE database as input and converts those input videos into a number of frames. Next, it defines the number of clusters and centroids and consequently initializes the gene populations with number of video frames. After that, CWT-GOFCC technique evaluates fuzzy membership with the assistance of fitness function for all input video frames based on spatial correlation between the fire flame colors. By using this fitness function, the technique groups the video frames into pre-fire stage or fire stage or critical fire stage with enhanced accuracy. From that, this technique accurately clusters all the video frames into related clusters with lower time consumption. The simulation of the technique is conducted using metrics such as fire detection accuracy, fire detection time and false positive rate with respect to different numbers of video frames. The simulation result depicts that the technique is able to improve the accuracy and also reduce the time of forest fire detection in video file when compared to state-of-the-art works.