Computer Vision Based Industrial and Forest Fire Detection Using Support Vector Machine (SVM)
Md. Abdur Rahman, Sayed Tanimun Hasan, Mohammed Abdul Kader
Abstract
The burning issue is a very serious issue nowadays in the forest and industries sector. The workers are facing the problem and losing valuable life. On the other hand, investors are losing their hope in this sector. In this paper, we have propounded a vision-based system which is capable to detect fire. We have developed a pipeline model consisting of Background Subtraction, Color Segmentation, Spatial Wavelet Analysis & Support Vector Machine which will detect real-time fire. For the SVM model, we have trained the dataset in two ways. One is the different kind of fire image and the other is the image that looks like fire but they are not fire. If the situation is breaking out of fire then the system will immediately raise an alarm and an automatic SMS/email will be sent to the nearby fire bigrade. In this study, the proposed strategy works on a very large dataset of fire videos that have been collected both in real-life situations and from the internet. This SVM pipeline model shows the maximum accuracy is 93.33%. The system can fulfill the precision and detect faster real-time fire detection. It’s forest and industrial application will aid in the early detection of fires, as well as emergency management, and so immensely contribute to loss prevention.