Fire Image Detection Based on Support Vector Machine with Improved Particle Swarm Optimization

For the purpose of reducing unrecoverable economic losses and casualties all over the world, automatic fire detection is expected to recognize fire and give an alarm as early as possible. Due to the disadvantages of traditional methods, fire image detection has become an attractive solution. This paper pro-poses an innovative approach, based on multi-feature vector and support vector machine coupling with improved particle swarm optimization (IPSO-SVM). Firstly, a multi-feature vector is established, including geometric, texture, spectrum information. Then, an improved particle swarm optimization (IPSO) is developed by introducing dynamic inertia weight factor and cross-variation. Next, an IPSO-SVM model is established to achieve the fire image detection, where the IPSO algorithm is imported to select the optimal parameters of support vector machine (SVM). Afterwards, the detection performance of presented method is verified by a series of case studies. Eventually, the results indicate that the provided method has an advantage over other benchmark algorithms, obtaining the highest rate of 98.33, and proving its effectiveness and feasibility.