Smoke Identification of Low-light Indoor Video Based on Support Vector Machine

In order to improve the accuracy and efficiency of low-light indoor fire detection, and forewarn fire timely, a video smoke recognition algorithm based on support vector machine is proposed in this paper. After extracting the smoke target,the area diffusion and the main direction of motion are chosen as the dynamic characteristics for the identification of low-light indoor smoke, the texture features are chosen as the static characteristics for the identification of low-light indoor smoke, after the feature extraction, the support vector machine (SVM) is used to build the classifier to realize the identification of smoke. Finally, the smoke recognition algorithm is tested under different conditions. The experimental results show that the algorithm has high adaptability, high recognition rate and good anti-interference ability, Which provides an effective solution for the fire smoke identification in low-light indoor conditions.