Fire and Smoke Detection Transmission Optical Flow Based on the Optimal Mass Method and Neural Network

• Main Authors: WANG Wei-bing, XU Qie, HAN Zai-bo
• Format: Article
• Language: zho
• Published: Harbin University of Science and Technology Publications 2017-02-01
• Series: Journal of Harbin University of Science and Technology
• Subjects: optimal mass transmission; neural network; video detection; supervised Bayesian classification

Aiming at the problems that the traditional optical flow method is not suitable for gas and liquid image detection，this paper proposes a method which uses the optimal mass transmission optical flow as a low dimensional descriptor of the complex process for fire and smoke detection. The detection process can be abstracted into a problem about the supervised Bayesian classification of spatio-temporal neighborhood pixels;feature vectors are composed of the optimal mass transmission optical flow and R，G，B color channels and the single hidden layer neural network classifier are employed. Finally，we determine the pixel belongs to the flame or belongs to the smoke by the analysis the pixel probability. Experiments show that the proposed method successfully distinguishes smoke and the color-similar cloud，also distinguish between the flame and the flame color-similar background，and has strong robustness.