Visibility estimation of foggy weather based on continuous video information

Abstract

ABSTRACT Low visibility in foggy weather can easily cause accidents and affect normal life. Accurate visibility estimate is critical to transportation, aviation, marine and other fields. For visibility estimation, this paper proposes a visibility estimation algorithm Mean Square Error Based on Convolution Neural Network (MSEBCNN) based on continuous surveillance video, which is an improved neural network deep learning algorithm. In this paper, the images of airport surveillance video were extracted every 15 s and the Region of Interest (ROI) in each image was selected as the measurement area. The improved Convolution Neural Network (CNN) was constructed by replacing the Softmax layer of the last layer of the convolutional neural network with the Mean Square Error (MSE) layer of the objective regression function, and the gradient descent method was used for fitting training to achieve the continuous prediction of visibility. By experiment, the accuracy of prediction at a range of 0–500 m is 97.51%, while the accuracy of prediction at a range of 500–1600 m is 91.67%, which obtained a high prediction accuracy.