Single Image Defogging Method based on Deep Learning

Abstract

The invention provides a single image defogging method based on deep learning. The method comprises: acquiring a data set of indoor and outdoor synthetic fog and real fog, the data set comprising: a training set, a test set and a verification set; constructing an end-to-end based on a Residual Network (end-to-end) a deep convolutional neural network, inputting the training set and the verificationset into the deep convolutional neural network and training the model, reaching the maximum number of iterations and ending the training, acquiring the deep convolutional neural network in this time;using the test set to test the defogging effect of the deep convolutional neural network and the optimal model; using the deep convolutional neural network and the optimal model to perform the dehazing treatment on the fogged image of the defogging so that a no-fog image is obtained. The method of the invention realizes end-to-end recovery image clearing and visualization for different concentrations of synthetic fog maps and outdoor real fog maps, and has good defogging effect and practical application value.