Restoration of an atmospherically blurred image based on physical model fusion approach

摘要

This paper proposes a new restoration method, only using the single image information, combining atmospheric physical model with fusion techniques to reduce the degradation of the image contrast in bad weather conditions caused by atmospheric aerosols, such as haze and fog. The basic idea of this method is to utilize physics-based model method instead of multi-sensors to generate a serial of virtual images, and then to fuse those virtual images into a high contrast image based on the wavelet fusion technique. In contrast to previous methods, our restoration technique is not only independent on predicted structure, distributions of scene reflectance, or detailed knowledge about the particular weather condition, but also adapt to the situation without a reference image or images with moving objects captured by a video camera. Experiments on different poor-contrast images demonstrate the availability of the proposed method in case of restoring the atmospherically blurred images.