Wavelet-Based Retinex Algorithm for Unmanned Aerial Vehicle Image Defogging

A wavelet-based Retinex algorithm for unmanned aerial vehicle image defogging is proposed to avoid edge fuzziness, image dinginess, noise pollution and inefficiency, etc. in classical Retinex. In light of different energy distribution of fog, noise and edge information of subjects in the wavelet domain, this algorithm uses Retinex to restrain the influence of the fog, and adopts the wavelet threshold method to restrain noise while preserving the edge information, in order to reduce the influence of fog and noise of image. Experiment results show that this algorithm can effectively improve the degradation of foggy and enhance its definition.