Image Enhancement Study Based on Adaptive Median Filtering with Secondary Noise Detection and Neighborhood Pixel Recovery

Abstract

When a coal mine accident occurs, rescue operations can only be carried out by rescue robots. However, the images collected by the rescue robots are not clear because of various downhole interference, so they must be denoised and restored neighborhood pixel first. In this paper, aiming at improving the deficiency of classical adaptive median filtering algorithm, an adaptive median filtering algorithm based on secondary detection of noise and neighborhood pixel restoration is proposed, whose feasibility has been verified by MATLAB tool simulation. Compared with other kinds of algorithms, this algorithm has been proved to have stronger denoising ability and image detail protection.