MSRCR image defogging method based on multi-channel convolution

Abstract

The invention provides an MSRCR image defogging method based on multi-channel convolution. The method comprises the steps of performing guided filtering processing on a source image, convolving the processed R, G and B channels by six 3*3 Gaussian convolution kernels; obtaining six feature maps with the same size as a single input channel, enhancing the six feature maps corresponding to each channel through a Retinex algorithm, then carrying out linear weighted fusion, carrying out weighted fusion on an image after Retinex enhancement and a detail image after secondary guided filtering processing, and reconstructing a final defogged image. According to the invention, convolution is carried out by using a multi-scale Gaussian convolution kernel; the finer characteristic estimation incidentcomponents are extracted; the multi-scale linear weighted Retinex enhancement is performed on an incident component, and meanwhile, the smooth constraint of the incident component and a reflection image is considered in secondary guide filtering, so that the processed image not only meets the smooth constraint, but also reduces the noise, and the linear weighted fusion is performed on the two enhanced images to realize defogging of the image.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular, to a multi-channel convolution-based MSRCR image defogging method. Background technique [0002] In the field of digital imaging, sharp images are a key prerequisite for understanding real scenes. In outdoor environments, photos taken can suffer from severe reductions in visibility and contrast due to harsh weather conditions such as lighting, fog, and haze, which can lead to dull and distorted images. In order to effectively remove the influence of dense fog on image quality and highlight the details in dense fog, image enhancement based on image processing and image restoration based on physical models are commonly used methods. [0003] The dehazing algorithm based on the physical model obtains the optimal estimation value of the haze-free image by establishing an approximate atmospheric scattering model and inverting the degradation process. There are mainly ...

AI Technical Summary

Problems solved by technology

Since histogram equalization does not select the processed data, it may enhance the contrast of background noise and reduce the contrast of useful signals; the computational complexity of homomorphic filtering and bilateral filtering is high, and the efficiency and practicability of the algorithm are not as good. Satisfactory; as a local linear image filter, guided filtering has good edge preservation and smoothing filtering performance. When the original image is complex and noisy, the enhanced image may appear noise enhancement; algorithms based on Retinex theory SSR, MSR and For improved algorithms such as MSRCR, the estimation

Images