Multi-wavelet fusion image processing method for polarization haze removal

Abstract

The invention relates to a multi-wavelet fusion image processing method for polarization haze removal, and belongs to the technical field of image processing. According to the haze removing method, polarization detection is combined with a multi-wavelet fusion algorithm, on the basis of target polarization detection, a plurality of scale functions and a plurality of wavelet functions of multiple wavelets are utilized, properties such as symmetry, orthogonality and compact support are met simultaneously, and different rules are respectively adopted for fusion of polarization information such as the polarization degree and the polarization angel and the intensity information of a target according to characteristics of decomposed high / low frequency coefficients. By using the method, recognized details and brightness information of the target can be simultaneously integrated by a polarization fusion image, a target image with a relatively high recognition rate, relatively high quality and relatively much detail information is obtained in a haze weather environment, and the haze removal property of target detection is improved.

Description

technical field [0001] The invention relates to a multi-wavelet fusion image processing method for polarization and haze removal, and belongs to the technical field of image information processing. Background technique [0002] Polarization imaging technology is another new discipline in the field of detection and imaging. It combines polarization measurement with image processing methods. Defects, obtaining high-quality, high-contrast images required for measurement, have broad application prospects in military and civilian applications. [0003] However, due to the increasingly serious phenomenon of smog weather caused by urban pollution, some media in the environment have an attenuation effect on the absorption and scattering of light, and the final detected target image is not clear and has low contrast, which seriously affects the recognition of the target. Rate. In order to improve the polarization imaging quality of images in hazy weather, based on the characteristi...

AI Technical Summary

Problems solved by technology

[0004] Among the three commonly used fusion methods of pixel level, feature level and decision level, the pixel level fusion method has a great contribution to the improvement of image clarity, but the single resolution method is mostly used for image fusion, and the unified According to the multi-scale characteristics of wavelet, the multi-resolution fusion method of wavelet transform can apply different rules to the high-frequency and low-frequency information of the image for fusion, which can be easily It can improve the deficiency of single-resolution fusion, but this traditional single-wavelet method only has one scale and one wavelet function. For the polarization degree and polarization angle image with image edge and detail characteristics, it is difficult to fully express its details when decomposing information

Based on this, many researchers combine the wavelet decomposition algorithm with other fusion methods to obtain more target information, but this method has more restrictions on the image, and the completion steps are more cumbersome

Images