Different-source image matching method based on Gabor coding

Abstract

The invention provides a different-source image matching method based on Gabor coding, which comprises the steps of carrying out filtering on a reference image and a real-time image by using a Gabor filter group, and acquiring a group of reference image filtering images and a group of real-time image filtering images, wherein the reference image and the real-time image are different-source images; carrying out pooling on each reference image filtering image and each real-time image filtering image, and acquiring pooling data of each reference image filtering image and pooling data of each real-time image filtering image; and carrying out binaryzation and binary presentation on the pooling data of each reference image filtering image and the pooling data of each real-time image filtering image, and acquiring a Gabor coding characteristic of the reference image and a Gabor coding characteristic of the real-time image; calculating the similarity between the Gabor coding characteristic of the reference image and the Gabor coding characteristic of the real-time image by using bit manipulation of binary data, and acquiring a matching result of the reference image and the real-time image. The method provided by the invention can realize effective matching for the different-source images, and reduce the amount of calculation in the matching process.

Description

technical field [0001] The invention relates to the technical field of scene matching, in particular to a method for matching heterogeneous images based on Gabor coding. Background technique [0002] The so-called heterogeneous images refer to images obtained by different types of sensors. Due to the differences in imaging characteristics between different sensors, the same scene may present completely different images on heterogeneous images. In practice, the matching of heterogeneous images is very important. [0003] Existing heterogeneous image matching methods can be divided into two categories: feature-based methods and region-based methods, specifically: [0004] Feature-based methods include: matching methods using edge features, matching methods using contour features, matching methods using artificial scene features, matching methods that combine edge features and point features, etc. Such methods require that consistent features can be detected in heterogeneous ...

AI Technical Summary

Problems solved by technology

Usually mutual information is very good for matching infrared images and visible light images, but the matching effect for SAR images and visible light images is not ideal. The factors that affect the matching results mainly include the following two aspects: first, there may be serious noise in the image, Such as speckle noise in SAR images, and the second is the non-uniform change of gray level between images

In addition, the mutual information method needs to calculate the joint entropy for each search window, which requires a lot of calculation

Images