Robust multi-mode remote sensing image matching method and system

Abstract

The invention discloses a robust multi-mode remote sensing image matching method and system, and various local feature descriptors are integrated to carry out multi-mode remote sensing image automaticmatching. The method comprises firstly, carrying out dense grid sampling on images, extracting a local feature descriptor of each lattice point to form a three-dimensional dense feature expression graph, and then establishing a fast matching similarity measurement in a frequency domain by utilizing a three-dimensional Fourier transform on the basis of the feature expression graph, and finally, carrying out homonymous point identification by means of the template matching. In addition, the invention further provides a new dense feature expression method channel feature of oriented gradient (CFOG) according to the matching method, the channel feature of oriented gradient (CFOG) is superior to the existing dense feature expression modes based on HOG, LSS, SIFT, SURF in the aspects of matching performance and calculation efficiency. According to the invention, the non-linear radiation difference of multi-mode images of the visible light, the infrared ray, the laser radar, the synthetic aperture radar and the map can be effectively overcome, the homonymous point can be rapidly and accurately identified among the images, and the automatic matching of the images can be realized.

Description

technical field [0001] The invention relates to the technical field of satellite image processing, in particular to a multimodal remote sensing image matching method and system for automatic matching of multimodal images such as visible light, infrared, laser radar, contract aperture radar, and maps. Background technique [0002] Image matching is the process of identifying points with the same name between two or more images. It is the basic preprocessing step of many remote sensing image analyzes such as image fusion, change detection, image mosaic, etc. The matching accuracy is important for subsequent analysis work. influences. At present, remote sensing satellite sensors are equipped with global positioning system and inertial navigation system, which can directly locate and roughly match remote sensing images, eliminate obvious rotation and scale changes between images, so that only a certain amount (such as within dozens of pixels) exists between images translation d...

AI Technical Summary

Problems solved by technology

Nevertheless, HOG and LSS only use the local information of the image to construct features, or use the neighborhood information of the extracted feature points to calculate features, which is a sparse feature expression method, which is difficult to reflect the commonality between multi-modal images. properties, and its computational efficiency is low

Images