Remote sensing image matching method

Abstract

The invention relates to a remote sensing image matching method, and belongs to an image matching technology. According to the method, the gray-level co-occurrence matrix and the analytic hierarchy process are combined, and the complexity information of the image is quantitatively calculated, so that more efficient matching of the remote sensing image can be realized. In addition, by calculating the complexity of the key points of the image, the control parameters of the key points are estimated according to the complexity of the image and the number information of the key points. In a threshold value iteration updating stage, comprehensive information of two images to be matched is considered, so that a matching result is obtained. Therefore, the method can be applied to matching of copied remote sensing images, simultaneously detects information of a reference image and a target image, robustly extracts key points, fully utilizes image information, saves matching time, and has better alignment precision and real-time performance; therefore, the method can be better applied to a plurality of fields such as environment monitoring, topographic survey, military reconnaissance, disaster early warning and the like.

Description

technical field [0001] The invention relates to image matching technology, in particular to a remote sensing image matching method. Background technique [0002] Remote sensing imaging technology is widely used in target positioning, geological survey and detection of changes in the earth's surface environment. Image matching is one of the research hotspots in remote sensing imaging technology. Remote sensing image matching refers to the process of correcting two or more remote sensing images of the same scene under different radiation and geometric conditions. In remote sensing applications, factors such as different sensors, different times, different angles, different times, and different brightness are very common. Therefore, it is of great significance to study the matching of different remote sensing images. [0003] Image matching methods are generally divided into region-based and feature-based methods. In region-based methods, developers focus on the feature mat...

AI Technical Summary

Problems solved by technology

Due to the high resolution and complexity of remote sensing images, the SIFT algorithm used for remote sensing image matching still has problems such as insufficient utilization of image information, unstable number of feature extraction, poor matching accuracy, and long matching time.

Images