A large-scale difference image feature point matching method based on a deformation space pyramid

Abstract

The invention provides a large-scale difference image feature point matching method based on a deformation space pyramid. The method comprises: taking two images with large resolution scale differences as objects, firstly, adopting the Dense SIFT algorithm to extract feature points and their descriptions from a left-to-right, top-to-bottom overlap on a fixed-size grid or bounding box by using a fixed step length, then matching the feature points by using a deformation space pyramid algorithm, and finally eliminating mismatching points by using RANSAC to obtain a final matching result. The algorithm matching effect is very good; The method can provide multi-source data cooperative technical support for land resource dynamic remote sensing monitoring of land resource management departments and production units, can be applied to the aspects of geological survey, mine monitoring, agriculture and forestry survey, resource and environment remote sensing, disaster early warning and the like,and has great potential social value, economic value and benefits.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image processing data preprocessing, and relates to a large-scale difference image feature point matching method based on a deformation space pyramid. Background technique [0002] The high-precision registration of multi-source remote sensing images is the premise of multi-source remote sensing data fusion, and it is also a necessary means for multi-sensor collaborative land and resources investigation and monitoring. It is the basis for remote sensing image change detection, target extraction, classification recognition and understanding. In terms of dynamic remote sensing monitoring and investigation of resources, it has important scientific research and application value. The high-precision registration method of high- and medium-resolution images with large differences in resolution and scale has become a hot spot and difficult problem in current research. Compared with low- and mediu...

AI Technical Summary

Problems solved by technology

Among them, the registration accuracy of the regional feature method is affected by the accuracy of the segmentation algorithm, and there are enough regions with the same name in the image; the extraction of line features depends on the accuracy and precision of edge detection; remote sensing image registration based on feature points has a relative Advantages, which are the most widely used, but in the case of large differences in image spatial resolution, it is easy to generate mismatched point pairs, resulting in registration errors

It is difficult to obtain the same direct features between large-scale difference images, and it is difficult to effectively match

Images