Deep learning-based method for identifying newly added building in remote sensing image

Abstract

The invention discloses a deep learning-based method for identifying a newly added building in a remote sensing image. The method includes the following steps that: sample images including remote sensing images of two time periods and newly added building background images are obtained; the sample images having original size are cut, so that small-sized images can be obtained; data enhancement processing is performed on all the small-sized images; centralization and global comparison normalization are performed on the enhanced small-sized remote sensing images of the two time periods, and theprocessed images are subtracted from one another, so that remote sensing difference images can be obtained; the remote sensing difference images and the small-sized newly added building background images are inputted into two modified deep neural networks so as to perform network parameter training on the deep neural networks; and a remote sensing image to be tested is inputted into the two deep neural networks which are obtained by means of training, model fusion is performed at the softmax output layers of the networks, and modification processing is performed on an outputted preliminary result, and a final newly added building identification image can be obtained. The method of the invention has the advantages of high accuracy of identifying the newly added building in the remote sensing image and wide application range.

Description

Technical field [0001] The invention relates to the technical field of image processing, in particular to a method for identifying newly added buildings in remote sensing images based on deep learning. Background technique [0002] The recognition of new buildings in remote sensing images based on deep learning relies on image segmentation technology. The purpose is to find new buildings in a specific land area between two time periods to assist in completing the land inspection business. [0003] The existing traditional image segmentation algorithms include: color and brightness-based segmentation methods, region-based segmentation methods, graph theory-based segmentation methods, and energy functional-based segmentation methods. The segmentation method based on color and brightness is to divide each pixel by the color or brightness of the image. For example, the K-Means algorithm regards the image as a point set composed of RGB three-dimensional features, and performs all the pi...

AI Technical Summary

Problems solved by technology

Due to external interference such as shooting weather, altitude, and cloud cover, the clarity and integrity of the available remote sensing images are lower than those of other types of images

Images