Remote sensing image building extraction and contour optimization method based on deep learning

Abstract

The invention provides a remote sensing image building extraction and contour optimization method based on deep learning, and belongs to the field of environment measurement. The thought of semantic segmentation is applied to building extraction, and building contour optimization is carried out by fusing the Hausdorff distance. A residual structure, a convolution attention module and pyramid pooling are introduced into a Unet model by utilizing the feature extraction capability of a residual module, the balance capability of a convolution attention module on space information and channel information and the multi-scale scene analysis characteristic of a pyramid pooling module, a PRCUnet model is established, semantic information and detail information are concerned at the same time, and the defect of Unet on small target detection is made up. According to the method, the used data set IoU and the recall rate both reach 85% or above, the precision is remarkably superior to that of a Unet model, the precision of the extracted building is higher, and the optimized building boundary is closer to the boundary contour of a real building.

Description

technical field [0001] The invention relates to a remote sensing image building extraction and contour optimization method, and is especially suitable for a deep learning-based remote sensing image building extraction and contour optimization method used in the field of surveying and cartography. Background technique [0002] With the rapid development of earth observation technology, the spatial resolution of remote sensing images has been significantly improved, and more accurate geometric structures, texture features, and richer ground object information can be obtained from remote sensing images. Building extraction based on remote sensing images is an important direction for target recognition. Buildings are of great significance to urban planning, change detection, and disaster management, and are also important basic data for location-based services. The rich data of remote sensing images provides a good data basis for building extraction. Therefore, building extracti...

AI Technical Summary

Problems solved by technology

However, how to find the best architecture for deep convolutional neural networks is still a great challenge

Images