Remote Sensing Image Segmentation Method Combining Complete Residual and Feature Fusion

Abstract

A remote sensing image segmentation method combining complete residual and multi-scale feature fusion includes S100 improving a convolution coding-decoding network as a segmentation backbone network,separately comprising S101 using the convolution coding-decoding network as the segmentation backbone network; S102 adding a feature pyramid module for aggregating multi-scale context information intothe backbone network; S103 adding a residual unit into the convolution layer corresponding to the encoder and the decoder of the backbone network, and meanwhile, fusing the features in the encoder into the corresponding layer of the decoder in a pixel-by-pixel manner; S200 using the improved image segmentation network combined with complete residual and multi-scale feature fusion for remote sensing image segmentation; S300 outputting the segmentation result of the remote sensing image. This method not only simplifies the training of the deep network and enhances the feature fusion, but also enables the network to extract rich context information, cope with changes in the scale of the target, and improve the segmentation performance.

Description

technical field [0001] The disclosure belongs to the technical field of remote sensing image processing, and in particular relates to a remote sensing image segmentation method combining complete residual and multi-scale feature fusion. Background technique [0002] With the advent of drones and improvements in acquisition sensors, remote sensing images of extreme resolution (<10 cm) became available, especially in urban areas. Compared with ordinary images, with the improvement of spatial resolution, remote sensing images contain more and more spectral information and ground object information, the scale of the target is different, and there are more occlusions, shadows and other phenomena in the image, these are high-resolution images. Interpretation of high-rate remote sensing images poses challenges. Therefore, research on remote sensing image segmentation is of great significance to people's growing demand for remote sensing data processing, such as environmental mo...

AI Technical Summary

Problems solved by technology

For deep convolutional neural networks, first of all, multi-scale atrous convolution and spatial pyramid pooling structures can extract feature information at different scales, but the grid phenomenon and local information loss caused by atrous convolution and pooling operations are harmful to The improvement of the final segmentation accuracy is very limited

Secondly, using a convolutional neural network with higher performance and deeper layers as the backbone network for segmentation can improve segmentation accuracy and overcome gradient disappearance to a certain extent, but their network structure is too complex, and training consumes a lot of memory.

Images