面向遥感图像道路提取的多尺度上下文感知网络

打开文本图片集

doi：10.37188/OPE.20253304.0610 CSTR：32169.14.OPE.20253304.0610

Multi-scale context-aware network for road extraction in remote sensing images

LI Zhijie，HUIAiting，LIChanghua，DONGWei，ZHANGJie，JIEJun （School of Information and Control Engineering，Xi'an University of Architectural Science and Technology，Xi'an710055，China） * Corresponding author， E-mail： huiaiting@xauat. edu. cn

Abstract：To address the issues of local feature loss and low extraction accuracy faced by deep neural networks in remote sensing image road extraction，a multi-scale context-aware network was proposed based on the SwinUnet network for remote sensing image road extraction. Firstly，a branch with a context aggregation module was designed in the encoder to enhance the extraction of contextual information and allviate the problem of semantic ambiguity caused by oclusion. Secondly，to solve the problem of semantic information mismatch between the encoder and decoder and to improve the model's ability to extract spatial information，a spatial feature extraction module was introduced in the skip connections，replacing the direct copying of encoder features in SwinUnet. Finally，a feature compression module was designed in the down-sampling stage to reduce information loss in the encoder and enhance the network's segmentation capability.The test results on the

Massachusetts road dataset show that this method achieved F1，IoU，Pr，and Re scores of 80.91% ， 69.40% ， 78.03% ，and 65.20% ，respectively. In comparison with mainstream methods such as UNet and SwinUnet，the IoU improved by 4.45% and 2.72% ，respectively，demonstrating that the proposed algorithm effectively improves the accuracy and performance of remote sensing image road extraction through global modeling，context enhancement，and information matching optimization.

Key words：remote sensing；road extraction；semantic segmentation；SwinUnet

1引言

遥感图像蕴含大量的数据，通过提取其中的道路信息可以实现导航地图的构建，这不仅是自动驾驶的关键步骤，而且对于城市规划[1]、环境监测、车辆导航等领域发挥着重要作用。（剩余19852字）