Affiliation:
1. The School of Geosciences and Info-Physics, Central South University, Changsha 410083, China
2. The School of Civil Engineering and Geomatics, Southwest Petroleum University, Chengdu 610500, China
Abstract
Road extraction from high-resolution remote sensing images is a critical task in image understanding and analysis, yet it poses significant challenges because of road occlusions caused by vegetation, buildings, and shadows. Deep convolutional neural networks have emerged as the leading approach for road extraction because of their exceptional feature representation capabilities. However, existing methods often yield incomplete and disjointed road extraction results. To address this issue, we propose CR-HR-RoadNet, a novel high-resolution road extraction network that incorporates local and global context reasoning. In this work, we introduce a road-adapted high-resolution network as the feature encoder, effectively preserving intricate details of narrow roads and spatial information. To capture multi-scale local context information and model the interplay between roads and background environments, we integrate multi-scale features with residual learning in a specialized multi-scale feature representation module. Moreover, to enable efficient long-range dependencies between different dimensions and reason the correlation between various road segments, we employ a lightweight coordinate attention module as a global context-aware algorithm. Extensive quantitative and qualitative experiments on three datasets demonstrate that CR-HR-RoadNet achieves superior extraction accuracy across various road datasets, delivering road extraction results with enhanced completeness and continuity. The proposed method holds promise for advancing road extraction in challenging remote sensing scenarios and contributes to the broader field of deep-learning-based image analysis for geospatial applications.
Funder
National Key Research and Development Program of China
National Natural Science Foundation of China
Subject
General Earth and Planetary Sciences
Reference53 articles.
1. Adaboost-like End-to-End multiple lightweight U-nets for road extraction from optical remote sensing images;Chen;Int. J. Appl. Earth Obs. Geoinf.,2021
2. Shan, B., and Fang, Y. (2020). A Cross Entropy Based Deep Neural Network Model for Road Extraction from Satellite Images. Entropy, 22.
3. DBRANet: Road Extraction by Dual-Branch Encoder and Regional Attention Decoder;Chen;IEEE Geosci. Remote Sens. Lett.,2022
4. ConDinet++: Full-Scale Fusion Network Based on Conditional Dilated Convolution to Extract Roads from Remote Sensing Images;Yang;IEEE Geosci. Remote Sens. Lett.,2022
5. Road Extraction Methods in High-Resolution Remote Sensing Images: A Comprehensive Review;Lian;IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.,2020
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献