MS-AGAN: Road Extraction via Multi-Scale Information Fusion and Asymmetric Generative Adversarial Networks from High-Resolution Remote Sensing Images under Complex Backgrounds
-
Published:2023-06-30
Issue:13
Volume:15
Page:3367
-
ISSN:2072-4292
-
Container-title:Remote Sensing
-
language:en
-
Short-container-title:Remote Sensing
Author:
Lin Shaofu1ORCID, Yao Xin1ORCID, Liu Xiliang1ORCID, Wang Shaohua234, Chen Hua-Min1ORCID, Ding Lei5, Zhang Jing6, Chen Guihong7, Mei Qiang8
Affiliation:
1. Faculty of Information Technology, Beijing University of Technology, Chaoyang District, Beijing 100124, China 2. International Research Center of Big Data for Sustainable Development Goals, Beijing 100094, China 3. Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China 4. State Key Laboratory of Remote Sensing Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China 5. Big Data Analysis, PLA Strategic Force Information Engineering University, Zhengzhou 450001, China 6. Department of Information Engineering and Computer Science, University of Trento, 38123 Trento, Italy 7. Beijing Big Data Centre, Chaoyang District, Beijing 100101, China 8. Navigation College, Jimei University, Xiamen 361021, China
Abstract
Extracting roads from remote sensing images is of significant importance for automatic road network updating, urban planning, and construction. However, various factors in complex scenes (e.g., high vegetation coverage occlusions) may lead to fragmentation in the extracted road networks and also affect the robustness of road extraction methods. This study proposes a multi-scale road extraction method with asymmetric generative adversarial learning (MS-AGAN). First, we design an asymmetric GAN with a multi-scale feature encoder to better utilize the context information in high-resolution remote sensing images (HRSIs). Atrous spatial pyramid pooling (ASPP) and feature fusion are integrated into the asymmetric encoder–decoder structure to avoid feature redundancy caused by multi-level cascading operations and enhance the generator network’s ability to extract fine-grained road information at the pixel level. Second, to maintain road connectivity, topologic features are considered in the pixel segmentation process. A linear structural similarity loss (LSSIM) is introduced into the loss function of MS-AGAN, which guides MS-AGAN to generate more accurate segmentation results. Finally, to fairly evaluate the performance of deep models under complex backgrounds, the Bayesian error rate (BER) is introduced into the field of road extraction for the first time. Experiments are conducted via Gaofen-2 (GF-2) high-resolution remote sensing images with high vegetation coverage in the Daxing District of Beijing, China, and the public DeepGlobe dataset. The performance of MS-AGAN is compared with a list of advanced models, including RCFSNet, CoANet, UNet, DeepLabV3+, and DiResNet. The final results show that (1) with respect to road extraction performance, the Recall, F1, and IoU values of MS-AGAN on the Daxing dataset are 2.17%, 0.04%, and 2.63% higher than the baselines. On DeepGlobe, the Recall, F1, and IoU of MS-AGAN improve by 1.12%, 0.42%, and 0.25%, respectively. (2) On road connectivity, the Conn index of MS-AGAN from the Daxing dataset is 46.39%, with an improvement of 0.62% over the baselines, and the Conn index of MS-AGAN on DeepGlobe is 70.08%, holding an improvement of 1.73% over CoANet. The quantitative and qualitative analyses both demonstrate the superiority of MS-AGAN in preserving road connectivity. (3) In particular, the BER of MS-AGAN is 20.86% over the Daxing dataset with a 0.22% decrease compared to the best baselines and 11.77% on DeepGlobe with a 0.85% decrease compared to the best baselines. The proposed MS-AGAN provides an efficient, cost-effective, and reliable method for the dynamic updating of road networks via HRSIs.
Subject
General Earth and Planetary Sciences
Reference131 articles.
1. Semi automatic road extraction from digital images;Bakhtiari;Egypt. J. Remote Sens. Space Sci.,2017 2. Liu, P., Di, L., Du, Q., and Wang, L. (2018). Remote sensing big data: Theory, methods and applications. Remote Sens., 10. 3. BT-RoadNet: A boundary and topologically-aware neural network for road extraction from high-resolution remote sensing imagery;Zhou;ISPRS J. Photogramm. Remote Sens.,2020 4. Senthilnath, J., Varia, N., Dokania, A., Anand, G., and Benediktsson, J.A. (2020). Deep tec: Deep transfer learning with ensemble classifier for road extraction from Uav imagery. Remote Sens., 12. 5. Tan, Y.Q., Gao, S.H., Li, X.Y., Cheng, M.M., and Ren, B. (2020, January 13–19). Vecroad: Point-based iterative graph exploration for road graphs extraction. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.
Cited by
1 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
|
|