An Improved U-Net Network for Sandy Road Extraction from Remote Sensing Imagery
-
Published:2023-10-10
Issue:20
Volume:15
Page:4899
-
ISSN:2072-4292
-
Container-title:Remote Sensing
-
language:en
-
Short-container-title:Remote Sensing
Author:
Nie Yunfeng1, An Kang12ORCID, Chen Xingfeng2ORCID, Zhao Limin2, Liu Wantao3, Wang Xing45, Yu Yihao1, Luo Wenyi2, Li Kewei1, Zhang Zhaozhong1
Affiliation:
1. School of Information Engineering, Nanchang Hangkong University, Nanchang 330063, China 2. Aerospace Information Institute, Chinese Academy of Sciences, Beijing 100094, China 3. Tianjin Institute of Advanced Technology, Tianjin 300459, China 4. School of Computer Engineering, Nanjing Institute of Technology, Nanjing 211167, China 5. School of Atmosphere Science, Nanjing University, Nanjing 210023, China
Abstract
The extraction of sandy roads from remote sensing images is important for field ecological patrols and path planning. Extraction studies on sandy roads face limitations because of various factors (e.g., sandy roads may have poor continuity, may be obscured by external objects, and/or have multi-scale and banding characteristics), in addition to the absence of publicly available datasets. Accordingly, in this study, we propose using the remote sensing imagery of a sandy road (RSISR) dataset and design a sandy road extraction model (Parallel Attention Mechanism-Unet, or PAM-Unet) based on Gaofen-2 (GF-2) satellite images. Firstly, the model uses a residual stacking module, which can solve the problem of poor road feature consistency and improve the extraction of fine features. Secondly, we propose a parallel attention module (PAM), which can reduce the occlusion effect of foreign objects on roads during the extraction process and improve feature map reduction. Finally, with this model, the SASPP (Strip Atrous Spatial Pyramid Pooling) structure, which enhances the model’s ability to perceive contextual information and capture banding features, is introduced at the end of the encoder. For this study, we conducted experiments on road extraction using the RSISR dataset and the DeepGlobe dataset. The final results show the following: (a) On the RSISR dataset, PAM-Unet achieves an IoU value of 0.762, and its F1 and IoU values are improved by 2.7% and 4.1%, respectively, compared to U-Net. In addition, compared to the models Unet++ and DeepLabv3+, PAM-Unet improves IoU metrics by 3.6% and 5.3%, respectively. (b) On the DeepGlobe dataset, the IoU value of PAM-Unet is 0.658; compared with the original U-Net, the F1 and IoU values are improved by 2.5% and 3.1%, respectively. The experimental results show that PAM-Unet has a positive impact by way of improving the continuity of sandy road extraction and reducing the occlusion of irrelevant features, and it is an accurate, reliable, and effective road extraction method.
Funder
National Natural Science Foundation of China Natural Science Foundation of Jiangxi Province National Key Research and Development Program 03 Special Project and 5G Project of the Science and Technology Department of Jiangxi Province
Subject
General Earth and Planetary Sciences
Reference54 articles.
1. Li, S.F., Liao, C., Ding, Y.L., Hu, H., Jia, Y., Chen, M., Xu, B., Ge, X.M., Liu, T.Y., and Wu, D. (2022). Cascaded residual attention enhanced road extraction from remote sensing images. ISPRS Int. J. Geo-Inf., 11. 2. Abdollahi, A., Pradhan, B., Shukla, N., Chakraborty, S., and Alamri, A. (2020). Deep learning approaches applied to remote sensing datasets for road extraction: A state-of-the-art review. Remote Sens., 12. 3. Road extraction in remote sensing data: A survey;Chen;Int. J. Appl. Earth Obs.,2022 4. Estimation of initiation thresholds and soil loss from gully erosion on unpaved roads on China’s Loess Plateau;Zhao;Earth Surf. Proc. Land,2021 5. A survey of deep learning techniques for autonomous driving;Grigorescu;J. Field Robot.,2020
|
|