Road Extraction from High Resolution Remote Sensing Images Based on Vector Field Learning
1
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430072, China
2
Department of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University, Hong Kong, China
3
Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
4
Piesat Information Technology Co., Ltd., Beijing 100195, China
*
Author to whom correspondence should be addressed.
Academic Editors: Chiman Kwan and Gwanggil Jeon
Sensors 2021, 21(9), 3152; https://doi.org/10.3390/s21093152
Received: 15 March 2021
/
Revised: 11 April 2021
/
Accepted: 28 April 2021
/
Published: 1 May 2021
(This article belongs to the Section Remote Sensors)
Accurate and up-to-date road network information is very important for the Geographic Information System (GIS) database, traffic management and planning, automatic vehicle navigation, emergency response and urban pollution sources investigation. In this paper, we use vector field learning to extract roads from high resolution remote sensing imaging. This method is usually used for skeleton extraction in nature image, but seldom used in road extraction. In order to improve the accuracy of road extraction, three vector fields are constructed and combined respectively with the normal road mask learning by a two-task network. The results show that all the vector fields are able to significantly improve the accuracy of road extraction, no matter the field is constructed in the road area or completely outside the road. The highest F1 score is 0.7618, increased by 0.053 compared with using only mask learning.
View Full-Text
Keywords:
road extraction; vector field learning; high resolution remote sensing image; encoder-decoder; DCNN
▼
Show Figures
Figure 1
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited
MDPI and ACS Style
Liang, P.; Shi, W.; Ding, Y.; Liu, Z.; Shang, H. Road Extraction from High Resolution Remote Sensing Images Based on Vector Field Learning. Sensors 2021, 21, 3152. https://doi.org/10.3390/s21093152
AMA Style
Liang P, Shi W, Ding Y, Liu Z, Shang H. Road Extraction from High Resolution Remote Sensing Images Based on Vector Field Learning. Sensors. 2021; 21(9):3152. https://doi.org/10.3390/s21093152
Chicago/Turabian StyleLiang, Peng, Wenzhong Shi, Yixing Ding, Zhiqiang Liu, and Haolv Shang. 2021. "Road Extraction from High Resolution Remote Sensing Images Based on Vector Field Learning" Sensors 21, no. 9: 3152. https://doi.org/10.3390/s21093152
Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.
