Next Article in Journal
Novel Approach to Automatic Traffic Sign Inventory Based on Mobile Mapping System Data and Deep Learning
Next Article in Special Issue
A New Framework for Automatic Airports Extraction from SAR Images Using Multi-Level Dual Attention Mechanism
Previous Article in Journal
Spatiotemporal Analysis of Land Use/Cover Patterns and Their Relationship with Land Surface Temperature in Nanjing, China
Previous Article in Special Issue
Online Semantic Subspace Learning with Siamese Network for UAV Tracking
Open AccessArticle

A New Deep Learning Network for Automatic Bridge Detection from SAR Images Based on Balanced and Attention Mechanism

by Lifu Chen 1,2, Ting Weng 1,2, Jin Xing 3,*, Zhouhao Pan 4, Zhihui Yuan 1,2, Xuemin Xing 2,5 and Peng Zhang 1,2
1
School of Electrical and Information Engineering, Changsha University of Science & Technology, Changsha 410114, China
2
Laboratory of Radar Remote Sensing Applications, Changsha University of Science & Technology, Changsha 410014, China
3
School of Engineering, Newcastle University, Newcastle upon Tyne NE1 7RU, UK
4
China Academy of Electronics and Information Technology, Beijing 100041, China
5
School of Traffic & Transportation Engineering, Changsha University of Science & Technology, Changsha 410114, China
*
Author to whom correspondence should be addressed.
Remote Sens. 2020, 12(3), 441; https://doi.org/10.3390/rs12030441
Received: 31 December 2019 / Revised: 23 January 2020 / Accepted: 29 January 2020 / Published: 31 January 2020
(This article belongs to the Special Issue Deep Learning Approaches for Urban Sensing Data Analytics)
Bridge detection from Synthetic Aperture Radar (SAR) images has very important strategic significance and practical value, but there are still many challenges in end-to-end bridge detection. In this paper, a new deep learning-based network is proposed to identify bridges from SAR images, namely, multi-resolution attention and balance network (MABN). It mainly includes three parts, the attention and balanced feature pyramid (ABFP) network, the region proposal network (RPN), and the classification and regression. First, the ABFP network extracts various features from SAR images, which integrates the ResNeXt backbone network, balanced feature pyramid, and the attention mechanism. Second, extracted features are used by RPN to generate candidate boxes of different resolutions and fused. Furthermore, the candidate boxes are combined with the features extracted by the ABFP network through the region of interest (ROI) pooling strategy. Finally, the detection results of the bridges are produced by the classification and regression module. In addition, intersection over union (IOU) balanced sampling and balanced L1 loss functions are introduced for optimal training of the classification and regression network. In the experiment, TerraSAR data with 3-m resolution and Gaofen-3 data with 1-m resolution are used, and the results are compared with faster R-CNN and SSD. The proposed network has achieved the highest detection precision (P) and average precision (AP) among the three networks, as 0.877 and 0.896, respectively, with the recall rate (RR) as 0.917. Compared with the other two networks, the false alarm targets and missed targets of the proposed network in this paper are greatly reduced, so the precision is greatly improved. View Full-Text
Keywords: deep learning; bridge detection; attention mechanism; feature pyramid; SAR image; automatic detection deep learning; bridge detection; attention mechanism; feature pyramid; SAR image; automatic detection
Show Figures

Graphical abstract

MDPI and ACS Style

Chen, L.; Weng, T.; Xing, J.; Pan, Z.; Yuan, Z.; Xing, X.; Zhang, P. A New Deep Learning Network for Automatic Bridge Detection from SAR Images Based on Balanced and Attention Mechanism. Remote Sens. 2020, 12, 441.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop