Toggle Main Menu Toggle Search

Open Access padlockePrints

Employing deep learning for automatic river bridge detection from SAR images based on Adaptively effective feature fusion

Lookup NU author(s): Dr Jin XingORCiD, Professor Zhenhong Li

Downloads


Licence

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND).


Abstract

© 2021 The AuthorsAutomatic river bridge detection is a typical and valuable application for SAR image analysis. However, the background information of SAR image is complex, and there are many specious targets with similar features, such as road, ponds and ridges, which usually cause false alarms. And current river bridge detection methods fail to handle these interference efficiently. Therefore, this paper applies deep learning to SAR and proposes a new river bridge detection algorithm, which is named as Single Short Detection-Adaptively Effective Feature Fusion (SSD-AEFF). It can effectively reduce the interference of noisy information, and achieve fast and high-precision detection of river bridges in complex SAR imagery. SSD-AEFF is based on SSD, and AEFF module is innovated to enhance the multi-scale feature maps together with effective Squeeze-Excitation (eSE) module to further fuse effective features and decrease the interference of background information. Additionally, Non-Maximum Suppression (NMS) is used to screen out redundant candidate boxes to produce the final detection result. Moreover, Gradient Harmonizing Mechanism (GHM) loss function is introduced to solve the problem of sample imbalance in the training process. Experimental results on TerraSAR data compared with existing baseline models demonstrate the superiority of the proposed SSD-AEFF algorithm.


Publication metadata

Author(s): Chen L, Weng T, Xing J, Li Z, Yuan Z, Pan Z, Tan S, Luo R

Publication type: Article

Publication status: Published

Journal: International Journal of Applied Earth Observation and Geoinformation

Year: 2021

Volume: 102

Print publication date: 01/10/2021

Online publication date: 03/07/2021

Acceptance date: 26/06/2021

Date deposited: 06/01/2022

ISSN (print): 1569-8432

ISSN (electronic): 1872-826X

Publisher: Elsevier B.V.

URL: https://doi.org/10.1016/j.jag.2021.102425

DOI: 10.1016/j.jag.2021.102425


Altmetrics

Altmetrics provided by Altmetric


Share