MFFC-SDN: multi-level feature fusion codec-based ship detection network in SAR images

被引:0
作者
Li, Yanshan [1 ]
Liu, Wenjun [1 ]
Qi, Ruo [1 ]
机构
[1] Shenzhen Univ, Coll Elect & Informat Engn, 3688 Nanhai Ave, Shenzhen 518060, Peoples R China
基金
中国国家自然科学基金;
关键词
SAR image; target detection; deep learning; CenterNet; TUTORIAL;
D O I
10.1080/01431161.2024.2360706
中图分类号
TP7 [遥感技术];
学科分类号
081102 ; 0816 ; 081602 ; 083002 ; 1404 ;
摘要
In recent years, with the development of deep learning, SAR image-based ship target-detection technology has become a current research hotspot. SAR images are characterized by complex backgrounds, significant speckle noise interference, and poor interpretability. To address this challenge, this study proposes a new Gaussian circle radius determination strategy and a multi-level feature fusion codec-based ship detection network (MFFC-SDN) for SAR images. Differing from CenterNet's corner-oriented Gaussian circle strategy, the Gaussian circle strategy proposed in this paper takes the centre point coordinates of the real target as the origin to define a circular region. This approach allows for more precise supervision of the training model. Meanwhile, we propose MFFC-SDN to solve the problem of the poor performance of CenterNet in SAR ship detection. MFFC-SDN is an anchor-free, single-stage target-detection method with a low computation cost. In MFFC-SDN, we introduce a Multilevel Feature Recapture Codec Module (MFR-CM) to enhance the feature extraction capability of the network by using the features of the encoding stage twice because of the easy loss of image features in the lengthy codec process of the CenterNet network backbone. A Residual Attention Pyramid Feature Fusion Module (RA-PFFM) is designed to enhance the feature map and obtain multi-scale features. Experimental results on the SSDD and SAR-ship-dataset show that MFFC-SDN significantly enhances SAR image target-detection performance, effectively addressing detection challenges related to large target size variations and complex environmental conditions. Compared with existing algorithms, MFFC-SDN achieves the highest $A{P<^>{50}}$AP50.
引用
收藏
页码:4407 / 4427
页数:21
相关论文
共 94 条
[1]   Analysis of Crash Severity of Texas Two Lane Rural Roads Using Solar Altitude Angle Based Lighting Condition [J].
Abbasi, Mohammadhossein ;
Piccioni, Cristiana ;
Sierpinski, Grzegorz ;
Farzin, Iman .
SUSTAINABILITY, 2022, 14 (03)
[2]   Linear interpolation revitalized [J].
Blu, T ;
Thévenaz, P ;
Unser, M .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2004, 13 (05) :710-719
[3]   Comparing prediction power and stability of broadband and hyperspectral vegetation indices for estimation of green leaf area index and canopy chlorophyll density [J].
Broge, NH ;
Leblanc, E .
REMOTE SENSING OF ENVIRONMENT, 2001, 76 (02) :156-172
[4]   A Deep Neural Network Based on an Attention Mechanism for SAR Ship Detection in Multiscale and Complex Scenarios [J].
Chen, Chen ;
He, Chuan ;
Hu, Changhua ;
Pei, Hong ;
Jiao, Licheng .
IEEE ACCESS, 2019, 7 :104848-104863
[5]   Estimation of soil moisture content under high maize canopy coverage from UAV multimodal data and machine learning [J].
Cheng, Minghan ;
Jiao, Xiyun ;
Liu, Yadong ;
Shao, Mingchao ;
Yu, Xun ;
Bai, Yi ;
Wang, Zixu ;
Wang, Siyu ;
Tuohuti, Nuremanguli ;
Liu, Shuaibing ;
Shi, Lei ;
Yin, Dameng ;
Huang, Xiao ;
Nie, Chenwei ;
Jin, Xiuliang .
AGRICULTURAL WATER MANAGEMENT, 2022, 264
[6]   Covariance matrix estimation for adaptive CFAR detection in compound-Gaussian clutter [J].
Conte, E ;
De Maio, A ;
Ricci, G .
IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, 2002, 38 (02) :415-426
[7]   Estimating Forest Canopy Height Using MODIS BRDF Data Emphasizing Typical-Angle Reflectances [J].
Cui, Lei ;
Jiao, Ziti ;
Dong, Yadong ;
Sun, Mei ;
Zhang, Xiaoning ;
Yin, Siyang ;
Ding, Anxin ;
Chang, Yaxuan ;
Guo, Jing ;
Xie, Rui .
REMOTE SENSING, 2019, 11 (19)
[8]   Dense Attention Pyramid Networks for Multi-Scale Ship Detection in SAR Images [J].
Cui, Zongyong ;
Li, Qi ;
Cao, Zongjie ;
Liu, Nengyuan .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2019, 57 (11) :8983-8997
[9]  
Curlander J. C., 1991, Synthetic aperture radar, V11
[10]   The PASCAL Visual Object Classes Challenge: A Retrospective [J].
Everingham, Mark ;
Eslami, S. M. Ali ;
Van Gool, Luc ;
Williams, Christopher K. I. ;
Winn, John ;
Zisserman, Andrew .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2015, 111 (01) :98-136