Target Region Segmentation in SAR Vehicle Chip Image With ACM Net

被引:15
作者
Feng, Sijia [1 ,2 ]
Ji, Kefeng [1 ,2 ]
Ma, Xiaojie [1 ,2 ]
Zhang, Linbin [1 ,2 ]
Kuang, Gangyao [1 ,2 ]
机构
[1] Natl Univ Def Technol, State Key Lab Complex Electromagnet Environm Effe, Changsha 410073, Peoples R China
[2] Natl Univ Def Technol, Coll Elect Sci & Technol, Changsha 410073, Peoples R China
基金
中国国家自然科学基金;
关键词
Image segmentation; Synthetic aperture radar; Training; Head; Data models; Semantics; Semiconductor device measurement; Attribute scattering center (ASC) model; convolutional neural network (CNN); synthetic aperture radar (SAR); target segmentation; MODEL;
D O I
10.1109/LGRS.2021.3085188
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
Target region segmentation of synthetic aperture radar (SAR) images is one of the challenging problems in SAR image interpretation. The existing conventional segmentation methods rely on parameter selection in different backgrounds. Compared with traditional methods, the deep-learning-based methods can reduce the dependency on parameters and achieve more accurate results. However, lacking annotation data limits the application of the deep-learning-based methods in SAR chip image segmentation aspect. To solve these problems, a refined network structure for SAR vehicle image semantic segmentation, namely, All-Convolutional networks (A-ConvNets)-based Mask (ACM) net, is proposed. The mask in the training dataset of the network is extracted from image reconstruction using the Attribute Scattering Center (ASC) model, which can solve the problem of the lack of manual annotation in the segmentation methods based on deep learning. The proposed ACM Net consists of a modified A-ConvNets-based backbone and two decoupled head branches which achieve target segmentation and label prediction results, respectively. Experiments on moving and stationary target acquisition and recognition (MSTAR) dataset show that the comprehensive segmentation performance of ACM Net is better than both traditional segmentation methods and deep-learning-based segmentation methods. The classification results outperform other instance or semantic segmentation methods with the state-of-the-art recognition accuracy.
引用
收藏
页数:5
相关论文
共 18 条
[1]   Sequence SAR Image Classification Based on Bidirectional Convolution-Recurrent Network [J].
Bai, Xueru ;
Xue, Ruihang ;
Wang, Li ;
Zhou, Feng .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2019, 57 (11) :9223-9235
[2]  
Belloni Carole, 2017, International Conference on Radar Systems (Radar 2017)
[3]   Explainability of Deep SAR ATR Through Feature Analysis [J].
Belloni, Carole ;
Balleri, Alessio ;
Aouf, Nabil ;
Le Caillec, Jean-Marc ;
Merlet, Thomas .
IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, 2021, 57 (01) :659-673
[4]   Highly efficient neoteric histogram-entropy-based rapid and automatic thresholding method for moving vehicles and pedestrians detection [J].
Chandrasekar, Karnam Silpaja ;
Geetha, Planisamy .
IET IMAGE PROCESSING, 2020, 14 (02) :354-365
[5]   Target Classification Using the Deep Convolutional Networks for SAR Images [J].
Chen, Sizhe ;
Wang, Haipeng ;
Xu, Feng ;
Jin, Ya-Qiu .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2016, 54 (08) :4806-4817
[6]   A parametric model for synthetic aperture radar measurements [J].
Gerry, MJ ;
Potter, LC ;
Gupta, IJ ;
van der Merwe, A .
IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION, 1999, 47 (07) :1179-1188
[7]  
He K., P IEEE C COMP VIS PA, P770, DOI [10.1007/978-3-319-46493-0_38, DOI 10.1007/978-3-319-46493-0_38]
[8]  
He KM, 2017, IEEE I CONF COMP VIS, P2980, DOI [10.1109/TPAMI.2018.2844175, 10.1109/ICCV.2017.322]
[9]   MSTAR extended operating conditions - A tutorial [J].
Keydel, ER ;
Lee, SW ;
Moore, JT .
ALGORITHMS FOR SYNTHETIC APERTURE RADAR IMAGERY III, 1996, 2757 :228-242
[10]   SAR Automatic Target Recognition Based on Attribute Scattering Center Model and Discriminative Dictionary Learning [J].
Li, Tingli ;
Du, Lan .
IEEE SENSORS JOURNAL, 2019, 19 (12) :4598-4611