SAR image classification with convolutional neural network using modified functions
Authors: 
AliAsghar Soltanali, Vahid Ghods, Seyed Farhood Mousavizadeh, Meysam AmirahmadiAuthors Info & Claims
Abstract
Identifying a target accurately in the presence of noise in synthetic aperture radar (SAR) images poses significant challenges considering various parameters, such as viewing angle and configuration changes. In this paper, SAR images are classified using the proposed convolutional neural network. The limitation of data concerning moving and stationary target acquisition and recognition (MSTAR) database led us to develop a primary network (learning network) by employing the proposed N-Sigmoid function and training it using eight different satellite databases with images more than MSTAR. We saved the best weights for the main network. Next, we replace the weights of the two fully connected (FC) layers of the ResNet-50 with the saved weights of the training network and employed the main network for classification. Our proposed method’s primary contribution is twofold, based on the availability of additional information in heterogeneous SAR images and differences in intensity and clarity. First, we utilize the weights learned by the training network, and second, we keep negative neurons and neurons close to zero active instead of deactivating them to facilitate better training of the main network. Our proposed method outperformed other references in terms of sensitivity in all classes and achieved an accuracy of 98% for classification with good machine weight learning.
References
[1]
Avery RP, Wang Y, Rutherford GS (2004) Length-based vehicle classification using images from uncalibrated video cameras. In: The 7th international IEEE conference on intelligent transportation systems (IEEE Cat. No.04TH8749)
[2]
Chang M and You X Target recognition in SAR images based on information-decoupled representation Remote Sens 2018 10 1 138
[3]
Chen S, Wang H, Xu F, and Jin Y-Q Target classification using the deep convolutional networks for SAR images IEEE Trans Geosci Remote Sens 2016 54 8 4806-4817
[4]
Cheng X, Zhang M, Lin S, Zhou K, Wang L, and Wang H Multiscale superpixel guided discriminative forest for hyperspectral anomaly detection Remote Sens 2022 14 4828
[5]
Cheng X, Zhang M, Lin S, Zhou K, Zhao S, and Wang H Two-stream isolation forest based on deep features for hyperspectral anomaly detection IEEE Geosci Remote Sens Lett 2023 20 1-5
[6]
Choi HH, Lee JH, Kim SM, and Park SY Speckle noise reduction in ultrasound images using a discrete wavelet transform-based image fusion technique Bio-Med Mater Eng 2015 26 s1 S1587-S1597
[7]
Clady X, Negri P, Milgram M, and Poulenard R Prevost L, Marinai S, and Schwenker F Multi-class vehicle type recognition system Artificial neural networks in pattern recognition 2008 Berlin Springer
[8]
Cozzolino D, Verdoliva L, Scarpa G, and Poggi G Nonlocal CNN SAR image despeckling Remote Sens 2020 12 6 1006
[9]
Cui Z, Dang S, Cao Z, Wang S, and Liu N SAR target recognition in large scene images via region-based convolutional neural networks Remote Sens 2018 10 5 776
[10]
Cui Z, Tang C, Cao Z, and Liu N D-ATR for SAR images based on deep neural networks Remote Sens 2019 11 8 906
[11]
Cumming IG and Wong FH Digital processing of synthetic aperture radar data Artech House 2005 1 3 108-110
[12]
Ding B, Wen G, Huang X, Ma C, and Yang X Target recognition in synthetic aperture radar images via matching of attributed scattering centers IEEE J Select Top Appl Earth Observ Remote Sens 2017 10 7 3334-3347
[13]
Dong Z, Wu Y, Pei M, and Jia Y Vehicle type classification using a semisupervised convolutional neural network IEEE Trans Intell Transport Syst 2015 16 4 2247-2256
[14]
Dong G, Liu H, Kuang G, and Chanussot J Target recognition in SAR images via sparse representation in the frequency domain Pattern Recognit 2019 96 106972
[15]
Du L, Li L, Guo Y, Wang Y, Ren K, and Chen J Two-stream deep fusion network based on VAE and CNN for synthetic aperture radar target recognition Remote Sens 2021 13 20 4021
[16]
Fernández-Caballero A, Gómez FJ, and López-López J Knowledge-based road traffic monitoring Nature inspired problem-solving methods in knowledge engineering 2007 Berlin Springer 182-191
[17]
Gao F, Shi W, Wang J, Hussain A, and Zhou H A semi-supervised synthetic aperture radar (SAR) image recognition algorithm based on an attention mechanism and bias-variance decomposition IEEE Access 2019 7 108617-108632
[18]
Gao F, Huang T, Sun J, Wang J, Hussain A, and Yang E A new algorithm for SAR image target recognition based on an improved deep convolutional neural network Cogn Comput 2019 11 6 809-824
[19]
Geng Z, Xu Y, Wang B-N, Yu X, Zhu D-Y, and Zhang G Target recognition in SAR images by deep learning with training data augmentation Sensors 2023 23 941
[20]
Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition
[21]
Hinton GE Deep belief networks Scholarpedia 2009 4 5 5947
[22]
Hinton G et al. Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups IEEE Signal Process Mag 2012 29 6 82-97
[23]
Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7132–7141
[24]
Huang Z, Pan Z, and Lei B Transfer learning with deep convolutional neural network for SAR target classification with limited labeled data Remote Sens 2017 9 9 907
[25]
Huo Y, Qian X, Li C, and Wang W Multiple instance complementary detection and difficulty evaluation for weakly supervised object detection in remote sensing images IEEE Geosci Remote Sens Lett 2023 20 1-5
[26]
Itti L, Koch C, and Niebur E A model of saliency-based visual attention for rapid scene analysis IEEE Trans Pattern Anal Mach Intell 1998 20 11 1254-1259
[27]
Jeong N-H, Choi J-H, Lee G, Park J-H, and Kim K-T Feature selection for SAR target discrimination and efficient two-stage detection method Remote Sens 2022 14 16 4044
[28]
Jiang H, Wang J, Yuan Z, Wu Y, Zheng N, Li S (2017) Salient object detection: a discriminative regional feature integration approach. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 123–134
[29]
Karine A, Toumi A, Khenchaf A, El Hassouni M (2017) Saliency attention and sift keypoints combination for automatic target recognition on MSTAR dataset. In: 2017 International conference on advanced technologies for signal and image processing (ATSIP)
[30]
Lawrence S, Giles CL, Tsoi AC, and Back AD Face recognition: a convolutional neural-network approach IEEE Trans Neural Netw 1997 8 1 98-113
[31]
Li L, Du Y, and Du L Vehicle target detection network in SAR images based on rectangle-invariant rotatable convolution Remote Sens 2022 14 13 3086
[32]
Li K, Zhang M, Xu M, Tang R, Wang L, and Wang H Ship detection in SAR images based on feature enhancement Swin transformer and adjacent feature fusion Remote Sens 2022 14 13 3186
[33]
Li W, Yang W, Liu L, Zhang W, and Liu Y Discovering and explaining the non-causality of deep learning in SAR ATR IEEE Geosci Remote Sens Lett 2023 20 1-5
[34]
Liao L, Du L, and Guo Y Semi-supervised SAR target detection based on an improved faster R-CNN Remote Sens 2022 14 1 143
[35]
Lin S, Zhang M, Cheng X, Wang L, Xu M, and Wang H Hyperspectral anomaly detection via dual dictionaries construction guided by two-stage complementary decision Remote Sens 2022 14 1784
[36]
Lin S, Zhang M, Cheng X, Zhou K, Zhao S, and Wang H Hyperspectral anomaly detection via sparse representation and collaborative representation IEEE J Select Top Appl Earth Observ Remote Sens 2023 16 94-961
[37]
Liu M, Chen S, Lu F, and Xing M SAR target configuration recognition via product sparse representation Sensors 2018 18 10 3535
[38]
Mateus P, Mendes VB, and Pires CAL Global empirical models for tropopause height determination Remote Sens 2022 14 17 4303
[39]
Men P, Guo H, An J, and Li G An improved L2Net for repetitive texture image registration with intensity difference heterogeneous SAR images Remote Sens 2022 14 11 2527
[40]
Mhangara P and Odindi J Potential of texture-based classification in urban landscapes using multispectral aerial photos S Afr J Sci 2013
[41]
Mikolov T, Karafiát M, Burget L, Cernocký J, Khudanpur S (2010) Recurrent neural network based language model. In: INTERSPEECH 2010, 2, 3
[42]
Mo D and Lai Z Robust jointly sparse regression with generalized orthogonal learning for image feature selection Pattern Recognit 2019 93 164-178
[43]
Nogueira K, Miranda WO, Dos Santos JA (2015) Improving spatial feature representation from aerial scenes by using convolutional networks. In: 2015 28th SIBGRAPI conference on graphics, patterns and images, IEEE
[44]
Oliver C and Quegan S Understanding synthetic aperture radar images 1998 Boston Artech House, Inc.
[45]
Pan SJ and Yang Q A survey on transfer learning IEEE Trans Knowl Data Eng 2009 22 10 1345-1359
[46]
Qian X, Lin S, Cheng G, Yao X, Ren H, and Wang W Object detection in remote sensing images based on improved bounding box regression and multi-level features fusion Remote Sens 2020 12 143
[47]
Salimi A, Ziaii M, Amiri A, and Hosseinjanizadeh M Evaluation of a Feature Subset Selection method to find informative spectral bands of Hyperion hyperspectral data for hydrothermal alteration mapping: a case study from the Darrehzar porphyry copper mine, Kerman, Iran J Econ Geol 2018
[48]
Shao J, Qu C, Li J, and Peng S A lightweight convolutional neural network based on visual attention for SAR image target classification Sensors 2018 18 9 3039
[49]
Song H, Ji K, Zhang Y, Xing X, and Zou H Sparse representation-based SAR image target classification on the 10-class MSTAR data set Appl Sci 2016 6 1 26
[50]
Song Y, Wang S, Li Q, Mu H, Feng R, Tian T, and Tian J Vehicle target detection method for wide-area SAR images based on coarse-grained judgment and fine-grained detection Remote Sens 2023 15 13 3242
[51]
Tan J, Fan X, Wang S, and Ren Y Target recognition of SAR images via matching attributed scattering centers with binary target region Sensors 2018 18 9 3019
[52]
Van Rossum G, Drake FL (2009) Python 3 reference manual CreateSpace
[53]
Wang L, Bai X, and Zhou F SAR ATR of ground vehicles based on ESENet Remote Sens 2019 11 11 1316
[54]
Wang Z, Chen L, Shi H, Qi B, and Wang G SAR image classification method based on Gabor feature and K-NN J Eng 2019 20 2019
[55]
Wang J, Tian S, Feng X, Zhang B, Fan W, Zhang H, and Wang C Locality preserving property constrained contrastive learning for object classification in SAR imagery Remote Sens 2023 15 14 3697
[56]
Wei D, Du Y, Du L, and Li L Target detection network for SAR images based on semi-supervised learning and attention mechanism Remote Sens 2021 13 14 2686
[57]
Xie Y, Dai W, Hu Z, Liu Y, Li C, and Pu X A novel convolutional neural network architecture for SAR target recognition J Sens 2019 2019 1-9
[58]
Xie Z, Shi J, Zhou Y, Yang X, Guo W, and Zhang X S2-PCM: super-resolution structural point cloud matching for high-accuracy video-SAR image registration Remote Sens 2022 14 17 4302
[59]
Yin S, Ouyang P, Liu L, Guo Y, and Wei S Fast traffic sign recognition with a rotation invariant binary pattern based feature Sensors 2015 15 1 2161-2180
[60]
Zhang Q, Wu Y, Zhao W, Wang F, Fan J, and Li M Multiple-scale salient-region detection of SAR image based on Gamma distribution and local intensity variation IEEE Geosci Remote Sens Lett 2013 11 8 1370-1374
[61]
Zhang P, Liu W, Lei Y, and Lu H Hyperfusion-net: hyper-densely reflective feature fusion for salient object detection Pattern Recognit 2019 93 521-533
[62]
Zhang J, Song H, and Zhou B SAR target classification based on deep forest model Remote Sens 2020 12 1 128
[63]
Zhao T, Hoffman J, McNitt-Gray M, and Ruan D Ultra-low-dose CT image denoising using modified BM3D scheme tailored to data statistics Med Phys 2019 46 1 190-198
[64]
Zhu J and Chen Z Comparative analysis of various new activation functions based on convolutional neural network J Phys Conf Ser 2020 1676 012228
Recommendations
Polarimetric SAR image classification by using artificial neural network
ICWET '10: Proceedings of the International Conference and Workshop on Emerging Trends in TechnologyThe classification of various land cover features using fully polarimetric Synthetic Aperture Radar (SAR) data sets is an important application of radar remote sensing. The data acquired is over various parts of India are SIR-C L- and C-band data over ...
Conversion from multi-spectral data into SAR data with Deep Convolution Neural Architecture using Generative Adversarial Network
AbstractSynthetic Aperture Radar (SAR) is a high-resolution radar extensively used for aerial and terrestrial images in numerous applications. The SAR images are all weather and day/night capable. It is extensively used in defense/military systems for ...
Polarimetric synthetic aperture radar image segmentation by convolutional neural network using graphical processing units
Image segmentation is an important application of polarimetric synthetic aperture radar. This study aimed to create an 11-layer deep convolutional neural network for this task. The Pauli decomposition formed the RGB image and was used as the input. We ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
© The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 25 November 2023
Accepted: 27 October 2023
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 15 Jan 2025