Abstract
The popularity of deep learning has grown significantly among various researchers worldwide. Different deep learning models have been adopted in multiple applications wherein appreciable results are witnessed. However, several new models are yet to be explored for SAR image classification. Classification of SAR images are still suffering from issues such as misclassification or faulty predictions due to unreadable quality of images acquired by SAR systems, resulting in erroneous outcomes. This work focuses on applying one of the recent deep learning models called DenseNet to SAR image classification. Based on the study and experimental analysis carried in this work, a modified version of DenseNet called DenseNet179 is proposed in this work, by incorporating two types of dense blocks in the architecture of the model: one with the usual convolution, while the second with the depthwise convolution. The model is implemented and tested using the MSTAR benchmark acquired by the X-band SAR sensor. Results show that the incorporation of depthwise convolutions enables advanced feature learning of the model, with not as many parameters compared to all the DenseNet variants. The accuracy achieved on the new model is \(93.9\%\) which is higher than any of the variants of DenseNet implemented in this work for SAR image classification and outperforms various existing methods such as ATR-CNN and CDSPP.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
AFRL: The Air Force Research Laboratory. https://www.afrl.af.mil/ (2022). Accessed 25 Jan 2022
Bentes, C., Velotto, D., Lehner, S.: Target classification in oceanographic sar images with deep neural networks: architecture and initial results. In: 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), pp. 3703–3706 (2015)
Bentes, C., Velotto, D., Tings, B.: Ship classification in TerrasSAR-X images with convolutional neural networks. IEEE J. Oceanic Eng. 43(1), 258–266 (2018)
Chen, S., Wang, H.: Sar target recognition based on deep learning. In: 2014 International Conference on Data Science and Advanced Analytics (DSAA), pp. 541–547 (2014)
Chen, S., Wang, H., Xu, F., Jin, Y.: Target classification using the deep convolutional networks for SAR images. IEEE Trans. Geosci. Remote Sens. 54(8), 4806–4817 (2016)
Cui, Z., Tang, C., Cao, Z., Dang, S.: Sar unlabeled target recognition based on updating CNN with assistant decision. IEEE Geosci. Remote Sens. Lett. 15(10), 1585–1589 (2018)
DARPA: Defense Advanced Research Projects Agency. https://www.darpa.mil/ (2022). Accessed 25 Jan 2022
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Hearst, M.A., Dumais, S.T., Osuna, E., Platt, J., Scholkopf, B.: Support vector machines. IEEE Intell. Syst. Appl. 13(4), 18–28 (1998)
Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2261–2269 (2017)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980, pp. 1–15 (2014)
Air Force Research Laboratory: MSTAR Public Targets (2021). https://www.sdms.afrl.af.mil/index.php?collection=mstar. Accessed 22 May 2020
Liu, M., Chen, S., Wu, J., Lu, F., Wang, J., Yang, T.: Configuration recognition via class-dependent structure preserving projections with application to targets in SAR images. IEEE J. Select. Top. Appl. Earth Observ. Remote Sens. 11(6), 2134–2146 (2018). https://doi.org/10.1109/JSTARS.2018.2830103
Luo, X., Li, J., Chen, M., Yang, X., Li, X.: Ophthalmic disease detection via deep learning with a novel mixture loss function. IEEE J. Biomed. Health Inform. 25(9), 3332–3339 (2021)
Passah, A., Sur, S.N., Paul, B., Kandar, D.: Sar image classification: a comprehensive study and analysis. IEEE Access 10, 20385–20399 (2022)
Ross, T.D., Worrell, S.W., Velten, V.J., Mossing, J.C., Bryant, M.L.: Standard SAR ATR evaluation experiments using the MSTAR public release data set. In: Zelnio, E.G. (ed.) Algorithms for Synthetic Aperture Radar Imagery V, vol. 3370, pp. 566–573. International Society for Optics and Photonics (1998)
Saleh, H., Alharbi, A., Alsamhi, S.H.: OPCNN-FAKE: optimized convolutional neural network for fake news detection. IEEE Access 9, 129471–129489 (2021)
Shang, R., Wang, J., Jiao, L., Stolkin, R., Hou, B., Li, Y.: SAR targets classification based on deep memory convolution neural networks and transfer parameters. IEEE J. Select. Top. Appl. Earth Observ. Remote Sens. 11(8), 2834–2846 (2018)
Singh, R., Kumar, B.V.: Performance of the extended maximum average correlation height (emach) filter and the polynomial distance classifier correlation filter (pdccf) for multiclass SAR detection and classification. In: Algorithms for Synthetic Aperture Radar Imagery IX. vol. 4727, pp. 265–276. International Society for Optics and Photonics (2002)
Tetila, E.C., et al.: Automatic recognition of soybean leaf diseases using UAV images and deep convolutional neural networks. IEEE Geosci. Remote Sens. Lett. 17(5), 903–907 (2020)
Wang, C., Zhang, H., Wang, Y., Zhang, B.: Sea ice classification with convolutional neural networks using sentinel-l scansar images. In: IGARSS 2018–2018 IEEE International Geoscience and Remote Sensing Symposium, pp. 7125–7128 (2018)
Yu, H., et al.: Corn leaf diseases diagnosis based on k-means clustering and deep learning. IEEE Access 9, 143824–143835 (2021)
Zhang, A., Yang, X., Fang, S., Ai, J.: Region level SAR image classification using deep features and spatial constraints. ISPRS J. Photogramm. Remote. Sens. 163, 36–48 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Passah, A., Kandar, D. (2023). Classification of Synthetic Aperture Radar Images Using a Modified DenseNet Model. In: Gupta, D., Bhurchandi, K., Murala, S., Raman, B., Kumar, S. (eds) Computer Vision and Image Processing. CVIP 2022. Communications in Computer and Information Science, vol 1777. Springer, Cham. https://doi.org/10.1007/978-3-031-31417-9_46
Download citation
DOI: https://doi.org/10.1007/978-3-031-31417-9_46
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-31416-2
Online ISBN: 978-3-031-31417-9
eBook Packages: Computer ScienceComputer Science (R0)