One-vs-All Convolutional Neural Networks for Synthetic Aperture Radar Target Recognition

Babu, Bileesh Plakkal; Narayanan, Swathi Jamjala

doi:10.2478/cait-2022-0035

Abstract

Convolutional Neural Networks (CNN) have been widely utilized for Automatic Target Recognition (ATR) in Synthetic Aperture Radar (SAR) images. However, a large number of parameters and a huge training data requirements limit CNN’s use in SAR ATR. While previous works have primarily focused on model compression and structural modification of CNN, this paper employs the One-Vs-All (OVA) technique on CNN to address these issues. OVA-CNN comprises several Binary classifying CNNs (BCNNs) that act as an expert in correctly recognizing a single target. The BCNN that predicts the highest probability for a given target determines the class to which the target belongs. The evaluation of the model using various metrics on the Moving and Stationary Target Acquisition and Recognition (MSTAR) benchmark dataset illustrates that the OVA-CNN has fewer weight parameters and training sample requirements while exhibiting a high recognition rate.

References

1. Novak, L. M., G. J. Owirka, W. S. Brower, A. L. Weaver. The Automatic Target Recognition System in SAIP. – Lincoln Laboratory Journal, Vol. 10, 1983, No 2.
Search in Google Scholar Back to article
2. Owirka, G. J., A. L. Weaver, L. M. Novak. Performance of a Multiresolution Classifier Using Enhanced-Resolution SAR Data. – Radar Sensor Technology II, Vol. 3066, 1997, pp. 90-100.10.1117/12.276091
Search in Google Scholar Back to article
3. Zhang, K., W. Zuo, L. Zhang. FFDNet: Toward a Fast and Flexible Solution for CNN-Based Image Denoising. – IEEE Transactions on Image Processing, Vol. 27, 2018, No 9, pp. 4608-4622.10.1109/TIP.2018.283989129993717
Search in Google Scholar Back to article
4. Mu, N., X. Xu, X. Zhang, H. Zhang. Salient Object Detection Using a Covariance-Based CNN Model in Low-Contrast Images. – Neural Computing and Applications, Vol. 29, 2018, No 8, pp. 181-192.10.1007/s00521-017-2870-6
Search in Google Scholar Back to article
5. Xie, F., Q. Gao, C. Jin, F. Zhao. Hyperspectral Image Classification Based on Superpixel Pooling Convolutional Neural Network with Transfer Learning. – Remote Sensing, Vol. 13, 2021, No 5, pp. 930.10.3390/rs13050930
Search in Google Scholar Back to article
6. Deng, J., W. Dong, R. Socher, L. J. Li, K. Li, L. Fei-Fei. Imagenet: A Large-Scale Hierarchical Image Database. – In: Proc. of IEEE Conference on Computer Vision and Pattern Recognition, 2009, pp. 248-255.10.1109/CVPR.2009.5206848
Search in Google Scholar Back to article
7. Morgan, D. A. E. Deep Convolutional Neural Networks for ATR from SAR Imagery. – In: Algorithms for Synthetic Aperture Radar Imagery XXII. Vol. 9475. 2015, p. 94750F.10.1117/12.2176558
Search in Google Scholar Back to article
8. Gao, F., T. Huang, J. Sun, J. Wang, A. Hussain, E. Yang. A New Algorithm for SAR Image Target Recognition Based on an Improved Deep Convolutional Neural Network. – Cognitive Computation, Vol. 11, 2019, No 6, pp. 809-824.10.1007/s12559-018-9563-z
Search in Google Scholar Back to article
9. Tian, Z., L. Wang, R. Zhan, J. Hu, J. Zhang. Classification via Weighted Kernel CNN: Application to SAR Target Recognition. – International Journal of Remote Sensing, Vol. 39, 2018, No 23, pp. 9249-9268.10.1080/01431161.2018.1531317
Search in Google Scholar Back to article
10. Zhang, J., M. Xing, Y. Xie. FEC: A Feature Fusion Framework for SAR Target Recognition Based on Electromagnetic Scattering Features and Deep CNN Features. – IEEE Transactions on Geoscience and Remote Sensing, Vol. 59, 2020, No 3, pp. 2174-2187.10.1109/TGRS.2020.3003264
Search in Google Scholar Back to article
11. Guo, Y., Z. Pan, M. Wang, J. Wang, W. Yang. Learning Capsules for SAR Target Recognition. – IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol. 13, 2020, pp. 4663-4673.10.1109/JSTARS.2020.3015909
Search in Google Scholar Back to article
12. Krizhevsky, A., I. Sutskever, G. E. Hinton. ImageNet Classification with Deep Convolutional Neural Networks. – Advances in Neural Information Processing Systems, Vol. 25, 2017, pp. 1097-1105.
Search in Google Scholar Back to article
13. Simonyan, K., A. Zisserman. Very Deep Convolutional Networks for Large-Scale Image Recognition. – arXiv Preprint arXiv:1409.1556, 2014.
Search in Google Scholar Back to article
14. Szegedy, C., W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, A. Rabinovich. Going Deeper with Convolutions. – In: Proc. of IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 1-9.10.1109/CVPR.2015.7298594
Search in Google Scholar Back to article
15. He, K., X. Zhang, S. Ren, J. Sun. Deep Residual Learning for Image Recognition. – In: Proc. of IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770-778.10.1109/CVPR.2016.90
Search in Google Scholar Back to article
16. Cheng, Y., D. Wang, P. Zhou, T. Zhang. A Survey of Model Compression and Acceleration for Deep Neural Networks. – arXiv Preprint arXiv:1710.09282, 2017.
Search in Google Scholar Back to article
17. Ding, X., X. Zhang, J. Han, G. Ding. RepMLP: Re-Parameterizing Convolutions into Fully-Connected Layers for Image Recognition. – arXiv Preprint arXiv:2105.01883, 2021.
Search in Google Scholar Back to article
18. Ding, X., X. Zhang, N. Ma, J. Han, G. Ding, J. Sun. RepVGG: Making VGG-style Convnets Great Again. – In: Proc. of IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 13733-13742.10.1109/CVPR46437.2021.01352
Search in Google Scholar Back to article
19. Chen, S., H. Wang, F. Xu, Y. Q. Jin. Target Classification Using the Deep Convolutional Networks for SAR Images. – IEEE Transactions on Geoscience and Remote Sensing, Vol. 54, 2016, No 8, pp. 4806-4817.10.1109/TGRS.2016.2551720
Search in Google Scholar Back to article
20. Wagner, S. A. SAR ATR by a Combination of Convolutional Neural Network and Support Vector Machines. – IEEE Transactions on Aerospace and Electronic Systems, Vol. 52, 2016, No 6, pp. 2861-2872.10.1109/TAES.2016.160061
Search in Google Scholar Back to article
21. Zhong, C., X. Mu, X. He, J. Wang, M. Zhu. SAR Target Image Classification Based on Transfer Learning and Model Compression. – IEEE Geoscience and Remote Sensing Letters, Vol. 16, 2021, No 3, pp. 412-416.10.1109/LGRS.2018.2876378
Search in Google Scholar Back to article
22. Liu, Y., F. Zhang, F. Ma, Q. Yin, Y. Zhou. Incremental Multitask SAR Target Recognition with Dominant Neuron Preservation. – In: Proc. of IEEE International Geoscience And Remote Sensing Symposium (IGARSS’20), 2020, pp. 754-757.10.1109/IGARSS39084.2020.9323212
Search in Google Scholar Back to article
23. Chen, S., R. Zhan, W. Wang, J. Zhang. Learning Slimming SAR Ship Object Detector through Network Pruning and Knowledge Distillation. – IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, No 14, pp. 1267-1282.10.1109/JSTARS.2020.3041783
Search in Google Scholar Back to article
24. Chen, H., F. Zhang, B. Tang, Q. Yin, X. Sun. Slim and Efficient Neural Network Design for Resource-Constrained SAR Target Recognition. – Remote Sensing, Vol. 10, 2018, No 10, pp. 1618.10.3390/rs10101618
Search in Google Scholar Back to article
25. Yu, M., G. Dong, H. Fan, G. Kuang. SAR Target Recognition via Local Sparse Representation of Multi-Manifold Regularized Low-Rank Approximation. – Remote Sensing, Vol. 10, 2018, No 2, pp. 211.10.3390/rs10020211
Search in Google Scholar Back to article
26. Min, R., H. Lan, Z. Cao, Z. Cui. A Gradually Distilled CNN for SAR Target Recognition. – IEEE Access, Vol. 7, 2019, pp. 42190-42200.10.1109/ACCESS.2019.2906564
Search in Google Scholar Back to article
27. Zhang, F., Y. Liu, Y. Zhou, Q. Yin, H. C. Li. A Lossless Lightweight CNN Design for SAR Target Recognition. – Remote Sensing Letters, Vol. 11, 2020, No 5, pp. 485-494.10.1080/2150704X.2020.1730472
Search in Google Scholar Back to article
28. Peng, L., M. Liu, X. Liu, L. Dong, M. Hui, Y. Zhao. SAR Image Classification Based on CNN in Real and Simulation Datasets. – In: Proc. of 9th International Conference on Graphic and Image Processing, 2018, p. 106152V.
Search in Google Scholar Back to article
29. Ding, J., B. Chen, H. Liu, M. Huang. Convolutional Neural Network with Data Augmentation for SAR Target Recognition. – IEEE Geoscience and Remote Sensing Letters, Vol. 13, 2016, No 3, pp. 364-368.10.1109/LGRS.2015.2513754
Search in Google Scholar Back to article
30. Pei, J., Y. Huang, W. Huo, Y. Zhang, J. Yang, T. S. Yeo. SAR Automatic Target Recognition Based on Multiview Deep Learning Framework. – IEEE Transactions on Geoscience and Remote Sensing, Vol. 56, 2017, No 4, pp. 2196-2210.10.1109/TGRS.2017.2776357
Search in Google Scholar Back to article
31. Yan, Y. Convolutional Neural Networks Based on Augmented Training Samples for Synthetic Aperture Radar Target Recognition. – Journal of Electronic Imaging, Vol. 27, 2018, No 2, pp. 023024.10.1117/1.JEI.27.2.023024
Search in Google Scholar Back to article
32. Wang, K., G. Zhang, H. Leung. SAR Target Recognition Based on Cross-Domain and Cross-Task Transfer Learning. – IEEE Access, Vol. 7, 2019, pp. 153391-153399.10.1109/ACCESS.2019.2948618
Search in Google Scholar Back to article
33. Malmgren-Hansen, D., A. Kusk, J. Dall, A. A. Nielsen, R. Engholm, H. Skriver. Improving SAR Automatic Target Recognition Models with Transfer Learning from Simulated Data. – IEEE Geoscience and Remote Sensing Letters, Vol. 14, 2017, No 9, pp. 1484-1488.10.1109/LGRS.2017.2717486
Search in Google Scholar Back to article
34. Wang, Z., L. Du, J. Mao, B. Liu, D. Yang. SAR Target Detection Based on SSD with Data Augmentation and Transfer Learning. – IEEE Geoscience and Remote Sensing Letters, Vol. 16, 2018, No 1, pp. 150-154.10.1109/LGRS.2018.2867242
Search in Google Scholar Back to article
35. Huang, Z., C. O. Dumitru, Z. Pan, B. Lei, M. Datcu. Classification of Large-Scale High-Resolution SAR Images with Deep Transfer Learning. – IEEE Geoscience and Remote Sensing Letters, Vol. 18, 2020, No 1, pp. 107-111.10.1109/LGRS.2020.2965558
Search in Google Scholar Back to article
36. Huang, Z., Z. Pan, B. Lei. What, Where, and How to Transfer in SAR Target Recognition Based on Deep CNNs. – IEEE Transactions on Geoscience and Remote Sensing, Vol. 58, 2019, No 4, pp. 2324-2336.10.1109/TGRS.2019.2947634
Search in Google Scholar Back to article
37. Lee, S., S. Purushwalkam, M. Cogswell, D. Crandall, D. Batra. Why M Heads Are Better Than One: Training a Diverse Ensemble of Deep Networks. – arXiv Preprint arXiv:1511.06314, 2015.
Search in Google Scholar Back to article
38. Huang, X., Q. Yang, H. Qiao. Lightweight Two-Stream Convolutional Neural Network for SAR Target Recognition. – IEEE Geoscience and Remote Sensing Letters, Vol. 18, 2020, No 4, pp. 667-671.10.1109/LGRS.2020.2983718
Search in Google Scholar Back to article
39. Hafiz, A. M., M. Hassaballah. Digit Image Recognition Using an Ensemble of One-Versus-All Deep Network Classifiers. – arXiv Preprint arXiv:2007.01192, 2020.
Search in Google Scholar Back to article
40. Polat, K., K. O. Koc. Detection of Skin Diseases from Dermoscopy Image Using the Combination of Convolutional Neural Network and One-Versus-All. – Journal of Artificial Intelligence and Systems, Vol. 2, 2020, No 1, pp. 80-97.10.33969/AIS.2020.21006
Search in Google Scholar Back to article
41. Le Cun, Y., L. Bottou, Y. Bengio, P. Haffner. Gradient-Based Learning Applied to Document Recognition. – Proceedings of the IEEE, Vol. 86, 1998, No 1, pp. 2278-2324.10.1109/5.726791
Search in Google Scholar Back to article
42. Nair, V., G. E. Hinton. Rectified Linear Units Improve Restricted Boltzmann Machines. – In: Proc. of 27th International Conference on Machine Learning (ICML’10), Haifa, Israel, 2010.
Search in Google Scholar Back to article
43. Ioffe, S., C. Szegedy. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. – In: Proc. of International Conference on Machine Learning, 2015, pp. 448-456.
Search in Google Scholar Back to article
44. Kingma, D. P., J. Ba. Adam: A Method for Stochastic Optimization. – arXiv preprint arXiv:1412.6980, 2014.
Search in Google Scholar Back to article
45. Vapnik, V. N., A. Y. Chervonenkis. On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities. – In: Measures of Complexity. Springer Cham, 2015, pp. 11-30.10.1007/978-3-319-21852-6_3
Search in Google Scholar Back to article
46. Zhang, K., W. Zuo, L. Zhang. FFDNet: Toward a Fast and Flexible Solution for CNN-Based Image Denoising. – IEEE Transactions on Image Processing, Vol. 27, 2018, No 9, pp. 4608-4622.10.1109/TIP.2018.283989129993717
Search in Google Scholar Back to article
47. Ros s, T. D., S. W. W o r r e l l, V. J. V e l t e n, J. C. M o s s i n g, M. L. B r y a n t. Standard SAR ATR Evaluation Experiments Using the MSTAR Public Release Data Set. – In: Algorithms for Synthetic Aperture Radar Imagery V. Vol. 3370. 1998, pp. 566-573.10.1117/12.321859
Search in Google Scholar Back to article
48. Feng, Z., H. Ji, L. Stankovic, J. Fan, M. Zhu. SC-SM CAM: An Efficient Visual Interpretation of CNN for SAR Images Target Recognition. – Remote Sensing, Vol. 13, 2021, No 20, pp. 4139.10.3390/rs13204139
Search in Google Scholar Back to article
49. Zhang, A., X. Yang, S. Fang, J. Ai. Region Level SAR Image Classification Using Deep Features and Spatial Constraints. – ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 163, 2020, pp. 36-48.10.1016/j.isprsjprs.2020.03.001
Search in Google Scholar Back to article

One-vs-All Convolutional Neural Networks for Synthetic Aperture Radar Target Recognition

Abstract

Paradigm

My account