{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T16:11:53Z","timestamp":1774627913630,"version":"3.50.1"},"reference-count":61,"publisher":"MDPI AG","issue":"22","license":[{"start":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T00:00:00Z","timestamp":1668038400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004488","name":"Croatian Science Foundation","doi-asserted-by":"publisher","award":["IP-2019-04-1064"],"award-info":[{"award-number":["IP-2019-04-1064"]}],"id":[{"id":"10.13039\/501100004488","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>The availability of low-cost microwave components today enables the development of various high-frequency sensors and radars, including Ground-based Synthetic Aperture Radar (GBSAR) systems. Similar to optical images, radar images generated by applying a reconstruction algorithm on raw GBSAR data can also be used in object classification. The reconstruction algorithm provides an interpretable representation of the observed scene, but may also negatively influence the integrity of obtained raw data due to applied approximations. In order to quantify this effect, we compare the results of a conventional computer vision architecture, ResNet18, trained on reconstructed images versus one trained on raw data. In this process, we focus on the task of multi-label classification and describe the crucial architectural modifications that are necessary to process raw data successfully. The experiments are performed on a novel multi-object dataset RealSAR obtained using a newly developed 24 GHz (GBSAR) system where the radar images in the dataset are reconstructed using the Omega-k algorithm applied to raw data. Experimental results show that the model trained on raw data consistently outperforms the image-based model. We provide a thorough analysis of both approaches across hyperparameters related to model pretraining and the size of the training dataset. This, in conclusion, shows how processing raw data provides overall better classification accuracy, it is inherently faster since there is no need for image reconstruction and it is therefore useful tool in industrial GBSAR applications where processing speed is critical.<\/jats:p>","DOI":"10.3390\/rs14225673","type":"journal-article","created":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T21:33:02Z","timestamp":1668115982000},"page":"5673","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Deep Learning Approach for Object Classification on Raw and Reconstructed GBSAR Data"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7509-1013","authenticated-orcid":false,"given":"Marin","family":"Ka\u010dan","sequence":"first","affiliation":[{"name":"Faculty of Electrical Engineering and Computing, University of Zagreb, Unska 3, 10000 Zagreb, Croatia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3978-1716","authenticated-orcid":false,"given":"Filip","family":"Tur\u010dinovi\u0107","sequence":"additional","affiliation":[{"name":"Faculty of Electrical Engineering and Computing, University of Zagreb, Unska 3, 10000 Zagreb, Croatia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9969-1849","authenticated-orcid":false,"given":"Dario","family":"Bojanjac","sequence":"additional","affiliation":[{"name":"Faculty of Electrical Engineering and Computing, University of Zagreb, Unska 3, 10000 Zagreb, Croatia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8065-7376","authenticated-orcid":false,"given":"Marko","family":"Bosiljevac","sequence":"additional","affiliation":[{"name":"Faculty of Electrical Engineering and Computing, University of Zagreb, Unska 3, 10000 Zagreb, Croatia"}]}],"member":"1968","published-online":{"date-parts":[[2022,11,10]]},"reference":[{"key":"ref_1","unstructured":"Copernicus Space Component Mission Management Team (2022, July 23). Sentinel High Level Operations Plan (HLOP). Available online: https:\/\/sentinels.copernicus.eu\/documents\/247904\/685154\/Sentinel+HLOP+-+Issue+3.1+-+16+Dec+2021.pdf."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Liu, B., He, K., Han, M., Hu, X., Ma, G., and Wu, M. (2021). Application of UAV and GB-SAR in Mechanism Research and Monitoring of Zhonghaicun Landslide in Southwest China. Remote Sens., 13.","DOI":"10.3390\/rs13091653"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Izumi, Y., Zou, L., Kikuta, K., and Sato, M. (August, January 28). Anomalous Atmospheric Phase Screen Compensation in Ground-Based SAR over Mountainous Area. Proceedings of the IGARSS 2019\u20142019 IEEE International Geoscience and Remote Sensing Symposium, Yokohama, Japan.","DOI":"10.1109\/IGARSS.2019.8898647"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Chet, K.V., Siong, L.C., Hsin, W.H.H., Wei, L.L., Guey, C.W., Yam, C.M., Sze, L.T., and Kit, C.Y. (2015, January 1\u20134). Ku-band ground-based SAR experiments for surface deformation monitoring. Proceedings of the 2015 IEEE 5th Asia-Pacific Conference on Synthetic Aperture Radar (APSAR), Singapore.","DOI":"10.1109\/APSAR.2015.7306288"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"14441","DOI":"10.1007\/s00521-021-06084-6","article-title":"A deep learning approach using graph convolutional networks for slope deformation prediction based on time-series displacement data","volume":"33","author":"Ma","year":"2021","journal-title":"Neural Comput. Appl."},{"key":"ref_6","unstructured":"Sassa, K., Fukuoka, H., Wang, F., and Wang, G. (2005). On the Use of Ground-Based SAR Interferometry for Slope Failure Early Warning: The Cortenova Rock Slide (Italy). Landslides: Risk Analysis and Sustainable Disaster Management, Springer."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"3948","DOI":"10.1109\/TGRS.2008.2001387","article-title":"A GB-SAR Processor for Snow Avalanche Identification","volume":"46","year":"2008","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Miccinesi, L., Consumi, T., Beni, A., and Pieraccini, M. (2021). W-band MIMO GB-SAR for Bridge Testing\/Monitoring. Electronics, 10.","DOI":"10.3390\/electronics10182261"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"123287","DOI":"10.1109\/ACCESS.2020.3005343","article-title":"Dam Structure Deformation Monitoring by GB-InSAR Approach","volume":"8","author":"Qiu","year":"2020","journal-title":"IEEE Access"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Du, S., Feng, G., Wang, J., Feng, S., Malekian, R., and Li, Z. (2019). A New Machine-Learning Prediction Model for Slope Deformation of an Open-Pit Mine: An Evaluation of Field Data. Energies, 12.","DOI":"10.3390\/en12071288"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Kang, M.K., Kim, K.E., Cho, S.J., Lee, H., and Lee, J.H. (2011, January 24\u201329). Wishart supervised classification results of C-band polarimetric GB-SAR image data. Proceedings of the 2011 IEEE International Geoscience and Remote Sensing Symposium, Vancouver, BC, Canada.","DOI":"10.1109\/IGARSS.2011.6049164"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"10213","DOI":"10.1109\/JSTARS.2021.3116979","article-title":"SAR Target Classification Based on Integration of ASC Parts Model and Deep Learning Algorithm","volume":"14","author":"Feng","year":"2021","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1016\/j.neucom.2013.01.033","article-title":"Decision fusion of sparse representation and support vector machine for SAR image target recognition","volume":"113","author":"Liu","year":"2013","journal-title":"Neurocomputing"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Huang, Z., Pan, Z., and Lei, B. (2017). Transfer Learning with Deep Convolutional Neural Network for SAR Target Classification with Limited Labeled Data. Remote Sens., 9.","DOI":"10.3390\/rs9090907"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"4806","DOI":"10.1109\/TGRS.2016.2551720","article-title":"Target Classification Using the Deep Convolutional Networks for SAR Images","volume":"54","author":"Chen","year":"2016","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_16","first-page":"1","article-title":"EFTL: Complex Convolutional Networks With Electromagnetic Feature Transfer Learning for SAR Target Recognition","volume":"60","author":"Liu","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2174","DOI":"10.1109\/TGRS.2020.3003264","article-title":"FEC: A Feature Fusion Framework for SAR Target Recognition Based on Electromagnetic Scattering Features and Deep CNN Features","volume":"59","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2196","DOI":"10.1109\/TGRS.2017.2776357","article-title":"SAR Automatic Target Recognition Based on Multiview Deep Learning Framework","volume":"56","author":"Pei","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2861","DOI":"10.1109\/TAES.2016.160061","article-title":"SAR ATR by a combination of convolutional neural network and support vector machines","volume":"52","author":"Wagner","year":"2016","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"ref_20","first-page":"143","article-title":"Ship Detection in SAR images Based on Generative Adversarial Network and Online Hard Examples Mining","volume":"41","author":"Li","year":"2019","journal-title":"Dianzi Yu Xinxi Xuebao\/J. Electron. Inf. Technol."},{"key":"ref_21","first-page":"1953","article-title":"Ship detection in SAR images based on convolutional neural network","volume":"40","author":"Li","year":"2018","journal-title":"Xi Tong Gong Cheng Yu Dian Zi Ji Shu\/Syst. Eng. Electron."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Zhang, T., and Zhang, X. (2019). High-Speed Ship Detection in SAR Images Based on a Grid Convolutional Neural Network. Remote Sens., 11.","DOI":"10.3390\/rs11101206"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Li, J., Qu, C., and Shao, J. (2017, January 13\u201314). Ship detection in SAR images based on an improved faster R-CNN. Proceedings of the 2017 SAR in Big Data Era: Models, Methods and Applications (BIGSARDATA), Beijing, China.","DOI":"10.1109\/BIGSARDATA.2017.8124934"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Xia, R., Chen, J., Huang, Z., Wan, H., Wu, B., Sun, L., Yao, B., Xiang, H., and Xing, M. (2022). CRTransSar: A Visual Transformer Based on Contextual Joint Representation Learning for SAR Ship Detection. Remote Sens., 14.","DOI":"10.3390\/rs14061488"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Koyama, C.N., and Sato, M. (2015, January 27\u201330). Detection and classfication of subsurface objects by polarimetric radar imaging. Proceedings of the 2015 IEEE Radar Conference, Johannesburg, South Africa.","DOI":"10.1109\/RadarConf.2015.7411924"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1227","DOI":"10.1007\/s10762-012-9938-2","article-title":"Millimeter-wave Ground-based Synthetic Aperture Radar Imaging for Foreign Object Debris Detection: Experimental Studies at Short Ranges","volume":"33","author":"Yigit","year":"2012","journal-title":"J. Infrared Millim. Terahertz Waves"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Zhang, T., Zhang, X., Ke, X., Zhan, X., Shi, J., Wei, S., Pan, D., Li, J., Su, H., and Zhou, Y. (2020). LS-SSDD-v1.0: A Deep Learning Dataset Dedicated to Small Ship Detection from Large-Scale Sentinel-1 SAR Images. Remote. Sens., 12.","DOI":"10.3390\/rs12182997"},{"key":"ref_28","unstructured":"Zhang, T., and Zhang, X. (2022). A Dual-Polarization Information Guided Network for SAR Ship Classification. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"108365","DOI":"10.1016\/j.patcog.2021.108365","article-title":"A polarization fusion network with geometric feature embedding for SAR ship classification","volume":"123","author":"Zhang","year":"2022","journal-title":"Pattern Recognit."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1016\/j.isprsjprs.2021.10.010","article-title":"Balance learning for ship detection from synthetic aperture radar remote sensing imagery","volume":"182","author":"Zhang","year":"2021","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Zhang, T., and Zhang, X. (2022). A Mask Attention Interaction and Scale Enhancement Network for SAR Ship Instance Segmentation. arXiv.","DOI":"10.1109\/IGARSS46834.2022.9884709"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Zhang, T., and Zhang, X. (2022). HTC+ for SAR Ship Instance Segmentation. Remote Sens., 14.","DOI":"10.3390\/rs14102395"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","article-title":"Deep learning in neural networks: An overview","volume":"61","author":"Schmidhuber","year":"2015","journal-title":"Neural Netw."},{"key":"ref_34","first-page":"1","article-title":"Deep Learning of Representations: Looking Forward","volume":"Volume 7978","author":"Dediu","year":"2013","journal-title":"SLSP 2013: Statistical Language and Speech Processing, Proceedings of the First International Conference, SLSP 2013, Tarragona, Spain, 29\u201331 July 2013"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Am\u00e9zaga, A., L\u00f3pez-Mart\u00ednez, C., and Jov\u00e9, R. (2021, January 11\u201316). A Multi-Frequency FMCW GBSAR: System Description and First Results. Proceedings of the 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, Brussels, Belgium.","DOI":"10.1109\/IGARSS47720.2021.9554489"},{"key":"ref_36","unstructured":"Jankiraman, M. (2018). FMCW Radar Design, Artech House."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Guo, S., and Dong, X. (2016, January 6\u201310). Modified Omega-K algorithm for ground-based FMCW SAR imaging. Proceedings of the 2016 IEEE 13th International Conference on Signal Processing (ICSP), Chengdu, China.","DOI":"10.1109\/ICSP.2016.7878107"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Cruz, H., V\u00e9stias, M., Monteiro, J., Neto, H., and Duarte, R.P. (2022). A Review of Synthetic-Aperture Radar Image Formation Algorithms and Implementations: A Computational Perspective. Remote Sens., 14.","DOI":"10.3390\/rs14051258"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1060","DOI":"10.1109\/IGARSS.2005.1525297","article-title":"An Omega-K algorithm for SAR bistatic systems","volume":"Volume 2","author":"Giroux","year":"2005","journal-title":"Proceedings of the 2005 IEEE International Geoscience and Remote Sensing Symposium, IGARSS\u201905"},{"key":"ref_40","unstructured":"Hamasaki, T., Ferro-Famil, L., Pottier, E., and Sato, M. (2005, January 3\u20134). Applications of polarimetric interferometric ground-based SAR (GB-SAR) system to environment monitoring and disaster prevention. Proceedings of the European Radar Conference 2005\u2014EURAD 2005, Paris, France."},{"key":"ref_41","unstructured":"Innosent (2022, July 19). Radar Sensor IVS-362. Available online: https:\/\/www.innosent.de\/en\/radarsensoren\/ivs-series\/ivs-362\/."},{"key":"ref_42","unstructured":"RSHub FER (2022, July 24). Omega-K Algorithm in Python. Available online: https:\/\/github.com\/filt27\/OmegaK\/blob\/main\/OmegaK.py."},{"key":"ref_43","first-page":"1833","article-title":"Permutation Tests for Studying Classifier Performance","volume":"11","author":"Ojala","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref_44","unstructured":"Zheng, A., and Casari, A. (2018). Feature Engineering for Machine Learning: Principles and Techniques for Data Scientists, O\u2019Reilly Media, Inc.. [1st ed.]."},{"key":"ref_45","first-page":"2493","article-title":"Natural Language Processing (Almost) from Scratch","volume":"12","author":"Collobert","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_47","first-page":"630","article-title":"Identity Mappings in Deep Residual Networks","volume":"Volume 9908","author":"Leibe","year":"2016","journal-title":"ECCV 2016: Computer Vision\u2014ECCV 2016, Proceedings of the 14th European Conference, Amsterdam, The Netherlands, 11\u201314 October 2016"},{"key":"ref_48","first-page":"160","article-title":"A unified architecture for natural language processing: Deep neural networks with multitask learning","volume":"Volume 307","author":"Cohen","year":"2008","journal-title":"Machine Learning, Proceedings of the Twenty-Fifth International Conference (ICML 2008), Helsinki, Finland, 5\u20139 June 2008"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","article-title":"Representation Learning: A Review and New Perspectives","volume":"35","author":"Bengio","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"1757","DOI":"10.1016\/j.patcog.2004.03.009","article-title":"Learning multi-label scene classification","volume":"37","author":"Boutell","year":"2004","journal-title":"Pattern Recognit."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Howard, A., Pang, R., Adam, H., Le, Q.V., Sandler, M., Chen, B., Wang, W., Chen, L., Tan, M., and Chu, G. (November, January 27). Searching for MobileNetV3. Proceedings of the 2019 IEEE\/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea.","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short-Term Memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3065386","article-title":"ImageNet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Commun. ACM"},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1016\/j.compbiomed.2018.03.016","article-title":"A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification","volume":"96","author":"Yildirim","year":"2018","journal-title":"Comput. Biol. Med."},{"key":"ref_55","unstructured":"Burges, C.J.C., Bottou, L., Ghahramani, Z., and Weinberger, K.Q. (2013). Distributed Representations of Words and Phrases and their Compositionality. Advances in Neural Information Processing Systems 26, Proceedings of the 27th Annual Conference on Neural Information Processing Systems 2013, Lake Tahoe, NV, USA, 5\u20138 December 2013, Curran Associates, Inc."},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Studer, L., Alberti, M., Pondenkandath, V., Goktepe, P., Kolonko, T., Fischer, A., Liwicki, M., and Ingold, R. (2019, January 20\u201325). A Comprehensive Study of ImageNet Pre-Training for Historical Document Image Analysis. Proceedings of the 2019 International Conference on Document Analysis and Recognition, ICDAR 2019, Sydney, Australia.","DOI":"10.1109\/ICDAR.2019.00120"},{"key":"ref_57","doi-asserted-by":"crossref","unstructured":"Cherti, M., and Jitsev, J. (2022, January 18\u201323). Effect of pre-training scale on intra- and inter-domain, full and few-shot transfer learning for natural and X-ray chest images. Proceedings of the International Joint Conference on Neural Networks, IJCNN 2022, Padua, Italy.","DOI":"10.1109\/IJCNN55064.2022.9892393"},{"key":"ref_58","unstructured":"Glorot, X., and Bengio, Y. (2010, January 13\u201315). Understanding the difficulty of training deep feedforward neural networks. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, AISTATS 2010, Chia Laguna Resort, Sardinia, Italy."},{"key":"ref_59","unstructured":"Fujino, A., Isozaki, H., and Suzuki, J. (2008, January 7\u201312). Multi-label Text Categorization with Model Combination based on F1-score Maximization. Proceedings of the Third International Joint Conference on Natural Language Processing, IJCNLP 2008, Hyderabad, India."},{"key":"ref_60","unstructured":"Kr\u00fcger, F. (2016). Activity, Context, and Plan Recognition with Computational Causal Behaviour Models. [Ph.D. Thesis, University of Rostock]."},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1007\/s00365-006-0663-2","article-title":"On Early Stopping in Gradient Descent Learning","volume":"26","author":"Yao","year":"2007","journal-title":"Constr. Approx."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/22\/5673\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:13:50Z","timestamp":1760145230000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/22\/5673"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,10]]},"references-count":61,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2022,11]]}},"alternative-id":["rs14225673"],"URL":"https:\/\/doi.org\/10.3390\/rs14225673","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,10]]}}}