Synthetic Range-Doppler Map Generating with WGAN-GP: A Study on Convergence and Image Realism for Radar Data Augmentation

• Clara Reis Prata Baldansa Instituto Militar de Engenharia (IME)
• Ronaldo Ribeiro Goldschmidt Instituto Militar de Engenharia (IME)
• Julio Cesar Duarte Instituto Militar de Engenharia (IME) https://orcid.org/0000-0001-6656-1247

DOI: https://doi.org/10.5753/bresci.2026.249342

Resumo

Generating data for radar applications, such as range-Doppler maps, is often expensive and time-consuming, and available datasets are typically small, which limits the effectiveness of deep learning models and can significantly hinder performance in tasks like target classification. In this study, we analyzed the feasibility of using Generative Adversarial Networks (GANs), particularly a WGAN-GP with spectral normalization, to generate synthetic range-Doppler map images and expand data availability. Despite our efforts, the results showed that the WGAN-GP struggled to capture the dataset’s complexity, with the discriminator being excessively stronger than the generator. This imbalance led to low visual quality in the generated images and poor performance in the Geometric Score (GS) and SSIM metrics. These findings highlight the challenges of training GANs in complex scenarios and the need for more robust methodologies for future data augmentation applications in radar systems.

Palavras-chave: WGAN-GP, Spectral Normalization, Range-Doppler Maps, Radar Data Augmentation, Training Instability

Referências

de Andrade, C., Nogueira, M., Fidelis, M., Campos, L., Campos, P., Schön, P., and de Abreu Faria, T. (2023). Exploiting gan capacity to generate synthetic automotive radar data. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023), volume 4: VISAPP, pages 262–271, Lisbon, Portugal. SciTePress.

de Oliveira, M. L. L. and Bekooij, M. J. G. (2020). Generating synthetic short-range fmcw range-doppler maps using generative adversarial networks and deep convolutional autoencoders. In 2020 IEEE Radar Conference (RadarConf20), pages 1–6, Florence, Italy. IEEE.

Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., and Courville, A. (2017). Improved training of wasserstein gans. In Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS’17, page 5769–5779, Red Hook, NY, USA. Curran Associates Inc.

Gusland, D., Christiansen, J. M., Torvik, B., Fioranelli, F., Gurbuz, S. Z., and Ritchie, M. (2021). Open radar initiative: Large scale dataset for benchmarking of micro-doppler recognition algorithms. In 2021 IEEE Radar Conference (RadarConf21), pages 1–6, Atlanta, GA, USA. IEE.

He, K., Zhang, X., Ren, S., and Sun, J. (2015). Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In 2015 IEEE International Conference on Computer Vision (ICCV), pages 1026–1034, Santiago, Chile. IEEE.

Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., and Hochreiter, S. (2017). Gans trained by a two time-scale update rule converge to a local nash equilibrium. In Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS’17, page 6629–6640, Red Hook, NY, USA. Curran Associates Inc.

Holder, M., Rosenberger, P., Winner, H., D’hondt, T., Makkapati, V. P., Maier, M., Schreiber, H., Magosi, Z., Slavik, Z., Bringmann, O., and Rosenstiel, W. (2018). Measurements revealing challenges in radar sensor modeling for virtual validation of autonomous driving. In 2018 21st International Conference on Intelligent Transportation Systems (ITSC), pages 2616–2622, Maui, HI, USA. IEEE.

Ioffe, S. and Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. CoRR, abs/1502.03167:448–456.

Jiang, W., Ren, Y., Liu, Y., and Leng, J. (2022). Artificial neural networks and deep learning techniques applied to radar target detection: A review. Electronics, 11(1).

Khrulkov, V. and Oseledets, I. (2018). Geometry score: A method for comparing generative adversarial networks. In International Conference on Machine Learning.

Lee, H., Kim, J., Kim, E. K., and Kim, S. (2020). Wasserstein generative adversarial networks based data augmentation for radar data analysis. Applied Sciences, 10(4).

Luo, C., Li, X., Wang, L., He, J., Li, D., and Zhou, J. (2018). How does the data set affect cnn-based image classification performance? In 2018 5th International Conference on Systems and Informatics (ICSAI), pages 361–366, Nanjing, China. IEEE.

Miyato, T., Kataoka, T., Koyama, M., and Yoshida, Y. (2018). Spectral normalization for generative adversarial networks. In International Conference on Learning Representations, Vancouver,Canada. OpenReview.net.

Park, S., Lee, S., and Kwak, N. (2022). Range-doppler map augmentation by generative adversarial network for deep uav classification. In 2022 IEEE Radar Conference (RadarConf22), pages 1–7, New York City, NY, USA. IEEE.

Queiroz, S. S. A., Shiguemori, E. H., Augusto, C. V. S., Souza, R. P., Damore, R., and Faria, L. A. (2021). Experimental assessment of the viability of a gan model for radar data generation. In Simpósio de Aplicações Operacionais em Áreas de Defesa (SIGE), São José dos Campos - SP. SIGE.

Roldan, I., Del-Blanco, C. R., Duque de Quevedo, Á., Ibañez Urzaiz, F., Gismero Menoyo, J., Asensio López, A., Berjón, D., Jaureguizar, F., and García, N. (2020). Dopplernet: a convolutional neural network for recognising targets in real scenarios using a persistent range–doppler radar. IET Radar, Sonar & Navigation, 14(4):593–600.

Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., and Chen, X. (2016). Improved techniques for training gans. In Proceedings of the 30th International Conference on Neural Information Processing Systems, NIPS’16, page 2234–2242, Red Hook, NY, USA. Curran Associates Inc.

Singh, P., Menkudale, S., Soni, S., Tank, V. R., and Raj, A. A. B. (2025). Comprehensive survey on radar systems and its target classification techniques. Journal of Electronic and Electrical Engineering, 4(1):234–269.

Slesinski, J. and Wierzbicki, D. (2025). Review of synthetic aperture radar automatic target recognition: A dual perspective on classical and deep learning techniques. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 18:18978–19024.

Upadhyay, M., Murthy, S. K., and Raj, A. A. B. (2021). Intelligent system for real time detection and classification of aerial targets using cnn. In 2021 5th International Conference on Intelligent Computing and Control Systems (ICICCS), pages 1676–1681, Madurai, India. IEEE.

Wang, Z., Bovik, A., Sheikh, H., and Simoncelli, E. (2004). Image quality assessment: from error visibility to structural similarity. IEEE Transactions on Image Processing, 13(4):600–612.

Wang, Z., Guo, Z., Shu, G., and Li, N. (2025). Radar jamming recognition: Models, methods, and prospects. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 18:3315–3343.