IMPROVING THE YOLOv11 NETWORK FOR RADIO FREQUENCY INTERFERENCE DETECTION IN SENTINEL-1A LEVEL-1 DATA

Lưu Hoàng Đạt; Nguyễn Tiến Phát; Nguyễn Minh Tuấn; Ngô Xuân Sơn; Trần Văn Ánh

doi:10.34238/tnu-jst.12082

IMPROVING THE YOLOv11 NETWORK FOR RADIO FREQUENCY INTERFERENCE DETECTION IN SENTINEL-1A LEVEL-1 DATA

About this article

Received: 18/02/25 Revised: 05/06/25 Published: 08/06/25

Authors

1. Luu Hoang Dat, Le Quy Don Technical University
2. Nguyen Tien Phat , Le Quy Don Technical University
3. Nguyen Minh Tuan, Operations Division - Department of Electronic Warfare
4. Ngo Xuan Son, Center 80 - Department of Electronic Warfare
5. Tran Van anh, Radar Institute – Military Institute of Science and Technology

Abstract

Radio frequency interference is a significant issue that affects the data quality of Sentinel-1A Level-1 satellite imagery, leading to difficulties in data analysis and application. Therefore, radio frequency interference detection and removal are crucial step in Sentinel-1A data preprocessing. This study focuses on developing an advanced detection method based on the YOLOv11 network. The YOLOv11 model is a state-of-the-art model known for its fast and accurate object detection capabilities. However, to enhance the effectiveness of radio frequency interference detection in Sentinel-1A data, this research presents an improved model by integrating Attention Module into the network architecture, namely: ECA (Efficient Channel Attention), GAM (Global Attention Mechanism), SA (Shuffle Attention), and ResCBAM (ResBlock + Convolutional Block Attention Module). The paper also constructed a high-precision, manually labeled RFI image dataset to facilitate the training and evaluation of the models. Experimental results demonstrate that the improved YOLOv11 + SA model achieves higher accuracy and faster execution speed compared to the original model.

Keywords

Radio frequency interference; Sentinel-1A Level-1; YOLOv11; Object detection; Deep Learning

Full Text:

PDF (Tiếng Việt)

References

[1] P. P. Sitompul, T. Manik, M. Batubara, and B. Suhandi, "Radio Frequency Interference Measurements for a Radio Astronomy Observatory Site in Indonesia," Aerospace, vol. 8, 2021, Art. no. 51.

[2] M. T. Gamba, B. D. Polidori, A. Minetto, F. Dovis, E. Banfi, and F. Dominici, “GNSS Radio Frequency Interference Monitoring from LEO Satellites: An In-Laboratory Prototype,” Sensors, vol. 24, 2024, Art. no. 508.

[3] X. Dong, Y. Sui, Y. Li, Z. Chen, and C. Hu, "Modeling and Analysis of RFI Impacts on Imaging between Geosynchronous SAR and Low Earth Orbit SAR," Remote Sensing, vol. 14, 2022, Art. no. 3048.

[4] W. Shen, Z. Qin, and Z. Lin, "A New Restoration Method for Radio Frequency Interference Effects on AMSR-2 over North America," Remote Sensing, vol. 11, 2019, Art. no. 2917.

[5] M.-G. Andrea, G. Davide, and R. Andrea, "Identification of C-Band Radio Frequency Interferences from Sentinel-1 Data," Remote Sensing, vol. 9, 2017, Art. no. 1183.

[6] D. Yi, F. Weiwei, Z. Zijing, Z.Feng, and L. Bingbing, "Radio Frequency Interference Mitigation for Synthetic Aperture Radar Based on the Time-Frequency Constraint Joint Low-Rank and Sparsity Properties," Remote Sensing, vol. 14, 2022, Art. no. 775.

[7] A. Recchia, N. Franceschi, A. Cotrufo, R. Piantanida, D. Giudici, and A. M. Guarnieri, "Exploiting Sentinel-1 data to assess Radio Frequency Interference impact on geosynchronous SAR," EUSAR 2021; 13th European Conference on Synthetic Aperture Radar, 2021, pp. 1-4.

[8] M. H. Same, G. Gleeton, G. Gandubert, P. Ivanov, and R. J. Landry, “Multiple Narrowband Interferences Characterization, Detection and Mitigation Using Simplified Welch Algorithm and Notch Filtering,” Applied Sciences, vol. 11, 2021, Art. no. 1331.

[9] G. Li, W. Ye, G. Lao, S. Kong, and D. Yan, "Narrowband Interference Separation for Synthetic Aperture Radar via Sensing Matrix Optimization-Based Block Sparse Bayesian Learning," Electronics, vol. 8, 2019, Art. no. 458.

[10] A. Chojka, P. Artiemjew, and J. Rapiński, “RFI Artefacts Detection in Sentinel-1 Level-1 SLC Data Based On Image Processing Techniques,” Sensors, vol. 20, 2020, Art. no. 2919.

[11] Z. Fu, H. Zhang, J. Zhao, N. Li, and F. Zheng, “A Modified 2-D Notch Filter Based on Image Segmentation for RFI Mitigation in Synthetic Aperture Radar,” Remote Sensing, vol. 15, 2023, Art. no. 846.

[12] W. Xing, W. Xu, P. Huang, W. Tan, J. Hu, and M. Zhang, "A Novel Radio Frequency Interference Suppression Method for SAR Based on Spectrum Extrapolation," Photonics & Electromagnetics Research Symposium - Fall (PIERS - Fall), 2019, pp. 1300-1305.

[13] Y. Huang, L. Zhang, J. Li, Z. Chen, and X. Yang, "Reweighted Tensor Factorization Method for SAR Narrowband and Wideband Interference Mitigation Using Smoothing Multiview Tensor Model," IEEE Transactions on Geoscience and Remote Sensing, vol. 58, pp. 3298 - 3313, 2020.

[14] H. Zhang, L. Min, J. Lu, J. Chang, Z. Guo, and N. Li, “An Improved RFI Mitigation Approach for SAR Based on Low-Rank Sparse Decomposition: From the Perspective of Useful Signal Protection,” Remote Sensing, vol. 14, 2022, Art. no. 3278.

[15] D. W. Shin, C. S. Yang, and S. J. K. Chowdhury, "Enhancement of Small Ship Detection Using Polarimetric Combination from Sentinel-1 Imagery," Remote Sensing, vol. 16, 2024, Art. no. 1198.

[16] J. Yu, J. Li, B. Sun, Y. Jiang, and L. Xu, "Multiple RFI Sources Location Method Combining Two-Dimensional ESPRIT DOA Estimation and Particle Swarm Optimization for Spaceborne SAR," Remote Sensing, vol. 13, 2021, Art. no. 1207.

[17] J. Yu, J. Li, B. Sun, J. Chen, C. Li, W. Li, and L. Xu, “Single RFI Localization Based On Conjugate Cross-Correlation Of Dual-Channel SAR Signals,” IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium, 2019, pp. 385-388.

[18] W. Fan, F. Zhou, M. Tao, X. Bai, P. Rong, S. Yang, and T. Tian, "Interference Mitigation for Synthetic Aperture Radar Based on Deep Residual Network," Remote Sensing, vol. 11, 2019, Art. no. 1654.

[19] J. Wang, T. Zheng, P. Lei, and X. Bai, "A Hierarchical Convolution Neural Network (CNN)-Based Ship Target Detection Method in Spaceborne SAR Imagery," Remote Sensing, vol. 11, 2019, Art. no. 620.

[20] A. Sharma, V. Kumar, and L. Longchamps, “Comparative performance of YOLOv8, YOLOv9, YOLOv10, YOLOv11 and Faster R-CNN models for detection of multiple weed species,” Smart Agricultural Technology, vol. 9, 2024, Art. no. 100648.

[21] C.-T. Chien, R.-Y. Ju, K.-Yi Chou, E. Xieerke, and J.-S. Chiang, “YOLOv8-AM: YOLOv8 Based on Effective Attention Mechanisms for Pediatric Wrist Fracture Detection,” International Conference on Neural Information Processing, 2024, pp. 52461-52477.

[22] NASA EarthData, “Create an RGB Composite from Multi-Temporal Sentinel-1 Data,” 2024. [Online]. Available: https://www.earthdata.nasa.gov/learn/data-recipes/create-rgb-composite-from-multi-temporal-sentinel-1-data. [Accessed February 15, 2025].

DOI: https://doi.org/10.34238/tnu-jst.12082

Refbacks

There are currently no refbacks.



Remember me