Label Self-Supervised Ship Detection Training Method on One-Bit Non-Reconstructed SAR Images
Remote Sensing · 30.10.2026 · 18 (21) · 3748
DOI: 10.3390/rs18213748 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 30.10.2026. Verfasst von Can Su und 8 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, Wuyi University Hong Kong and Macao Joint Research and Development Fund.
Abstract (Originalsprache)
One-bit quantization technology effectively simplifies the hardware architecture of synthetic aperture radar (SAR) and significantly reduces the volume of echo data, making it a pivotal research direction in spaceborne SAR systems. However, the high computational cost and latency associated with one-bit SAR signal reconstruction have limited the efficiency of downstream target detection applications. To address the demand for efficient ship target detection in one-bit SAR imagery, a label self-supervised ship detection training method on one-bit non-reconstructed SAR images is proposed in this paper, which enables generic deep learning models to perform detection directly in one-bit SAR images based on the chirp scaling algorithm (CSA) without signal recovery during inference. First, a training framework based on curriculum learning is designed, aiming to discriminate between real ship targets and false targets. Second, a one-bit reconstruction and training label self-supervised correction branch is incorporated into the training framework to autonomously generate false target labels and progressively guide the model to learn false target features. Third, a one-bit non-reconstructed image dataset is proposed to validate the trained model, which maps only reliable ship target annotations from full-precision echo imaging results. Finally, experiments conducted on real SAR data demonstrate that the detection model derived from the proposed training method can directly detect ship targets in the non-reconstructed images. Compared with the classic “reconstruction-and-detection” workflow, the trained model runs inference, bypassing the reconstruction process, and achieves a 20-fold improvement in efficiency without compromising detection accuracy. This method provides a practical solution for the rapid acquisition of target information in large-scale ship monitoring using one-bit SAR.
Förderung
- National Key Research and Development Program of China
- Wuyi University Hong Kong and Macao Joint Research and Development Fund
Zitieren
APA
Su, C., Yang, W., Zeng, H., An, X., Jiang, D., Wen, Z., Zhai, Y., Tian, X., & Chen, J. (2026). Label Self-Supervised Ship Detection Training Method on One-Bit Non-Reconstructed SAR Images. Remote Sensing, 18(21), 3748. https://doi.org/10.3390/rs18213748
Vancouver
Su C, Yang W, Zeng H, An X, Jiang D, Wen Z, et al. Label Self-Supervised Ship Detection Training Method on One-Bit Non-Reconstructed SAR Images. Remote Sensing. 2026;18(21):3748. doi:10.3390/rs18213748
BibTeX
@article{Su2026,
author = {Su, Can and Yang, Wei and Zeng, Hongcheng and An, Xinwei and Jiang, Danni and Wen, Zhengqi and Zhai, Yikui and Tian, Xiaolin and Chen, Jie},
title = {Label Self-Supervised Ship Detection Training Method on One-Bit Non-Reconstructed SAR Images},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {21},
pages = {3748},
doi = {10.3390/rs18213748}
}
EUVIMED