Quasi-Static In Situ Deep Learning for Forward-Looking Sonar Target Detection in Complex Underwater Environments
Journal of Marine Science and Engineering · 16.05.2026 · 14 (10) · 918
DOI: 10.3390/jmse14100918 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Marine Science and Engineering, online erschienen am 16.05.2026. Verfasst von Yixuan Chen und 7 weiteren Autor:innen. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Forward-looking sonar (FLS) target detection is essential for autonomous underwater vehicles (AUVs), yet its effectiveness is severely hindered by complex acoustic distortions, environmental volatility and the scarcity of fine-annotated data, which limit the success of standard deep learning approaches. To address these challenges, this study proposes a novel quasi-static in situ learning paradigm for underwater acoustic target detection (UATD). The hybrid methodology integrates scene priors into a lightweight deep learning detector by incorporating explicit probability weighting based on echo-intensity statistics and acoustic attenuation compensation. By using these models for pixel-wise image enhancement and fusing statistical descriptors with deep learning predictions at the score level, the framework dynamically adapts to in situ environmental contexts during quasi-static operational tranches. Experimental evaluations on the UATD dataset demonstrate that this in situ adaptation significantly enhances overall detection performance, achieving an F1-score of 0.865 for our approach, an 8.1% improvement over the baseline YOLOv12n, with only a 2.1 G increase in FLOPs, while outperforming YOLOv12x (F1 = 0.844) with 95% fewer FLOPs. Ultimately, this paradigm overcomes the limitations of purely deep learning-based methods, offering a robust and interpretable solution tailored for practical AUV deployment.
Zitieren
APA
Chen, Y., Ding, Z., Feng, Y., He, J., Xie, Z., Xiong, T., Chen, K., & Gao, Q. (2026). Quasi-Static In Situ Deep Learning for Forward-Looking Sonar Target Detection in Complex Underwater Environments. Journal of Marine Science and Engineering, 14(10), 918. https://doi.org/10.3390/jmse14100918
Vancouver
Chen Y, Ding Z, Feng Y, He J, Xie Z, Xiong T, et al. Quasi-Static In Situ Deep Learning for Forward-Looking Sonar Target Detection in Complex Underwater Environments. Journal of Marine Science and Engineering. 2026;14(10):918. doi:10.3390/jmse14100918
BibTeX
@article{Chen2026,
author = {Chen, Yixuan and Ding, Zhenqing and Feng, Yu and He, Jiale and Xie, Ziqin and Xiong, Tinggang and Chen, Kai and Gao, Qi},
title = {Quasi-Static In Situ Deep Learning for Forward-Looking Sonar Target Detection in Complex Underwater Environments},
journal = {Journal of Marine Science and Engineering},
year = {2026},
volume = {14},
number = {10},
pages = {918},
doi = {10.3390/jmse14100918}
}
EUVIMED