A novel target detection method with dual‐domain multi‐frequency feature in side‐scan sonar images
IET Image Processing · 2024-11 · 18 (13) · 4168-4188
DOI: 10.1049/ipr2.13241 ↗Kurz gefasst
Fachartikel in der Zeitschrift IET Image Processing, online erschienen am 18.09.2024. Verfasst von Wen Wang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Outstanding Youth Foundation of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
Side‐scan sonar (SSS) detection is a key method in underwater environmental security and subsea resource development. However, many detection approaches primarily concentrate on tracking the evolution path of optical image object detection tasks when using acoustic images, resulting in complex structures and limited versatility. To tackle this issue, we introduce a pioneering dual‐domain multi‐frequency network (D 2 MFNet) meticulously crafted to harness the distinct characteristics of SSS image detection. In D 2 MFNet, a novel method for optimizing and improving the detection sensitivity in different frequency ranges called multi‐frequency combined attention mechanism (MFCAM) is proposed. This mechanism amplifies the relevance of dual‐domain features across different channels and spaces. Moreover, we introduce a dual‐domain feature pyramid network (D 2 FPN) significantly augments the depth and breadth of feature information in underwater small datasets. The methods offer plug‐and‐play functionality with substantial performance enhancements. Extensive experiments are conducted to validate the efficacy of the proposed techniques, and the results showcase their state‐of‐the‐art performance. MFCAM improves the mAP by 16.9% in the KLSG dataset and 15.5% in the SCTD dataset. The mAP of D 2 FPN was improved by 8.4% in the KLSG dataset and by 9.8% in the SCTD dataset. The code and models will be publicly available at https://dagshub.com/estrellaww00/D2MFNet .
Förderung
- National Outstanding Youth Foundation of China
- National Natural Science Foundation of China
Zitieren
APA
Wang, W., Zhang, Y., Li, H., Kang, Y., Liu, L., Chen, C., & Zhai, G. (2024). A novel target detection method with dual‐domain multi‐frequency feature in side‐scan sonar images. IET Image Processing, 18(13), 4168-4188. https://doi.org/10.1049/ipr2.13241
Vancouver
Wang W, Zhang Y, Li H, Kang Y, Liu L, Chen C, et al. A novel target detection method with dual‐domain multi‐frequency feature in side‐scan sonar images. IET Image Processing. 2024;18(13):4168-4188. doi:10.1049/ipr2.13241
BibTeX
@article{Wang2024,
author = {Wang, Wen and Zhang, Yifan and Li, Houpu and Kang, Yixin and Liu, Lei and Chen, Cheng and Zhai, Guojun},
title = {A novel target detection method with dual‐domain multi‐frequency feature in side‐scan sonar images},
journal = {IET Image Processing},
year = {2024},
volume = {18},
number = {13},
pages = {4168--4188},
doi = {10.1049/ipr2.13241}
}
EUVIMED