LH-YOLO: A Lightweight and High-Precision SAR Ship Detection Model Based on the Improved YOLOv8n
Remote Sensing · 20.11.2024 · 16 (22) · 4340
DOI: 10.3390/rs16224340 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 20.11.2024. Verfasst von Qi Cao und 6 weiteren Autor:innen. Die Arbeit wurde bisher 36-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Aeronautical Science Foundation of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
Synthetic aperture radar is widely applied to ship detection due to generating high-resolution images under diverse weather conditions and its penetration capabilities, making SAR images a valuable data source. However, detecting multi-scale ship targets in complex backgrounds leads to issues of false positives and missed detections, posing challenges for lightweight and high-precision algorithms. There is an urgent need to improve accuracy of algorithms and their deployability. This paper introduces LH-YOLO, a YOLOv8n-based, lightweight, and high-precision SAR ship detection model. We propose a lightweight backbone network, StarNet-nano, and employ element-wise multiplication to construct a lightweight feature extraction module, LFE-C2f, for the neck of LH-YOLO. Additionally, a reused and shared convolutional detection (RSCD) head is designed using a weight sharing mechanism. These enhancements significantly reduce model size and computational demands while maintaining high precision. LH-YOLO features only 1.862 M parameters, representing a 38.1% reduction compared to YOLOv8n. It exhibits a 23.8% reduction in computational load while achieving a mAP50 of 96.6% on the HRSID dataset, which is 1.4% higher than YOLOv8n. Furthermore, it demonstrates strong generalization on the SAR-Ship-Dataset with a mAP50 of 93.8%, surpassing YOLOv8n by 0.7%. LH-YOLO is well-suited for environments with limited resources, such as embedded systems and edge computing platforms.
Förderung
- Aeronautical Science Foundation of China
- National Natural Science Foundation of China
Zitieren
APA
Cao, Q., Chen, H., Wang, S., Wang, Y., Fu, H., Chen, Z., & Liang, F. (2024). LH-YOLO: A Lightweight and High-Precision SAR Ship Detection Model Based on the Improved YOLOv8n. Remote Sensing, 16(22), 4340. https://doi.org/10.3390/rs16224340
Vancouver
Cao Q, Chen H, Wang S, Wang Y, Fu H, Chen Z, et al. LH-YOLO: A Lightweight and High-Precision SAR Ship Detection Model Based on the Improved YOLOv8n. Remote Sensing. 2024;16(22):4340. doi:10.3390/rs16224340
BibTeX
@article{Cao2024,
author = {Cao, Qi and Chen, Hang and Wang, Shang and Wang, Yongqiang and Fu, Haisheng and Chen, Zhenjiao and Liang, Feng},
title = {LH-YOLO: A Lightweight and High-Precision SAR Ship Detection Model Based on the Improved YOLOv8n},
journal = {Remote Sensing},
year = {2024},
volume = {16},
number = {22},
pages = {4340},
doi = {10.3390/rs16224340}
}
EUVIMED