计算机工程与应用 ›› 2024, Vol. 60 ›› Issue (16): 248-257.DOI: 10.3778/j.issn.1002-8331.2403-0217

• 图形图像处理 • 上一篇    下一篇

改进YOLOv8的轻量级光学遥感图像船舶目标检测算法

杨志渊,罗亮,吴天阳,于博向   

  1. 1.武汉理工大学 三亚科教创新园,海南 三亚 572000
    2.高性能船舶技术教育部重点实验室,武汉 430063
    3.武汉理工大学 船海与能源动力工程学院,武汉 430063
  • 出版日期:2024-08-15 发布日期:2024-08-15

Improved Lightweight Ship Target Detection Algorithm for Optical Remote Sensing Images with YOLOv8

YANG Zhiyuan, LUO Liang, WU Tianyang, YU Boxiang   

  1. 1.Sanya Science and Education Innovation Park, Wuhan University of Technology, Sanya, Hainan 572000, China
    2.Key Laboratory of High Performance Ship Technology, Ministry of Education, Wuhan 430063, China
    3.School of Naval Architecture Ocean and Energy Power Engineering, Wuhan University of Technology, Wuhan 430063, China
  • Online:2024-08-15 Published:2024-08-15

摘要: 针对现有基于深度学习的轻量级目标检测算法,在应用于光学遥感图像船舶目标检测任务时所面临的精度低、检测速度慢的情况,提出一种基于YOLOv8s的轻量级光学遥感图像船舶目标检测算法。引入一种新的轻量级非对称检测头,使模型在复杂背景中更加关注船舶对象;主干网络融合选择注意力模块,通过动态调整特征提取主干的感受野来提高目标检测的性能;引入Slim-FPN的思想来改进颈部,在保持检测精度的同时减少参数数量;设计快速卷积模块FasterConv,基于此重构C2f中的Bottleneck结构,命名为Faster_C2f,增强了网络的特征提取能力。实验结果表明,改进的算法在保证检测速度的同时取得了95.2%的检测精度,比基线模型提高1.4%,每秒检测帧数提高8%,模型参数减少33%,较主流算法在检测效果上有一定的提升。

关键词: YOLOv8, 遥感图像, 非对称检测头, 注意力模块, 特征提取

Abstract: Aiming at the low accuracy and slow detection speed faced by existing deep learning-based lightweight target detection algorithms when they are applied to the task of detecting ship targets in optical remote sensing images, a lightweight ship target detection algorithm based on YOLOv8s is proposed for optical remote sensing images. A new lightweight asymmetric detection head is introduced to make the model pay more attention to ship targets in complex backgrounds. The backbone network fusion selects an attention module to improve the performance of target detection by dynamically adjusting the sensing field of the feature extraction backbone. The idea of Slim-FPN is introduced to improve the neck part, which reduces the number of parameters while maintaining the detection accuracy. A new fast convolutional module FasterConv is designed, based on which, the bottleneck structure in C2f is reconstructed and named Faster_C2f, which enhances the feature extraction ability of the network. The experimental results show that the improved algorithm achieves a detection accuracy of 95.2% while ensuring the detection speed, which is 1.4% higher than the baseline model, the number of detected frames per second is increased by 8%, and the model parameters are reduced by 33%, which is a certain improvement over the mainstream algorithms in terms of detection effect.

Key words: YOLOv8, remote sensing image, asymmetric detection head, attention module, feature extraction