可变形卷积与注意力的SAR舰船检测轻量化模型  

Lightweight model for SAR ship detection incorporating deformable convolution and attention mechanism

作　　者：余光浩 陈润霖 徐金燕 徐前祥 王大寒 陈峰 Yu Guanghao;Chen Runlin;Xu Jinyan;Xu Qianxiang;Wang Dahan;Chen Feng(College of Computer and Information Engineering,Xiamen University of Technology,Xiamen 361024,China;Fujian Key Laboratory of Pattern Recognition and Image Understanding,Xiamen 361024,China;Island Research Center,Ministry of Natural Resources,Pingtan 350400,China;Shenzhen Smart Cities Technology Development Group Co.,Ltd.,Shenzhen 518036,China;Big Data Institute of Digital Natural Disaster Monitoring in Fujian,Xiamen 361024,China)

机构地区：[1]厦门理工学院计算机与信息工程学院,厦门361024 [2]福建省模式识别与图像理解重点实验室,厦门361024 [3]自然资源部海岛研究中心,平潭350400 [4]深圳市智慧城市科技发展集团有限公司,深圳518036 [5]数字福建自然灾害监测大数据研究所,厦门361024

出　　处：《中国图象图形学报》2025年第3期724-736,共13页Journal of Image and Graphics

基　　金：厦门理工学院研究生科技创新计划项目(YKJCX2023063);福建省自然科学基金项目(2021J011190)。

摘　　要：目的针对合成孔径雷达(synthetic aperture radar,SAR)图像舰船检测中因背景复杂、目标尺寸各异等因素导致的漏检、误检结果,提出一种基于YOLOv8(you only look once v8)的改进算法。方法首先,轻量化处理YOLOv8的原有网络结构,大幅降低网络的冗余度,使轻量化的网络更适合SAR图像舰船检测任务。其次,在主干网络中融入可变形卷积,增强模型对目标的感知能力,能更好地适应目标形变和复杂背景;同时,在颈部网络融入卷积注意力模块,减弱背景信息的干扰,使网络更专注舰船目标的特征。最后,采用EIoU(efficient intersection over union)损失函数,最小化预测框与真实框间的差值(包括宽度和高度),实现更快的收敛速度。结果分别在SSDD(SAR ship detection dataset)和HRSID(high-resolution SAR images dataset)上进行测试,结果表明,改进算法的检测性能优于当前几种流行的目标检测算法。其中,与YOLOv8相比,在两个公开数据集上,改进算法的精度评估指标mAP(mean average precision)@0.5分别提升0.68%和1.29%,mAP@0.75分别提升3.32%和3.10%,其处理速度FPS(frames per second)分别提升22帧/s和18帧/s。结论本文在轻量化处理YOLOv8基础上融合可变形卷积与注意力机制构建的改进算法,能实现SAR舰船检测精度和速度的双重提升。Objective Synthetic aperture radar(SAR)has recently been widely used in fields such as maritime monitoring,military intelligence acquisition,and maritime management,primarily due to its capability to acquire data at any time under all weather conditions.Algorithms with better performance not only help improve ocean monitoring and navigation safety but also play a key role in areas such as maritime rescue,border security,and ocean resource management.Ship target detection methods can be divided into two categories:those based on deep learning and traditional methods.Deep learning methods offer high accuracy and strong generalization capabilities.These methods can be further classified into two categories:one-stage detection and two-stage detection.Compared to two-stage detection methods,one-stage detection methods generally achieve faster detection speeds at the expense of lower detection accuracy.One-stage detection methods,such as YOLO and single shot multibox detector(SSD),extract features through a backbone network,followed by direct classification and spatial position regression.Two-stage detection methods,such as R-CNN(region-based convolutional neural network)and Fast R-CNN,typically involve initial region generation followed by final region classification and regression.Currently,an increasing number of scholars are focusing on deep learning-based algorithms for ship target detection using SAR images.However,most of these methods have struggled to achieve an optimal balance between detection accuracy and processing efficiency.In this study,a lightweight model based on YOLOv8 was proposed to improve the performance of SAR ship detection while considering the balance between detection accuracy and efficiency.Method This study proposed a new method that substantially improved YOLOv8,called LDCE(lightweight-deformable convolution-CBAM-EIoU)-YOLOv8.The network structure of YOLOv8 was initially reconstructed to reduce network redundancy while maintaining sensitivity to ship features in SAR images.Furthermore,the

关 键 词：合成孔径雷达(SAR) 目标检测 YOLOv8 卷积注意力模块(CBAM) 可变形卷积 EIoU 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]