SAR-LtYOLOv8:A Lightweight YOLOv8 Model for Small Object Detection in SAR Ship Images
作者机构：School of Information EngineeringShanghai Maritime UniversityShanghai201306China Shanghai Ship and Shipping Research Institute Co.Ltd.Shanghai200135China
出 版 物：《Computer Systems Science & Engineering》 (计算机系统科学与工程（英文）)
年 卷 期：2024年第48卷第6期
页 面：1723-1748页
基 金：supported by the Open Research Fund Program of State Key Laboratory of Maritime Technology and Safety in 2024 the National Natural Science Foundation of China(Grant No.52331012) the Natural Science Foundation of Shanghai(Grant No.21ZR1426500)
主 题：SAR ship detection MSCA deep learning
摘 要：The high coverage and all-weather capabilities of Synthetic Aperture Radar(SAR)image ship detection make it a widely accepted method for maritime ship positioning and ***,SAR ship detection faces challenges such as indistinct ship contours,low resolution,multi-scale features,noise,and complex background *** paper proposes a lightweight YOLOv8 model for small object detection in SAR ship images,incorporating key structures to enhance *** YOLOv8 backbone is replaced by the Slim Backbone(SB),and the Delete Medium-sized Detection Head(DMDH)structure is eliminated to concentrate on shallow *** adjusting the convolution kernel weights of the Omni-Dimensional Dynamic Convolution(ODConv)module can result in a reduction in computation and enhanced *** the model’s receptive field is done by the Large Selective Kernel Network(LSKNet)module,which captures shallow ***,a Multi-scale Spatial-Channel Attention(MSCA)module addresses multi-scale ship feature differences,enhancing feature fusion and local region *** results on the HRSID and SSDD datasets demonstrate the model’s effectiveness,with a 67.8%reduction in parameters,a 3.4%improvement in AP(average precision)@0.5,and a 5.4%improvement in AP@0.5:0.95 on the HRSID dataset,and a 0.5%improvement in AP@0.5 and 1.7%in AP@0.5:0.95 on the SSDD dataset,surpassing other state-of-the-art methods.
维普期刊数据库