基于改进YOLOv8的船舰遥感图像旋转目标检测算法  

Rotating target detection algorithm in ship remote sensing images based on YOLOv8

作　　者：牛为华[1,2] 郭迅 NIU Weihua;GUO Xun(Department of Computer Science,North China Electric Power University,Baoding Hebei 071003,China;Engineering Research Center of Intelligent Computing for Complex Energy System,Ministry of Education,Baoding Hebei 071003,China)

机构地区：[1]华北电力大学计算机系,河北保定071003 [2]复杂能源系统与智能计算教育部工程研究中心,河北保定071003

出　　处：《图学学报》2024年第4期726-735,共10页Journal of Graphics

摘　　要：针对船舰遥感目标图像检测中存在的小目标检测困难,船舰形状各异以及传统水平边界框对于高长宽比的目标所框选冗余信息较多的问题,提出了一种基于改进YOLOv8的船舰遥感图像旋转目标检测算法。通过改进主干网络中的卷积结构,缓解了由于跨步卷积所导致的细粒度信息丢失的问题,对于小目标检测的精度有所提升;将C2f中的部分卷积模块替换为DCNv3可变形卷积,使其可以更好提取不规则物体的特征信息,提高模型的非线性建模能力;在颈部网络中融入主干网络中的浅层特征信息,缓解了经多次卷积操作所导致的细节信息丢失的问题,提升了模型对小目标物体的检测能力。实验结果表明,改进后的算法在ShipRSImageNet数据集上的检测精度(mAP50)达到了84.317%,较基准模型提升了4.054%,在HRSC2016数据集上达到了93.235%,较基准模型提升了1.555%,在少量增加模型参数量的情况下取得了较高的检测性能,很好地平衡了模型的效率和性能。Aiming at the problems of difficulty in detecting small targets in ship remote sensing target image detection,varied ship shapes,and excessive redundant information in traditional horizontal bounding boxes for targets with high aspect ratios,a rotating target detection algorithm for ship remote sensing images based on an improved YOLOv8 was proposed.By improving the convolution structure in the backbone network,the problem of fine-grained information loss caused by stride convolution was alleviated,improving the accuracy of small target detection.By replacing some of the convolution modules in C2f with DCNv3 deformable convolution,the feature information extraction of irregular objects was enhanced,improving the nonlinear modeling capabilities of the model.Integrating the shallow feature map from the backbone network into the neck alleviated the problem of detailed information loss caused by multiple convolution operations,enhancing the detection capability for small target objects.Experimental results showed that the detection accuracy(mAP50)of the improved algorithm on the ShipRSImageNet dataset reached 84.317%,which is 4.054%higher than the baseline model.The model accuracy reached 93.235%on the HRSC2016 dataset,which is 1.555%higher than the baseline model.The improved algorithm achieved high detection performance with a small increase in the number of model parameters,effectively balancing model efficiency and performance.

关 键 词：YOLOv8 旋转目标检测 可变形卷积 特征融合 深度学习 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] TP751[自动化与计算机技术—计算机科学与技术] U675[交通运输工程—船舶及航道工程]