计算机工程与应用2025，Vol.61Issue(10)：185-191,7.DOI:10.3778/j.issn.1002-8331.2402-0204
基于改进DETR模型的SAR图像舰船检测方法
Ship Detection Method for SAR Images Based on Improved DETR Model
摘要
Abstract
Aiming at the slow convergence of DETR(detection transformer)in ship detection of SAR(synthetic aperture radar)images and easy omission of small and dim targets,an improved DETR based on multi-scale attention module and tag countermeasure training is proposed in this paper.The backbone network is used to extract the multi-scale feature map,construct the multi-scale attention weight matrix and feature map region sampling mode,and effectively improve the detection capability of DETR.A label antagonism training module is designed in the decoder structure to solve the repeated prediction of the target,suppress the confusion of the target preselection frame,and greatly accelerate the convergence of the model.The algorithm is tested on the HRSID dataset.The results show that mAP_0.5,mAP_0.5:0.95 and AR of 36 batches of training are 0.921,0.696 and 0.753,respectively,which are improved by 12.4%,13.3%and 14.7%compared with Faster R-CNN.The superiority of the proposed method in improving target detection accuracy and convergence speed is verified.关键词
合成孔径雷达/目标检测/DETR/多尺度注意力Key words
synthetic aperture radar/target detection/DETR/multi-scale attention分类
信息技术与安全科学引用本文复制引用
秦伟伟,迟昊,朱晓菲,秦庆强,梁卓..基于改进DETR模型的SAR图像舰船检测方法[J].计算机工程与应用,2025,61(10):185-191,7.基金项目
国家自然科学基金(61503392). （61503392）
