期刊文献+

基于空间联合的红外舰船目标数据增强方法 被引量:7

Data augmentation method of infrared ship target based on spatial association
下载PDF
导出
摘要 针对红外舰船目标图像数据少、获取难度高等问题,结合图像的几何变化以及金字塔生成对抗网络的特征拟合,提出一种几何空间与特征空间联合的红外舰船目标图像数据增强方法。首先,利用基于几何空间的几何变换、混合图像及随机擦除等图像变换方法对红外舰船目标图像进行增强;然后,根据红外舰船图像特点,改进金字塔生成对抗网络(SinGAN),在生成器引入In-SE通道间注意力机制模块,增强小感受野特征表达,使其更适合用于红外舰船目标;最后,在数据集层面联合基于几何空间的几何数据变换和基于特征空间的生成对抗网络两种方法,完成对原始数据集的数据增强。结果表明:以YOLOv3、SSD、R-FCN和Faster R-CNN目标检测算法为基准模型,开展红外舰船图像数据增强仿真实验,采用增强数据训练的网络模型的舰船目标检测平均精度(mAP)均提高了10%左右,验证了所提方法在小样本红外舰船图像数据增强方面的可行性,为提高红外舰船目标检测算法提供了数据基础。 In order to solve the problems that lacking of infrared images for ship target and the difficulty of acquiring them, an improved infrared image data augmentation method with geometric space and feature space association for ship target is proposed based on the image geometry changes and feature fitting method with generative adversarial network. Firstly, the IR image of ship target was augmented by image transformation methods such as geometric transformation on geometric space, image hybridization and random erasure;Secondly, the pyramidal generative adversarial network(SinGAN) structure was improved according to the characteristics of the IR ship image, and the In-SE-Net inter-channel attention mechanism module was introduced in the generator to enhance the small sensory field feature representation, making it more suitable for the IR ship target;Finally, at the data set level, geometric data transformation based on geometric space and generative adversarial network based on feature space were combined to complete the data augmentation of the original dataset. Object detection algorithms such as YOLOv3, SSD, R-FCN and Faster R-CNN were used as benchmark models to carry out in infrared ship image data augmentation experiments. The average accuracy(mAP) of object detection were all improved by about 10% trained on the augmented data, which verified the feasibility of the proposed method on small-sample infrared ship image data augmentation. It also provides a data basis for improving object detection algorithm carried of infrared ship.
作者 黄攀 杨小冈 卢瑞涛 常振良 刘闯 Huang Pan;Yang Xiaogang;Lu Ruitao;Chang Zhenliang;Liu Chuang(College of Missile Engineering,Rocket Force Engineering University,Xi’an 710025,China;Science and Technology on Electro-Optic Control Laboratory,Luoyang 471023,China)
出处 《红外与激光工程》 EI CSCD 北大核心 2021年第12期535-544,共10页 Infrared and Laser Engineering
基金 陕西省自然科学基础研究计划(2021JQ-373) 国家自然科学基金(61806209) 航空基金(201851U8012)。
关键词 红外图像 舰船目标 生成对抗网络 数据增强 infrared image ship target generative adversarial network data augmentation
  • 相关文献

参考文献6

二级参考文献35

  • 1陈彦彤,李雨阳,陈伟楠,张献中,王俊生.基于深度语义分割的遥感图像海面舰船检测研究[J].仪器仪表学报,2020,41(1):233-240. 被引量:24
  • 2肖亮,吴慧中,汤淑春,刘扬.全天候景像匹配实时图模拟生成的建模与仿真[J].系统仿真学报,2005,17(2):378-383. 被引量:9
  • 3曹菲,杨小冈,缪栋,张云鹏.景象匹配制导基准图选定准则研究[J].计算机应用研究,2005,22(5):137-139. 被引量:15
  • 4李秋华,李吉成,沈振康.基于多尺度特征融合的红外图像小目标检测[J].系统工程与电子技术,2005,27(9):1557-1560. 被引量:8
  • 5H J Johnson. Image Registration Methods for the Synthesis and Evaluation of Anatomical Population Summaries [D]. USA: The University of Iowa, 2002.
  • 6B Zitova, J Flusser. Image Registration Methods: A Survey [J]. Image and Vision Computing (S0262-8856), 2003, 21 (3): 977-1000.
  • 7赵峰伟.景像匹配算法、性能评估及其应用[D].国防科学技术大学硕士学位论文,2002.
  • 8L Xiao, H Z Wu. Modeling and Simulation of Digital Scene Image Synthesis Using Image Intensified CCD under Different Weathers in Scene Matching Simulation System [C]// D-K Baik (Ed.): AsiaSim 2004, LNAI 3398. Berlin, Heidelberg: Springer-Verlag, 2005: 607-616.
  • 9Ni Lin. Research on algorithms for image segmentation Based on otsu theory[D]. Chongqing: College of Mathematics and Statistics of Chongqing University, 2013. (in Chinese).
  • 10Liu Yunhe. Research on IR small target detection and tracking based on attention mechanism[D]. Harbin: Harbin Engineering University, 2009. (in Chinese).

共引文献74

同被引文献65

引证文献7

二级引证文献4

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部