| 211 | 0 | 66 |
| 下载次数 | 被引频次 | 阅读次数 |
针对合成孔径雷达(Synthetic Aperture Radar, SAR)图像采集成本高、多样性不足,影响图像解译效果的问题,在现有深度卷积生成对抗网络(Deep Convolutional Generative Adversarial Network, DCGAN)的基础上,提出了基于条件输入的DCGAN模型,实现了方位角/俯仰角/斜视角可控的SAR图像增广,完成了对现有仿真数据集的扩充。建立了SAR增广图像评价指标体系,对增广图像进行了客观的质量评估。结果表明,提出的SAR图像增广方法可以高质量地实现SAR图像多角度可控样本扩增,对于提升SAR图像角度丰富性具有积极意义。
Abstract：To address the problems of high cost and lack of diversity of Synthetic Aperture Radar( SAR) image acquisition which affect the effect of image interpretation, on the basis of existing Deep Convolutional Generative Adversarial Network( DCGAN), this paper proposed a model based on conditional DCGAN( DCGAN with conditional input) which realizes SAR image augmentation with customized azimuth/pitch/oblique angle and greatly expands the existing simulation dataset. Also, an evaluation index system of SAR augmented images is established to evaluate the quality of SAR augmented images objectively. The results show that the proposed method can successfully achieve the expansion of SAR image samples with multiple customized angles with satisfied quality and lower time cost, which is of positive significance for enhancing the diversity of SAR image angles.
[1]梅文豪.基于生成对抗网络的SAR图像增广研究及应用[D].重庆:重庆邮电大学,2023.
[2] HENRI M. Processing of Synthetic Aperture Radar(SAR)Images[M]. Hoboken:John Wiley&Sons, 2019.
[3]夏伟杰.合成孔径雷达回波仿真与图像模拟[D].南京:南京航空航天大学,2010.
[4]赖丽娜,米瑜,周龙龙,等.生成对抗网络与文本图像生成方法综述[J].计算机工程与应用,2023,59(19):21-39.
[5] GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative Adversarial Nets[C]∥NIPS’ 14:Neural Information Processing Systems. Montreal:ACM, 2014:2672-2680.
[6]石嘉晨.基于神经网络架构搜索算法的图像生成技术研究[D].南京:南京邮电大学,2023.
[7] RADFORD A, METZ L, CHINTALA S. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks[EB/OL].(2015-11-19)[2024-05-10]. https:∥arxiv. org/abs/1511. 06434.
[8]汪晶,王恺,严迎建.基于条件生成对抗网络的侧信道攻击技术研究[J].计算机工程与应用,2022,58(6):110-117.
[9]孟先新,李俊伟,韩立伟,等.基于DCGAN的手写汉字图像生成研究[J].现代计算机,2023,29(20):29-34.
[10]刘洁怡,张林让,于恒力,等.分集MIMO雷达目标回波相关性分析[J].西安电子科技大学学报,2018,45(4):69-74.
[11]李毅,杜兰,周可儿,等.基于属性散射中心卷积核调制的SAR目标识别深层网络[J].雷达学报,2024,13(2):113-156.
[12]甄勇,刘伟,陈建宏,等.高分辨率SAR图像舰船目标几何结构特征提取[J].信号处理, 2016, 32(4):424-429.
[13]项德良. SAR图像相似度评估技术研究[D].长沙:国防科学技术大学,2012.
[14] GERRY M J, POTTER L C, GUPTA I J. A Parametric Model for Synthetic Aperture Radar Measurements[J].IEEE Transactions on Antennas and Propagation, 1999,47(7):1179-1188.
[15]许延龙,潘昊,丁柏圆.基于深度信念网络的属性散射中心匹配及在SAR图像目标识别中的应用[J].液晶与显示,2023,38(11):1511-1520.
[16] LEE J Y, HUDSON R E,YAO K. Exploiting AML Algorithm for Multiple Acoustic Source 2D and 3D DOA Estimations[J]. Journal of Control Theory and Applications,2011,9:34-43.
[17] KIM T, DONG M M. An Iterative Hungarian Method to Joint Relay Selection and Resource Allocation for D2D Communications[J]. IEEE Wireless Communications Letters, 2014, 3(6):625-625.
[18]丁柏圆,文贡坚,余连生,等.属性散射中心匹配及其在SAR目标识别中的应用[J].雷达学报,2017,6(2):157-166.
基本信息:
中图分类号:TN957.52;TP183
引用信息:
[1]赵竹新,范纯卓,刘艳博,等.基于CDCGAN的SAR图像数据增广[J].无线电工程,2025,55(03):580-587.
2024-09-03
2024-09-03
2024-09-03