首页 > 论文 > 激光与光电子学进展 > 57卷 > 20期(pp:201018--1)

基于多尺度生成对抗网络的SAR图像样本增广

Data Augmentation in SAR Images Based on Multi-Scale Generative Adversarial Networks

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对军用无人飞行器对海上重要舰船合成孔径雷达图像获取困难的问题,提出了一种从单一图像学习图像内部分布的无条件图像生成网络。该网络采用金字塔式多尺度生成对抗网络(GAN)思想,在每一层金字塔中都有一个GAN负责该尺度下图像块的生成和判别,且每个GAN具有相似的结构。生成器前端采用不同大小卷积核连接的Inception模块获取不同尺度下的图像特征,为了充分利用这些特征,加入了残差密集模块;判别器采用马尔科夫判别器的思想,捕捉不同尺度下的图像分布。将所有生成的图像制成数据集用于训练不同的目标检测算法,结果表明,训练后模型的平均精度得到了一定的提升,验证了该网络模型的有效性。

Abstract

To solve the problem that it is difficult for military unmanned aerial vehicles to acquire synthetic aperture radar images of important ships at sea, this paper introduces an unconditional image generation network which can learn the internal distribution of images from a single image. The network adopts the idea of a pyramid of multi-scale generative adversarial networks (GAN). In each layer of pyramid, there is a GAN responsible for the generation and discrimination of image blocks at this scale, and each GAN has a similar structure. The head of generator contains Inception modules connected with different sizes of convolution kernels to obtain image features at different scales. In order to make full use of these features, a residual dense block is added. The discriminator uses the idea of Markov discriminator to capture images distribution at different scales. All the generated images are made into data sets for training different target detection algorithms, the results show that the average accuracy of the model is improved to a certain extent, which verifies the effectiveness of the network model.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:TP751

DOI:10.3788/LOP57.201018

所属栏目:图像处理

基金项目:国家自然科学青年科学基金、陕西省自然科学基础研究计划;

收稿日期:2020-02-13

修改稿日期:2020-03-09

网络出版日期:2020-10-01

作者单位    点击查看

李诗怡:火箭军工程大学作战保障学院, 陕西 西安 710025北京遥感设备研究所, 北京 100854
付光远:火箭军工程大学作战保障学院, 陕西 西安 710025
崔忠马:北京遥感设备研究所, 北京 100854
杨小婷:北京遥感设备研究所, 北京 100854
汪洪桥:火箭军工程大学作战保障学院, 陕西 西安 710025
陈雨魁:北京遥感设备研究所, 北京 100854

联系人作者:李诗怡(www.ryqlm@qq.com)

备注:国家自然科学青年科学基金、陕西省自然科学基础研究计划;

【1】Wang Z W, She Q, Ward T E. Generative adversarial networks: a survey and taxonomy [2020-01-31].https:∥arxiv.[2020-01-31]. 0, org/abs/1701: 04862.

【2】Yi W, Zeng Y, Yuan Z. Fusion of GF-3 SAR and optical images based on the nonsubsampled contourlet transform [J]. Acta Optica Sinica. 2018, 38(11): 1110002.
易维, 曾湧, 原征. 基于NSCT变换的高分三号SAR与光学图像融合 [J]. 光学学报. 2018, 38(11): 1110002.

【3】Balz T, Stilla U. Hybrid GPU-based single-and double-bounce SAR simulation [J]. IEEE Transactions on Geoscience and Remote Sensing. 2009, 47(10): 3519-3529.Balz T, Stilla U. Hybrid GPU-based single-and double-bounce SAR simulation [J]. IEEE Transactions on Geoscience and Remote Sensing. 2009, 47(10): 3519-3529.

【4】Hammer H, Schulz K. Coherent simulation of SAR images [J]. Proceedings of SPIE. 2009, 7477: 74771G.

【5】Cubuk E D, Zoph B, Mané D, et al. AutoAugment: learning augmentation strategies from data . [C]∥2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 15-20, 2019, Long Beach, CA, USA. New York: IEEE. 2019, 113-123.

【6】Goodfellow I J, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets [2020-01-27].https:∥arxiv.[2020-01-27]. 0, org/abs/1406: 2661.

【7】Arjovsky M, Bottou L. Towards principled methods for training generative adversarial networks [2020-02-05].https:∥arxiv.[2020-02-05]. 0, org/abs/1701: 04862.

【8】Mirza M, Osindero S. Conditional generative adversarial nets [2020-01-30].https:∥arxiv.[2020-01-30]. 0, org/abs/1411: 1784.

【9】Chen X, Duan Y, Houthooft R, et al. InfoGAN: interpretable representation learning by information maximizing generative adversarial nets [2020-02-03].https:∥arxiv.[2020-02-03]. 0, org/abs/1606: 03657.

【10】Isola P, Zhu J Y, Zhou T H, et al. Image-to-image translation with conditional adversarial networks . [C]∥2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 21-26, 2017, Honolulu, HI, USA. New York: IEEE. 2017, 5967-5976.

【11】Zhu J Y, Park T, Isola P, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks . [C]∥2017 IEEE International Conference on Computer Vision (ICCV), October 22-29, 2017, Venice, Italy. New York: IEEE. 2017, 2242-2251.

【12】Choi Y, Choi M, Kim M, et al. StarGAN: unified generative adversarial networks for multi-domain image-to-image translation . [C]∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 18-23, 2018, Salt Lake City, UT, USA. New York: IEEE. 2018, 8789-8797.

【13】Ajocsky M, Chintala S, Bottou L. Wasserstein GAN [2020-02-04].https:∥arxiv.[2020-02-04]. 0, org/abs/1701: 07875.

【14】GulrajaniI I, Ahmed F, Arjovsky M, et al. Improved training of Wasserstein GAN[2020-01-27]. https:∥arxiv.[2020-01-27]. 0, org/abs/1704: 00028.

【15】Cui Z Y, Zhang M R, Cao Z J, et al. Image data augmentation for SAR sensor via generative adversarial nets [J]. IEEE Access. 2019, 7: 42255-42268.

【16】Shaham T R, Dekel T, Michaeli T. SinGAN: learning a generative model from a single natural image . [C]∥2019 IEEE/CVF International Conference on Computer Vision (ICCV), October 27-November 2, 2019, Seoul, Korea (South). New York: IEEE. 2019, 4569-4579.

【17】Szegedy C, Vanhoucke V, Ioffe S, et al. Rethinking the inception architecture for computer vision . [C]∥2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 27-30, 2016, Las Vegas, NV, USA. New York: IEEE. 2016, 2818-2826.

【18】Wang X T, Yu K, Wu S X, et al. ESRGAN: enhanced super-resolution generative adversarial networks [M]. ∥ Leal-Taixé L, Roth S, et al. Computer Vision -ECCV 2018. Lecture Notes in Computer Science. Cham: Springer. 2018, 11133: 63-79.

【19】Huang G. Liu Z, van der Maaten L, et al. Densely connected convolutional networks . [C]∥2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 21-26, 2017, Honolulu, HI, USA. New York: IEEE. 2017, 2261-2269.

【20】Lim B, Son S, Kim H, et al. Enhanced deep residual networks for single image super-resolution . [C]∥2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), July 21-26, 2017, Honolulu, HI, USA. New York: IEEE. 2017, 1132-1140.

【21】Szegedy C, Ioffe S, Vanhoucke V, et al. Inception-v4, inception-ResNet and the impact of residual connections on learning [2020-01-30].https:∥arxiv.[2020-01-30]. 0, org/abs/1602: 07261.

【22】Li J W, Qu C W, Peng S J, et al. Ship detection in SAR images based on generative adversarial network and online hard examples mining [J]. Journal of Electronics & Information Technology. 2019, 41(1): 143-149.
李健伟, 曲长文, 彭书娟, 等. 基于生成对抗网络和线上难例挖掘的SAR图像舰船目标检测 [J]. 电子与信息学报. 2019, 41(1): 143-149.

引用该论文

Li Shiyi,Fu Guangyuan,Cui Zhongma,Yang Xiaoting,Wang Hongqiao,Chen Yukui. Data Augmentation in SAR Images Based on Multi-Scale Generative Adversarial Networks[J]. Laser & Optoelectronics Progress, 2020, 57(20): 201018

李诗怡,付光远,崔忠马,杨小婷,汪洪桥,陈雨魁. 基于多尺度生成对抗网络的SAR图像样本增广[J]. 激光与光电子学进展, 2020, 57(20): 201018

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF