结合数据增广和迁移学习的高分辨率遥感影像场景分类

doi:10.13474/j.cnki.11-2246.2020.0041

测绘通报 ›› 2020, Vol. 0 ›› Issue (2): 37-42.doi: 10.13474/j.cnki.11-2246.2020.0041

结合数据增广和迁移学习的高分辨率遥感影像场景分类

乔婷婷, 李鲁群

上海师范大学信息与机电工程学院, 上海 201400

收稿日期:2019-09-16 修回日期:2019-12-11 出版日期:2020-02-25 发布日期:2020-03-04
通讯作者: 李鲁群。E-mail:liluqun@gmail.com E-mail:liluqun@gmail.com
作者简介:乔婷婷(1996-),女,硕士生,研究方向为遥感与深度学习。E-mail:qiaotingting1124@gmail.com
基金资助:
上海教委重点项目（304-AC9103-19-368405029）；教育部产学合作协同育人项目（309-C-6105-18-060）

Scene classification of high-resolution remote sensing image combining data augmentation and transfer learning

QIAO Tingting, LI Luqun

School of Information and Mechanical Engineering, Shanghai Normal University, Shanghai 201400, China

Received:2019-09-16 Revised:2019-12-11 Online:2020-02-25 Published:2020-03-04

摘要/Abstract

摘要： 深度学习在计算机视觉领域取得了显著的成果，如图像分类、人脸识别、图像检索等。对于遥感领域而言，获取用于训练CNN的有标签数据集通常是一个重大挑战。本文研究了如何将CNN用于高分辨率遥感影像的场景分类，为了克服缺乏大量有标签遥感影像数据集的问题，结合CNN采用了两种技术：数据增广和迁移学习。在UC Merced Land Use数据集上，验证了VGG16、VGG19、ResNet50、InceptionV3、DenseNet121等5种网络的性能，分别达到了98.10%、96.19%、99.05%、97.62%、99.52%的分类准确率。

关键词: 高分辨率遥感影像, 场景分类, 卷积神经网络, 数据增广, 迁移学习

Abstract: Deep learning has achieved remarkable results in the field of computer vision, such as image classification, face recognition, image retrieval and so on. For remote sensing, obtaining a labeled dataset for training DCNN is often a major challenge. In this paper, the use of DCNN for scene classification in high-resolution remote sensing imagery is investigated. In order to overcome the lack of a large number of labeled remote sensing image datasets, two technologieswere combined with DCNN:data augmentation and transfer learning. On the UC Merced Land Use dataset, the performances of 5 networks including VGG16, VGG19, ResNet50, InceptionV3, and DenseNet121 were verified, which achieved classification accuracy of 98.10%, 96.19%, 99.05%, 97.62%, and 99.52%, respectively.

Key words: high-resolution remote sensing imagery, scene classification, convolutional neural network, data augmentation, transfer learning

中图分类号:

P237

乔婷婷, 李鲁群. 结合数据增广和迁移学习的高分辨率遥感影像场景分类[J]. 测绘通报, 2020, 0(2): 37-42.

QIAO Tingting, LI Luqun. Scene classification of high-resolution remote sensing image combining data augmentation and transfer learning[J]. Bulletin of Surveying and Mapping, 2020, 0(2): 37-42.

参考文献

[1] 梅安新.遥感理论[M].北京:高等教育出版社,2001.
[2] 李德仁,童庆禧,李荣兴,等.高分辨率对地观测的若干前沿科学问题[J].中国科学:地球科学,2012,42(6):805-813.
[3] LOWE D G. Distinctive image features fromscale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110.
[4] DALAL N, TRIGGS B.Histograms of oriented gradients for human detection[C]//Proceedings of 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE, 2005:886-893.
[5] AVRAMOVIĆ A, RISOJEVIĆ V. Block-based semantic classification of high-resolution multispectral aerial images[J]. Signal, Image and Video Processing, 2016, 10(1):75-84.
[6] PHILBIN J, CHUM O, ISARD M, et al. Object retrieval with large vocabularies and fast spatial matching[C]//Proceedings of 2007 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway,NJ:IEEE,2007:1-8.
[7] ZHAO B, ZHONG Y, ZHANG L. A spectral-structural bag-of-features scene classifier for very high spatial resolution remote sensing imagery[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2016, 116:73-85.
[8] HINTON G E, OSINDERO S, TEH Y W. A fast learning algorithm for deep belief nets[J]. Neural computation, 2006, 18(7):1527-1554.
[9] 曲景影,孙显,高鑫.基于CNN模型的高分辨率遥感图像目标识别[J].国外电子测量技术, 2016,35(8):45-50.
[10] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11):2278-2324.
[11] 党宇,张继贤,邓喀中,等.基于深度学习AlexNet的遥感影像地表覆盖分类评价研究[J].地球信息科学学报,2017,19(11):130-137.
[12] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Imagenet classification with deep convolutional neuralnetworks[C]//Advances in Neural Information Processing Systems.Red Hook,NY:Curran Associates,2012:1097-1105.
[13] YANG Y, NEWSAM S. Bag-of-visual-words and spatial extensions for land-use classification[C]//Proceedings of the 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems. New York:ACM, 2010:270-279.
[14] PAN S J, YANG Q. A survey on transfer learning[J].IEEE Transactions on knowledge and data engineering, 2009,22(10):1345-1359.
[15] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J].arXiv preprint arXiv:1409.1556, 2014.
[16] HE K,ZHANG X,REN S, et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE, 2016:770-778.
[17] SZEGEDY C, VANHOUCKE V, IOFFE S, et al. Rethinking the inception architecture for computer vision[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE,2016:2818-2826.
[18] HUANG G, LIU Z, VAN DER MAATEN L, et al. Densely connected convolutional networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway,NJ:IEEE,2017:4700-4708.
[19] YANG Y, NEWSAM S. Spatial pyramid co-occurrence for image classification[C]//Proceedings of 2011 International Conference on Computer Vision.Piscataway,NJ:IEEE,2011:1465-1472.
[20] MARMANIS D, DATCU M, ESCH T, et al.Deep learning earth observation classification using ImageNet pretrained networks[J].IEEE Geoscience and Remote Sensing Letters, 2015,13(1):105-109.
[21] 张康,黑保琴,李盛阳,等.基于CNN模型的遥感图像复杂场景分类[J].国土资源遥感,2018, 30(4):49-55.
[22] 龚希,吴亮,谢忠,等.融合全局和局部深度特征的高分辨率遥感影像场景分类方法[J].光学学报,2019,39(3):19-29.

结合数据增广和迁移学习的高分辨率遥感影像场景分类

Scene classification of high-resolution remote sensing image combining data augmentation and transfer learning

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	柳林, 孙毅, 李万武. 基于CNN海上钻井平台检测模型的构建及训练算法分析[J]. 测绘通报, 2022, 0(7): 26-32,99.
[2]	蔡柔丹. 一种基于用户异步轨迹的身份识别智能方法[J]. 测绘通报, 2022, 0(7): 158-162,167.
[3]	滕文鑫, 张建辰, 邵杰. 集成时空邻近与卷积网络车道级高精度定位算法[J]. 测绘通报, 2022, 0(6): 1-5,61.
[4]	文奴, 郭仁忠, 贺彪, 万远. YOLO v4框架下Multi-Patch多帧增量式交通视频目标检测[J]. 测绘通报, 2022, 0(5): 38-44.
[5]	潘建平, 付占宝, 程卫华, 陆世安, 李鑫, 孙博文, 黄桂萍. 基于地表类型的山地海绵城市生态建设评估[J]. 测绘通报, 2022, 0(5): 84-88.
[6]	陈智朗, 付振华, 朱紫阳, 王慧慧, 刘沁雯, 杨钰灵, 许耿然. 基于HRNet的高分辨率遥感影像建筑物变化信息提取[J]. 测绘通报, 2022, 0(5): 126-132.
[7]	段晨阳, 冯建中, 全斌, 白林燕, 王盼盼. 利用深度学习进行GF-6影像枣园检测识别[J]. 测绘通报, 2022, 0(3): 54-59.
[8]	王胜利, 朱寿红, 蒋毅. 基于CNN模型迁移的OLI影像光伏电池板场景识别[J]. 测绘通报, 2022, 0(2): 5-9.
[9]	杨素妨, 杜林. 多特征流形鉴别嵌入的高分辨率遥感影像分类[J]. 测绘通报, 2021, 0(9): 37-42.
[10]	耿万轩, 周维勋, 金双根. 基于LDCNN特征提取的多核SVM高分辨率遥感影像场景分类[J]. 测绘通报, 2021, 0(8): 14-21.
[11]	赵恒谦, 杨屹峰, 刘泽龙, 宋瑞. 农作物叶片病害迁移学习分步识别方法[J]. 测绘通报, 2021, 0(7): 34-38.
[12]	聂倩, 七珂珂, 赵艳福. 融入超像素分割的高分辨率影像面向对象分类[J]. 测绘通报, 2021, 0(6): 44-49.
[13]	贾文翰, 刘越岩. 基于卷积神经网络的高分遥感影像内陆盐沼湿地信息提取[J]. 测绘通报, 2021, 0(6): 89-92.
[14]	段雅鸣, 张锦水, 朱爽. 基于深度卷积神经网络的云检测方法[J]. 测绘通报, 2021, 0(4): 33-39.
[15]	陈利燕, 林鸿, 吴健华. 融合随机森林和超像素分割的建筑物自动提取[J]. 测绘通报, 2021, 0(2): 49-53.