基于深度卷积神经网络的高分辨率遥感影像场景分类

doi:10.13474/j.cnki.11-2246.2019.0211

测绘通报 ›› 2019, Vol. 0 ›› Issue (7): 17-22.doi: 10.13474/j.cnki.11-2246.2019.0211

基于深度卷积神经网络的高分辨率遥感影像场景分类

孟庆祥, 吴玄

武汉大学遥感信息工程学院, 湖北武汉 430072

收稿日期:2018-11-13 修回日期:2019-01-03 出版日期:2019-07-25 发布日期:2019-07-31
通讯作者: 吴玄。E-mail:412079042@qq.com E-mail:412079042@qq.com
作者简介:孟庆祥(1977-),男,讲师,研究方向为图像处理。E-mail:mqx@whu.edu.cn
基金资助:
国家重点研发计划（2016YFC0803107；2016YFB052601；2017YFB0504103）；深圳市科技创新项目基础研究基金（JCYJ20170307152553273）

Scene classification of high-resolution remote sensing image based on deep convolution neural network

MENG Qingxiang, WU Xuan

School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430072, China

Received:2018-11-13 Revised:2019-01-03 Online:2019-07-25 Published:2019-07-31

摘要/Abstract

摘要： 场景分类对于高分辨率遥感影像的理解和信息提取具有重要意义。传统方法利用低、中级或语义特征来对影像的场景进行判别，但是针对高分影像涵盖的细节多、类别复杂等特点，中低层特征无法对影像语义进行准确描述。本文提出了一种基于深度卷积神经网络DCNN场景分类模型。首先利用卷积层对影像的纹理、颜色等低阶特征进行提取，然后利用池化层对重要特征进行筛选，最后将提取到的特征进行组合，形成高阶语义特征，利用高阶语义特征对高分影像进行场景分类。为了解决模型的过拟合问题，使用了数据增广、正则化及Dropout提高模型的泛化能力。本文方法在UC Merced-21取得了91.33%的准确率，相比于传统方法，有效地提高了分类精度，同时证明了深度卷积神经网络在遥感影像分类领域优越性。

关键词: 高分辨率遥感影像, 场景分类, 深度卷积神经网络, 过拟合, 特征组合

Abstract: Scene classification makes great sense to the understanding and information extraction of high-resolution remote sensing images. The traditional method has used low-level, middle-level or semantic features to distinguish the class of the image scene, but the low or middle level features can't exactly describe the image which are more detailed and complex. In this paper, a DCNN scene classification model based on deep convolution neural network is proposed. The convolution layer is used to extract the image texture, color and other low-level features firstly. Then we use the pool layer to select important features. Finally, the extracted features are merged into high-level semantic features which are used to classify the high resolution remote sensing images. To solve the problem of over fitting, data augmentation, regularization and Dropout are used to improve the generalization ability. This method has obtained 91.33% accuracies on UC Merced-21. Compared with traditional method, the classification accuracies is effectively improved. At the same time, the superiority of deep convolution neural network in remote sensing image classification is proved.

Key words: high-resolution remote sensing image, scene classification, DCNN, overfitting, feature combination

中图分类号:

P237

孟庆祥, 吴玄. 基于深度卷积神经网络的高分辨率遥感影像场景分类[J]. 测绘通报, 2019, 0(7): 17-22.

MENG Qingxiang, WU Xuan. Scene classification of high-resolution remote sensing image based on deep convolution neural network[J]. 测绘通报, 2019, 0(7): 17-22.

参考文献

[1] 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.
[2] 赵理君, 唐娉, 霍连志, 等. 图像场景分类中视觉词包模型方法综述[J]. 中国图象图形学报, 2018, 19(3):333-343.
[3] OLIVA A, TORRALBA A. Modeling the shape of the scene:a holistic representation of the spatial envelope[J]. International Journal of Computer Vision, 2001, 42(3):145-175.
[4] LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110.
[5] OKUMURA S, MAEDA N, NAKATA K, et al. Visual categorization method with a bag of PCA packed keypoints[C]//International Congress on Image and Signal Processing.[S.l.]:IEEE, 2011.
[6] HU F, XIA G S, HU J W, et al. Transferring deep convolutional neural networks for the scene classification of high-resolution remote sensing imagery[J]. Remote Sensing, 2015, 7(11):14680-14707.
[7] ZHONG Y F, ZHU Q Q, ZHANG L P. Scene classification based on the multifeature fusion probabilistic topic model for high spatial resolution remote sensing imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(11):6207-6222.
[8] KRIZHEVSKY A, SUTSKEVER I, HINTON G. Imagenet classification with deep convolutional neural networks[C]//NIPS. Lake Tahoe:ACM, 2012.
[9] 张敏, 刘利雄, 贾云得. 一种基于图像区域系综分类的室外场景理解方法[J]. 中国图象图形学报, 2018, 9(12):1443-1448.
[10] 何小飞, 邹峥嵘, 陶超, 等. 联合显著性和多层卷积神经网络的高分影像场景分类[J]. 测绘学报, 2016, 45(9):1073-1080.
[11] 李冠东, 张春菊, 王铭恺, 等. 卷积神经网络迁移的高分影像场景分类学习[BE/OL].[2018-09-03]. http://kns.cnki.net/kcms/detail/11.4415.P.20180412.1032.w2.html.
[12] LECUN Y, BENGIO Y, HINTON G. Deep learning.[J]. Nature, 2015(521):436-444.
[13] SRIVASTAVA N, HINTON G, KRIZHEVSKY A, et al. Dropout:a simple way to prevent neural networks from overfitting[J]. Journal of Machine Learning Research, 2014, 15(1):1929-1958.
[14] LIU Q, FURBER S.Noisy Softplus:a biology inspired activation function[C]//Proceedings of International Conference on Neural Information Processing.[S.l.]:Springer International Publishing, 2016.
[15] ZHOU L, ZHOU Z T, HU D W. Scene classification using a multi-resolution bag-of-features model[J]. Pattern Recognition, 2013, 46(1):424-433.
[16] SERRANO N, SAVAKIS A E, LUO J. Improved scene classification using efficient low-level features and semantic cues[J]. Pattern Recognition, 2004, 37(9):1773-1784.
[17] YANG Y, NEWSAM S.Bag-of-visual-words and spatial extensions for land-use classification[C]//Sigspatial International Conference on Advances in Geographic Information Systems. San Jose:ACM,2010.
[18] YANG Y, NEWSAM S. Spatial pyramid co-occurrence for image classification[C]//Proceedings of IEEE International Conference on Computer Vision. Barcelona:IEEE, 2011.
[19] 徐侃, 陈丽君, 杨文, 等. 利用特征选择的遥感图像场景分类[J]. 哈尔滨工业大学学报, 2011, 43(9):117-121.
[20] CHERIYADAT A M. Unsupervised feature learning for aerial scene classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2013, 52(1):439-451.
[21] HU F, XIA G S, HU J W, et al. Fast binary coding for the scene classification of high-resolution remote sensing imagery[J]. Remote Sensing, 2016, 8(7):555-567.
[22] ZHONG Y F, FEI F, ZHANG L P. Large patch convolutional neural networks for the scene classification of high spatial resolution imagery[J]. Journal of Applied Remote Sensing, 2016,10(2):025006.

基于深度卷积神经网络的高分辨率遥感影像场景分类

Scene classification of high-resolution remote sensing image based on deep convolution neural network

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]	杨俊, 刘灵辉. 加权全极化SAR图像分类下的功能区土地时空变化特征提取[J]. 测绘通报, 2022, 0(7): 138-142,153.
[2]	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.
[3]	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.
[4]	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.
[5]	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.
[6]	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.
[7]	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.
[8]	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.
[9]	王媛, 杜明义, 杨柳忠, 蔡国印, 张宁. 多源遥感数据支持下的城市生态状况评价[J]. 测绘通报, 2021, 0(11): 16-20.
[10]	迪里胡玛尔·阿汗木江, 玉素甫江·如素力. 新疆焉耆盆地土壤湿度时空分布特征[J]. 测绘通报, 2021, 0(11): 36-41.
[11]	常京新, 高贤君, 杨元维, 王双喜. 融合多时相高分影像的建筑物轮廓优化方法[J]. 测绘通报, 2020, 0(7): 112-115.
[12]	谢梦, 刘伟, 李二珠, 杨梦圆, 王晓檀. 深度卷积神经网络支持下的遥感影像语义分割[J]. 测绘通报, 2020, 0(5): 36-42.
[13]	郭云开, 许敏, 张晓炯, 刘雨玲. 结合PRO-4SAIL和BP神经网络的叶绿素含量高光谱反演[J]. 测绘通报, 2020, 0(3): 21-24.
[14]	徐世武, 曾珏, 张诗慧, 李长征, 李亭谕. 一种深度卷积神经网络土地利用场景照片的分类方法[J]. 测绘通报, 2020, 0(2): 24-28,42.
[15]	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.