The classification by medium resolution remote sensing images based on deep learning algorithm of GoogleNet model

doi:10.13474/j.cnki.11-2246.2019.0179

Abstract

Abstract:

We proposed a remote sensing classification method based on deep learning technology, which can effectively solve the problem of pixel mixing in the medium resolution images classification. The research selected the Landsat 7 ETM+ remote sensing image of Wuhan City on May 12, 2016. Based on the Inception V3 network structure in the GoogleNet model, the remote sensing image classification model was constructed by means of migration learning method, and four typical features of the main urban area of Wuhan were realized. Automatic classification of permeable layers, vegetation, water bodies and other land uses, and the classification results were compared with traditional maximum likelihood classification (ML) results. The research shows that the overall classification accuracy of remote sensing image based on deep learning method is as high as 88.33%, and the Kappa coefficient is 0.834 2, which is obviously better than the traditional classification accuracy of 83% and Kappa coefficient of 0.755 0, and it effectively suppresses the phenomenon of pixel mis-or leakage in the classification process.

Key words: spatial resolution, deep learning, remote sensing classification, GoogleNet

CLC Number:

P237

CHEN Bin, WANG Hongzhi, XU Xinliang, WANG Shoutai, ZHANG Yaqing. The classification by medium resolution remote sensing images based on deep learning algorithm of GoogleNet model[J]. 测绘通报, 2019, 0(6): 29-33,40.

References

[1] 徐佳, 袁春琦, 程圆娥, 等. 基于主动深度学习的极化SAR图像分类[J]. 国土资源遥感, 2018, 30(1):72-77.
[2] 高常鑫, 桑农. 基于深度学习的高分辨率遥感影像目标检测[J]. 测绘通报, 2014(S1):108-111.
[3] 石祥滨, 房雪键, 张德园, 等. 基于深度学习混合模型迁移学习的图像分类[J]. 系统仿真学报, 2016, 28(1):167-173.
[4] 郑胤, 陈权崎, 章毓晋. 深度学习及其在目标和行为识别中的新进展[J]. 中国图象图形学报, 2014, 19(2):175-184.
[5] 陈星沅, 姜文博, 张培楠. 深度学习和机器学习及模式识别的研究[J]. 科技资讯, 2015, 13(31):12-13.
[6] LEE H, PHAM P, LARGMAN Y, et al. Unsupervised feature learning for audio classification using convolutional deep belief networks[C]//Advances in Neural Information Processing Systems. Cam-bridge:MIT Press, 2009:1096-1104.
[7] HAMEL P, ECK D. Learning features from music audio with deep belief networks[C]//Proceedings of the 11th International Society for Music Information Retrieval Conference.[S.l.]:IEEE, 2010:339-344.
[8] 翟剑锋. 深度学习在自然语言处理中的应用[J]. 电脑编程技巧与维护, 2013(18):74-76.
[9] LeCUN Y,CHOPRA S,RANZATO M,et al. Energy-based models in document recognition and computer vision[C]//Proceedings of the 9th International Conference on Document Analysis and Recognition. New York:New York University, 2007:337-341.
[10] 奚雪峰, 周国栋. 面向自然语言处理的深度学习研究[J]. 自动化学报, 2016, 42(10):1445-1465.
[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):1530-1537.
[12] 龚健雅, 钟燕飞. 光学遥感影像智能化处理研究进展[J]. 遥感学报, 2016, 20(5):733-747.
[13] 金永涛, 杨秀峰, 高涛, 等.基于面向对象与深度学习的典型地物提取[J]. 国土资源遥感, 2018, 30(1):22-29.
[14] 范大昭, 董杨, 张永生. 卫星影像匹配的深度卷积神经网络方法[J]. 测绘学报, 2018, 47(6):844-853.
[15] 刘大伟, 韩玲, 韩晓勇. 基于深度学习的高分辨率遥感影像分类研究[J]. 光学学报, 2016, 36(4):306-314.
[16] 陈趁新, 胡昌苗, 霍连志, 等. Landsat TM数据不同辐射校正方法对土地覆盖遥感分类的影响[J]. 遥感学报, 2014, 18(2):320-334.
[17] 张树清, 陈春, 万恩璞. 三江平原湿地遥感分类模式研究[J]. 遥感技术与应用, 1999(1):54-58.
[18] 刘娟, 蔡演军, 王瑾.青海湖流域土壤遥感分类[J]. 国土资源遥感, 2014, 26(1):57-62.
[19] BAATZ M, SCHAPE A. Multi-resolution segmentation:an optimization approach for high quality multiscale image segmentation[R]. Heidelberg:[s.n.], 2000.
[20] 程乾, 陈金凤. 基于高分1号杭州湾南岸滨海陆地土地覆盖信息提取方法研究[J]. 自然资源学报, 2015, 30(2):350-360.
[21] 宋晓阳, 姜小三, 江东, 等. 基于面向对象的高分影像分类研究[J]. 遥感技术与应用, 2015, 30(1):99-105.
[22] ZHAN Q M, MOLENAAR M, TEMPFLI K, et al. Quality assessment for geo-spatial objects derived from remotely sensed data[J]. International Journal of Remote Sensing, 2005, 26(14):2953-2974.