李海涛,戴莉莉,顾海燕,杨懿,韩颜顺

• 1:中国测绘科学研究院
• 2:北京四维图新科技股份有限公司

摘要(Abstract)：

针对如何选择合适尺寸的影像样本来得到较好的网络模型这一问题,该文基于全卷积神经网络(FCN)的遥感影像分类方法,开展了不同样本尺寸下的网络模型训练实验,分析了样本尺寸分别为128、256、512像素大小时对FCN网络模型的影响。结果表明:512像素×512像素大小样本尺寸下像素准确率、平均准确率、平均交叉联合度量和带权交叉联合度量4个评价指标的精度值均高于128像素×128像素和256像素×256像素大小的值,比128像素×128像素样本尺寸平均高出20%以上,比256像素×256像素样本尺寸高出10%以上,因此,在计算机内存允许范围内采用大尺寸样本进行网络模型的训练,有利于提高模型训练精度,可得到更好的分类结果。

关键词(KeyWords)： 深度学习;全卷积神经网络;训练模型;遥感影像分类

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目(41701506,41671440,41330750)

作者(Author): 李海涛,戴莉莉,顾海燕,杨懿,韩颜顺

DOI: 10.16251/j.cnki.1009-2307.2019.06.019

参考文献(References)：

• [1]BALL J E,ANDERSON D T,CHAN C S.A comprehensive survey of deep learning in remote sensing:theories,tools and challenges for the community[J].Journal of Applied Remote Sensing,2017,11(4):042609.
• [2]ZHANG L,ZHANG L,DU B.Deep learning for remote sensing data:a technical tutorial on the state of the art[J].IEEE Geoscience and Remote Sensing Magazine,2016,4(2):22-40.
• [3]CHENG G,HAN J,LU X.Remote sensing image scene classification:benchmark and state of the art[J].Proceedings of the IEEE,2017,105(10):1865-1883.
• [4]ZHU X X,TUIA D,et al.Deep learning in remote sensing:a comprehensive review and list of resources[J].IEEE Geoscience and Remote Sensing Magazine,2017,5(4):8-36.
• [5]LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2014,39(4):640-651.
• [6]ZHAO W Z,DU S H,EMERY W J.Object-based convolutional neural network for high-resolution imagery classification[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2017,10(7):1-11.
• [7]轩永仓.基于全卷积神经网络的大田复杂场景图像的语义分割研究[D].西安:西北农林科技大学,2017.(XUAN Yongcang.Research on the Semantic segmentation of complex scene image of field based on fully convolutional networks[D].Xi’an:Northwest A&FUniversity,2017.)
• [8]方旭,王光辉,杨化超,等.结合均值漂移分割与全卷积神经网络的高分辨遥感影像分类[J].激光与光电子学进展,2018(55):446-454.(FANG Xu,WANG Guanghui,YANG Huachao,et al.High resolution remote sensing image classification combining with mean-shift segmentation and fully convolution neural network[J].Laser&Optoelectronics Progress,2018(55):446-454.)
• [9]陈广胜,陈守玉,景维鹏,等.基于遗传算法与全卷积网络的遥感影像像素级分类方法[J].小型微型计算机系统,2018,39(7):1590-1595.(CHEN Guangsheng,CHEN Shouyu,JING Weipeng,et al.Remote sensing image pixel-level classification with genetic algorithm and fully convolu-tional network[J].Journal of Chinese Computer Systems,2018,39(7):1590-1595.)
• [10]SHRESTHA S,VANNESCHI L.Improved fully convolutional network with conditional random fields for building extraction[J].Remote Sensing,2018,10(7):1135.
• [11]FU G,LIU C J,ZHOU R,et al.Classification for high resolution remote sensing imagery using a fully convolutional network[J].Remote Sensing,2017,9(5):498.
• [12]MOU L,ZHU X X.Vehicle instance segmentation from aerial image and video using a multitask learning residual fully convolutional network[J].IEEE Transactions on Geoscience and Remote Sensing,2018,56(11):6699-6711.
• [13]MOU L,ZHU X X.RiFCN:Recurrent network in fully convolutional network for semantic segmentation of high resolution remote sensing images[EB/OL].(2018-05-16)[2019-02-11].https:∥arxiv.org/abs/1805.02091.
• [14]VIJAY B,ALEX K,ROBERTO C.SegNet:a deep convolutional encoder-decoder architecture for image segmentation[EB/OL].(2015-11-02)[2019-02-11].https:∥arxiv.org/abs/1511.00561.
• [15]CHEN L C,GEORGE P,IASONAS K,et al.DeepLab:semantic image segmentation with deep convolutional nets,atrous convolution,and fully connected CRFs[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2016,40(4):834-848.