Land Use/Land Cover Classification Based on Transfer Learning

doi:10.13474/j.cnki.11-2246.2018.0278

Abstract

Abstract:

Land use/land cover classification of small sized datasets cannot be accurately and automatically classified by deep learning method.In order to solve this problem,a land ues/land cover automatic classification algorithm applying the reduced-modified deep residual neural network(Resnet-50) for the transfer learning is proposed.Firstly,use the original remote sensing data provided by Sentinel-1 satellite to create dataset.Secondly,compress convolution template numbers of per convolution layer in Resnet-50 and cascade the adaptive networks behind to the obtained reduced residual network.Finally,pre-training the network with ImageNet dataset and transferthe trained model to the Sentinel-1 dataset to fine-tune the parameter of the network.And the high-precision automatic classification of land use/land cover employing deep learning on small datasets is finally achieved.Experimental results show that the classification accuracy of this algorithm on SAR data set is 95.15%,which verifies the feasibility of the proposedalgorithm.

Key words: land use/land cover classification, Sentinel-1 satellite, deep residual neural network, transfer learning, deep learning

CLC Number:

P237

LI Hailei, HU Xiaojuan, GUO Hang, WU Wenjin. Land Use/Land Cover Classification Based on Transfer Learning[J]. 测绘通报, 2018, 0(9): 50-54,73.

References

[1] 陈佑启,杨鹏.国际上土地利用/土地覆盖变化研究的新进展[J].经济地理,2001,21(1):95-100.
[2] 牛颖超,周忠发,王历,等.GABA算法的遥感图像分类[J].测绘通报,2018(1):62-66.
[3] 魏立飞,俸秀强,李丹丹,等.基于S3VM模型的高光谱遥感影像分类[J].测绘通报,2017(12):43-47.
[4] PAREA S,BRUZZONE L.A Fast Cluster-assumption Based Active-learning Technique for Classification of Remote Sensing Image[J].IEEE Transactions on Geoscience and Remote Sensing,2011,49(5):1617-1626.
[5] PASOLLI E,MELGANI F,BAZI Y.Support Vector Machine Active Learning through Significance Space Construction[J].IEEE Geoscience & Remote Sensing Letters,2011,8(3):431-435.
[6] DEMIR B,PERSELLO C,BRUZZONE L.Batch-mode Active-learning Methods for the Interactive Classification of Remote Sensing Images[J].IEEE Transactions on Geoscience & Remote Sensing,2011,49(3):1014-1031.
[7] TUIA D,PASOLLI E,EMERY W J.Using Active Learning to Adapt Remote Sensing Image Classifiers[J].Remote Sensing of Environment,2011,115(9):2232-2242.
[8] PERSELLO C,BRUZZONE L.Active Learning for Domain Adaptation in the Supervised Classification of Remote Sensing Images[J].IEEE Transactions on Geoscience & Remote Sensing,2012,50(11):4468-4483.
[9] 吴文豪,李陶,陈志国,等.Sentinel-1A卫星TOPS模式数据干涉处理[J].测绘通报,2016(2):42-45.
[10] 王云艳.基于多层网络模型的全极化SAR图像分类[D].武汉:武汉大学,2015.
[11] HE K,ZHANG X,REN S,et al.Deep Residual Learning for Image Recognition[C]//Computer Vision and Pattern Recognition.[S.l.]:IEEE,2016:770-778.
[12] GENG J,WANG H,FAN J,et al.Deep Supervised and Contractive Neural Network for SAR Image Classification[J].IEEE Transactions on Geoscience & Remote Sensing,2017,55(4):2442-2459.
[13] YOSINSKI J,CLUNE J,BENGIO Y,et al.How Transferable are Features in Deep Neural Networks?[J].International Conference on Netural Information Processing Systems,2014,27:3320-3328.
[14] GLOROT X,BORDES A,BENGIO Y.Deep Sparse Rectifier Neural Networks[C]//Proceedings of the 14th International Conference on Artificial Inteligence and Statistics.[S.l.]:AISTATS,2010:315-323.
[15] NAIR V,HINTON G E.Rectified Linear Units Improve Restricted Boltzmann Machines[C]//International Conference on International Conference on Machine Learning.Omnipress:[s.n.],2010:807-814.