High-Resolution Remote Sensing Imagery Classification of Imbalanced Data Using Multistage Sampling Method and Deep Neural Networks
Class imbalance is a key issue for the application of deep learning for remote sensing image classification because a model generated by imbalanced samples training has low classification accuracy for minority classes. In this study, an accurate classification approach using the multistage sampling...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-10-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/11/21/2523 |
id |
doaj-121e701e3fd5469a96d01ac193b35a75 |
---|---|
record_format |
Article |
spelling |
doaj-121e701e3fd5469a96d01ac193b35a752020-11-25T01:41:44ZengMDPI AGRemote Sensing2072-42922019-10-011121252310.3390/rs11212523rs11212523High-Resolution Remote Sensing Imagery Classification of Imbalanced Data Using Multistage Sampling Method and Deep Neural NetworksWei Xia0Caihong Ma1Jianbo Liu2Shibin Liu3Fu Chen4Zhi Yang5Jianbo Duan6Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaChina Electric Power Research Institute Co., Ltd., Beijing 100055, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaClass imbalance is a key issue for the application of deep learning for remote sensing image classification because a model generated by imbalanced samples training has low classification accuracy for minority classes. In this study, an accurate classification approach using the multistage sampling method and deep neural networks was proposed to classify imbalanced data. We first balance samples by multistage sampling to obtain the training sets. Then, a state-of-the-art model is adopted by combining the advantages of atrous spatial pyramid pooling (ASPP) and Encoder-Decoder for pixel-wise classification, which are two different types of fully convolutional networks (FCNs) that can obtain contextual information of multiple levels in the Encoder stage. The details and spatial dimensions of targets are restored using such information during the Decoder stage. We employ four deep learning-based classification algorithms (basic FCN, FCN-8S, ASPP, and Encoder-Decoder with ASPP of our approach) on multistage training sets (original, MUS1, and MUS2) of WorldView-3 images in southeastern Qinghai-Tibet Plateau and GF-2 images in northeastern Beijing for comparison. The experiments show that, compared with existing sets (original, MUS1, and identical) and existing method (cost weighting), the MUS2 training set of multistage sampling significantly enhance the classification performance for minority classes. Our approach shows distinct advantages for imbalanced data.https://www.mdpi.com/2072-4292/11/21/2523high-resolution remote sensing imageclassificationdeep learningimbalanced datamultistage samplingasppencoder-decoder |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Wei Xia Caihong Ma Jianbo Liu Shibin Liu Fu Chen Zhi Yang Jianbo Duan |
spellingShingle |
Wei Xia Caihong Ma Jianbo Liu Shibin Liu Fu Chen Zhi Yang Jianbo Duan High-Resolution Remote Sensing Imagery Classification of Imbalanced Data Using Multistage Sampling Method and Deep Neural Networks Remote Sensing high-resolution remote sensing image classification deep learning imbalanced data multistage sampling aspp encoder-decoder |
author_facet |
Wei Xia Caihong Ma Jianbo Liu Shibin Liu Fu Chen Zhi Yang Jianbo Duan |
author_sort |
Wei Xia |
title |
High-Resolution Remote Sensing Imagery Classification of Imbalanced Data Using Multistage Sampling Method and Deep Neural Networks |
title_short |
High-Resolution Remote Sensing Imagery Classification of Imbalanced Data Using Multistage Sampling Method and Deep Neural Networks |
title_full |
High-Resolution Remote Sensing Imagery Classification of Imbalanced Data Using Multistage Sampling Method and Deep Neural Networks |
title_fullStr |
High-Resolution Remote Sensing Imagery Classification of Imbalanced Data Using Multistage Sampling Method and Deep Neural Networks |
title_full_unstemmed |
High-Resolution Remote Sensing Imagery Classification of Imbalanced Data Using Multistage Sampling Method and Deep Neural Networks |
title_sort |
high-resolution remote sensing imagery classification of imbalanced data using multistage sampling method and deep neural networks |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2019-10-01 |
description |
Class imbalance is a key issue for the application of deep learning for remote sensing image classification because a model generated by imbalanced samples training has low classification accuracy for minority classes. In this study, an accurate classification approach using the multistage sampling method and deep neural networks was proposed to classify imbalanced data. We first balance samples by multistage sampling to obtain the training sets. Then, a state-of-the-art model is adopted by combining the advantages of atrous spatial pyramid pooling (ASPP) and Encoder-Decoder for pixel-wise classification, which are two different types of fully convolutional networks (FCNs) that can obtain contextual information of multiple levels in the Encoder stage. The details and spatial dimensions of targets are restored using such information during the Decoder stage. We employ four deep learning-based classification algorithms (basic FCN, FCN-8S, ASPP, and Encoder-Decoder with ASPP of our approach) on multistage training sets (original, MUS1, and MUS2) of WorldView-3 images in southeastern Qinghai-Tibet Plateau and GF-2 images in northeastern Beijing for comparison. The experiments show that, compared with existing sets (original, MUS1, and identical) and existing method (cost weighting), the MUS2 training set of multistage sampling significantly enhance the classification performance for minority classes. Our approach shows distinct advantages for imbalanced data. |
topic |
high-resolution remote sensing image classification deep learning imbalanced data multistage sampling aspp encoder-decoder |
url |
https://www.mdpi.com/2072-4292/11/21/2523 |
work_keys_str_mv |
AT weixia highresolutionremotesensingimageryclassificationofimbalanceddatausingmultistagesamplingmethodanddeepneuralnetworks AT caihongma highresolutionremotesensingimageryclassificationofimbalanceddatausingmultistagesamplingmethodanddeepneuralnetworks AT jianboliu highresolutionremotesensingimageryclassificationofimbalanceddatausingmultistagesamplingmethodanddeepneuralnetworks AT shibinliu highresolutionremotesensingimageryclassificationofimbalanceddatausingmultistagesamplingmethodanddeepneuralnetworks AT fuchen highresolutionremotesensingimageryclassificationofimbalanceddatausingmultistagesamplingmethodanddeepneuralnetworks AT zhiyang highresolutionremotesensingimageryclassificationofimbalanceddatausingmultistagesamplingmethodanddeepneuralnetworks AT jianboduan highresolutionremotesensingimageryclassificationofimbalanceddatausingmultistagesamplingmethodanddeepneuralnetworks |
_version_ |
1725039943313522688 |