Joint Feature-Space and Sample-Space Based Heterogeneous Feature Transfer Method for Object Recognition Using Remote Sensing Images with Different Spatial Resolutions

To improve the classification results of high-resolution remote sensing images (RSIs), it is necessary to use feature transfer methods to mine the relevant information between high-resolution RSIs and low-resolution RSIs to train the classifiers together. Most of the existing feature transfer method...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Wei Hu, Xiyuan Kong, Liang Xie, Huijiong Yan, Wei Qin, Xiangyi Meng, Ye Yan, Erwei Yin
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Acceso en línea:https://doaj.org/article/782560f7745a484095a819da22719c99
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:782560f7745a484095a819da22719c99
record_format dspace
spelling oai:doaj.org-article:782560f7745a484095a819da22719c992021-11-25T18:57:31ZJoint Feature-Space and Sample-Space Based Heterogeneous Feature Transfer Method for Object Recognition Using Remote Sensing Images with Different Spatial Resolutions10.3390/s212275681424-8220https://doaj.org/article/782560f7745a484095a819da22719c992021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/22/7568https://doaj.org/toc/1424-8220To improve the classification results of high-resolution remote sensing images (RSIs), it is necessary to use feature transfer methods to mine the relevant information between high-resolution RSIs and low-resolution RSIs to train the classifiers together. Most of the existing feature transfer methods can only handle homogeneous data (i.e., data with the same dimension) and are susceptible to the quality of the RSIs, while RSIs with different resolutions present different feature dimensions and samples obtained from illumination conditions. To obtain effective classification results, unlike existing methods that focus only on the projection transformation in feature space, a joint feature-space and sample-space heterogeneous feature transfer (JFSSS-HFT) method is proposed to simultaneously process heterogeneous multi-resolution images in feature space using projection matrices of different dimensions and reduce the impact of outliers by adaptive weight factors in the sample space simultaneously to reduce the occurrence of negative transfer. Moreover, the maximum interclass variance term is embedded to improve the discriminant ability of the transferred features. To solve the optimization problem of JFSSS-HFT, the alternating-direction method of multipliers (ADMM) is introduced to alternatively optimize the parameters of JFSSS-HFT. Using different types of ship patches and airplane patches with different resolutions, the experimental results show that the proposed JFSSS-HFT obtains better classification results than the typical feature transferred methods.Wei HuXiyuan KongLiang XieHuijiong YanWei QinXiangyi MengYe YanErwei YinMDPI AGarticleheterogeneous feature transferclassification of remote sensing imagestransfer learningnegative transferChemical technologyTP1-1185ENSensors, Vol 21, Iss 7568, p 7568 (2021)
institution DOAJ
collection DOAJ
language EN
topic heterogeneous feature transfer
classification of remote sensing images
transfer learning
negative transfer
Chemical technology
TP1-1185
spellingShingle heterogeneous feature transfer
classification of remote sensing images
transfer learning
negative transfer
Chemical technology
TP1-1185
Wei Hu
Xiyuan Kong
Liang Xie
Huijiong Yan
Wei Qin
Xiangyi Meng
Ye Yan
Erwei Yin
Joint Feature-Space and Sample-Space Based Heterogeneous Feature Transfer Method for Object Recognition Using Remote Sensing Images with Different Spatial Resolutions
description To improve the classification results of high-resolution remote sensing images (RSIs), it is necessary to use feature transfer methods to mine the relevant information between high-resolution RSIs and low-resolution RSIs to train the classifiers together. Most of the existing feature transfer methods can only handle homogeneous data (i.e., data with the same dimension) and are susceptible to the quality of the RSIs, while RSIs with different resolutions present different feature dimensions and samples obtained from illumination conditions. To obtain effective classification results, unlike existing methods that focus only on the projection transformation in feature space, a joint feature-space and sample-space heterogeneous feature transfer (JFSSS-HFT) method is proposed to simultaneously process heterogeneous multi-resolution images in feature space using projection matrices of different dimensions and reduce the impact of outliers by adaptive weight factors in the sample space simultaneously to reduce the occurrence of negative transfer. Moreover, the maximum interclass variance term is embedded to improve the discriminant ability of the transferred features. To solve the optimization problem of JFSSS-HFT, the alternating-direction method of multipliers (ADMM) is introduced to alternatively optimize the parameters of JFSSS-HFT. Using different types of ship patches and airplane patches with different resolutions, the experimental results show that the proposed JFSSS-HFT obtains better classification results than the typical feature transferred methods.
format article
author Wei Hu
Xiyuan Kong
Liang Xie
Huijiong Yan
Wei Qin
Xiangyi Meng
Ye Yan
Erwei Yin
author_facet Wei Hu
Xiyuan Kong
Liang Xie
Huijiong Yan
Wei Qin
Xiangyi Meng
Ye Yan
Erwei Yin
author_sort Wei Hu
title Joint Feature-Space and Sample-Space Based Heterogeneous Feature Transfer Method for Object Recognition Using Remote Sensing Images with Different Spatial Resolutions
title_short Joint Feature-Space and Sample-Space Based Heterogeneous Feature Transfer Method for Object Recognition Using Remote Sensing Images with Different Spatial Resolutions
title_full Joint Feature-Space and Sample-Space Based Heterogeneous Feature Transfer Method for Object Recognition Using Remote Sensing Images with Different Spatial Resolutions
title_fullStr Joint Feature-Space and Sample-Space Based Heterogeneous Feature Transfer Method for Object Recognition Using Remote Sensing Images with Different Spatial Resolutions
title_full_unstemmed Joint Feature-Space and Sample-Space Based Heterogeneous Feature Transfer Method for Object Recognition Using Remote Sensing Images with Different Spatial Resolutions
title_sort joint feature-space and sample-space based heterogeneous feature transfer method for object recognition using remote sensing images with different spatial resolutions
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/782560f7745a484095a819da22719c99
work_keys_str_mv AT weihu jointfeaturespaceandsamplespacebasedheterogeneousfeaturetransfermethodforobjectrecognitionusingremotesensingimageswithdifferentspatialresolutions
AT xiyuankong jointfeaturespaceandsamplespacebasedheterogeneousfeaturetransfermethodforobjectrecognitionusingremotesensingimageswithdifferentspatialresolutions
AT liangxie jointfeaturespaceandsamplespacebasedheterogeneousfeaturetransfermethodforobjectrecognitionusingremotesensingimageswithdifferentspatialresolutions
AT huijiongyan jointfeaturespaceandsamplespacebasedheterogeneousfeaturetransfermethodforobjectrecognitionusingremotesensingimageswithdifferentspatialresolutions
AT weiqin jointfeaturespaceandsamplespacebasedheterogeneousfeaturetransfermethodforobjectrecognitionusingremotesensingimageswithdifferentspatialresolutions
AT xiangyimeng jointfeaturespaceandsamplespacebasedheterogeneousfeaturetransfermethodforobjectrecognitionusingremotesensingimageswithdifferentspatialresolutions
AT yeyan jointfeaturespaceandsamplespacebasedheterogeneousfeaturetransfermethodforobjectrecognitionusingremotesensingimageswithdifferentspatialresolutions
AT erweiyin jointfeaturespaceandsamplespacebasedheterogeneousfeaturetransfermethodforobjectrecognitionusingremotesensingimageswithdifferentspatialresolutions
_version_ 1718410470067535872