Auto‐encoder‐based shared mid‐level visual dictionary learning for scene classification using very high resolution remote sensing images
Effective representation and classification of scenes using very high resolution (VHR) remote sensing images cover a wide range of applications. Although robust low‐level image features have been proven to be effective for scene classification, they are not semantically meaningful and thus have diff...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2015-10-01
|
Series: | IET Computer Vision |
Subjects: | |
Online Access: | https://doi.org/10.1049/iet-cvi.2014.0270 |
_version_ | 1797684542745608192 |
---|---|
author | Gong Cheng Peicheng Zhou Junwei Han Lei Guo Jungong Han |
author_facet | Gong Cheng Peicheng Zhou Junwei Han Lei Guo Jungong Han |
author_sort | Gong Cheng |
collection | DOAJ |
description | Effective representation and classification of scenes using very high resolution (VHR) remote sensing images cover a wide range of applications. Although robust low‐level image features have been proven to be effective for scene classification, they are not semantically meaningful and thus have difficulty to deal with challenging visual recognition tasks. In this study, the authors propose a new and effective auto‐encoder‐based method to learn a shared mid‐level visual dictionary. This dictionary serves as a shared and universal basis to discover mid‐level visual elements. On the one hand, the mid‐level visual dictionary learnt using machine learning technique is more discriminative and contains rich semantic information, compared with the traditional low‐level visual words. On the other hand, the mid‐level visual dictionary is more robust to occlusions and image clutters. In the authors' scene‐classification scheme, they use discriminative mid‐level visual elements, rather than individual pixels or low‐level image features, to represent images. This new image representation is able to capture much of the high‐level meaning and contents of the image, facilitating challenging remote sensing image scene‐classification tasks. Comprehensive evaluations on a challenging VHR remote sensing images data set and comparisons with state‐of‐the‐art approaches demonstrate the effectiveness and superiority of their study. |
first_indexed | 2024-03-12T00:31:17Z |
format | Article |
id | doaj.art-756995db6dac4351b4dd9684f8099763 |
institution | Directory Open Access Journal |
issn | 1751-9632 1751-9640 |
language | English |
last_indexed | 2024-03-12T00:31:17Z |
publishDate | 2015-10-01 |
publisher | Wiley |
record_format | Article |
series | IET Computer Vision |
spelling | doaj.art-756995db6dac4351b4dd9684f80997632023-09-15T10:21:07ZengWileyIET Computer Vision1751-96321751-96402015-10-019563964710.1049/iet-cvi.2014.0270Auto‐encoder‐based shared mid‐level visual dictionary learning for scene classification using very high resolution remote sensing imagesGong Cheng0Peicheng Zhou1Junwei Han2Lei Guo3Jungong Han4School of AutomationNorthwestern Polytechnical UniversityXi'an710072People's Republic of ChinaSchool of AutomationNorthwestern Polytechnical UniversityXi'an710072People's Republic of ChinaSchool of AutomationNorthwestern Polytechnical UniversityXi'an710072People's Republic of ChinaSchool of AutomationNorthwestern Polytechnical UniversityXi'an710072People's Republic of ChinaCivolution TechnologyEindhovenThe NetherlandsEffective representation and classification of scenes using very high resolution (VHR) remote sensing images cover a wide range of applications. Although robust low‐level image features have been proven to be effective for scene classification, they are not semantically meaningful and thus have difficulty to deal with challenging visual recognition tasks. In this study, the authors propose a new and effective auto‐encoder‐based method to learn a shared mid‐level visual dictionary. This dictionary serves as a shared and universal basis to discover mid‐level visual elements. On the one hand, the mid‐level visual dictionary learnt using machine learning technique is more discriminative and contains rich semantic information, compared with the traditional low‐level visual words. On the other hand, the mid‐level visual dictionary is more robust to occlusions and image clutters. In the authors' scene‐classification scheme, they use discriminative mid‐level visual elements, rather than individual pixels or low‐level image features, to represent images. This new image representation is able to capture much of the high‐level meaning and contents of the image, facilitating challenging remote sensing image scene‐classification tasks. Comprehensive evaluations on a challenging VHR remote sensing images data set and comparisons with state‐of‐the‐art approaches demonstrate the effectiveness and superiority of their study.https://doi.org/10.1049/iet-cvi.2014.0270autoencoder-based shared midlevel visual dictionary learningscene classificationvery high resolution remote sensing imagesVHR remote sensing imagesauto-encoder-based methodmid-level visual dictionary |
spellingShingle | Gong Cheng Peicheng Zhou Junwei Han Lei Guo Jungong Han Auto‐encoder‐based shared mid‐level visual dictionary learning for scene classification using very high resolution remote sensing images IET Computer Vision autoencoder-based shared midlevel visual dictionary learning scene classification very high resolution remote sensing images VHR remote sensing images auto-encoder-based method mid-level visual dictionary |
title | Auto‐encoder‐based shared mid‐level visual dictionary learning for scene classification using very high resolution remote sensing images |
title_full | Auto‐encoder‐based shared mid‐level visual dictionary learning for scene classification using very high resolution remote sensing images |
title_fullStr | Auto‐encoder‐based shared mid‐level visual dictionary learning for scene classification using very high resolution remote sensing images |
title_full_unstemmed | Auto‐encoder‐based shared mid‐level visual dictionary learning for scene classification using very high resolution remote sensing images |
title_short | Auto‐encoder‐based shared mid‐level visual dictionary learning for scene classification using very high resolution remote sensing images |
title_sort | auto encoder based shared mid level visual dictionary learning for scene classification using very high resolution remote sensing images |
topic | autoencoder-based shared midlevel visual dictionary learning scene classification very high resolution remote sensing images VHR remote sensing images auto-encoder-based method mid-level visual dictionary |
url | https://doi.org/10.1049/iet-cvi.2014.0270 |
work_keys_str_mv | AT gongcheng autoencoderbasedsharedmidlevelvisualdictionarylearningforsceneclassificationusingveryhighresolutionremotesensingimages AT peichengzhou autoencoderbasedsharedmidlevelvisualdictionarylearningforsceneclassificationusingveryhighresolutionremotesensingimages AT junweihan autoencoderbasedsharedmidlevelvisualdictionarylearningforsceneclassificationusingveryhighresolutionremotesensingimages AT leiguo autoencoderbasedsharedmidlevelvisualdictionarylearningforsceneclassificationusingveryhighresolutionremotesensingimages AT jungonghan autoencoderbasedsharedmidlevelvisualdictionarylearningforsceneclassificationusingveryhighresolutionremotesensingimages |