Cross-Domain Ground-Based Cloud Classification Based on Transfer of Local Features and Discriminative Metric Learning
Cross-domain ground-based cloud classification is a challenging issue as the appearance of cloud images from different cloud databases possesses extreme variations. Two fundamental problems which are essential for cross-domain ground-based cloud classification are feature representation and similari...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2017
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs10010008 |
id |
ftmdpi:oai:mdpi.com:/2072-4292/10/1/8/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2072-4292/10/1/8/ 2023-08-20T04:06:09+02:00 Cross-Domain Ground-Based Cloud Classification Based on Transfer of Local Features and Discriminative Metric Learning Zhong Zhang Donghong Li Shuang Liu Baihua Xiao Xiaozhong Cao agris 2017-12-21 application/pdf https://doi.org/10.3390/rs10010008 EN eng Multidisciplinary Digital Publishing Institute Remote Sensing Image Processing https://dx.doi.org/10.3390/rs10010008 https://creativecommons.org/licenses/by/4.0/ Remote Sensing; Volume 10; Issue 1; Pages: 8 ground-based cloud classification machine learning transfer of local features discriminative metric learning Text 2017 ftmdpi https://doi.org/10.3390/rs10010008 2023-07-31T21:19:27Z Cross-domain ground-based cloud classification is a challenging issue as the appearance of cloud images from different cloud databases possesses extreme variations. Two fundamental problems which are essential for cross-domain ground-based cloud classification are feature representation and similarity measurement. In this paper, we propose an effective feature representation called transfer of local features (TLF), and measurement method called discriminative metric learning (DML). The TLF is a generalized representation framework that can integrate various kinds of local features, e.g., local binary patterns (LBP), local ternary patterns (LTP) and completed LBP (CLBP). In order to handle domain shift, such as variations of illumination, image resolution, capturing location, occlusion and so on, the TLF mines the maximum response in regions to make a stable representation for domain variations. We also propose to learn a discriminant metric, simultaneously. We make use of sample pairs and the relationship among cloud classes to learn the distance metric. Furthermore, in order to improve the practicability of the proposed method, we replace the original cloud images with the convolutional activation maps which are then applied to TLF and DML. The proposed method has been validated on three cloud databases which are collected in China alone, provided by Chinese Academy of Meteorological Sciences (CAMS), Meteorological Observation Centre (MOC), and Institute of Atmospheric Physics (IAP). The classification accuracies outperform the state-of-the-art methods. Text DML MDPI Open Access Publishing Remote Sensing 10 2 8 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
ground-based cloud classification machine learning transfer of local features discriminative metric learning |
spellingShingle |
ground-based cloud classification machine learning transfer of local features discriminative metric learning Zhong Zhang Donghong Li Shuang Liu Baihua Xiao Xiaozhong Cao Cross-Domain Ground-Based Cloud Classification Based on Transfer of Local Features and Discriminative Metric Learning |
topic_facet |
ground-based cloud classification machine learning transfer of local features discriminative metric learning |
description |
Cross-domain ground-based cloud classification is a challenging issue as the appearance of cloud images from different cloud databases possesses extreme variations. Two fundamental problems which are essential for cross-domain ground-based cloud classification are feature representation and similarity measurement. In this paper, we propose an effective feature representation called transfer of local features (TLF), and measurement method called discriminative metric learning (DML). The TLF is a generalized representation framework that can integrate various kinds of local features, e.g., local binary patterns (LBP), local ternary patterns (LTP) and completed LBP (CLBP). In order to handle domain shift, such as variations of illumination, image resolution, capturing location, occlusion and so on, the TLF mines the maximum response in regions to make a stable representation for domain variations. We also propose to learn a discriminant metric, simultaneously. We make use of sample pairs and the relationship among cloud classes to learn the distance metric. Furthermore, in order to improve the practicability of the proposed method, we replace the original cloud images with the convolutional activation maps which are then applied to TLF and DML. The proposed method has been validated on three cloud databases which are collected in China alone, provided by Chinese Academy of Meteorological Sciences (CAMS), Meteorological Observation Centre (MOC), and Institute of Atmospheric Physics (IAP). The classification accuracies outperform the state-of-the-art methods. |
format |
Text |
author |
Zhong Zhang Donghong Li Shuang Liu Baihua Xiao Xiaozhong Cao |
author_facet |
Zhong Zhang Donghong Li Shuang Liu Baihua Xiao Xiaozhong Cao |
author_sort |
Zhong Zhang |
title |
Cross-Domain Ground-Based Cloud Classification Based on Transfer of Local Features and Discriminative Metric Learning |
title_short |
Cross-Domain Ground-Based Cloud Classification Based on Transfer of Local Features and Discriminative Metric Learning |
title_full |
Cross-Domain Ground-Based Cloud Classification Based on Transfer of Local Features and Discriminative Metric Learning |
title_fullStr |
Cross-Domain Ground-Based Cloud Classification Based on Transfer of Local Features and Discriminative Metric Learning |
title_full_unstemmed |
Cross-Domain Ground-Based Cloud Classification Based on Transfer of Local Features and Discriminative Metric Learning |
title_sort |
cross-domain ground-based cloud classification based on transfer of local features and discriminative metric learning |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2017 |
url |
https://doi.org/10.3390/rs10010008 |
op_coverage |
agris |
genre |
DML |
genre_facet |
DML |
op_source |
Remote Sensing; Volume 10; Issue 1; Pages: 8 |
op_relation |
Remote Sensing Image Processing https://dx.doi.org/10.3390/rs10010008 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/rs10010008 |
container_title |
Remote Sensing |
container_volume |
10 |
container_issue |
2 |
container_start_page |
8 |
_version_ |
1774717090178007040 |