Ground-Based Cloud-Type Recognition Using Manifold Kernel Sparse Coding and Dictionary Learning
Recognizing cloud type of ground-based images automatically has a great influence on the weather service but poses a significant challenge. Based on the symmetric positive definite (SPD) matrix manifold, a novel method named “manifold kernel sparse coding and dictionary learning” (MKSCDL) is propose...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi Limited
2018-01-01
|
Series: | Advances in Meteorology |
Online Access: | http://dx.doi.org/10.1155/2018/9684206 |
id |
doaj-7622f50454f642b39739173c26e46228 |
---|---|
record_format |
Article |
spelling |
doaj-7622f50454f642b39739173c26e462282020-11-25T00:47:01ZengHindawi LimitedAdvances in Meteorology1687-93091687-93172018-01-01201810.1155/2018/96842069684206Ground-Based Cloud-Type Recognition Using Manifold Kernel Sparse Coding and Dictionary LearningQixiang Luo0Zeming Zhou1Yong Meng2Qian Li3Miaoying Li4College of Meteorology and Oceanology, National University of Defense Technology, Nanjing 211101, ChinaCollege of Meteorology and Oceanology, National University of Defense Technology, Nanjing 211101, ChinaCollege of Meteorology and Oceanology, National University of Defense Technology, Nanjing 211101, ChinaCollege of Meteorology and Oceanology, National University of Defense Technology, Nanjing 211101, ChinaCollege of Meteorology and Oceanology, National University of Defense Technology, Nanjing 211101, ChinaRecognizing cloud type of ground-based images automatically has a great influence on the weather service but poses a significant challenge. Based on the symmetric positive definite (SPD) matrix manifold, a novel method named “manifold kernel sparse coding and dictionary learning” (MKSCDL) is proposed for cloud classification. Different from classical features extracted in the Euclidean space, the SPD matrix fuses multiple features and represents non-Euclidean geometric characteristics. MKSCDL is composed of three steps: feature extraction, dictionary learning, and classification. With the learned dictionary, the SPD matrix of the cloud image can be described with the sparse code. The experiments are conducted on two different ground-based cloud image datasets. Benefitting from the sparse representation on the Riemannian matrix manifold, compared to the recent baselines, experimental results demonstrate that MKSCDL possesses a more competitive performance on both grayscale and colour image datasets.http://dx.doi.org/10.1155/2018/9684206 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Qixiang Luo Zeming Zhou Yong Meng Qian Li Miaoying Li |
spellingShingle |
Qixiang Luo Zeming Zhou Yong Meng Qian Li Miaoying Li Ground-Based Cloud-Type Recognition Using Manifold Kernel Sparse Coding and Dictionary Learning Advances in Meteorology |
author_facet |
Qixiang Luo Zeming Zhou Yong Meng Qian Li Miaoying Li |
author_sort |
Qixiang Luo |
title |
Ground-Based Cloud-Type Recognition Using Manifold Kernel Sparse Coding and Dictionary Learning |
title_short |
Ground-Based Cloud-Type Recognition Using Manifold Kernel Sparse Coding and Dictionary Learning |
title_full |
Ground-Based Cloud-Type Recognition Using Manifold Kernel Sparse Coding and Dictionary Learning |
title_fullStr |
Ground-Based Cloud-Type Recognition Using Manifold Kernel Sparse Coding and Dictionary Learning |
title_full_unstemmed |
Ground-Based Cloud-Type Recognition Using Manifold Kernel Sparse Coding and Dictionary Learning |
title_sort |
ground-based cloud-type recognition using manifold kernel sparse coding and dictionary learning |
publisher |
Hindawi Limited |
series |
Advances in Meteorology |
issn |
1687-9309 1687-9317 |
publishDate |
2018-01-01 |
description |
Recognizing cloud type of ground-based images automatically has a great influence on the weather service but poses a significant challenge. Based on the symmetric positive definite (SPD) matrix manifold, a novel method named “manifold kernel sparse coding and dictionary learning” (MKSCDL) is proposed for cloud classification. Different from classical features extracted in the Euclidean space, the SPD matrix fuses multiple features and represents non-Euclidean geometric characteristics. MKSCDL is composed of three steps: feature extraction, dictionary learning, and classification. With the learned dictionary, the SPD matrix of the cloud image can be described with the sparse code. The experiments are conducted on two different ground-based cloud image datasets. Benefitting from the sparse representation on the Riemannian matrix manifold, compared to the recent baselines, experimental results demonstrate that MKSCDL possesses a more competitive performance on both grayscale and colour image datasets. |
url |
http://dx.doi.org/10.1155/2018/9684206 |
work_keys_str_mv |
AT qixiangluo groundbasedcloudtyperecognitionusingmanifoldkernelsparsecodinganddictionarylearning AT zemingzhou groundbasedcloudtyperecognitionusingmanifoldkernelsparsecodinganddictionarylearning AT yongmeng groundbasedcloudtyperecognitionusingmanifoldkernelsparsecodinganddictionarylearning AT qianli groundbasedcloudtyperecognitionusingmanifoldkernelsparsecodinganddictionarylearning AT miaoyingli groundbasedcloudtyperecognitionusingmanifoldkernelsparsecodinganddictionarylearning |
_version_ |
1725262463746703360 |