An all-sky camera image classification method using cloud cover features
<p>The all-sky camera (ASC) images can reflect the local cloud cover information, and the cloud cover is one of the first factors considered for astronomical observatory site selection. Therefore, the realization of automatic classification of the ASC images plays an important role in astronom...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2022-06-01
|
| Series: | Atmospheric Measurement Techniques |
| Online Access: | https://amt.copernicus.org/articles/15/3629/2022/amt-15-3629-2022.pdf |
| _version_ | 1828822533238947840 |
|---|---|
| author | X. Li B. Wang B. Qiu C. Wu |
| author_facet | X. Li B. Wang B. Qiu C. Wu |
| author_sort | X. Li |
| collection | DOAJ |
| description | <p>The all-sky camera (ASC) images can reflect the local
cloud cover information, and the cloud cover is one of the first factors
considered for astronomical observatory site selection. Therefore, the
realization of automatic classification of the ASC images plays an important
role in astronomical observatory site selection. In this paper, three cloud
cover features are proposed for the TMT (Thirty Meter Telescope)
classification criteria, namely cloud weight, cloud area ratio and cloud
dispersion. After the features are quantified, four classifiers are used to
recognize the classes of the images. Four classes of ASC images are
identified: “clear”, “inner”, “outer” and “covered”. The proposed
method is evaluated on a large dataset, which contains 5000 ASC images taken
by an all-sky camera located in Xinjiang (38.19<span class="inline-formula"><sup>∘</sup></span> N,
74.53<span class="inline-formula"><sup>∘</sup></span> E). In the end, the method achieves an accuracy
of 96.58 % and F1_score of 96.24 % by a random forest
(RF) classifier, which greatly improves the efficiency of automatic
processing of the ASC images.</p> |
| first_indexed | 2024-12-12T13:16:36Z |
| format | Article |
| id | doaj.art-4474cd54a6304ec8ae8bca3f22eff8c8 |
| institution | Directory Open Access Journal |
| issn | 1867-1381 1867-8548 |
| language | English |
| last_indexed | 2024-12-12T13:16:36Z |
| publishDate | 2022-06-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | Atmospheric Measurement Techniques |
| spelling | doaj.art-4474cd54a6304ec8ae8bca3f22eff8c82022-12-22T00:23:24ZengCopernicus PublicationsAtmospheric Measurement Techniques1867-13811867-85482022-06-01153629363910.5194/amt-15-3629-2022An all-sky camera image classification method using cloud cover featuresX. LiB. WangB. QiuC. Wu<p>The all-sky camera (ASC) images can reflect the local cloud cover information, and the cloud cover is one of the first factors considered for astronomical observatory site selection. Therefore, the realization of automatic classification of the ASC images plays an important role in astronomical observatory site selection. In this paper, three cloud cover features are proposed for the TMT (Thirty Meter Telescope) classification criteria, namely cloud weight, cloud area ratio and cloud dispersion. After the features are quantified, four classifiers are used to recognize the classes of the images. Four classes of ASC images are identified: “clear”, “inner”, “outer” and “covered”. The proposed method is evaluated on a large dataset, which contains 5000 ASC images taken by an all-sky camera located in Xinjiang (38.19<span class="inline-formula"><sup>∘</sup></span> N, 74.53<span class="inline-formula"><sup>∘</sup></span> E). In the end, the method achieves an accuracy of 96.58 % and F1_score of 96.24 % by a random forest (RF) classifier, which greatly improves the efficiency of automatic processing of the ASC images.</p>https://amt.copernicus.org/articles/15/3629/2022/amt-15-3629-2022.pdf |
| spellingShingle | X. Li B. Wang B. Qiu C. Wu An all-sky camera image classification method using cloud cover features Atmospheric Measurement Techniques |
| title | An all-sky camera image classification method using cloud cover features |
| title_full | An all-sky camera image classification method using cloud cover features |
| title_fullStr | An all-sky camera image classification method using cloud cover features |
| title_full_unstemmed | An all-sky camera image classification method using cloud cover features |
| title_short | An all-sky camera image classification method using cloud cover features |
| title_sort | all sky camera image classification method using cloud cover features |
| url | https://amt.copernicus.org/articles/15/3629/2022/amt-15-3629-2022.pdf |
| work_keys_str_mv | AT xli anallskycameraimageclassificationmethodusingcloudcoverfeatures AT bwang anallskycameraimageclassificationmethodusingcloudcoverfeatures AT bqiu anallskycameraimageclassificationmethodusingcloudcoverfeatures AT cwu anallskycameraimageclassificationmethodusingcloudcoverfeatures AT xli allskycameraimageclassificationmethodusingcloudcoverfeatures AT bwang allskycameraimageclassificationmethodusingcloudcoverfeatures AT bqiu allskycameraimageclassificationmethodusingcloudcoverfeatures AT cwu allskycameraimageclassificationmethodusingcloudcoverfeatures |