Cumulus Clouds Under Varying Lighting Conditions.

<div><p>Automatic recognition of ground-based clouds is crucial for meteorology and especially for the operational safety of Unmanned Aerial Vehicles (UAVs), but it is challenged by variable cloud shapes, complex lighting, and background interference. This paper introduces ALGA-DenseNet,...

Full description

Saved in:
Bibliographic Details
Main Author: Binbin Tu (1499677) (author)
Other Authors: Haoyuan Zhou (22530459) (author), Xiaowei Han (5219507) (author), Jiawei Bao (17737830) (author), Linfei Zhao (4099297) (author), Nanmu Hui (22530462) (author)
Published: 2025
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1852015334591037440
author Binbin Tu (1499677)
author2 Haoyuan Zhou (22530459)
Xiaowei Han (5219507)
Jiawei Bao (17737830)
Linfei Zhao (4099297)
Nanmu Hui (22530462)
author2_role author
author
author
author
author
author_facet Binbin Tu (1499677)
Haoyuan Zhou (22530459)
Xiaowei Han (5219507)
Jiawei Bao (17737830)
Linfei Zhao (4099297)
Nanmu Hui (22530462)
author_role author
dc.creator.none.fl_str_mv Binbin Tu (1499677)
Haoyuan Zhou (22530459)
Xiaowei Han (5219507)
Jiawei Bao (17737830)
Linfei Zhao (4099297)
Nanmu Hui (22530462)
dc.date.none.fl_str_mv 2025-10-30T17:41:23Z
dc.identifier.none.fl_str_mv 10.1371/journal.pone.0333999.g002
dc.relation.none.fl_str_mv https://figshare.com/articles/figure/Cumulus_Clouds_Under_Varying_Lighting_Conditions_/30492903
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Evolutionary Biology
Plant Biology
Space Science
Environmental Sciences not elsewhere classified
Biological Sciences not elsewhere classified
Chemical Sciences not elsewhere classified
Information Systems not elsewhere classified
unmanned aerial vehicles
tianjin normal university
model &# 8217
incorporates adaptive local
enhancing feature selection
enhance image robustness
depthwise separable convolutions
scale feature extraction
scale attention mechanism
paper introduces alga
improved densenet model
variable cloud shapes
complex cloud features
based cloud dataset
scale extraction
cloud textures
complex lighting
based clouds
merge features
head attention
global attention
color features
vision transformer
uavs ),
reducing parameters
operational safety
integrates mixed
improve learning
enhances representation
computational complexity
class variations
class differences
background interference
dc.title.none.fl_str_mv Cumulus Clouds Under Varying Lighting Conditions.
dc.type.none.fl_str_mv Image
Figure
info:eu-repo/semantics/publishedVersion
image
description <div><p>Automatic recognition of ground-based clouds is crucial for meteorology and especially for the operational safety of Unmanned Aerial Vehicles (UAVs), but it is challenged by variable cloud shapes, complex lighting, and background interference. This paper introduces ALGA-DenseNet, an improved DenseNet model with a multi-scale attention mechanism. The model employs Color Jitter to enhance image robustness and improve learning of intra-class variations and inter-class differences. It incorporates Adaptive Local and Global Attention (ALGA) to merge features, enhancing feature selection. Additionally, it integrates mixed and depthwise separable convolutions to optimize multi-scale feature extraction, reducing parameters and computational complexity. Furthermore, integrating a Vision Transformer (ViT) and Dynamic Multi-head Attention (DMA) enhances representation of complex cloud features. Experimental results show recognition accuracies of 97.94% on the TJNU (Tianjin Normal University) Ground-based Cloud Dataset (GCD) and 97.25% on the Cirrus Cumulus Stratus Nimbus (CCSN) dataset. This indicates the model’s capability for fine-grained, multi-scale extraction of cloud textures, shapes, and color features, along with strong generalization performance.</p></div>
eu_rights_str_mv openAccess
id Manara_e9dac2e99d4414a7bb9155b5bc47fc76
identifier_str_mv 10.1371/journal.pone.0333999.g002
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/30492903
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Cumulus Clouds Under Varying Lighting Conditions.Binbin Tu (1499677)Haoyuan Zhou (22530459)Xiaowei Han (5219507)Jiawei Bao (17737830)Linfei Zhao (4099297)Nanmu Hui (22530462)Evolutionary BiologyPlant BiologySpace ScienceEnvironmental Sciences not elsewhere classifiedBiological Sciences not elsewhere classifiedChemical Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedunmanned aerial vehiclestianjin normal universitymodel &# 8217incorporates adaptive localenhancing feature selectionenhance image robustnessdepthwise separable convolutionsscale feature extractionscale attention mechanismpaper introduces algaimproved densenet modelvariable cloud shapescomplex cloud featuresbased cloud datasetscale extractioncloud texturescomplex lightingbased cloudsmerge featureshead attentionglobal attentioncolor featuresvision transformeruavs ),reducing parametersoperational safetyintegrates mixedimprove learningenhances representationcomputational complexityclass variationsclass differencesbackground interference<div><p>Automatic recognition of ground-based clouds is crucial for meteorology and especially for the operational safety of Unmanned Aerial Vehicles (UAVs), but it is challenged by variable cloud shapes, complex lighting, and background interference. This paper introduces ALGA-DenseNet, an improved DenseNet model with a multi-scale attention mechanism. The model employs Color Jitter to enhance image robustness and improve learning of intra-class variations and inter-class differences. It incorporates Adaptive Local and Global Attention (ALGA) to merge features, enhancing feature selection. Additionally, it integrates mixed and depthwise separable convolutions to optimize multi-scale feature extraction, reducing parameters and computational complexity. Furthermore, integrating a Vision Transformer (ViT) and Dynamic Multi-head Attention (DMA) enhances representation of complex cloud features. Experimental results show recognition accuracies of 97.94% on the TJNU (Tianjin Normal University) Ground-based Cloud Dataset (GCD) and 97.25% on the Cirrus Cumulus Stratus Nimbus (CCSN) dataset. This indicates the model’s capability for fine-grained, multi-scale extraction of cloud textures, shapes, and color features, along with strong generalization performance.</p></div>2025-10-30T17:41:23ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0333999.g002https://figshare.com/articles/figure/Cumulus_Clouds_Under_Varying_Lighting_Conditions_/30492903CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/304929032025-10-30T17:41:23Z
spellingShingle Cumulus Clouds Under Varying Lighting Conditions.
Binbin Tu (1499677)
Evolutionary Biology
Plant Biology
Space Science
Environmental Sciences not elsewhere classified
Biological Sciences not elsewhere classified
Chemical Sciences not elsewhere classified
Information Systems not elsewhere classified
unmanned aerial vehicles
tianjin normal university
model &# 8217
incorporates adaptive local
enhancing feature selection
enhance image robustness
depthwise separable convolutions
scale feature extraction
scale attention mechanism
paper introduces alga
improved densenet model
variable cloud shapes
complex cloud features
based cloud dataset
scale extraction
cloud textures
complex lighting
based clouds
merge features
head attention
global attention
color features
vision transformer
uavs ),
reducing parameters
operational safety
integrates mixed
improve learning
enhances representation
computational complexity
class variations
class differences
background interference
status_str publishedVersion
title Cumulus Clouds Under Varying Lighting Conditions.
title_full Cumulus Clouds Under Varying Lighting Conditions.
title_fullStr Cumulus Clouds Under Varying Lighting Conditions.
title_full_unstemmed Cumulus Clouds Under Varying Lighting Conditions.
title_short Cumulus Clouds Under Varying Lighting Conditions.
title_sort Cumulus Clouds Under Varying Lighting Conditions.
topic Evolutionary Biology
Plant Biology
Space Science
Environmental Sciences not elsewhere classified
Biological Sciences not elsewhere classified
Chemical Sciences not elsewhere classified
Information Systems not elsewhere classified
unmanned aerial vehicles
tianjin normal university
model &# 8217
incorporates adaptive local
enhancing feature selection
enhance image robustness
depthwise separable convolutions
scale feature extraction
scale attention mechanism
paper introduces alga
improved densenet model
variable cloud shapes
complex cloud features
based cloud dataset
scale extraction
cloud textures
complex lighting
based clouds
merge features
head attention
global attention
color features
vision transformer
uavs ),
reducing parameters
operational safety
integrates mixed
improve learning
enhances representation
computational complexity
class variations
class differences
background interference