Satellite Image for Cloud and Snow Recognition Based on Lightweight Feature Map Attention Network
Cloud and snow recognition technology is of great significance in the field of meteorology, and is also widely used in remote sensing mapping, aerospace, and other fields. Based on the traditional method of manually labeling cloud-snow areas, a method of labeling cloud and snow areas using deep lear...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | ISPRS International Journal of Geo-Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2220-9964/11/7/390 |
| _version_ | 1797406174950195200 |
|---|---|
| author | Chaoyun Yang Yonghong Zhang Min Xia Haifeng Lin Jia Liu Yang Li |
| author_facet | Chaoyun Yang Yonghong Zhang Min Xia Haifeng Lin Jia Liu Yang Li |
| author_sort | Chaoyun Yang |
| collection | DOAJ |
| description | Cloud and snow recognition technology is of great significance in the field of meteorology, and is also widely used in remote sensing mapping, aerospace, and other fields. Based on the traditional method of manually labeling cloud-snow areas, a method of labeling cloud and snow areas using deep learning technology has been gradually developed to improve the accuracy and efficiency of recognition. In this paper, from the perspective of designing an efficient and lightweight network model, a cloud snow recognition model based on a lightweight feature map attention network (Lw-fmaNet) is proposed to ensure the performance and accuracy of the cloud snow recognition model. The model is improved based on the ResNet18 network with the premise of reducing the network parameters and improving the training efficiency. The main structure of the model includes a shallow feature extraction module, an intrinsic feature mapping module, and a lightweight adaptive attention mechanism. Overall, in the experiments conducted in this paper, the accuracy of the proposed cloud and snow recognition model reaches 95.02%, with a Kappa index of 93.34%. The proposed method achieves an average precision rate of 94.87%, an average recall rate of 94.79%, and an average F1-Score of 94.82% for four sample recognition classification tasks: no snow and no clouds, thin cloud, thick cloud, and snow cover. Meanwhile, our proposed network has only 5.617M parameters and takes only 2.276 s. Compared with multiple convolutional neural networks and lightweight networks commonly used for cloud and snow recognition, our proposed lightweight feature map attention network has a better performance when it comes to performing cloud and snow recognition tasks. |
| first_indexed | 2024-03-09T03:21:36Z |
| format | Article |
| id | doaj.art-81147fe224f04db48802a91eff34376f |
| institution | Directory Open Access Journal |
| issn | 2220-9964 |
| language | English |
| last_indexed | 2024-03-09T03:21:36Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | ISPRS International Journal of Geo-Information |
| spelling | doaj.art-81147fe224f04db48802a91eff34376f2023-12-03T15:08:49ZengMDPI AGISPRS International Journal of Geo-Information2220-99642022-07-0111739010.3390/ijgi11070390Satellite Image for Cloud and Snow Recognition Based on Lightweight Feature Map Attention NetworkChaoyun Yang0Yonghong Zhang1Min Xia2Haifeng Lin3Jia Liu4Yang Li5Collaborative Innovation Center on Atmospheric Environment and Equipment Technology, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaCollaborative Innovation Center on Atmospheric Environment and Equipment Technology, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaCollaborative Innovation Center on Atmospheric Environment and Equipment Technology, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaCollege of Information Science and Technology, Nanjing Forestry University, Nanjing 210037, ChinaCollaborative Innovation Center on Atmospheric Environment and Equipment Technology, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaCollaborative Innovation Center on Atmospheric Environment and Equipment Technology, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaCloud and snow recognition technology is of great significance in the field of meteorology, and is also widely used in remote sensing mapping, aerospace, and other fields. Based on the traditional method of manually labeling cloud-snow areas, a method of labeling cloud and snow areas using deep learning technology has been gradually developed to improve the accuracy and efficiency of recognition. In this paper, from the perspective of designing an efficient and lightweight network model, a cloud snow recognition model based on a lightweight feature map attention network (Lw-fmaNet) is proposed to ensure the performance and accuracy of the cloud snow recognition model. The model is improved based on the ResNet18 network with the premise of reducing the network parameters and improving the training efficiency. The main structure of the model includes a shallow feature extraction module, an intrinsic feature mapping module, and a lightweight adaptive attention mechanism. Overall, in the experiments conducted in this paper, the accuracy of the proposed cloud and snow recognition model reaches 95.02%, with a Kappa index of 93.34%. The proposed method achieves an average precision rate of 94.87%, an average recall rate of 94.79%, and an average F1-Score of 94.82% for four sample recognition classification tasks: no snow and no clouds, thin cloud, thick cloud, and snow cover. Meanwhile, our proposed network has only 5.617M parameters and takes only 2.276 s. Compared with multiple convolutional neural networks and lightweight networks commonly used for cloud and snow recognition, our proposed lightweight feature map attention network has a better performance when it comes to performing cloud and snow recognition tasks.https://www.mdpi.com/2220-9964/11/7/390cloud and snow recognitionconvolutional neural networklightweight feature mapattention network |
| spellingShingle | Chaoyun Yang Yonghong Zhang Min Xia Haifeng Lin Jia Liu Yang Li Satellite Image for Cloud and Snow Recognition Based on Lightweight Feature Map Attention Network ISPRS International Journal of Geo-Information cloud and snow recognition convolutional neural network lightweight feature map attention network |
| title | Satellite Image for Cloud and Snow Recognition Based on Lightweight Feature Map Attention Network |
| title_full | Satellite Image for Cloud and Snow Recognition Based on Lightweight Feature Map Attention Network |
| title_fullStr | Satellite Image for Cloud and Snow Recognition Based on Lightweight Feature Map Attention Network |
| title_full_unstemmed | Satellite Image for Cloud and Snow Recognition Based on Lightweight Feature Map Attention Network |
| title_short | Satellite Image for Cloud and Snow Recognition Based on Lightweight Feature Map Attention Network |
| title_sort | satellite image for cloud and snow recognition based on lightweight feature map attention network |
| topic | cloud and snow recognition convolutional neural network lightweight feature map attention network |
| url | https://www.mdpi.com/2220-9964/11/7/390 |
| work_keys_str_mv | AT chaoyunyang satelliteimageforcloudandsnowrecognitionbasedonlightweightfeaturemapattentionnetwork AT yonghongzhang satelliteimageforcloudandsnowrecognitionbasedonlightweightfeaturemapattentionnetwork AT minxia satelliteimageforcloudandsnowrecognitionbasedonlightweightfeaturemapattentionnetwork AT haifenglin satelliteimageforcloudandsnowrecognitionbasedonlightweightfeaturemapattentionnetwork AT jialiu satelliteimageforcloudandsnowrecognitionbasedonlightweightfeaturemapattentionnetwork AT yangli satelliteimageforcloudandsnowrecognitionbasedonlightweightfeaturemapattentionnetwork |