Lightweight Deep Learning Model, ConvNeXt-U: An Improved U-Net Network for Extracting Cropland in Complex Landscapes from Gaofen-2 Images
Extracting fragmented cropland is essential for effective cropland management and sustainable agricultural development. However, extracting fragmented cropland presents significant challenges due to its irregular and blurred boundaries, as well as the diversity in crop types and distribution. Deep l...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/1/261 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841548950960603136 |
|---|---|
| author | Shukuan Liu Shi Cao Xia Lu Jiqing Peng Lina Ping Xiang Fan Feiyu Teng Xiangnan Liu |
| author_facet | Shukuan Liu Shi Cao Xia Lu Jiqing Peng Lina Ping Xiang Fan Feiyu Teng Xiangnan Liu |
| author_sort | Shukuan Liu |
| collection | DOAJ |
| description | Extracting fragmented cropland is essential for effective cropland management and sustainable agricultural development. However, extracting fragmented cropland presents significant challenges due to its irregular and blurred boundaries, as well as the diversity in crop types and distribution. Deep learning methods are widely used for land cover classification. This paper proposes ConvNeXt-U, a lightweight deep learning network that efficiently extracts fragmented cropland while reducing computational requirements and saving costs. ConvNeXt-U retains the U-shaped structure of U-Net but replaces the encoder with a simplified ConvNeXt architecture. The decoder remains unchanged from U-Net, and the lightweight CBAM (Convolutional Block Attention Module) is integrated. This module adaptively adjusts the channel and spatial dimensions of feature maps, emphasizing key features and suppressing redundant information, which enhances the capture of edge features and improves extraction accuracy. The case study area is Hengyang County, Hunan Province, China, using GF-2 remote sensing imagery. The results show that ConvNeXt-U outperforms existing methods, such as Swin Transformer (Acc = 85.1%, IoU = 79.1%), MobileNetV3 (Acc = 83.4%, IoU = 77.6%), VGG16 (Acc = 80.5%, IoU = 74.6%), and ResUnet (Acc = 81.8%, IoU = 76.1%), achieving an IoU of 79.5% and Acc of 85.2%. Under the same conditions, ConvNeXt-U has a faster inference speed of 37 images/s, compared to 28 images/s for Swin Transformer, 35 images/s for MobileNetV3, and 0.43 and 0.44 images/s for VGG16 and ResUnet, respectively. Moreover, ConvNeXt-U outperforms other methods in processing the boundaries of fragmented cropland, producing clearer and more complete boundaries. The results indicate that the ConvNeXt and CBAM modules significantly enhance the accuracy of fragmented cropland extraction. ConvNeXt-U is also an effective method for extracting fragmented cropland from remote sensing imagery. |
| format | Article |
| id | doaj-art-d1d8fbe03b314ddf954d6e698fdb966f |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-d1d8fbe03b314ddf954d6e698fdb966f2025-01-10T13:21:23ZengMDPI AGSensors1424-82202025-01-0125126110.3390/s25010261Lightweight Deep Learning Model, ConvNeXt-U: An Improved U-Net Network for Extracting Cropland in Complex Landscapes from Gaofen-2 ImagesShukuan Liu0Shi Cao1Xia Lu2Jiqing Peng3Lina Ping4Xiang Fan5Feiyu Teng6Xiangnan Liu7School of Information Engineering, China University of Geosciences, Beijing 100083, ChinaThe Second Surveying and Mapping Institute of Hunan Province, Changsha 410004, ChinaThe Second Surveying and Mapping Institute of Hunan Province, Changsha 410004, ChinaThe Second Surveying and Mapping Institute of Hunan Province, Changsha 410004, ChinaThe Second Surveying and Mapping Institute of Hunan Province, Changsha 410004, ChinaThe Second Surveying and Mapping Institute of Hunan Province, Changsha 410004, ChinaSchool of Information Engineering, China University of Geosciences, Beijing 100083, ChinaSchool of Information Engineering, China University of Geosciences, Beijing 100083, ChinaExtracting fragmented cropland is essential for effective cropland management and sustainable agricultural development. However, extracting fragmented cropland presents significant challenges due to its irregular and blurred boundaries, as well as the diversity in crop types and distribution. Deep learning methods are widely used for land cover classification. This paper proposes ConvNeXt-U, a lightweight deep learning network that efficiently extracts fragmented cropland while reducing computational requirements and saving costs. ConvNeXt-U retains the U-shaped structure of U-Net but replaces the encoder with a simplified ConvNeXt architecture. The decoder remains unchanged from U-Net, and the lightweight CBAM (Convolutional Block Attention Module) is integrated. This module adaptively adjusts the channel and spatial dimensions of feature maps, emphasizing key features and suppressing redundant information, which enhances the capture of edge features and improves extraction accuracy. The case study area is Hengyang County, Hunan Province, China, using GF-2 remote sensing imagery. The results show that ConvNeXt-U outperforms existing methods, such as Swin Transformer (Acc = 85.1%, IoU = 79.1%), MobileNetV3 (Acc = 83.4%, IoU = 77.6%), VGG16 (Acc = 80.5%, IoU = 74.6%), and ResUnet (Acc = 81.8%, IoU = 76.1%), achieving an IoU of 79.5% and Acc of 85.2%. Under the same conditions, ConvNeXt-U has a faster inference speed of 37 images/s, compared to 28 images/s for Swin Transformer, 35 images/s for MobileNetV3, and 0.43 and 0.44 images/s for VGG16 and ResUnet, respectively. Moreover, ConvNeXt-U outperforms other methods in processing the boundaries of fragmented cropland, producing clearer and more complete boundaries. The results indicate that the ConvNeXt and CBAM modules significantly enhance the accuracy of fragmented cropland extraction. ConvNeXt-U is also an effective method for extracting fragmented cropland from remote sensing imagery.https://www.mdpi.com/1424-8220/25/1/261fragmented cropland extractionConvNeXt-Ulightweight modelGF-2remote sensing |
| spellingShingle | Shukuan Liu Shi Cao Xia Lu Jiqing Peng Lina Ping Xiang Fan Feiyu Teng Xiangnan Liu Lightweight Deep Learning Model, ConvNeXt-U: An Improved U-Net Network for Extracting Cropland in Complex Landscapes from Gaofen-2 Images Sensors fragmented cropland extraction ConvNeXt-U lightweight model GF-2 remote sensing |
| title | Lightweight Deep Learning Model, ConvNeXt-U: An Improved U-Net Network for Extracting Cropland in Complex Landscapes from Gaofen-2 Images |
| title_full | Lightweight Deep Learning Model, ConvNeXt-U: An Improved U-Net Network for Extracting Cropland in Complex Landscapes from Gaofen-2 Images |
| title_fullStr | Lightweight Deep Learning Model, ConvNeXt-U: An Improved U-Net Network for Extracting Cropland in Complex Landscapes from Gaofen-2 Images |
| title_full_unstemmed | Lightweight Deep Learning Model, ConvNeXt-U: An Improved U-Net Network for Extracting Cropland in Complex Landscapes from Gaofen-2 Images |
| title_short | Lightweight Deep Learning Model, ConvNeXt-U: An Improved U-Net Network for Extracting Cropland in Complex Landscapes from Gaofen-2 Images |
| title_sort | lightweight deep learning model convnext u an improved u net network for extracting cropland in complex landscapes from gaofen 2 images |
| topic | fragmented cropland extraction ConvNeXt-U lightweight model GF-2 remote sensing |
| url | https://www.mdpi.com/1424-8220/25/1/261 |
| work_keys_str_mv | AT shukuanliu lightweightdeeplearningmodelconvnextuanimprovedunetnetworkforextractingcroplandincomplexlandscapesfromgaofen2images AT shicao lightweightdeeplearningmodelconvnextuanimprovedunetnetworkforextractingcroplandincomplexlandscapesfromgaofen2images AT xialu lightweightdeeplearningmodelconvnextuanimprovedunetnetworkforextractingcroplandincomplexlandscapesfromgaofen2images AT jiqingpeng lightweightdeeplearningmodelconvnextuanimprovedunetnetworkforextractingcroplandincomplexlandscapesfromgaofen2images AT linaping lightweightdeeplearningmodelconvnextuanimprovedunetnetworkforextractingcroplandincomplexlandscapesfromgaofen2images AT xiangfan lightweightdeeplearningmodelconvnextuanimprovedunetnetworkforextractingcroplandincomplexlandscapesfromgaofen2images AT feiyuteng lightweightdeeplearningmodelconvnextuanimprovedunetnetworkforextractingcroplandincomplexlandscapesfromgaofen2images AT xiangnanliu lightweightdeeplearningmodelconvnextuanimprovedunetnetworkforextractingcroplandincomplexlandscapesfromgaofen2images |