A Land Use Classification Model Based on Conditional Random Fields and Attention Mechanism Convolutional Networks
Land use is used to reflect the expression of human activities in space, and land use classification is a way to obtain accurate land use information. Obtaining high-precision land use classification from remote sensing images remains a significant challenge. Traditional machine learning methods and...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/11/2688 |
| _version_ | 1827664093821009920 |
|---|---|
| author | Kang Zheng Haiying Wang Fen Qin Zhigang Han |
| author_facet | Kang Zheng Haiying Wang Fen Qin Zhigang Han |
| author_sort | Kang Zheng |
| collection | DOAJ |
| description | Land use is used to reflect the expression of human activities in space, and land use classification is a way to obtain accurate land use information. Obtaining high-precision land use classification from remote sensing images remains a significant challenge. Traditional machine learning methods and image semantic segmentation models are unable to make full use of the spatial and contextual information of images. This results in land use classification that does not meet high-precision requirements. In order to improve the accuracy of land use classification, we propose a land use classification model, called DADNet-CRFs, that integrates an attention mechanism and conditional random fields (CRFs). The model is divided into two modules: the Dual Attention Dense Network (DADNet) and CRFs. First, the convolution method in the UNet network is modified to Dense Convolution, and the band-hole pyramid pooling module, spatial location attention mechanism module, and channel attention mechanism module are fused at appropriate locations in the network, which together form DADNet. Second, the DADNet segmentation results are used as a priori conditions to guide the training of CRFs. The model is tested with the GID dataset, and the results show that the overall accuracy of land use classification obtained with this model is 7.36% and 1.61% higher than FCN-8s and BiSeNet in classification accuracy, 11.95% and 1.81% higher in MIoU accuracy, and with a 9.35% and 2.07% higher kappa coefficient, respectively. The proposed DADNet-CRFs model can fully use the spatial and contextual semantic information of high-resolution remote sensing images, and it effectively improves the accuracy of land use classification. The model can serve as a highly accurate automatic classification tool for land use classification and mapping high-resolution images. |
| first_indexed | 2024-03-10T00:55:22Z |
| format | Article |
| id | doaj.art-ff948355b3ff49a6903826dedbff46ad |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T00:55:22Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-ff948355b3ff49a6903826dedbff46ad2023-11-23T14:45:51ZengMDPI AGRemote Sensing2072-42922022-06-011411268810.3390/rs14112688A Land Use Classification Model Based on Conditional Random Fields and Attention Mechanism Convolutional NetworksKang Zheng0Haiying Wang1Fen Qin2Zhigang Han3College of Environment and Planning, Henan University, Kaifeng 475004, ChinaCollege of Environment and Planning, Henan University, Kaifeng 475004, ChinaCollege of Environment and Planning, Henan University, Kaifeng 475004, ChinaCollege of Environment and Planning, Henan University, Kaifeng 475004, ChinaLand use is used to reflect the expression of human activities in space, and land use classification is a way to obtain accurate land use information. Obtaining high-precision land use classification from remote sensing images remains a significant challenge. Traditional machine learning methods and image semantic segmentation models are unable to make full use of the spatial and contextual information of images. This results in land use classification that does not meet high-precision requirements. In order to improve the accuracy of land use classification, we propose a land use classification model, called DADNet-CRFs, that integrates an attention mechanism and conditional random fields (CRFs). The model is divided into two modules: the Dual Attention Dense Network (DADNet) and CRFs. First, the convolution method in the UNet network is modified to Dense Convolution, and the band-hole pyramid pooling module, spatial location attention mechanism module, and channel attention mechanism module are fused at appropriate locations in the network, which together form DADNet. Second, the DADNet segmentation results are used as a priori conditions to guide the training of CRFs. The model is tested with the GID dataset, and the results show that the overall accuracy of land use classification obtained with this model is 7.36% and 1.61% higher than FCN-8s and BiSeNet in classification accuracy, 11.95% and 1.81% higher in MIoU accuracy, and with a 9.35% and 2.07% higher kappa coefficient, respectively. The proposed DADNet-CRFs model can fully use the spatial and contextual semantic information of high-resolution remote sensing images, and it effectively improves the accuracy of land use classification. The model can serve as a highly accurate automatic classification tool for land use classification and mapping high-resolution images.https://www.mdpi.com/2072-4292/14/11/2688attention mechanismconvolutional neural networksconditional random fieldsland use classification |
| spellingShingle | Kang Zheng Haiying Wang Fen Qin Zhigang Han A Land Use Classification Model Based on Conditional Random Fields and Attention Mechanism Convolutional Networks Remote Sensing attention mechanism convolutional neural networks conditional random fields land use classification |
| title | A Land Use Classification Model Based on Conditional Random Fields and Attention Mechanism Convolutional Networks |
| title_full | A Land Use Classification Model Based on Conditional Random Fields and Attention Mechanism Convolutional Networks |
| title_fullStr | A Land Use Classification Model Based on Conditional Random Fields and Attention Mechanism Convolutional Networks |
| title_full_unstemmed | A Land Use Classification Model Based on Conditional Random Fields and Attention Mechanism Convolutional Networks |
| title_short | A Land Use Classification Model Based on Conditional Random Fields and Attention Mechanism Convolutional Networks |
| title_sort | land use classification model based on conditional random fields and attention mechanism convolutional networks |
| topic | attention mechanism convolutional neural networks conditional random fields land use classification |
| url | https://www.mdpi.com/2072-4292/14/11/2688 |
| work_keys_str_mv | AT kangzheng alanduseclassificationmodelbasedonconditionalrandomfieldsandattentionmechanismconvolutionalnetworks AT haiyingwang alanduseclassificationmodelbasedonconditionalrandomfieldsandattentionmechanismconvolutionalnetworks AT fenqin alanduseclassificationmodelbasedonconditionalrandomfieldsandattentionmechanismconvolutionalnetworks AT zhiganghan alanduseclassificationmodelbasedonconditionalrandomfieldsandattentionmechanismconvolutionalnetworks AT kangzheng landuseclassificationmodelbasedonconditionalrandomfieldsandattentionmechanismconvolutionalnetworks AT haiyingwang landuseclassificationmodelbasedonconditionalrandomfieldsandattentionmechanismconvolutionalnetworks AT fenqin landuseclassificationmodelbasedonconditionalrandomfieldsandattentionmechanismconvolutionalnetworks AT zhiganghan landuseclassificationmodelbasedonconditionalrandomfieldsandattentionmechanismconvolutionalnetworks |