A classification framework with multi-level fusion of object-based analysis and convolutional neural network: a case study for land use classification in mining areas
To enhance the accuracy of land use classification in mining areas, the Object-based Convolutional Neural Network (OCNN) method has been widely used. However, existing researches tend to neglect the importance of decision-level fusion, focusing only on feature-level fusion. This study proposes a new...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2025-05-01
|
| Series: | Geo-spatial Information Science |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/10095020.2024.2336594 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849397626021085184 |
|---|---|
| author | Jianghe Xing Zhenwei Li Jun Li Shouhang Du Wei Li Chengye Zhang |
| author_facet | Jianghe Xing Zhenwei Li Jun Li Shouhang Du Wei Li Chengye Zhang |
| author_sort | Jianghe Xing |
| collection | DOAJ |
| description | To enhance the accuracy of land use classification in mining areas, the Object-based Convolutional Neural Network (OCNN) method has been widely used. However, existing researches tend to neglect the importance of decision-level fusion, focusing only on feature-level fusion. This study proposes a new classification framework with Multi-level Fusion of Object-based analysis and CNN (MFOCNN) to achieves high-accuracy land use classification in mining areas. First, Simple Linear Iterative Cluster (SLIC) is employed to generate image objects, which serve as the basic unit for classification. Second, an improved DenseNet is proposed to extract deep features from image patches, which represent image objects, and provide the classification result. Third, handcrafted features including spectral, textural and geometric of the image objects are extracted and fused with the deep features to obtain the classification result with random forest classifier. Finally, the Dempster-Shafer (DS) evidence theory is applied to fuse the two previously described classification results at the decision-level to obtain the final result. Experiments conducted in the mining areas of Erdos using Gaofen-6 images demonstrate that the proposed MFOCNN achieves the best visual performance and accuracy among all tested methods. The MFOCNN, with its feature-level fusion and decision-level fusion, significantly improves the accuracy of land use classification in mining areas. The results suggest that the proposed MFOCNN is a promising method for achieving high-accuracy land use classification in mining areas. |
| format | Article |
| id | doaj-art-aec18898bc35477e89d1f34a06259a1e |
| institution | Kabale University |
| issn | 1009-5020 1993-5153 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Geo-spatial Information Science |
| spelling | doaj-art-aec18898bc35477e89d1f34a06259a1e2025-08-20T03:38:55ZengTaylor & Francis GroupGeo-spatial Information Science1009-50201993-51532025-05-0128386788310.1080/10095020.2024.2336594A classification framework with multi-level fusion of object-based analysis and convolutional neural network: a case study for land use classification in mining areasJianghe Xing0Zhenwei Li1Jun Li2Shouhang Du3Wei Li4Chengye Zhang5College of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing, ChinaCollege of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing, ChinaCollege of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing, ChinaCollege of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing, ChinaCollege of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing, ChinaKey Laboratory of Coupling Process and Effect of Natural Resources Elements, Ministry of Natural Resources, Beijing, ChinaTo enhance the accuracy of land use classification in mining areas, the Object-based Convolutional Neural Network (OCNN) method has been widely used. However, existing researches tend to neglect the importance of decision-level fusion, focusing only on feature-level fusion. This study proposes a new classification framework with Multi-level Fusion of Object-based analysis and CNN (MFOCNN) to achieves high-accuracy land use classification in mining areas. First, Simple Linear Iterative Cluster (SLIC) is employed to generate image objects, which serve as the basic unit for classification. Second, an improved DenseNet is proposed to extract deep features from image patches, which represent image objects, and provide the classification result. Third, handcrafted features including spectral, textural and geometric of the image objects are extracted and fused with the deep features to obtain the classification result with random forest classifier. Finally, the Dempster-Shafer (DS) evidence theory is applied to fuse the two previously described classification results at the decision-level to obtain the final result. Experiments conducted in the mining areas of Erdos using Gaofen-6 images demonstrate that the proposed MFOCNN achieves the best visual performance and accuracy among all tested methods. The MFOCNN, with its feature-level fusion and decision-level fusion, significantly improves the accuracy of land use classification in mining areas. The results suggest that the proposed MFOCNN is a promising method for achieving high-accuracy land use classification in mining areas.https://www.tandfonline.com/doi/10.1080/10095020.2024.2336594Mining areasland use classificationobject-based analysisDenseNet |
| spellingShingle | Jianghe Xing Zhenwei Li Jun Li Shouhang Du Wei Li Chengye Zhang A classification framework with multi-level fusion of object-based analysis and convolutional neural network: a case study for land use classification in mining areas Geo-spatial Information Science Mining areas land use classification object-based analysis DenseNet |
| title | A classification framework with multi-level fusion of object-based analysis and convolutional neural network: a case study for land use classification in mining areas |
| title_full | A classification framework with multi-level fusion of object-based analysis and convolutional neural network: a case study for land use classification in mining areas |
| title_fullStr | A classification framework with multi-level fusion of object-based analysis and convolutional neural network: a case study for land use classification in mining areas |
| title_full_unstemmed | A classification framework with multi-level fusion of object-based analysis and convolutional neural network: a case study for land use classification in mining areas |
| title_short | A classification framework with multi-level fusion of object-based analysis and convolutional neural network: a case study for land use classification in mining areas |
| title_sort | classification framework with multi level fusion of object based analysis and convolutional neural network a case study for land use classification in mining areas |
| topic | Mining areas land use classification object-based analysis DenseNet |
| url | https://www.tandfonline.com/doi/10.1080/10095020.2024.2336594 |
| work_keys_str_mv | AT jianghexing aclassificationframeworkwithmultilevelfusionofobjectbasedanalysisandconvolutionalneuralnetworkacasestudyforlanduseclassificationinminingareas AT zhenweili aclassificationframeworkwithmultilevelfusionofobjectbasedanalysisandconvolutionalneuralnetworkacasestudyforlanduseclassificationinminingareas AT junli aclassificationframeworkwithmultilevelfusionofobjectbasedanalysisandconvolutionalneuralnetworkacasestudyforlanduseclassificationinminingareas AT shouhangdu aclassificationframeworkwithmultilevelfusionofobjectbasedanalysisandconvolutionalneuralnetworkacasestudyforlanduseclassificationinminingareas AT weili aclassificationframeworkwithmultilevelfusionofobjectbasedanalysisandconvolutionalneuralnetworkacasestudyforlanduseclassificationinminingareas AT chengyezhang aclassificationframeworkwithmultilevelfusionofobjectbasedanalysisandconvolutionalneuralnetworkacasestudyforlanduseclassificationinminingareas AT jianghexing classificationframeworkwithmultilevelfusionofobjectbasedanalysisandconvolutionalneuralnetworkacasestudyforlanduseclassificationinminingareas AT zhenweili classificationframeworkwithmultilevelfusionofobjectbasedanalysisandconvolutionalneuralnetworkacasestudyforlanduseclassificationinminingareas AT junli classificationframeworkwithmultilevelfusionofobjectbasedanalysisandconvolutionalneuralnetworkacasestudyforlanduseclassificationinminingareas AT shouhangdu classificationframeworkwithmultilevelfusionofobjectbasedanalysisandconvolutionalneuralnetworkacasestudyforlanduseclassificationinminingareas AT weili classificationframeworkwithmultilevelfusionofobjectbasedanalysisandconvolutionalneuralnetworkacasestudyforlanduseclassificationinminingareas AT chengyezhang classificationframeworkwithmultilevelfusionofobjectbasedanalysisandconvolutionalneuralnetworkacasestudyforlanduseclassificationinminingareas |