Integration of Object-Based Image Analysis and Convolutional Neural Network for the Classification of High-Resolution Satellite Image: A Comparative Assessment
During the past decade, deep learning-based classification methods (e.g., convolutional neural networks—CNN) have demonstrated great success in a variety of vision tasks, including satellite image classification. Deep learning methods, on the other hand, do not preserve the precise edges of the targ...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/21/10890 |
| _version_ | 1797469234604802048 |
|---|---|
| author | Omer Saud Azeez Helmi Z. M. Shafri Aidi Hizami Alias Nuzul A. B. Haron |
| author_facet | Omer Saud Azeez Helmi Z. M. Shafri Aidi Hizami Alias Nuzul A. B. Haron |
| author_sort | Omer Saud Azeez |
| collection | DOAJ |
| description | During the past decade, deep learning-based classification methods (e.g., convolutional neural networks—CNN) have demonstrated great success in a variety of vision tasks, including satellite image classification. Deep learning methods, on the other hand, do not preserve the precise edges of the targets of interest and do not extract geometric features such as shape and area. Previous research has attempted to address such issues by combining deep learning with methods such as object-based image analysis (OBIA). Nonetheless, the question of how to integrate those methods into a single framework in such a way that the benefits of each method complement each other remains. To that end, this study compared four integration frameworks in terms of accuracy, namely OBIA artificial neural network (OBIA ANN), feature fusion, decision fusion, and patch filtering, according to the results. Patch filtering achieved 0.917 OA, whereas decision fusion and feature fusion achieved 0.862 OA and 0.860 OA, respectively. The integration of CNN and OBIA can improve classification accuracy; however, the integration framework plays a significant role in this. Future research should focus on optimizing the existing CNN and OBIA frameworks in terms of architecture, as well as investigate how CNN models should use OBIA outputs for feature extraction and classification of remotely sensed images. |
| first_indexed | 2024-03-09T19:18:29Z |
| format | Article |
| id | doaj.art-c9542263e3844a159036c0d1f103cf21 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T19:18:29Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-c9542263e3844a159036c0d1f103cf212023-11-24T03:34:38ZengMDPI AGApplied Sciences2076-34172022-10-0112211089010.3390/app122110890Integration of Object-Based Image Analysis and Convolutional Neural Network for the Classification of High-Resolution Satellite Image: A Comparative AssessmentOmer Saud Azeez0Helmi Z. M. Shafri1Aidi Hizami Alias2Nuzul A. B. Haron3Department of Civil Engineering, Faculty of Engineering, University Putra Malaysia (UPM), Serdang 43400, Selangor, MalaysiaDepartment of Civil Engineering, Faculty of Engineering, University Putra Malaysia (UPM), Serdang 43400, Selangor, MalaysiaDepartment of Civil Engineering, Faculty of Engineering, University Putra Malaysia (UPM), Serdang 43400, Selangor, MalaysiaDepartment of Civil Engineering, Faculty of Engineering, University Putra Malaysia (UPM), Serdang 43400, Selangor, MalaysiaDuring the past decade, deep learning-based classification methods (e.g., convolutional neural networks—CNN) have demonstrated great success in a variety of vision tasks, including satellite image classification. Deep learning methods, on the other hand, do not preserve the precise edges of the targets of interest and do not extract geometric features such as shape and area. Previous research has attempted to address such issues by combining deep learning with methods such as object-based image analysis (OBIA). Nonetheless, the question of how to integrate those methods into a single framework in such a way that the benefits of each method complement each other remains. To that end, this study compared four integration frameworks in terms of accuracy, namely OBIA artificial neural network (OBIA ANN), feature fusion, decision fusion, and patch filtering, according to the results. Patch filtering achieved 0.917 OA, whereas decision fusion and feature fusion achieved 0.862 OA and 0.860 OA, respectively. The integration of CNN and OBIA can improve classification accuracy; however, the integration framework plays a significant role in this. Future research should focus on optimizing the existing CNN and OBIA frameworks in terms of architecture, as well as investigate how CNN models should use OBIA outputs for feature extraction and classification of remotely sensed images.https://www.mdpi.com/2076-3417/12/21/10890deep learningconvolutional neural networksObject-Based Image Analysisremote sensingintegration frameworks |
| spellingShingle | Omer Saud Azeez Helmi Z. M. Shafri Aidi Hizami Alias Nuzul A. B. Haron Integration of Object-Based Image Analysis and Convolutional Neural Network for the Classification of High-Resolution Satellite Image: A Comparative Assessment Applied Sciences deep learning convolutional neural networks Object-Based Image Analysis remote sensing integration frameworks |
| title | Integration of Object-Based Image Analysis and Convolutional Neural Network for the Classification of High-Resolution Satellite Image: A Comparative Assessment |
| title_full | Integration of Object-Based Image Analysis and Convolutional Neural Network for the Classification of High-Resolution Satellite Image: A Comparative Assessment |
| title_fullStr | Integration of Object-Based Image Analysis and Convolutional Neural Network for the Classification of High-Resolution Satellite Image: A Comparative Assessment |
| title_full_unstemmed | Integration of Object-Based Image Analysis and Convolutional Neural Network for the Classification of High-Resolution Satellite Image: A Comparative Assessment |
| title_short | Integration of Object-Based Image Analysis and Convolutional Neural Network for the Classification of High-Resolution Satellite Image: A Comparative Assessment |
| title_sort | integration of object based image analysis and convolutional neural network for the classification of high resolution satellite image a comparative assessment |
| topic | deep learning convolutional neural networks Object-Based Image Analysis remote sensing integration frameworks |
| url | https://www.mdpi.com/2076-3417/12/21/10890 |
| work_keys_str_mv | AT omersaudazeez integrationofobjectbasedimageanalysisandconvolutionalneuralnetworkfortheclassificationofhighresolutionsatelliteimageacomparativeassessment AT helmizmshafri integrationofobjectbasedimageanalysisandconvolutionalneuralnetworkfortheclassificationofhighresolutionsatelliteimageacomparativeassessment AT aidihizamialias integrationofobjectbasedimageanalysisandconvolutionalneuralnetworkfortheclassificationofhighresolutionsatelliteimageacomparativeassessment AT nuzulabharon integrationofobjectbasedimageanalysisandconvolutionalneuralnetworkfortheclassificationofhighresolutionsatelliteimageacomparativeassessment |