End-to-End Convolutional Neural Network Feature Extraction for Remote Sensed Images Classification
Recently, land cover and land use (LCLU) classification in remote sensing imagery has attracted research interest. The LCLU contains dynamic remote sensed images due to sensor technology ability, seasonal changes, and distance for resolution. Therefore, the deep learning-based LCLU classification sy...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2022-12-01
|
| Series: | Applied Artificial Intelligence |
| Online Access: | http://dx.doi.org/10.1080/08839514.2022.2137650 |
| _version_ | 1797641092242341888 |
|---|---|
| author | Abebaw Alem Shailender Kumar |
| author_facet | Abebaw Alem Shailender Kumar |
| author_sort | Abebaw Alem |
| collection | DOAJ |
| description | Recently, land cover and land use (LCLU) classification in remote sensing imagery has attracted research interest. The LCLU contains dynamic remote sensed images due to sensor technology ability, seasonal changes, and distance for resolution. Therefore, the deep learning-based LCLU classification system needs more investigation using deep learning techniques. Deep learning approaches have gotten more attention for their powerful performance improvements. Most recent studies have been performed on deep convolutional neural networks (CNNs) that have been trained on pre-trained networks in remote sensing classification. However, designing CNNs from scratch has not yet been widely investigated in remote sensed images as they need ample training time and a powerful processor. Therefore, we used hyperparameters and early stopping techniques to apply an end-to-end CNN feature extractor (CNN-FE) model for LCLU classification in the UC-Merced dataset. We approved the model's applicability in the domain area by retraining it on another dataset called SIRI-WHU and building the VGG19 pre-trained feature extractor model built on the same hyperparameters. The CNN-FE has outperformed the state-of-the-art baseline studies' accuracy and the VGG19 pre-trained model. Moreover, a better CNN-FE performance was achieved when trained in the UC-Merced dataset than the model performance when trained in the SIRI-WHU dataset. |
| first_indexed | 2024-03-11T13:40:33Z |
| format | Article |
| id | doaj.art-9b5628fe70c142ebad6d0a22657a500b |
| institution | Directory Open Access Journal |
| issn | 0883-9514 1087-6545 |
| language | English |
| last_indexed | 2024-03-11T13:40:33Z |
| publishDate | 2022-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Applied Artificial Intelligence |
| spelling | doaj.art-9b5628fe70c142ebad6d0a22657a500b2023-11-02T13:36:39ZengTaylor & Francis GroupApplied Artificial Intelligence0883-95141087-65452022-12-0136110.1080/08839514.2022.21376502137650End-to-End Convolutional Neural Network Feature Extraction for Remote Sensed Images ClassificationAbebaw Alem0Shailender Kumar1Delhi Technological UniversityDelhi Technological UniversityRecently, land cover and land use (LCLU) classification in remote sensing imagery has attracted research interest. The LCLU contains dynamic remote sensed images due to sensor technology ability, seasonal changes, and distance for resolution. Therefore, the deep learning-based LCLU classification system needs more investigation using deep learning techniques. Deep learning approaches have gotten more attention for their powerful performance improvements. Most recent studies have been performed on deep convolutional neural networks (CNNs) that have been trained on pre-trained networks in remote sensing classification. However, designing CNNs from scratch has not yet been widely investigated in remote sensed images as they need ample training time and a powerful processor. Therefore, we used hyperparameters and early stopping techniques to apply an end-to-end CNN feature extractor (CNN-FE) model for LCLU classification in the UC-Merced dataset. We approved the model's applicability in the domain area by retraining it on another dataset called SIRI-WHU and building the VGG19 pre-trained feature extractor model built on the same hyperparameters. The CNN-FE has outperformed the state-of-the-art baseline studies' accuracy and the VGG19 pre-trained model. Moreover, a better CNN-FE performance was achieved when trained in the UC-Merced dataset than the model performance when trained in the SIRI-WHU dataset.http://dx.doi.org/10.1080/08839514.2022.2137650 |
| spellingShingle | Abebaw Alem Shailender Kumar End-to-End Convolutional Neural Network Feature Extraction for Remote Sensed Images Classification Applied Artificial Intelligence |
| title | End-to-End Convolutional Neural Network Feature Extraction for Remote Sensed Images Classification |
| title_full | End-to-End Convolutional Neural Network Feature Extraction for Remote Sensed Images Classification |
| title_fullStr | End-to-End Convolutional Neural Network Feature Extraction for Remote Sensed Images Classification |
| title_full_unstemmed | End-to-End Convolutional Neural Network Feature Extraction for Remote Sensed Images Classification |
| title_short | End-to-End Convolutional Neural Network Feature Extraction for Remote Sensed Images Classification |
| title_sort | end to end convolutional neural network feature extraction for remote sensed images classification |
| url | http://dx.doi.org/10.1080/08839514.2022.2137650 |
| work_keys_str_mv | AT abebawalem endtoendconvolutionalneuralnetworkfeatureextractionforremotesensedimagesclassification AT shailenderkumar endtoendconvolutionalneuralnetworkfeatureextractionforremotesensedimagesclassification |