Land-Cover Classification Using Deep Learning with High-Resolution Remote-Sensing Imagery
Land-area classification (LAC) research offers a promising avenue to address the intricacies of urban planning, agricultural zoning, and environmental monitoring, with a specific focus on urban areas and their complex land usage patterns. The potential of LAC research is significantly propelled by a...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/14/5/1844 |
| _version_ | 1827319838685528064 |
|---|---|
| author | Muhammad Fayaz Junyoung Nam L. Minh Dang Hyoung-Kyu Song Hyeonjoon Moon |
| author_facet | Muhammad Fayaz Junyoung Nam L. Minh Dang Hyoung-Kyu Song Hyeonjoon Moon |
| author_sort | Muhammad Fayaz |
| collection | DOAJ |
| description | Land-area classification (LAC) research offers a promising avenue to address the intricacies of urban planning, agricultural zoning, and environmental monitoring, with a specific focus on urban areas and their complex land usage patterns. The potential of LAC research is significantly propelled by advancements in high-resolution satellite imagery and machine learning strategies, particularly the use of convolutional neural networks (CNNs). Accurate LAC is paramount for informed urban development and effective land management. Traditional remote-sensing methods encounter limitations in precisely classifying dynamic and complex urban land areas. Therefore, in this study, we investigated the application of transfer learning with Inception-v3 and DenseNet121 architectures to establish a reliable LAC system for identifying urban land use classes. Leveraging transfer learning with these models provided distinct advantages, as it allows the LAC system to benefit from pre-trained features on large datasets, enhancing model generalization and performance compared to starting from scratch. Transfer learning also facilitates the effective utilization of limited labeled data for fine-tuning, making it a valuable strategy for optimizing model accuracy in complex urban land classification tasks. Moreover, we strategically employ fine-tuned versions of Inception-v3 and DenseNet121 networks, emphasizing the transformative impact of these architectures. The fine-tuning process enables the model to leverage pre-existing knowledge from extensive datasets, enhancing its adaptability to the intricacies of LC classification. By aligning with these advanced techniques, our research not only contributes to the evolution of remote-sensing methodologies but also underscores the paramount importance of incorporating cutting-edge methodologies, such as fine-tuning and the use of specific network architectures, in the continual enhancement of LC classification systems. Through experiments conducted on the UC-Merced_LandUse dataset, we demonstrate the effectiveness of our approach, achieving remarkable results, including 92% <i>accuracy</i>, 93% <i>recall</i>, 92% <i>precision</i>, and a 92% <i>F</i>1-<i>score</i>. Moreover, employing heatmap analysis further elucidates the decision-making process of the models, providing insights into the classification mechanism. The successful application of CNNs in LAC, coupled with heatmap analysis, opens promising avenues for enhanced urban planning, agricultural zoning, and environmental monitoring through more accurate and automated land-area classification. |
| first_indexed | 2024-04-25T00:35:22Z |
| format | Article |
| id | doaj.art-577fce2a7fbe4633ad243777dbd3add4 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-04-25T00:35:22Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-577fce2a7fbe4633ad243777dbd3add42024-03-12T16:39:11ZengMDPI AGApplied Sciences2076-34172024-02-01145184410.3390/app14051844Land-Cover Classification Using Deep Learning with High-Resolution Remote-Sensing ImageryMuhammad Fayaz0Junyoung Nam1L. Minh Dang2Hyoung-Kyu Song3Hyeonjoon Moon4Department of Computer Science and Engineering, Sejong University, Seoul 05006, Republic of KoreaDepartment of Computer Science and Engineering, Sejong University, Seoul 05006, Republic of KoreaDepartment of Information and Communication Engineering and Convergence Engineering for Intelligent Drone, Sejong University, Seoul 05006, Republic of KoreaDepartment of Information and Communication Engineering and Convergence Engineering for Intelligent Drone, Sejong University, Seoul 05006, Republic of KoreaDepartment of Computer Science and Engineering, Sejong University, Seoul 05006, Republic of KoreaLand-area classification (LAC) research offers a promising avenue to address the intricacies of urban planning, agricultural zoning, and environmental monitoring, with a specific focus on urban areas and their complex land usage patterns. The potential of LAC research is significantly propelled by advancements in high-resolution satellite imagery and machine learning strategies, particularly the use of convolutional neural networks (CNNs). Accurate LAC is paramount for informed urban development and effective land management. Traditional remote-sensing methods encounter limitations in precisely classifying dynamic and complex urban land areas. Therefore, in this study, we investigated the application of transfer learning with Inception-v3 and DenseNet121 architectures to establish a reliable LAC system for identifying urban land use classes. Leveraging transfer learning with these models provided distinct advantages, as it allows the LAC system to benefit from pre-trained features on large datasets, enhancing model generalization and performance compared to starting from scratch. Transfer learning also facilitates the effective utilization of limited labeled data for fine-tuning, making it a valuable strategy for optimizing model accuracy in complex urban land classification tasks. Moreover, we strategically employ fine-tuned versions of Inception-v3 and DenseNet121 networks, emphasizing the transformative impact of these architectures. The fine-tuning process enables the model to leverage pre-existing knowledge from extensive datasets, enhancing its adaptability to the intricacies of LC classification. By aligning with these advanced techniques, our research not only contributes to the evolution of remote-sensing methodologies but also underscores the paramount importance of incorporating cutting-edge methodologies, such as fine-tuning and the use of specific network architectures, in the continual enhancement of LC classification systems. Through experiments conducted on the UC-Merced_LandUse dataset, we demonstrate the effectiveness of our approach, achieving remarkable results, including 92% <i>accuracy</i>, 93% <i>recall</i>, 92% <i>precision</i>, and a 92% <i>F</i>1-<i>score</i>. Moreover, employing heatmap analysis further elucidates the decision-making process of the models, providing insights into the classification mechanism. The successful application of CNNs in LAC, coupled with heatmap analysis, opens promising avenues for enhanced urban planning, agricultural zoning, and environmental monitoring through more accurate and automated land-area classification.https://www.mdpi.com/2076-3417/14/5/1844deep learningtransfer learningland-area classificationCNN |
| spellingShingle | Muhammad Fayaz Junyoung Nam L. Minh Dang Hyoung-Kyu Song Hyeonjoon Moon Land-Cover Classification Using Deep Learning with High-Resolution Remote-Sensing Imagery Applied Sciences deep learning transfer learning land-area classification CNN |
| title | Land-Cover Classification Using Deep Learning with High-Resolution Remote-Sensing Imagery |
| title_full | Land-Cover Classification Using Deep Learning with High-Resolution Remote-Sensing Imagery |
| title_fullStr | Land-Cover Classification Using Deep Learning with High-Resolution Remote-Sensing Imagery |
| title_full_unstemmed | Land-Cover Classification Using Deep Learning with High-Resolution Remote-Sensing Imagery |
| title_short | Land-Cover Classification Using Deep Learning with High-Resolution Remote-Sensing Imagery |
| title_sort | land cover classification using deep learning with high resolution remote sensing imagery |
| topic | deep learning transfer learning land-area classification CNN |
| url | https://www.mdpi.com/2076-3417/14/5/1844 |
| work_keys_str_mv | AT muhammadfayaz landcoverclassificationusingdeeplearningwithhighresolutionremotesensingimagery AT junyoungnam landcoverclassificationusingdeeplearningwithhighresolutionremotesensingimagery AT lminhdang landcoverclassificationusingdeeplearningwithhighresolutionremotesensingimagery AT hyoungkyusong landcoverclassificationusingdeeplearningwithhighresolutionremotesensingimagery AT hyeonjoonmoon landcoverclassificationusingdeeplearningwithhighresolutionremotesensingimagery |