Continuous growth and development in urban planning, along with rapid changes on the ground, have increased the need for continuous examination of these changes. Remote sensing could be considered as one of the most suitable methods to achieve this goal. Utilizing deep learning methods to extract features from images is a common method in producing land cover maps because it enables the analysis of high-level abstract concepts. This not only minimizes human involvement in information production but also reduces time and costs. In this research, suitable training samples were prepared for automatically extracting urban features such as buildings, green spaces, bare land, and roads. Among various architectures of deep learning, the UNet model was chosen as the main model of the study due to its higher accuracy in results. Additionally, the VGG-16 model was used as the backbone for transfer learning technique. Training this network was performed once with three-band aerial images (RGB) and in another state by combining image bands with digital surface models (RGB+nDSM) to compare the results and introduce the best method for extracting urban features. The results showed that the VGG-16+UNet model performed class extraction with higher overall accuracy (88.14%) in the presence of a digital surface model compared to running the model with aerial image bands (76.34%). Furthermore, based on these results, it was evident that the algorithm used in this research and its architecture can be effective in preparing urban maps and detecting significant changes.
Kabolizadeh, M., Rangzan, K., & Ghanbari, N. (2024). Automatic Extraction of Urban Features from Very High-Resolution Digital Data Using Deep Neural Networks: A Case Study of Ahvaz City. Advanced Applied Geology, (), -. doi: 10.22055/aag.2024.47110.2457
MLA
Mostafa Kabolizadeh; Kazem Rangzan; Nazanin Ghanbari. "Automatic Extraction of Urban Features from Very High-Resolution Digital Data Using Deep Neural Networks: A Case Study of Ahvaz City", Advanced Applied Geology, , , 2024, -. doi: 10.22055/aag.2024.47110.2457
HARVARD
Kabolizadeh, M., Rangzan, K., Ghanbari, N. (2024). 'Automatic Extraction of Urban Features from Very High-Resolution Digital Data Using Deep Neural Networks: A Case Study of Ahvaz City', Advanced Applied Geology, (), pp. -. doi: 10.22055/aag.2024.47110.2457
VANCOUVER
Kabolizadeh, M., Rangzan, K., Ghanbari, N. Automatic Extraction of Urban Features from Very High-Resolution Digital Data Using Deep Neural Networks: A Case Study of Ahvaz City. Advanced Applied Geology, 2024; (): -. doi: 10.22055/aag.2024.47110.2457
)