China roof12/26/2023 ![]() ![]() Conventional image process techniques, however, involve complex empirical rules and threshold settings, and thus, exhibit limitations when applied to high-resolution remote sensing imagery in large-scale 14. Due to the development of image processing algorithms, such as the edge detection and image segmentation, rooftops data can be extracted from high-resolution remote sensing imagery 17, 18. However, the costs of acquiring 3D spatial data and of constructing the associated 3D models are costly, especially at the city scale. Three-dimensional (3D) spatial data, such as the Digital Surface Model (DSM) and Light Detection and Ranging (LiDAR), are exploited for reconstructing buildings, which includes the rooftop area representation and geometric modeling 13, 14, 15, 16. The automatic extraction of rooftop area data is gaining popularity in diverse fields, and studies involving varied data sources exist 13. Therefore, methods suitable for generating reliable data on rooftop areas of buildings at low cost are urgently needed 10, 11, 12. ![]() However, data on rooftop areas are unavailable in many developing countries because of resource constraints. These trends are useful for formulating development strategies and protecting urban and rural ecosystems 7, 8, 9. The rapid access to accurate rooftop information is important for the evaluation of urban and rural development trends. Owing to urbanization associated with the digital age, reliable information on rooftops is in increasing demand 4, 5, 6. Rooftops of buildings have been intensively studied in fields such as sustainable urban development, building energy modeling, and urban planning and design in recent decades 1, 2, 3. These results demonstrate that the generated dataset can be used for data support and decision-making that can facilitate sustainable urban development effectively. In addition, the generated rooftop area conforms to the urban morphological characteristics and reflects urbanization level. The data was validated on test samples of 180 km 2 across different regions with spatial resolution, overall accuracy, and F1 score of 1 m, 97.95%, and 83.11%, respectively. This framework is used to generate vectorized data for rooftops in 90 cities in China. In this study, a geospatial artificial intelligence framework is presented to obtain data for rooftops using high-resolution open-access remote sensing imagery. However, obtaining these data is challenging due to the limited capability of conventional computer vision methods and the high cost of 3D modeling involving aerial photogrammetry. In recent decades, the demand for accurate and up-to-date data on the areas of rooftops on a large-scale is increasing. Reliable information on building rooftops is crucial for utilizing limited urban space effectively. ![]()
0 Comments
Leave a Reply.AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |