Newswise – Accurate and comprehensive building data is critical for urban management and planning. Existing datasets, such as those from Microsoft and OpenStreetMap, often lack completeness and accuracy in East Asia, limiting their usefulness for large-scale applications. The complex distribution of buildings in this region and the lack of supporting data make the extraction of reliable building footprints even more complex. Based on these challenges, there is a need for more detailed and accurate datasets to support urban analysis and planning. Therefore, a comprehensive mapping framework was developed to address these issues and produce a high-quality building dataset for East Asia.
Researchers at Sun Yat-sen University, in collaboration with international experts, published their Conclusion (DOI: 10.34133/remotesensing.0138) In Remote Sensing JournalOn May 9, 2024. The study details a novel framework for building extraction using very high-resolution (VHR) images, marking a significant leap forward in urban data acquisition.
The study addresses the limitations of existing building datasets in East Asia by introducing a comprehensive large-scale building mapping (CLSM) framework. This framework employs innovative strategies such as region-based adaptive fine-tuning, stable boundary optimization, and high model efficiency through model distillation. Using high-resolution Google Earth images, researchers extracted traces of buildings in five East Asian countries, resulting in a dataset of more than 280 million buildings spanning 2,897 cities, with an average overall accuracy of 89.63% and F1 score of 82.55. % Was. The CLSM framework effectively manages the complex layout and diverse appearance typical of East Asian urban environments. Its boundary enhancement and regularization modules improve building boundary extraction accuracy, while model distillation techniques enhance computational efficiency. The region-based adaptive fine-tuning strategy enhances the generalization capabilities of the model, ensuring consistently high-quality results across different regions. Compared to existing datasets, this new dataset offers better quality and completeness, making it invaluable for urban planning, energy management and related research areas.
Dr. Jiajun Zhu, lead researcher of the study, said, “Our comprehensive mapping framework addresses the critical need for accurate and complete building data in East Asia. This dataset not only enhances urban planning and management but also supports a wide range of research. Also supports.” Application. “The high accuracy and detailed representation of building footprints offers new opportunities for urban analysis and sustainable development.”
The implications of this research are far-reaching, providing support for urban analysis, energy modeling and sustainable city planning. The availability of the dataset promises to be a cornerstone for future studies and urban development strategies in one of the world’s most populous and rapidly urbanizing regions.
,
Reference
DOI
original source url
https://spj.science.org/doi/10.34133/remotesensing.0138
Funding Information
This study was partially supported by the National Key R&D Program of China under grant 2022YFB3903402, partially by the National Natural Science Foundation of China under grant 422222106, partially by the National Natural Science Foundation of China under grant 61976234, and partially by Was supported. Fundamental Research Funds for the Central Universities, Sun Yat-sen University under grant 22lgqb12.
About this Remote Sensing Journal
Remote Sensing Journal, An online-open access journal published in collaboration with AIR-CAS, it promotes interdisciplinary research within the theory, science and technology of remote sensing, as well as Earth and information sciences.
