摘要
Building rooftop data are of importance in several urban applications and in natural disaster management. In contrast to traditional surveying and mapping, by using high spatial resolution aerial images, deep learning-based building rooftops extraction methods are efficient and accurate. Although more training data is preferred in deep learning-based tasks, the effect of data volume on building extraction models is underexplored. Therefore, the paper explores the impact of data volume on the performance of building rooftop extraction from very-high-spatial-resolution (VHSR) images using deep learning-based methods. To do so, we manually labelled 0.12m spatial resolution aerial images and perform a comparative analysis of models trained on datasets of different sizes using popular deep learning architectures for segmentation tasks, including Fully Convolutional Networks (FCN)-8s, U-Net and DeepLabv3+. The experiments showed that with more training data, algorithms converged faster and achieved higher accuracy, while better algorithms were able to better mitigate the lack of training data.
| 源语言 | 英语 |
|---|---|
| 主期刊名 | IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings |
| 出版商 | Institute of Electrical and Electronics Engineers Inc. |
| 页 | 1343-1346 |
| 页数 | 4 |
| ISBN(电子版) | 9781665403696 |
| DOI | |
| 出版状态 | 已出版 - 2021 |
| 已对外发布 | 是 |
| 活动 | 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021 - Online, Virtual, 比利时 期限: 12 7月 2021 → 16 7月 2021 |
丛书
| 姓名 | International Geoscience and Remote Sensing Symposium (IGARSS) |
|---|---|
| 卷 | 2021-July |
| ISSN(印刷版) | 2153-6996 |
| ISSN(电子版) | 2153-7003 |
会议
| 会议 | 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021 |
|---|---|
| 国家/地区 | 比利时 |
| 市 | Online, Virtual |
| 时期 | 12/07/21 → 16/07/21 |
联合国可持续发展目标
此成果有助于实现下列可持续发展目标:
-
可持续发展目标 11 可持续城市和社区
学术指纹
探究 'THE IMPACT OF DATA VOLUME ON PERFORMANCE OF DEPP LEARNING BASED BUILDING ROOFTOP EXTRACTION USING VERY HIGH SPATIAL RESOLUTION AERIAL IMAGES' 的科研主题。它们共同构成独一无二的学术指纹。引用此
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver