Building Detection from SkySat Images with Transfer Learning: a Case Study over Ankara

IF 2.1 4区 地球科学 Q3 IMAGING SCIENCE & PHOTOGRAPHIC TECHNOLOGY
Kanako Sawa, Ilyas Yalcin, Sultan Kocaman
{"title":"Building Detection from SkySat Images with Transfer Learning: a Case Study over Ankara","authors":"Kanako Sawa, Ilyas Yalcin, Sultan Kocaman","doi":"10.1007/s41064-024-00279-x","DOIUrl":null,"url":null,"abstract":"<p>The detection and continuous updating of buildings in geodatabases has long been a major research area in geographic information science and is an important theme for national mapping agencies. Advancements in machine learning techniques, particularly state-of-the-art deep learning (DL) models, offer promising solutions for extracting and modeling building rooftops from images. However, tasks such as automatic labelling of learning data and the generalizability of models remain challenging. In this study, we assessed the sensor and geographic area adaptation capabilities of a pretrained DL model implemented in the ArcGIS environment using very-high-resolution (50 cm) SkySat imagery. The model was trained for digitizing building footprints via Mask R‑CNN with a ResNet50 backbone using aerial and satellite images from parts of the USA. Here, we utilized images from three different SkySat satellites with various acquisition dates and off-nadir angles and refined the pretrained model using small numbers of buildings as training data (5–53 buildings) over Ankara. We evaluated the buildings in areas with different characteristics, such as urban transformation, slums, regular, and obtained high accuracies with F‑1 scores of 0.92, 0.94, and 0.96 from SkySat 4, 7, and 17, respectively. The study findings showed that the DL model has high transfer learning capability for Ankara using only a few buildings and that the recent SkySat satellites demonstrate superior image quality.</p>","PeriodicalId":56035,"journal":{"name":"PFG-Journal of Photogrammetry Remote Sensing and Geoinformation Science","volume":"40 1","pages":""},"PeriodicalIF":2.1000,"publicationDate":"2024-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"PFG-Journal of Photogrammetry Remote Sensing and Geoinformation Science","FirstCategoryId":"89","ListUrlMain":"https://doi.org/10.1007/s41064-024-00279-x","RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"IMAGING SCIENCE & PHOTOGRAPHIC TECHNOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

The detection and continuous updating of buildings in geodatabases has long been a major research area in geographic information science and is an important theme for national mapping agencies. Advancements in machine learning techniques, particularly state-of-the-art deep learning (DL) models, offer promising solutions for extracting and modeling building rooftops from images. However, tasks such as automatic labelling of learning data and the generalizability of models remain challenging. In this study, we assessed the sensor and geographic area adaptation capabilities of a pretrained DL model implemented in the ArcGIS environment using very-high-resolution (50 cm) SkySat imagery. The model was trained for digitizing building footprints via Mask R‑CNN with a ResNet50 backbone using aerial and satellite images from parts of the USA. Here, we utilized images from three different SkySat satellites with various acquisition dates and off-nadir angles and refined the pretrained model using small numbers of buildings as training data (5–53 buildings) over Ankara. We evaluated the buildings in areas with different characteristics, such as urban transformation, slums, regular, and obtained high accuracies with F‑1 scores of 0.92, 0.94, and 0.96 from SkySat 4, 7, and 17, respectively. The study findings showed that the DL model has high transfer learning capability for Ankara using only a few buildings and that the recent SkySat satellites demonstrate superior image quality.

Abstract Image

利用迁移学习从天空卫星图像中探测建筑物:安卡拉上空的案例研究
长期以来,地理数据库中建筑物的检测和持续更新一直是地理信息科学的一个主要研究领域,也是国家测绘机构的一个重要课题。机器学习技术的进步,尤其是最先进的深度学习(DL)模型,为从图像中提取建筑物屋顶并对其进行建模提供了前景广阔的解决方案。然而,学习数据的自动标注和模型的通用性等任务仍然具有挑战性。在本研究中,我们利用超高分辨率(50 厘米)的 SkySat 图像,评估了在 ArcGIS 环境中实施的预训练 DL 模型的传感器和地理区域适应能力。利用美国部分地区的航空和卫星图像,通过以 ResNet50 为骨干的 Mask R-CNN 对该模型进行了训练,以实现建筑物足迹的数字化。在这里,我们使用了来自三颗不同的 SkySat 卫星的图像,这些图像具有不同的采集日期和离底角度,并使用安卡拉上空的少量建筑物作为训练数据(5-53 栋建筑物)对预训练模型进行了改进。我们对城市改造、贫民窟、常规等不同特征区域的建筑物进行了评估,从 SkySat 4、7 和 17 号卫星获得的 F-1 分数分别为 0.92、0.94 和 0.96,准确度较高。研究结果表明,DL 模型在安卡拉的迁移学习能力很强,只使用了几栋建筑,而且最近的 SkySat 卫星显示出卓越的图像质量。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
8.20
自引率
2.40%
发文量
38
期刊介绍: PFG is an international scholarly journal covering the progress and application of photogrammetric methods, remote sensing technology and the interconnected field of geoinformation science. It places special editorial emphasis on the communication of new methodologies in data acquisition and new approaches to optimized processing and interpretation of all types of data which were acquired by photogrammetric methods, remote sensing, image processing and the computer-aided interpretation of such data in general. The journal hence addresses both researchers and students of these disciplines at academic institutions and universities as well as the downstream users in both the private sector and public administration. Founded in 1926 under the former name Bildmessung und Luftbildwesen, PFG is worldwide the oldest journal on photogrammetry. It is the official journal of the German Society for Photogrammetry, Remote Sensing and Geoinformation (DGPF).
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信