File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1016/j.isprsjprs.2022.08.006
- Scopus: eid_2-s2.0-85136004620
- WOS: WOS:000848879100002
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Estimation of building height using a single street view image via deep neural networks
Title | Estimation of building height using a single street view image via deep neural networks |
---|---|
Authors | |
Keywords | Building height Deep learning Single view Street view image Uncertainty analysis |
Issue Date | 2022 |
Citation | ISPRS Journal of Photogrammetry and Remote Sensing, 2022, v. 192, p. 83-98 How to Cite? |
Abstract | Building smart cities requires three-dimensional (3D) modelling to facilitate the planning and management of built environments. This requirement leads to high demand for data on vertical dimensions, such as building height, that are critical for the construction of 3D city models. Despite increasing recognition of the importance of such data, their acquisition in a low-cost and efficient manner remains a daunting task. Big data, particularly street view images (SVIs), provide an opportunity to efficiently solve this problem. In this study, we aim to derive information on building height from openly available SVIs by using single view metrology. Unlike other methods using multisource inputs, our method capitalizes on deep neural networks to extract a set of features – such as vanishing points, line segments, and semantic segmentation maps – for single view measurement and then estimates the height from single SVIs. The minimal input required by the method increases its competitiveness in large-scale estimation of building heights, especially in areas with difficulty to obtain the conventional remote sensing data. In addition to experiments that demonstrate the effectiveness and efficiency of the proposed method, we also conduct a thorough analysis of uncertainties and errors brought by the method, thereby providing guidance for its future applications. |
Persistent Identifier | http://hdl.handle.net/10722/329873 |
ISSN | 2023 Impact Factor: 10.6 2023 SCImago Journal Rankings: 3.760 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yan, Yizhen | - |
dc.contributor.author | Huang, Bo | - |
dc.date.accessioned | 2023-08-09T03:35:58Z | - |
dc.date.available | 2023-08-09T03:35:58Z | - |
dc.date.issued | 2022 | - |
dc.identifier.citation | ISPRS Journal of Photogrammetry and Remote Sensing, 2022, v. 192, p. 83-98 | - |
dc.identifier.issn | 0924-2716 | - |
dc.identifier.uri | http://hdl.handle.net/10722/329873 | - |
dc.description.abstract | Building smart cities requires three-dimensional (3D) modelling to facilitate the planning and management of built environments. This requirement leads to high demand for data on vertical dimensions, such as building height, that are critical for the construction of 3D city models. Despite increasing recognition of the importance of such data, their acquisition in a low-cost and efficient manner remains a daunting task. Big data, particularly street view images (SVIs), provide an opportunity to efficiently solve this problem. In this study, we aim to derive information on building height from openly available SVIs by using single view metrology. Unlike other methods using multisource inputs, our method capitalizes on deep neural networks to extract a set of features – such as vanishing points, line segments, and semantic segmentation maps – for single view measurement and then estimates the height from single SVIs. The minimal input required by the method increases its competitiveness in large-scale estimation of building heights, especially in areas with difficulty to obtain the conventional remote sensing data. In addition to experiments that demonstrate the effectiveness and efficiency of the proposed method, we also conduct a thorough analysis of uncertainties and errors brought by the method, thereby providing guidance for its future applications. | - |
dc.language | eng | - |
dc.relation.ispartof | ISPRS Journal of Photogrammetry and Remote Sensing | - |
dc.subject | Building height | - |
dc.subject | Deep learning | - |
dc.subject | Single view | - |
dc.subject | Street view image | - |
dc.subject | Uncertainty analysis | - |
dc.title | Estimation of building height using a single street view image via deep neural networks | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1016/j.isprsjprs.2022.08.006 | - |
dc.identifier.scopus | eid_2-s2.0-85136004620 | - |
dc.identifier.volume | 192 | - |
dc.identifier.spage | 83 | - |
dc.identifier.epage | 98 | - |
dc.identifier.isi | WOS:000848879100002 | - |