File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.3390/rs11243022
- Scopus: eid_2-s2.0-85077840588
- WOS: WOS:000507333400136
Supplementary
- Citations:
- Appears in Collections:
Article: Automatic extraction of built-up areas from very high-resolution satellite imagery using patch-level spatial features and gestalt laws of perceptual grouping
Title | Automatic extraction of built-up areas from very high-resolution satellite imagery using patch-level spatial features and gestalt laws of perceptual grouping |
---|---|
Authors | |
Keywords | Built-up area extraction Gestalt laws of grouping High-resolution Satellite image |
Issue Date | 2019 |
Citation | Remote Sensing, 2019, v. 11, n. 24, article no. 3022 How to Cite? |
Abstract | Automatic extraction of built-up areas from very high-resolution (VHR) satellite images has received increasing attention in recent years. However, due to the complexity of spectral and spatial characteristics of built-up areas, it is still a challenging task to obtain their precise location and extent. In this study, a patch-based framework was proposed for unsupervised extraction of built-up areas from VHR imagery. First, a group of corner-constrained overlapping patches were defined to locate the candidate built-up areas. Second, for each patch, its salient textures and structural characteristics were represented as a feature vector using integrated high-frequency wavelet coefficients. Then, inspired by visual perception, a patch-level saliency model of built-up areas was constructed by incorporating Gestalt laws of proximity and similarity, which can effectively describe the spatial relationships between patches. Finally, built-up areas were extracted through thresholding and their boundaries were refined by morphological operations. The performance of the proposed method was evaluated on two VHR image datasets. The resulting average F-measure values were 0.8613 for the Google Earth dataset and 0.88 for theWorldView-2 dataset, respectively. Compared with existing models, the proposed method obtains better extraction results, which show more precise boundaries and preserve better shape integrity. |
Persistent Identifier | http://hdl.handle.net/10722/329599 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Chen, Yixiang | - |
dc.contributor.author | Lv, Zhiyong | - |
dc.contributor.author | Huang, Bo | - |
dc.contributor.author | Zhang, Pengdong | - |
dc.contributor.author | Zhang, Yu | - |
dc.date.accessioned | 2023-08-09T03:33:57Z | - |
dc.date.available | 2023-08-09T03:33:57Z | - |
dc.date.issued | 2019 | - |
dc.identifier.citation | Remote Sensing, 2019, v. 11, n. 24, article no. 3022 | - |
dc.identifier.uri | http://hdl.handle.net/10722/329599 | - |
dc.description.abstract | Automatic extraction of built-up areas from very high-resolution (VHR) satellite images has received increasing attention in recent years. However, due to the complexity of spectral and spatial characteristics of built-up areas, it is still a challenging task to obtain their precise location and extent. In this study, a patch-based framework was proposed for unsupervised extraction of built-up areas from VHR imagery. First, a group of corner-constrained overlapping patches were defined to locate the candidate built-up areas. Second, for each patch, its salient textures and structural characteristics were represented as a feature vector using integrated high-frequency wavelet coefficients. Then, inspired by visual perception, a patch-level saliency model of built-up areas was constructed by incorporating Gestalt laws of proximity and similarity, which can effectively describe the spatial relationships between patches. Finally, built-up areas were extracted through thresholding and their boundaries were refined by morphological operations. The performance of the proposed method was evaluated on two VHR image datasets. The resulting average F-measure values were 0.8613 for the Google Earth dataset and 0.88 for theWorldView-2 dataset, respectively. Compared with existing models, the proposed method obtains better extraction results, which show more precise boundaries and preserve better shape integrity. | - |
dc.language | eng | - |
dc.relation.ispartof | Remote Sensing | - |
dc.subject | Built-up area extraction | - |
dc.subject | Gestalt laws of grouping | - |
dc.subject | High-resolution | - |
dc.subject | Satellite image | - |
dc.title | Automatic extraction of built-up areas from very high-resolution satellite imagery using patch-level spatial features and gestalt laws of perceptual grouping | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.3390/rs11243022 | - |
dc.identifier.scopus | eid_2-s2.0-85077840588 | - |
dc.identifier.volume | 11 | - |
dc.identifier.issue | 24 | - |
dc.identifier.spage | article no. 3022 | - |
dc.identifier.epage | article no. 3022 | - |
dc.identifier.eissn | 2072-4292 | - |
dc.identifier.isi | WOS:000507333400136 | - |