A Scene Graph Generation Method for Historical District Street-view Imagery: A Case Study in Beijing, China

Using street-view imagery for interpreting diverse street-scale elements and their relationships within historical districts offers high efficiency and low cost for preservation and management. Scene graphs provide a structured representation of objects and their relationships within a scene. Howeve...

Full description

Saved in:
Bibliographic Details
Main Authors: X. Guo, X. Liu, J. Jiang
Format: Article
Language:English
Published: Copernicus Publications 2024-11-01
Series:The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://isprs-archives.copernicus.org/articles/XLVIII-3-2024/209/2024/isprs-archives-XLVIII-3-2024-209-2024.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850199135798427648
author X. Guo
X. Liu
J. Jiang
author_facet X. Guo
X. Liu
J. Jiang
author_sort X. Guo
collection DOAJ
description Using street-view imagery for interpreting diverse street-scale elements and their relationships within historical districts offers high efficiency and low cost for preservation and management. Scene graphs provide a structured representation of objects and their relationships within a scene. However, applying existing scene graph generation techniques directly to street-view imagery presents challenges due to the complexity of elements and narrow street spaces. This paper introduces HSSGG (Historical Street-view Scene Graph Generation), a predictive model that effectively identifies elements and their relationships. By incorporating an end-to-end Relation Transformer with the parameter-free attention and coordinate attention modules, HSSGG improves relationship prediction accuracy, even with limited samples, and enhances the precision of scene graph generation in complex environments. Test on 200 panoramic images from historical districts in Beijing shows that HSSGG outperforms existing single-stage relation prediction models (such as RelTR and FCSGG) in accuracy and stability. These results provide valuable insights for the preservation and management of historical districts.
format Article
id doaj-art-6421d69e52ca48e4853d90b9872161ab
institution OA Journals
issn 1682-1750
2194-9034
language English
publishDate 2024-11-01
publisher Copernicus Publications
record_format Article
series The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
spelling doaj-art-6421d69e52ca48e4853d90b9872161ab2025-08-20T02:12:41ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342024-11-01XLVIII-3-202420921610.5194/isprs-archives-XLVIII-3-2024-209-2024A Scene Graph Generation Method for Historical District Street-view Imagery: A Case Study in Beijing, ChinaX. Guo0X. Liu1J. Jiang2School of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, Beijing 102616, ChinaSchool of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, Beijing 102616, ChinaSchool of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, Beijing 102616, ChinaUsing street-view imagery for interpreting diverse street-scale elements and their relationships within historical districts offers high efficiency and low cost for preservation and management. Scene graphs provide a structured representation of objects and their relationships within a scene. However, applying existing scene graph generation techniques directly to street-view imagery presents challenges due to the complexity of elements and narrow street spaces. This paper introduces HSSGG (Historical Street-view Scene Graph Generation), a predictive model that effectively identifies elements and their relationships. By incorporating an end-to-end Relation Transformer with the parameter-free attention and coordinate attention modules, HSSGG improves relationship prediction accuracy, even with limited samples, and enhances the precision of scene graph generation in complex environments. Test on 200 panoramic images from historical districts in Beijing shows that HSSGG outperforms existing single-stage relation prediction models (such as RelTR and FCSGG) in accuracy and stability. These results provide valuable insights for the preservation and management of historical districts.https://isprs-archives.copernicus.org/articles/XLVIII-3-2024/209/2024/isprs-archives-XLVIII-3-2024-209-2024.pdf
spellingShingle X. Guo
X. Liu
J. Jiang
A Scene Graph Generation Method for Historical District Street-view Imagery: A Case Study in Beijing, China
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
title A Scene Graph Generation Method for Historical District Street-view Imagery: A Case Study in Beijing, China
title_full A Scene Graph Generation Method for Historical District Street-view Imagery: A Case Study in Beijing, China
title_fullStr A Scene Graph Generation Method for Historical District Street-view Imagery: A Case Study in Beijing, China
title_full_unstemmed A Scene Graph Generation Method for Historical District Street-view Imagery: A Case Study in Beijing, China
title_short A Scene Graph Generation Method for Historical District Street-view Imagery: A Case Study in Beijing, China
title_sort scene graph generation method for historical district street view imagery a case study in beijing china
url https://isprs-archives.copernicus.org/articles/XLVIII-3-2024/209/2024/isprs-archives-XLVIII-3-2024-209-2024.pdf
work_keys_str_mv AT xguo ascenegraphgenerationmethodforhistoricaldistrictstreetviewimageryacasestudyinbeijingchina
AT xliu ascenegraphgenerationmethodforhistoricaldistrictstreetviewimageryacasestudyinbeijingchina
AT jjiang ascenegraphgenerationmethodforhistoricaldistrictstreetviewimageryacasestudyinbeijingchina
AT xguo scenegraphgenerationmethodforhistoricaldistrictstreetviewimageryacasestudyinbeijingchina
AT xliu scenegraphgenerationmethodforhistoricaldistrictstreetviewimageryacasestudyinbeijingchina
AT jjiang scenegraphgenerationmethodforhistoricaldistrictstreetviewimageryacasestudyinbeijingchina