Investigating the Performance of Open-Vocabulary Classification Algorithms for Pathway and Surface Material Detection in Urban Environments

Mapping pavement types, especially in sidewalks, is essential for urban planning and mobility studies. Identifying pavement materials is a key factor in assessing mobility, such as walkability and wheelchair usability. However, satellite imagery in this scenario is limited, and in situ mapping can b...

Full description

Saved in:
Bibliographic Details
Main Authors: Kauê de Moraes Vestena, Silvana Phillipi Camboim, Maria Antonia Brovelli, Daniel Rodrigues dos Santos
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:ISPRS International Journal of Geo-Information
Subjects:
Online Access:https://www.mdpi.com/2220-9964/13/12/422
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850241299022610432
author Kauê de Moraes Vestena
Silvana Phillipi Camboim
Maria Antonia Brovelli
Daniel Rodrigues dos Santos
author_facet Kauê de Moraes Vestena
Silvana Phillipi Camboim
Maria Antonia Brovelli
Daniel Rodrigues dos Santos
author_sort Kauê de Moraes Vestena
collection DOAJ
description Mapping pavement types, especially in sidewalks, is essential for urban planning and mobility studies. Identifying pavement materials is a key factor in assessing mobility, such as walkability and wheelchair usability. However, satellite imagery in this scenario is limited, and in situ mapping can be costly. A promising solution is to extract such geospatial features from street-level imagery. This study explores using open-vocabulary classification algorithms to segment and identify pavement types and surface materials in this scenario. Our approach uses large language models (LLMs) to improve the accuracy of classifying different pavement types. The methodology involves two experiments: the first uses free prompting with random street-view images, employing Grounding Dino and SAM algorithms to assess performance across categories. The second experiment evaluates standardized pavement classification using the Deep Pavements dataset and a fine-tuned CLIP algorithm optimized for detecting OSM-compliant pavement categories. The study presents open resources, such as the Deep Pavements dataset and a fine-tuned CLIP-based model, demonstrating a significant improvement in the true positive rate (TPR) from 56.04% to 93.5%. Our findings highlight both the potential and limitations of current open-vocabulary algorithms and emphasize the importance of diverse training datasets. This study advances urban feature mapping by offering a more intuitive and accurate approach to geospatial data extraction, enhancing urban accessibility and mobility mapping.
format Article
id doaj-art-bcf09448cdf1465eb25a30d6d291897f
institution OA Journals
issn 2220-9964
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series ISPRS International Journal of Geo-Information
spelling doaj-art-bcf09448cdf1465eb25a30d6d291897f2025-08-20T02:00:38ZengMDPI AGISPRS International Journal of Geo-Information2220-99642024-11-01131242210.3390/ijgi13120422Investigating the Performance of Open-Vocabulary Classification Algorithms for Pathway and Surface Material Detection in Urban EnvironmentsKauê de Moraes Vestena0Silvana Phillipi Camboim1Maria Antonia Brovelli2Daniel Rodrigues dos Santos3Department of Geomatics, Federal University of Paraná, Curitiba 80060-000, BrazilDepartment of Geomatics, Federal University of Paraná, Curitiba 80060-000, BrazilPolitecnico di Milano, Department of Civil and Environmental Engineering, 20133 Milan, ItalyMilitary Institute of Engineering, Cartography Section, Rio de Janeiro 22290-270, BrazilMapping pavement types, especially in sidewalks, is essential for urban planning and mobility studies. Identifying pavement materials is a key factor in assessing mobility, such as walkability and wheelchair usability. However, satellite imagery in this scenario is limited, and in situ mapping can be costly. A promising solution is to extract such geospatial features from street-level imagery. This study explores using open-vocabulary classification algorithms to segment and identify pavement types and surface materials in this scenario. Our approach uses large language models (LLMs) to improve the accuracy of classifying different pavement types. The methodology involves two experiments: the first uses free prompting with random street-view images, employing Grounding Dino and SAM algorithms to assess performance across categories. The second experiment evaluates standardized pavement classification using the Deep Pavements dataset and a fine-tuned CLIP algorithm optimized for detecting OSM-compliant pavement categories. The study presents open resources, such as the Deep Pavements dataset and a fine-tuned CLIP-based model, demonstrating a significant improvement in the true positive rate (TPR) from 56.04% to 93.5%. Our findings highlight both the potential and limitations of current open-vocabulary algorithms and emphasize the importance of diverse training datasets. This study advances urban feature mapping by offering a more intuitive and accurate approach to geospatial data extraction, enhancing urban accessibility and mobility mapping.https://www.mdpi.com/2220-9964/13/12/422open-vocabulary algorithmspavement segmentationsurface material detectionstreet-view imageryurban mobility
spellingShingle Kauê de Moraes Vestena
Silvana Phillipi Camboim
Maria Antonia Brovelli
Daniel Rodrigues dos Santos
Investigating the Performance of Open-Vocabulary Classification Algorithms for Pathway and Surface Material Detection in Urban Environments
ISPRS International Journal of Geo-Information
open-vocabulary algorithms
pavement segmentation
surface material detection
street-view imagery
urban mobility
title Investigating the Performance of Open-Vocabulary Classification Algorithms for Pathway and Surface Material Detection in Urban Environments
title_full Investigating the Performance of Open-Vocabulary Classification Algorithms for Pathway and Surface Material Detection in Urban Environments
title_fullStr Investigating the Performance of Open-Vocabulary Classification Algorithms for Pathway and Surface Material Detection in Urban Environments
title_full_unstemmed Investigating the Performance of Open-Vocabulary Classification Algorithms for Pathway and Surface Material Detection in Urban Environments
title_short Investigating the Performance of Open-Vocabulary Classification Algorithms for Pathway and Surface Material Detection in Urban Environments
title_sort investigating the performance of open vocabulary classification algorithms for pathway and surface material detection in urban environments
topic open-vocabulary algorithms
pavement segmentation
surface material detection
street-view imagery
urban mobility
url https://www.mdpi.com/2220-9964/13/12/422
work_keys_str_mv AT kauedemoraesvestena investigatingtheperformanceofopenvocabularyclassificationalgorithmsforpathwayandsurfacematerialdetectioninurbanenvironments
AT silvanaphillipicamboim investigatingtheperformanceofopenvocabularyclassificationalgorithmsforpathwayandsurfacematerialdetectioninurbanenvironments
AT mariaantoniabrovelli investigatingtheperformanceofopenvocabularyclassificationalgorithmsforpathwayandsurfacematerialdetectioninurbanenvironments
AT danielrodriguesdossantos investigatingtheperformanceofopenvocabularyclassificationalgorithmsforpathwayandsurfacematerialdetectioninurbanenvironments