Fence detection in Amsterdam: transparent object segmentation in urban context

IntroductionAccessibility and safe movement in urban areas entail infrastructure that minimizes the risks for pedestrians and bikers with diverse levels of abilities. Recognizing and mapping unsafe areas can increase awareness among citizens and inform city projects to improve their infrastructure....

Full description

Bibliographic Details
Main Authors: Jorrit Ypenga, Maarten Sukel, Hamed S. Alavi
Format: Article
Language:English
Published: Frontiers Media S.A. 2023-07-01
Series:Frontiers in Computer Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fcomp.2023.1143945/full
_version_ 1797786063825010688
author Jorrit Ypenga
Maarten Sukel
Hamed S. Alavi
author_facet Jorrit Ypenga
Maarten Sukel
Hamed S. Alavi
author_sort Jorrit Ypenga
collection DOAJ
description IntroductionAccessibility and safe movement in urban areas entail infrastructure that minimizes the risks for pedestrians and bikers with diverse levels of abilities. Recognizing and mapping unsafe areas can increase awareness among citizens and inform city projects to improve their infrastructure. This contribution presents an example in which the specific objective is to recognize the unprotected areas around the canals in the city of Amsterdam.MethodThis is accomplished through running image processing algorithms on 11K waterside panoramas taken from the city of Amsterdam's open data portal. We created an annotated subset of 2K processed images for training and evaluation. This dataset debuts a novel pixel-level annotation style using multiple lines. To determine the best inference practice, we compared the IoU and robustness of several existing segmentation frameworks.ResultsThe best method achieves an IoU of 0.79. The outcome is superimposed on the map of Amsterdam, showing the geospatial distribution of the low, middle, and high fences around the canals.DiscussionIn addition to this specific application, we discuss the broader use of the presented method for the problem of “transparent object detection” in an urban context.
first_indexed 2024-03-13T01:02:47Z
format Article
id doaj.art-2ef06f59de8249b0a30be624f5ab8de8
institution Directory Open Access Journal
issn 2624-9898
language English
last_indexed 2024-03-13T01:02:47Z
publishDate 2023-07-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Computer Science
spelling doaj.art-2ef06f59de8249b0a30be624f5ab8de82023-07-06T10:06:06ZengFrontiers Media S.A.Frontiers in Computer Science2624-98982023-07-01510.3389/fcomp.2023.11439451143945Fence detection in Amsterdam: transparent object segmentation in urban contextJorrit YpengaMaarten SukelHamed S. AlaviIntroductionAccessibility and safe movement in urban areas entail infrastructure that minimizes the risks for pedestrians and bikers with diverse levels of abilities. Recognizing and mapping unsafe areas can increase awareness among citizens and inform city projects to improve their infrastructure. This contribution presents an example in which the specific objective is to recognize the unprotected areas around the canals in the city of Amsterdam.MethodThis is accomplished through running image processing algorithms on 11K waterside panoramas taken from the city of Amsterdam's open data portal. We created an annotated subset of 2K processed images for training and evaluation. This dataset debuts a novel pixel-level annotation style using multiple lines. To determine the best inference practice, we compared the IoU and robustness of several existing segmentation frameworks.ResultsThe best method achieves an IoU of 0.79. The outcome is superimposed on the map of Amsterdam, showing the geospatial distribution of the low, middle, and high fences around the canals.DiscussionIn addition to this specific application, we discuss the broader use of the presented method for the problem of “transparent object detection” in an urban context.https://www.frontiersin.org/articles/10.3389/fcomp.2023.1143945/fullsmart cityaccessible urban designstreet view image analysistransparent object detectionurban safety
spellingShingle Jorrit Ypenga
Maarten Sukel
Hamed S. Alavi
Fence detection in Amsterdam: transparent object segmentation in urban context
Frontiers in Computer Science
smart city
accessible urban design
street view image analysis
transparent object detection
urban safety
title Fence detection in Amsterdam: transparent object segmentation in urban context
title_full Fence detection in Amsterdam: transparent object segmentation in urban context
title_fullStr Fence detection in Amsterdam: transparent object segmentation in urban context
title_full_unstemmed Fence detection in Amsterdam: transparent object segmentation in urban context
title_short Fence detection in Amsterdam: transparent object segmentation in urban context
title_sort fence detection in amsterdam transparent object segmentation in urban context
topic smart city
accessible urban design
street view image analysis
transparent object detection
urban safety
url https://www.frontiersin.org/articles/10.3389/fcomp.2023.1143945/full
work_keys_str_mv AT jorritypenga fencedetectioninamsterdamtransparentobjectsegmentationinurbancontext
AT maartensukel fencedetectioninamsterdamtransparentobjectsegmentationinurbancontext
AT hamedsalavi fencedetectioninamsterdamtransparentobjectsegmentationinurbancontext