Automatic Detection of Tiny Drainage Outlets and Ventilations on Flat Rooftops from Aerial Imagery

Flat rooftops on residential and industrial buildings house critical drainage and ventilation systems, which play essential roles in channeling water away from structures and preventing moisture accumulation. These utilities are vital for maintaining the structural integrity of rooftops, safeguardin...

Full description

Saved in:
Bibliographic Details
Main Authors: L. Arzoumanidis, W. Li, J. Knechtel, Y. Kosmayadi, Y. Dehbi
Format: Article
Language:English
Published: Copernicus Publications 2025-07-01
Series:ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://isprs-annals.copernicus.org/articles/X-G-2025/125/2025/isprs-annals-X-G-2025-125-2025.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850117842639257600
author L. Arzoumanidis
W. Li
W. Li
J. Knechtel
Y. Kosmayadi
Y. Dehbi
author_facet L. Arzoumanidis
W. Li
W. Li
J. Knechtel
Y. Kosmayadi
Y. Dehbi
author_sort L. Arzoumanidis
collection DOAJ
description Flat rooftops on residential and industrial buildings house critical drainage and ventilation systems, which play essential roles in channeling water away from structures and preventing moisture accumulation. These utilities are vital for maintaining the structural integrity of rooftops, safeguarding against water pooling and moisture buildup that could otherwise lead to damage or even collapse, particularly during extreme weather events. However, current inspection and maintenance practices for these systems are predominantly manual, making them time-consuming, labor-intensive, and sometimes hazardous. This paper presents an automated approach to detecting drainage outlets and ventilation systems on flat rooftops, using a custom-labeled dataset of highresolution aerial imagery. We evaluated two different object detection methods, with FCOS (Fully Convolutional One-Stage Object Detection) outperforming Faster R-CNN in identifying these small utilities. The outcomes pave the way for new applications, as detected utilities can act as sparse data points that trigger constraint-based reasoning processes for estimating hidden utility networks in as-built Building Information Modeling (BIM) contexts. Embedding these identified objects into GIS or BIM models represents an initial step towards coarse-to-fine visual recognition, enabling customized semantic mission planning for autonomous exploration and inspection using Unmanned Aerial Vehicles (UAVs). The labeled dataset used in this study is publicly available by following this link <code>https://zenodo.org/records/14040571</code>.
format Article
id doaj-art-93efc11a52d547b38251217da1bf4db2
institution OA Journals
issn 2194-9042
2194-9050
language English
publishDate 2025-07-01
publisher Copernicus Publications
record_format Article
series ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
spelling doaj-art-93efc11a52d547b38251217da1bf4db22025-08-20T02:36:00ZengCopernicus PublicationsISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences2194-90422194-90502025-07-01X-G-202512513210.5194/isprs-annals-X-G-2025-125-2025Automatic Detection of Tiny Drainage Outlets and Ventilations on Flat Rooftops from Aerial ImageryL. Arzoumanidis0W. Li1W. Li2J. Knechtel3Y. Kosmayadi4Y. Dehbi5Computational Methods Lab, HafenCity University Hamburg, GermanyComputational Methods Lab, HafenCity University Hamburg, GermanyFaculty of Geosciences and Engineering, Southwest Jiaotong University, ChinaInstitute of Geodesy and Geoinformation, University of Bonn, GermanyComputational Methods Lab, HafenCity University Hamburg, GermanyComputational Methods Lab, HafenCity University Hamburg, GermanyFlat rooftops on residential and industrial buildings house critical drainage and ventilation systems, which play essential roles in channeling water away from structures and preventing moisture accumulation. These utilities are vital for maintaining the structural integrity of rooftops, safeguarding against water pooling and moisture buildup that could otherwise lead to damage or even collapse, particularly during extreme weather events. However, current inspection and maintenance practices for these systems are predominantly manual, making them time-consuming, labor-intensive, and sometimes hazardous. This paper presents an automated approach to detecting drainage outlets and ventilation systems on flat rooftops, using a custom-labeled dataset of highresolution aerial imagery. We evaluated two different object detection methods, with FCOS (Fully Convolutional One-Stage Object Detection) outperforming Faster R-CNN in identifying these small utilities. The outcomes pave the way for new applications, as detected utilities can act as sparse data points that trigger constraint-based reasoning processes for estimating hidden utility networks in as-built Building Information Modeling (BIM) contexts. Embedding these identified objects into GIS or BIM models represents an initial step towards coarse-to-fine visual recognition, enabling customized semantic mission planning for autonomous exploration and inspection using Unmanned Aerial Vehicles (UAVs). The labeled dataset used in this study is publicly available by following this link <code>https://zenodo.org/records/14040571</code>.https://isprs-annals.copernicus.org/articles/X-G-2025/125/2025/isprs-annals-X-G-2025-125-2025.pdf
spellingShingle L. Arzoumanidis
W. Li
W. Li
J. Knechtel
Y. Kosmayadi
Y. Dehbi
Automatic Detection of Tiny Drainage Outlets and Ventilations on Flat Rooftops from Aerial Imagery
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
title Automatic Detection of Tiny Drainage Outlets and Ventilations on Flat Rooftops from Aerial Imagery
title_full Automatic Detection of Tiny Drainage Outlets and Ventilations on Flat Rooftops from Aerial Imagery
title_fullStr Automatic Detection of Tiny Drainage Outlets and Ventilations on Flat Rooftops from Aerial Imagery
title_full_unstemmed Automatic Detection of Tiny Drainage Outlets and Ventilations on Flat Rooftops from Aerial Imagery
title_short Automatic Detection of Tiny Drainage Outlets and Ventilations on Flat Rooftops from Aerial Imagery
title_sort automatic detection of tiny drainage outlets and ventilations on flat rooftops from aerial imagery
url https://isprs-annals.copernicus.org/articles/X-G-2025/125/2025/isprs-annals-X-G-2025-125-2025.pdf
work_keys_str_mv AT larzoumanidis automaticdetectionoftinydrainageoutletsandventilationsonflatrooftopsfromaerialimagery
AT wli automaticdetectionoftinydrainageoutletsandventilationsonflatrooftopsfromaerialimagery
AT wli automaticdetectionoftinydrainageoutletsandventilationsonflatrooftopsfromaerialimagery
AT jknechtel automaticdetectionoftinydrainageoutletsandventilationsonflatrooftopsfromaerialimagery
AT ykosmayadi automaticdetectionoftinydrainageoutletsandventilationsonflatrooftopsfromaerialimagery
AT ydehbi automaticdetectionoftinydrainageoutletsandventilationsonflatrooftopsfromaerialimagery