A benchmark dataset for class-wise segmentation of construction and demolition waste in cluttered environments

Abstract Efficient management of construction and demolition waste (CDW) is essential for enhancing resource recovery. The lack of publicly available, high-quality datasets for waste recognition limits the development and adoption of automated waste handling solutions. To facilitate data sharing and...

Full description

Saved in:
Bibliographic Details
Main Authors: Diani Sirimewan, Sanuwani Dayarathna, Sudharshan Raman, Yu Bai, Mehrdad Arashpour
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Data
Online Access:https://doi.org/10.1038/s41597-025-05243-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849704094674976768
author Diani Sirimewan
Sanuwani Dayarathna
Sudharshan Raman
Yu Bai
Mehrdad Arashpour
author_facet Diani Sirimewan
Sanuwani Dayarathna
Sudharshan Raman
Yu Bai
Mehrdad Arashpour
author_sort Diani Sirimewan
collection DOAJ
description Abstract Efficient management of construction and demolition waste (CDW) is essential for enhancing resource recovery. The lack of publicly available, high-quality datasets for waste recognition limits the development and adoption of automated waste handling solutions. To facilitate data sharing and reuse, this study introduces ‘CDW-Seg’, a benchmark dataset for class-wise segmentation of CDW. The dataset comprises high-resolution images captured at authentic construction sites, featuring skip bins filled with a diverse mixture of CDW materials in-the-wild. It includes 5,413 manually annotated objects across ten categories: concrete, fill dirt, timber, hard plastic, soft plastic, steel, fabric, cardboard, plasterboard, and the skip bin, representing a total of 2,492,021,189 pixels. Each object was meticulously annotated through semantic segmentation, providing reliable ground-truth labels. To demonstrate the applicability of the dataset, an adapter-based fine-tuning approach was implemented using a hierarchical Vision Transformer, ensuring computational efficiency suitable for deployment in automated waste handling scenarios. The CDW-Seg has been made publicly accessible to promote data sharing, facilitate further research, and support the development of automated solutions for resource recovery.
format Article
id doaj-art-118f8b7e97b049d5bb177a2ebb16f5e1
institution DOAJ
issn 2052-4463
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Data
spelling doaj-art-118f8b7e97b049d5bb177a2ebb16f5e12025-08-20T03:16:52ZengNature PortfolioScientific Data2052-44632025-05-011211910.1038/s41597-025-05243-xA benchmark dataset for class-wise segmentation of construction and demolition waste in cluttered environmentsDiani Sirimewan0Sanuwani Dayarathna1Sudharshan Raman2Yu Bai3Mehrdad Arashpour4Department of Civil Engineering, Faculty of Engineering, Monash UniversityDepartment of Data Science and AI, Faculty of IT, Monash UniversityCivil Engineering Discipline, School of Engineering, Monash UniversityDepartment of Civil Engineering, Faculty of Engineering, Monash UniversityDepartment of Civil Engineering, Faculty of Engineering, Monash UniversityAbstract Efficient management of construction and demolition waste (CDW) is essential for enhancing resource recovery. The lack of publicly available, high-quality datasets for waste recognition limits the development and adoption of automated waste handling solutions. To facilitate data sharing and reuse, this study introduces ‘CDW-Seg’, a benchmark dataset for class-wise segmentation of CDW. The dataset comprises high-resolution images captured at authentic construction sites, featuring skip bins filled with a diverse mixture of CDW materials in-the-wild. It includes 5,413 manually annotated objects across ten categories: concrete, fill dirt, timber, hard plastic, soft plastic, steel, fabric, cardboard, plasterboard, and the skip bin, representing a total of 2,492,021,189 pixels. Each object was meticulously annotated through semantic segmentation, providing reliable ground-truth labels. To demonstrate the applicability of the dataset, an adapter-based fine-tuning approach was implemented using a hierarchical Vision Transformer, ensuring computational efficiency suitable for deployment in automated waste handling scenarios. The CDW-Seg has been made publicly accessible to promote data sharing, facilitate further research, and support the development of automated solutions for resource recovery.https://doi.org/10.1038/s41597-025-05243-x
spellingShingle Diani Sirimewan
Sanuwani Dayarathna
Sudharshan Raman
Yu Bai
Mehrdad Arashpour
A benchmark dataset for class-wise segmentation of construction and demolition waste in cluttered environments
Scientific Data
title A benchmark dataset for class-wise segmentation of construction and demolition waste in cluttered environments
title_full A benchmark dataset for class-wise segmentation of construction and demolition waste in cluttered environments
title_fullStr A benchmark dataset for class-wise segmentation of construction and demolition waste in cluttered environments
title_full_unstemmed A benchmark dataset for class-wise segmentation of construction and demolition waste in cluttered environments
title_short A benchmark dataset for class-wise segmentation of construction and demolition waste in cluttered environments
title_sort benchmark dataset for class wise segmentation of construction and demolition waste in cluttered environments
url https://doi.org/10.1038/s41597-025-05243-x
work_keys_str_mv AT dianisirimewan abenchmarkdatasetforclasswisesegmentationofconstructionanddemolitionwasteinclutteredenvironments
AT sanuwanidayarathna abenchmarkdatasetforclasswisesegmentationofconstructionanddemolitionwasteinclutteredenvironments
AT sudharshanraman abenchmarkdatasetforclasswisesegmentationofconstructionanddemolitionwasteinclutteredenvironments
AT yubai abenchmarkdatasetforclasswisesegmentationofconstructionanddemolitionwasteinclutteredenvironments
AT mehrdadarashpour abenchmarkdatasetforclasswisesegmentationofconstructionanddemolitionwasteinclutteredenvironments
AT dianisirimewan benchmarkdatasetforclasswisesegmentationofconstructionanddemolitionwasteinclutteredenvironments
AT sanuwanidayarathna benchmarkdatasetforclasswisesegmentationofconstructionanddemolitionwasteinclutteredenvironments
AT sudharshanraman benchmarkdatasetforclasswisesegmentationofconstructionanddemolitionwasteinclutteredenvironments
AT yubai benchmarkdatasetforclasswisesegmentationofconstructionanddemolitionwasteinclutteredenvironments
AT mehrdadarashpour benchmarkdatasetforclasswisesegmentationofconstructionanddemolitionwasteinclutteredenvironments