Heavy Equipment Detection on Construction Sites Using You Only Look Once (YOLO-Version 10) with Transformer Architectures

Monitoring heavy equipment in real time is crucial for ensuring safety and operational efficiency at construction sites, yet achieving both high detection accuracy and fast inference remains challenging under diverse environmental conditions. Although previous studies have attempted to improve accur...

Full description

Saved in:
Bibliographic Details
Main Authors: Ikchul Eum, Jaejun Kim, Seunghyeon Wang, Juhyung Kim
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/5/2320
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850228282695352320
author Ikchul Eum
Jaejun Kim
Seunghyeon Wang
Juhyung Kim
author_facet Ikchul Eum
Jaejun Kim
Seunghyeon Wang
Juhyung Kim
author_sort Ikchul Eum
collection DOAJ
description Monitoring heavy equipment in real time is crucial for ensuring safety and operational efficiency at construction sites, yet achieving both high detection accuracy and fast inference remains challenging under diverse environmental conditions. Although previous studies have attempted to improve accuracy and speed, their findings often lack generalizability, partly due to inconsistent datasets and the need for more advanced techniques. In response, this study proposes an enhanced object detection method that integrates transformer-based backbone networks into the You Only Look Once (YOLO-version 10) framework. Evaluations conducted on a large-scale dataset of construction-site images demonstrate notable improvements in detecting the heavy equipment of varying sizes. Comparisons with other detectors confirm that the proposed model not only achieves higher accuracy but also maintains competitive processing speed, making it suitable for real-time deployment. Additionally, the dataset is made available for broader experimentation and development. These findings underscore the method’s potential to strengthen on-site safety by providing more reliable and efficient heavy equipment detection in complex work environments, while also acknowledging areas for further refinement.
format Article
id doaj-art-d1aa4e14428e4aeb8a3d55d2c3a236b6
institution OA Journals
issn 2076-3417
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-d1aa4e14428e4aeb8a3d55d2c3a236b62025-08-20T02:04:34ZengMDPI AGApplied Sciences2076-34172025-02-01155232010.3390/app15052320Heavy Equipment Detection on Construction Sites Using You Only Look Once (YOLO-Version 10) with Transformer ArchitecturesIkchul Eum0Jaejun Kim1Seunghyeon Wang2Juhyung Kim3Department of Architectural Engineering, Hanyang University, Seoul 133791, Republic of KoreaDepartment of Architectural Engineering, Hanyang University, Seoul 133791, Republic of KoreaDepartment of Architectural Engineering, Hanyang University, Seoul 133791, Republic of KoreaDepartment of Architectural Engineering, Hanyang University, Seoul 133791, Republic of KoreaMonitoring heavy equipment in real time is crucial for ensuring safety and operational efficiency at construction sites, yet achieving both high detection accuracy and fast inference remains challenging under diverse environmental conditions. Although previous studies have attempted to improve accuracy and speed, their findings often lack generalizability, partly due to inconsistent datasets and the need for more advanced techniques. In response, this study proposes an enhanced object detection method that integrates transformer-based backbone networks into the You Only Look Once (YOLO-version 10) framework. Evaluations conducted on a large-scale dataset of construction-site images demonstrate notable improvements in detecting the heavy equipment of varying sizes. Comparisons with other detectors confirm that the proposed model not only achieves higher accuracy but also maintains competitive processing speed, making it suitable for real-time deployment. Additionally, the dataset is made available for broader experimentation and development. These findings underscore the method’s potential to strengthen on-site safety by providing more reliable and efficient heavy equipment detection in complex work environments, while also acknowledging areas for further refinement.https://www.mdpi.com/2076-3417/15/5/2320heavy equipment detectionconstruction managementdeep learningobject detectionYOLOtransformers
spellingShingle Ikchul Eum
Jaejun Kim
Seunghyeon Wang
Juhyung Kim
Heavy Equipment Detection on Construction Sites Using You Only Look Once (YOLO-Version 10) with Transformer Architectures
Applied Sciences
heavy equipment detection
construction management
deep learning
object detection
YOLO
transformers
title Heavy Equipment Detection on Construction Sites Using You Only Look Once (YOLO-Version 10) with Transformer Architectures
title_full Heavy Equipment Detection on Construction Sites Using You Only Look Once (YOLO-Version 10) with Transformer Architectures
title_fullStr Heavy Equipment Detection on Construction Sites Using You Only Look Once (YOLO-Version 10) with Transformer Architectures
title_full_unstemmed Heavy Equipment Detection on Construction Sites Using You Only Look Once (YOLO-Version 10) with Transformer Architectures
title_short Heavy Equipment Detection on Construction Sites Using You Only Look Once (YOLO-Version 10) with Transformer Architectures
title_sort heavy equipment detection on construction sites using you only look once yolo version 10 with transformer architectures
topic heavy equipment detection
construction management
deep learning
object detection
YOLO
transformers
url https://www.mdpi.com/2076-3417/15/5/2320
work_keys_str_mv AT ikchuleum heavyequipmentdetectiononconstructionsitesusingyouonlylookonceyoloversion10withtransformerarchitectures
AT jaejunkim heavyequipmentdetectiononconstructionsitesusingyouonlylookonceyoloversion10withtransformerarchitectures
AT seunghyeonwang heavyequipmentdetectiononconstructionsitesusingyouonlylookonceyoloversion10withtransformerarchitectures
AT juhyungkim heavyequipmentdetectiononconstructionsitesusingyouonlylookonceyoloversion10withtransformerarchitectures