[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-640057-105":59,"doc-detail-640057-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","real-time-detection-of-unsafe-worker-behaviors-via-adaptive-vision-transformers-in-construction-sites-article","Real-Time Detection of Unsafe Worker Behaviors via Adaptive Vision Transformers in Construction Sites - Article","","Unsafe behavior of workers is a major cause of construction accidents, yet existing monitoring systems struggle with low efficiency and limited adaptability in dynamic site environments. The proposed work introduces an adaptive dual-stream vision transformer framework that combines Dynamic Adaptive Image Enhancement with a Lightweight Real-Time Behavior Network for accurate, responsive detection. An adaptive thresholding mechanism further tunes sensitivity under visual interference. Experiments on open-source construction datasets show higher precision, recall, and F1-score than Faster R-CNN, YOLO, and Mask R-CNN.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/real-time-detection-of-unsafe-worker-behaviors-via-adaptive-vision-transformers-in-construction-sites-article/640057/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/real-time-detection-of-unsafe-worker-behaviors-via-adaptive-vision-transformers-in-construction-sites-article/640057.png","ImageObject",300,407,{"name":92,"@type":93},"Well Done","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-31","2026-10-22",true,{"@type":102,"interactionType":103,"userInteractionCount":39},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does the study address in construction sites?","Question",{"text":112,"@type":113},"The study targets unsafe worker behaviors that can lead to construction accidents, while noting that current monitoring solutions are inefficient and not well adapted to changing on-site conditions.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does the proposed framework improve detection performance?",{"text":117,"@type":113},"It uses a Dynamic Adaptive Image Enhancement module to adjust image brightness, contrast, and sharpness, and a Lightweight Real-Time Behavior Network that models temporal action information from both enhanced and raw image streams.",{"name":119,"@type":110,"acceptedAnswer":120},"Which baseline methods does the study compare against, and what metrics are improved?",{"text":121,"@type":113},"The framework is compared with Faster R-CNN, YOLO, and Mask R-CNN, improving precision, recall, and F1-score, reported as 93.2%, 91.4%, and 92.3% respectively.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},640057,1793000300,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":39,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145},5909892210082,"https://ap-avatar.wpscdn.com/avatar/56001069da27c9f41e8?x-image-process=image/resize,m_fixed,w_180,h_180&k=1789614185077863061","Article  \nReal-Time Detection of Unsafe Worker Behaviors via Adaptive Vision Transformers in Construction Sites  \nRami Talal T. Alotaibi * and Shengbin Ma   \nSchool of Construction Engineering, Dalian University of Technology, Dalian 116024, China; [mshengbin@mail.dlut.edu.cn](mshengbin@mail.dlut.edu.cn)  \n* Correspondence: [ramit@mail.dlut.edu.cn](ramit@mail.dlut.edu.cn)  \nAbstract  \nUnsafe behavior of workers is a leading cause of construction accidents. However, existing monitoring systems remain limited by low efficiency and poor adaptability to dynamic on-site environments. This study proposes an adaptive dual-stream vision framework that integrates Dynamic Adaptive Image Enhancement (DAIE) and a Lightweight Real-Time Behavior Network (LR-BehaviorNet) to improve the accuracy and responsiveness of unsafe behavior detection. The DAIE module dynamically adjusts brightness, contrast, and sharpness according to scene conditions, ensuring visual clarity under varying lighting and weather. LR-BehaviorNet combines efficient convolutional blocks with Transformerbased temporal modeling to identify critical actions from both enhanced and raw image streams. Additionally, an adaptive thresholding mechanism fine-tunes detection sensitivity under complex visual interference. Experiments using open-source construction datasets demonstrate that the proposed framework outperforms conventional models—including Faster R-CNN, YOLO, and Mask R-CNN—in precision, recall, and F1-score, achieving 93.2%, 91.4%, and 92.3%, respectively. These results validate the robustness of the proposed method for real-time safety supervision and its potential integration with intelligent construction management platforms. Overall, the framework offers a scalable and efficient solution for automated safety monitoring, advancing the digital transformation of construction safety management.  \nKeywords: transformer network; computer vision; unsafe behavior; convolution neural  \nAcademic Editor: Pramen P. Shrestha  \nReceived: 19 October 2025  \nRevised: 14 November 2025  \nAccepted: 18 November 2025  \nPublished: 20 November 2025  \nCitation: Alotaibi, R.T.T.; Ma, S.  \nReal-Time Detection of Unsafe Worker Behaviors via Adaptive Vision Transformers in Construction Sites. Buildings 2025, 15, 4205. [https://](https://)[ ](https://)[doi.org/10.3390/buildings15224205](doi.org/10.3390/buildings15224205)  \n[Copyright:](Copyright:) © 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://creativecommons.org/](https://creativecommons.org/)[ ](https://creativecommons.org/)[licenses/by/4.0/](licenses/by/4.0/)) .  \nnetwork; construction worker  \n1. Introduction  \nIn construction management, ensuring operational safety is fundamental to sustaining project continuity and safeguarding the well-being of on-site personnel [1] . Given the inherent complexity and variability of construction environments, the prompt detection and mitigation of unsafe behaviors are essential for preventing accidents and reducing injuries [2] . Therefore, developing and implementing effective risk-control strategies is crucial to addressing persistent safety challenges in the construction industry, highlighting the necessity of continuous improvement in safety management practices [3] . Traditional monitoring methods—such as manual inspections, wearable sensors, and video surveillance—have been widely applied but often suffer from limitations, including low efficiency, high implementation costs, and inadequate integration of digital technologies [4–6] . These shortcomings impede the timely and accurate identification of unsafe behaviors, thus constraining their effectiveness in data-driven construction safety management.  \nFor example, a scaffold collapse case study in 2024 showed how emergency response and pre-incident controls can be undermined when site supervisio","cbCaipS6uWEhPtQj","https://ap.wps.com/l/cbCaipS6uWEhPtQj","pdf",3590286,28,"English","# Introduction\n## Construction safety monitoring challenges\n## Limitations of traditional and early computer vision approaches\n## Limitations of recent deep learning detectors","[{\"question\":\"What problem does the study address in construction sites?\",\"answer\":\"The study targets unsafe worker behaviors that can lead to construction accidents, while noting that current monitoring solutions are inefficient and not well adapted to changing on-site conditions.\"},{\"question\":\"How does the proposed framework improve detection performance?\",\"answer\":\"It uses a Dynamic Adaptive Image Enhancement module to adjust image brightness, contrast, and sharpness, and a Lightweight Real-Time Behavior Network that models temporal action information from both enhanced and raw image streams.\"},{\"question\":\"Which baseline methods does the study compare against, and what metrics are improved?\",\"answer\":\"The framework is compared with Faster R-CNN, YOLO, and Mask R-CNN, improving precision, recall, and F1-score, reported as 93.2%, 91.4%, and 92.3% respectively.\"}]","Real-Time Detection of Unsafe Worker Behaviors via Adaptive Vision Transformers in Construction Sites - Article | PDF",1792707310,71]