Automation in Construction最新文献_第2页

Computer vision-aided audio dataset generation for recognizing construction equipment actions

IF 10.3 1区工程技术

Automation in Construction Pub Date : 2025-01-28 DOI: 10.1016/j.autcon.2025.106014

Gilsu Jeong, Moonseo Park, Changbum R. Ahn

{"title":"Computer vision-aided audio dataset generation for recognizing construction equipment actions","authors":"Gilsu Jeong, Moonseo Park, Changbum R. Ahn","doi":"10.1016/j.autcon.2025.106014","DOIUrl":"https://doi.org/10.1016/j.autcon.2025.106014","url":null,"abstract":"Construction sites are dynamic with various activities and equipment sounds, essential for identifying equipment, understanding work processes, and assessing site conditions. However, recognizing equipment actions using audio data faces challenges like manual recording dependency, collecting high-quality datasets, and background noise. This paper introduces an automated framework, aided by computer vision algorithms, for generating an audio dataset for construction equipment from online sources. The framework uses computer vision to identify relevant visual content and audio classification models to filter out irrelevant content, ensuring high-quality data. Through the proposed framework, an audio dataset was generated with annotations covering equipment types and actions. Performance evaluation with classification models showed F-scores ranging from 61 % to 91 % at the equipment level and 52 % to 87 % at the action level. The framework offers an effective approach to creating audio datasets, supporting advancements in audio-based activity recognition, contributing to improvements in real-world construction site safety and productivity.","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"23 1","pages":""},"PeriodicalIF":10.3,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143071422","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Design Healing framework for automated code compliance

IF 10.3 1区工程技术

Automation in Construction Pub Date : 2025-01-28 DOI: 10.1016/j.autcon.2025.106004

Jiabin Wu, Stavros Nousias, André Borrmann

{"title":"Design Healing framework for automated code compliance","authors":"Jiabin Wu, Stavros Nousias, André Borrmann","doi":"10.1016/j.autcon.2025.106004","DOIUrl":"https://doi.org/10.1016/j.autcon.2025.106004","url":null,"abstract":"Automated Compliance Checking (ACC) techniques have advanced significantly, enabling designers to evaluate building designs against codes. However, architectural engineers have to improve the design by manually implementing the ACC results, which is laborious, iterative, and requires domain expertise. To address this challenge, this paper introduces a Design Healing framework that adapts the original design into code-compliant alternatives. By integrating design data and ACC results, the framework identifies critical non-compliant components through a graph-based topological algorithm and sensitivity analysis. A prior knowledge-informed design space exploration is conducted to find valid alternatives and quantify modifications using weighted Euclidean distances, allowing designers to select options closely aligned with the initial design. Multi-scenario experiments demonstrate the framework’s effectiveness in resolving architectural spatial design violations. By automating post-checking design adaptation, the framework reduces manual revisions and provides an efficient tool for achieving compliance while accommodating varying design constraints. This paper establishes a basis for advancing designer-centered automated design correction methods based on ACC techniques.","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"50 1","pages":""},"PeriodicalIF":10.3,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143071425","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Three-dimensional reconstruction of asphalt pavement macrotexture using event camera and evolved recurrent convolution network

IF 10.3 1区工程技术

Automation in Construction Pub Date : 2025-01-28 DOI: 10.1016/j.autcon.2025.106007

Kangnan Wang, Tao Ma, Yuanhang Yang, Zheng Tong

引用次数: 0

Prediction and risk assessment of lateral collapse in deep foundation pits using machine learning

IF 10.3 1区工程技术

Automation in Construction Pub Date : 2025-01-28 DOI: 10.1016/j.autcon.2025.106011

Hongyun Fan, Liping Li, Shen Zhou, Ming Zhu, Meixia Wang

引用次数: 0

Blockchain applications in the construction supply chain

IF 10.3 1区工程技术

Automation in Construction Pub Date : 2025-01-28 DOI: 10.1016/j.autcon.2025.105998

Mohammadhossein Heydari, Alireza Shojaei

引用次数: 0

Artificial intelligence in offsite and modular construction research

IF 10.3 1区工程技术

Automation in Construction Pub Date : 2025-01-27 DOI: 10.1016/j.autcon.2025.105994

Sitsofe Kwame Yevu, Karen B. Blay, Kudirat Ayinla, Georgios Hadjidemetriou

引用次数: 0

Automatic tile position and orientation detection combining deep-learning and rule-based computer vision algorithms

IF 10.3 1区工程技术

Automation in Construction Pub Date : 2025-01-27 DOI: 10.1016/j.autcon.2025.106001

Wenyao Liu, Jinhua Chen, Zemin Lyu, Rui Feng, Tong Hu, Lu Deng

{"title":"Automatic tile position and orientation detection combining deep-learning and rule-based computer vision algorithms","authors":"Wenyao Liu, Jinhua Chen, Zemin Lyu, Rui Feng, Tong Hu, Lu Deng","doi":"10.1016/j.autcon.2025.106001","DOIUrl":"https://doi.org/10.1016/j.autcon.2025.106001","url":null,"abstract":"Increasing interest in a tile-paving robot calls for a robust tile detection algorithm. This paper proposes the Ultra Clear Tile (UC-Tile) algorithm to detect corners and edges and assist tile paving automation in positioning and installation tasks. UC-Tile is designed to incorporate deep learning for semantic segmentation with rule-based post-processing algorithms. The semantic segmentation algorithm investigated herein is a fine-tuned version of YOLOv8. UC-Tile mainly contributes to refitting the edges and locating the tile corners with tailored algorithms. A dataset is developed comprising 1486 images exhibiting varying patterns of tiles, captured under disparate heights and illumination conditions. Results indicate that UC-Tile outperforms common benchmark algorithms, and can achieve the highest mIoU 98.68 %, F1-Score 99.31 %, and the lowest 95-HD. Further, UC-Tile can accurately predict real distance and angles with small differences to ground truth values, thereby informing robotic movement control. This algorithm is expected to enable precise automatic tile paving.","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"15 1","pages":""},"PeriodicalIF":10.3,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143071430","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Efficient visual inspection of fire safety equipment in buildings

IF 10.3 1区工程技术

Automation in Construction Pub Date : 2025-01-27 DOI: 10.1016/j.autcon.2025.105970

Fangzhou Lin, Boyu Wang, Zhengyi Chen, Xiao Zhang, Changhao Song, Liu Yang, Jack C.P. Cheng

{"title":"Efficient visual inspection of fire safety equipment in buildings","authors":"Fangzhou Lin, Boyu Wang, Zhengyi Chen, Xiao Zhang, Changhao Song, Liu Yang, Jack C.P. Cheng","doi":"10.1016/j.autcon.2025.105970","DOIUrl":"https://doi.org/10.1016/j.autcon.2025.105970","url":null,"abstract":"Fire safety equipment (FSE) in buildings is critical in ensuring occupant safety and mitigating losses during emergencies. However, its effectiveness is frequently compromised by inadequate maintenance. As buildings increase size and complexity, traditional manual inspection methods become impractical due to scalability and data management challenges. To address these issues, this paper proposes an advanced FSE detection framework with improvement strategies. The process commences with the developed YOLO-FSE algorithm, which is capable of identifying objects of varying sizes. This is complemented by precise localization of these objects through an enhanced tracking algorithm and visual simultaneous localization and mapping (vSLAM). The experiments demonstrate that this approach can effectively detect various fire safety equipment with the potential to replace labor-intensive manual methods. Notably, the YOLO-FSE network achieves a 7.9 % improvement in mean Average Precision (mAP) at a threshold of 0.5 (mAP@0.5), and a 9.4 % increase in mAP@0.95, indicating significant enhancements in detection accuracy.","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"75 1 1","pages":""},"PeriodicalIF":10.3,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143071465","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Curvature-informed paths for shell 3D printing

IF 10.3 1区工程技术

Automation in Construction Pub Date : 2025-01-27 DOI: 10.1016/j.autcon.2025.105988

Ioanna Mitropoulou, Mathias Bernhard, Benjamin Dillenburger

引用次数: 0

Agile digitization for historic architecture using 360° capture, deep learning, and virtual reality

IF 10.3 1区工程技术

Automation in Construction Pub Date : 2025-01-25 DOI: 10.1016/j.autcon.2025.105986

Farzan Baradaran Rahimi, Claude M.H. Demers, Mohammad Reza Karimi Dastjerdi, Jean-François Lalonde

{"title":"Agile digitization for historic architecture using 360° capture, deep learning, and virtual reality","authors":"Farzan Baradaran Rahimi, Claude M.H. Demers, Mohammad Reza Karimi Dastjerdi, Jean-François Lalonde","doi":"10.1016/j.autcon.2025.105986","DOIUrl":"https://doi.org/10.1016/j.autcon.2025.105986","url":null,"abstract":"The agile digitization of historic buildings is becoming increasingly critical for preservation, conservation, and maintenance in response to climate change, geopolitical conflicts, and other threats of destruction. This paper explores whether deep learning-based novel-view synthesis, combined with commercial 360° cameras and standalone virtual reality headsets, can streamline the digitization process for historic architecture. A case study of a historic interior in Québec, Canada, is used to evaluate the method's capacity to enhance agility, accuracy, and efficiency. The findings demonstrate that this approach significantly reduces complexity, labor, cost, and time while improving precision and workflow. These outcomes offer particular value to heritage experts, building engineers, and creative professionals seeking practical tools for agile digitization of historic architecture. By advancing digitization methods, this study also inspires future research into the broader applications of deep learning and immersive technologies for cultural heritage preservation.","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"10 1","pages":""},"PeriodicalIF":10.3,"publicationDate":"2025-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143071468","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0