Nasrullah Khan , Syed Farhan Alam Zaidi , Muhammad Sibtain Abbas , Doyeop Lee , Dongmin Lee
{"title":"Tracking multiple construction workers using pose estimation and feature-assisted re-identification model","authors":"Nasrullah Khan , Syed Farhan Alam Zaidi , Muhammad Sibtain Abbas , Doyeop Lee , Dongmin Lee","doi":"10.1016/j.autcon.2024.105771","DOIUrl":"10.1016/j.autcon.2024.105771","url":null,"abstract":"<div><div>Tracking construction workers is crucial for ensuring worker safety, productivity, appropriate resource allocation, and regulatory compliance. However, when multiple workers resemble each other or temporary obstructions occur, maintaining accurate identification of individual workers with computer-vision-based tracking techniques is challenging. This paper proposes a multi-worker tracking framework comprising three key components: 1) a pose estimation model that localizes and generates keypoints for each worker, 2) a selective region algorithm with unique visual signatures and a re-identification (ReID) model that extracts features to distinguish workers, and 3) data association techniques that accurately track multiple workers simultaneously. The evaluation results obtained by using the higher-order tracking accuracy (HOTA) and multi-object tracking accuracy (MOTA) metrics on 16 annotated videos demonstrate the effectiveness of the framework. The selective region algorithm, combined with different configurations of trackers and ReID models, achieves an HOTA index of 85.83 % across various scenarios. This pre-emptive intermediation fosters multi-worker monitoring in dynamic construction environments.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"168 ","pages":"Article 105771"},"PeriodicalIF":9.6,"publicationDate":"2024-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142275782","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}
Shengchuan Jiang , Hui Wang , Zhipeng Ning , Shenglin Li
{"title":"Lightweight pruning model for road distress detection using unmanned aerial vehicles","authors":"Shengchuan Jiang , Hui Wang , Zhipeng Ning , Shenglin Li","doi":"10.1016/j.autcon.2024.105789","DOIUrl":"10.1016/j.autcon.2024.105789","url":null,"abstract":"<div><div>The size and complexity of the multiobjective detection model restrict its applicability to real-time road distress detection with unmanned aerial vehicles (UAVs). To address this issue, this paper proposes a lightweight approach that integrates a performance-aware approximation global channel pruning (PAGCP) algorithm and a channel-wise knowledge distillation method. YOLOv7-RDD was selected as the baseline model, and ablation tests were conducted to analyze the modules. The SIoU loss function demonstrated superior performance to CIoU, Wise IoU, and EIoU, while SimAM exhibited enhanced results compared to SE, CBAM, LSKA, and ELA attention mechanism modules. The integration of the PAGCP pruning model and the channel-wise knowledge distillation method resulted in a 17 % reduction in model size and a 79 % reduction in computational complexity while maintaining accuracy. The model exhibited satisfactory performance in the detection of four types of pavement distress based on UAV-collected image data, with an <em>mAP</em> of 0.712.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"168 ","pages":"Article 105789"},"PeriodicalIF":9.6,"publicationDate":"2024-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142312451","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}
{"title":"Automatic assessment of concrete cracks in low-light, overexposed, and blurred images restored using a generative AI approach","authors":"Pengwei Guo , Xiangjun Meng , Weina Meng , Yi Bao","doi":"10.1016/j.autcon.2024.105787","DOIUrl":"10.1016/j.autcon.2024.105787","url":null,"abstract":"<div><div>Deep learning-based computer vision techniques have high efficiency in assessing concrete cracks from images, and the assessment can be automated using robots for higher efficiency. However, assessment accuracy is often compromised by low-quality images. This paper presents a Conditional Generative Adversarial Network (CGAN)-based approach to restore low-light, overexposed, and blurred images. The approach integrates attention mechanisms and residual learning and uses Wasserstein loss with gradient penalty. Crack assessment results show that the proposed approach outperforms state-of-the-art methods, regarding structural similarity (SSIM: 0.78 for deblurring, 0.95 for low-light enhancement, and 0.96 for overexposure correction) and peak signal-to-noise ratio (PSNR: 28.6 for deblurring, 31.4 for low-light enhancement, and 31.6 for overexposure correction). Restored images have been used to train a deep learning model for assessing concrete cracks. The Intersection over Union (IoU) and F1 score of crack segmentation are higher than 0.98 and 0.99, respectively, revealing high accuracy in crack assessment tasks.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"168 ","pages":"Article 105787"},"PeriodicalIF":9.6,"publicationDate":"2024-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142275780","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}
Nils Opgenorth , Daniel Nunes Locatelli , Samuel Leder , Hans Jakob Wagner , Achim Menges
{"title":"Multi-scalar robotic fabrication system for on-site press gluing in multi-storey timber buildings","authors":"Nils Opgenorth , Daniel Nunes Locatelli , Samuel Leder , Hans Jakob Wagner , Achim Menges","doi":"10.1016/j.autcon.2024.105774","DOIUrl":"10.1016/j.autcon.2024.105774","url":null,"abstract":"<div><div>The amount of timber construction has increased significantly in recent decades due to the development of digital processing technologies in prefabrication. However, on site, timber components are still commonly assembled manually and connected with low performance joint types. This paper presents a multi-storey timber building system with a co-designed heterogeneous multi-scalar robotic construction system, consisting of a clamping device, an industrial robotic arm, and an automated crane, for the automation of on-site timber construction. By integrating construction features into the building material, the different robotic entities can work together to assemble a point-supported quasi-monolithic timber panel of theoretically unlimited dimensions with high precision.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"168 ","pages":"Article 105774"},"PeriodicalIF":9.6,"publicationDate":"2024-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0926580524005107/pdfft?md5=5090c779f1c2884a399a03d43441002a&pid=1-s2.0-S0926580524005107-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142275785","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shengyuan Li , Yushan Le , Jiachen Gao , Xian Li , Xuefeng Zhao
{"title":"Bolt loosening angle measurement along full range of screw exposure length based on 3D point cloud","authors":"Shengyuan Li , Yushan Le , Jiachen Gao , Xian Li , Xuefeng Zhao","doi":"10.1016/j.autcon.2024.105785","DOIUrl":"10.1016/j.autcon.2024.105785","url":null,"abstract":"<div><div>The existing two-dimensional (2D) vision-based bolt loosening measurement range is generally limited to 0–60°. To overcome this limitation, a bolt loosening angle measurement method along full range of screw exposure length based on three-dimensional (3D) point cloud is proposed. Initially, 3D point clouds of bolt groups were reconstructed using 2D images under 18 working conditions, and the 3D point cloud of a single bolt was extracted from the bolt group. Subsequently, the bolt loosening angle along full range of screw exposure length was measured by calculating the rotation angle derived from the change in screw exposure length before and after loosening. The average relative error of all bolt loosening angle measurement results under the 18 working conditions was 3.46 %. Finally, the factors influencing the proposed method were analyzed. The results demonstrated that the proposed method could accurately measure the bolt loosening angle along full range of screw exposure length.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"168 ","pages":"Article 105785"},"PeriodicalIF":9.6,"publicationDate":"2024-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142275784","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}
{"title":"Vision-based construction robot for real-time automated welding with human-robot interaction","authors":"Doyun Lee , Kevin Han","doi":"10.1016/j.autcon.2024.105782","DOIUrl":"10.1016/j.autcon.2024.105782","url":null,"abstract":"<div><div>The construction industry is a major consumer of steel, with welding being a crucial aspect of steel fabrication. However, a shortage of welders has emerged as a significant issue. Therefore, the ultimate goal of this study is to develop a fully automated mobile robotic welding system. The preliminary paper presented a method for the automatic detection and alignment of various welding joints. Building on this, this paper proposes a real-time automated welding system capable of path planning and tracking for two butt joints using visual data. Given the precision required in welding, two robotic operations were devised: one for following a trajectory based on real-time image data, and another for welding guided by laser-scanned data. Additionally, human-robot interaction is proposed for path planning in cases where deep learning-based joint detection fails. The automated robotic welding was performed to test the performance of the proposed system, demonstrating its effectiveness and accuracy.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"168 ","pages":"Article 105782"},"PeriodicalIF":9.6,"publicationDate":"2024-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142275788","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}
{"title":"Effectiveness of alarm sounds in preventing operator habituation to auditory warnings in construction equipment","authors":"Jeonghyeun Chae , Sungjoo Hwang , Youngcheol Kang","doi":"10.1016/j.autcon.2024.105784","DOIUrl":"10.1016/j.autcon.2024.105784","url":null,"abstract":"<div><div>A proximity auditory warning (AW) system has been developed to mitigate accidents involving construction equipment blind spots. However, frequent AW sounds can lead to habituation among construction equipment operators, potentially reducing the system's effectiveness. This paper assessed the effectiveness of AW sounds in mitigating habituation. Twenty-one participants underwent a driving simulation, with reaction time and skin conductance level used as indicators of habituation. Participants' responses to the conventional probe-tone sound were compared with three proposed AW sounds: an auditory icon resembling a threat or dangerous situation, a self-owned name (SON) addressing the participant's name, and a combination of both. SON is recommended as a viable alternative for effective alarm sound. By investigating alarm sounds that enhance operators' responsiveness to obstacles in blind spots, particularly in environments where frequent alarms are unavoidable, this paper contributes to reducing struck-by accidents involving construction equipment.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"168 ","pages":"Article 105784"},"PeriodicalIF":9.6,"publicationDate":"2024-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142275786","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}
Jiangpeng Shu , Ziyue Zeng , Wenhao Li , Shukang Zhou , Congguang Zhang , Caie Xu , He Zhang
{"title":"Automatic geometric digital twin of box girder bridge using a laser-scanned point cloud","authors":"Jiangpeng Shu , Ziyue Zeng , Wenhao Li , Shukang Zhou , Congguang Zhang , Caie Xu , He Zhang","doi":"10.1016/j.autcon.2024.105781","DOIUrl":"10.1016/j.autcon.2024.105781","url":null,"abstract":"<div><div>Geometric modeling is a pivotal step in creating a digital twin for existing bridge structures. Its deficiency of automation makes geometric modeling step time-consuming and laborious. This paper presents a solution for automatically modeling box girder bridges, including external and internal structures, based on laser-scanned point cloud. The solution includes three vital methods: component segmentation, key points extraction of cross-section, and internal structure reconstruction. The results indicate that the established segmentation model, BCR-Net, exhibited better performance than PointNet++ in component segmentation, as demonstrated by mIoU of 0.9751 on the test set. The mean absolute error on the dimension of the pier, bent cap and external and internal structure of the box girder is 0.27 %, 0.38 %, 0.47 %, and 0.48 %, respectively. It means the proposed methods possessed excellent modeling accuracy while ensuring high efficiency than manual modeling, providing a promising solution for digital twin modeling of bridge structures.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"168 ","pages":"Article 105781"},"PeriodicalIF":9.6,"publicationDate":"2024-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142275787","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}
{"title":"Voxel-based path-driven 3D concrete printing process simulation framework embedding interlayer behavior","authors":"Baixi Chen, Xueqi Zhao, Xiaoping Qian","doi":"10.1016/j.autcon.2024.105776","DOIUrl":"10.1016/j.autcon.2024.105776","url":null,"abstract":"<div><p>This paper introduces a numerical framework to model the 3D concrete printing process, considering critical factors, particularly the print path and interlayer interactions. Within this framework, a finite element model is automatically generated for an arbitrary 3D-printed object. This is achieved by voxelizing the bounding space, incorporating a zero-thickness interlayer cohesive zone, and pinpointing the active elements. Additionally, a print path-driven element segment algorithm is developed, allowing for sequential element placement in alignment with the print path during simulation, thereby mirroring the actual printing process. The model efficacy is demonstrated through two benchmarks, focusing on elastic buckling and plastic failure, where it agrees with existing experimental and numerical data. Using this validated model, the impacts of various printing parameters, such as print width, speed, path, and interlayer behaviors are explored, and an integrated toolbox for both educational and academic purposes is created. This toolbox is available at <span><span>https://github.com/Baixi-Chen/3DCPProcessSimulaion.git</span><svg><path></path></svg></span>.</p></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"168 ","pages":"Article 105776"},"PeriodicalIF":9.6,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142239202","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}
{"title":"Intelligent ergonomic optimization in bimanual worker-robot interaction: A Reinforcement Learning approach","authors":"Mani Amani , Reza Akhavian","doi":"10.1016/j.autcon.2024.105741","DOIUrl":"10.1016/j.autcon.2024.105741","url":null,"abstract":"<div><p>Robots have the potential to enhance safety on construction job sites by assuming hazardous tasks. While existing safety research on physical human-robot interaction (pHRI) primarily addresses collision risks, ensuring inherently safe collaborative workflows is equally important. For example, ergonomic optimization in co-manipulation is an important safety consideration in pHRI. While frameworks such as Rapid Entire Body Assessment (REBA) have been an industry standard for these interventions, their lack of a rigorous mathematical structure poses challenges for using them with optimization algorithms. Previous works have tackled this gap by developing approximations or statistical approaches that are error-prone or data-dependent. This paper presents a framework using Reinforcement Learning for precise ergonomic optimization that generalizes to different types of tasks. To ensure practicality and safe experimentations, the training leverages Inverse Kinematics in virtual reality to simulate human movement mechanics. Results of a comparison between the developed framework and ergonomically naive approaches are presented.</p></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"168 ","pages":"Article 105741"},"PeriodicalIF":9.6,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0926580524004771/pdfft?md5=2b2b2036cf1904a46046f0d067750809&pid=1-s2.0-S0926580524004771-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142239124","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}