Actual Construction Site Research Articles

Improving construction site efficiency through automated progress monitoring of underground pipe installation sites using image color analysis of iPhone LiDAR camera data

This study presents an innovative method utilizing smartphone for automated progress monitoring at underground pipe installation sites. Leveraging the LiDAR iPhone camera, the method captures detailed point cloud data of construction sites. Sophisticated color analysis of images accurately distinguishes between areas with and without pipes within excavations. Key aspects of the proposed workflow include segmentation of the excavation area, differentiation between main and side excavations, and application of an earth color mask in the RGB space to isolate pipes. The research focuses on enhancing measurement precision for excavation width, depth, and pipe burial depth, significantly reducing the manual labor traditionally required at construction sites, thereby offering an efficient and cost-effective solution. We further demonstrated the robustness of the proposed algorithm by applying it to two types of data acquired at actual construction sites. This approach is expected to contribute significantly to the digital transformation in the construction industry.

Monocular 3D Multi-Person Pose Estimation for On-Site Joint Flexion Assessment: A Case of Extreme Knee Flexion Detection.

Work-related musculoskeletal disorders (WMSDs) represent a significant health challenge for workers in construction environments, often arising from prolonged exposure to ergonomic risks associated with manual labor, awkward postures, and repetitive motions. These conditions not only lead to diminished worker productivity but also incur substantial economic costs for employers and healthcare systems alike. Thus, there is an urgent need for effective tools to assess and mitigate these ergonomic risks. This study proposes a novel monocular 3D multi-person pose estimation method designed to enhance ergonomic risk assessments in construction environments. Leveraging advanced computer vision and deep learning techniques, this approach accurately captures and analyzes the spatial dynamics of workers' postures, with a focus on detecting extreme knee flexion, a critical indicator of work-related musculoskeletal disorders (WMSDs). A pilot study conducted on an actual construction site demonstrated the method's feasibility and effectiveness, achieving an accurate detection rate for extreme flexion incidents that closely aligned with supervisory observations and worker self-reports. The proposed monocular approach enables universal applicability and enhances ergonomic analysis through 3D pose estimation and group pose recognition for timely interventions. Future efforts will focus on improving robustness and integration with health monitoring to reduce WMSDs and promote worker health.

Risk early warning model of tunnel engineering based on computer vision and CNN

Abstract Safety management in tunnel construction is important to ensure the safety of construction personnel and equipment. This paper proposes a tunnel engineering risk early warning model based on computer vision and convolutional neural network (CNN), aiming at realizing real-time monitoring and risk early warning of the construction site using modern image processing technology and deep learning algorithm. Many image data of tunnel engineering construction sites were collected, and the data were preprocessed and marked. Then, the paper designs a depth CNN model for feature extraction and risk identification of construction site images. Through the performance evaluation of the model on the training set and test set, the effectiveness and feasibility of the model in risk early warning are verified. The experimental results show that the proposed model achieves high accuracy, recall, and F1 score on the test set, which is superior to the traditional method based on image features and artificial rules. At the same time, we analyzed the prediction results of the model on the actual construction site images. We found that the model can effectively identify different risk factors and has strong generalization ability and practicability. To sum up, this study provides a new technical means and solution for the safety management of tunnel engineering, which has important theoretical and practical significance.

A Reconstruction Methodology of Dynamic Construction Site Activities in 3D Digital Twin Models Based on Camera Information

Digital twin technology significantly enhances construction site management efficiency; however, dynamically reconstructing site activities presents a considerable challenge. This study introduces a methodology that leverages camera data for the 3D reconstruction of construction site activities. The methodology was initiated using 3D scanning to meticulously reconstruct the construction scene and dynamic elements, forming a model base. It further integrates deep learning algorithms to precisely identify static and dynamic elements in obstructed environments. An enhanced semi-global block-matching algorithm was then applied to derive depth information from the imagery, facilitating accurate element localization. Finally, a near-real-time projection method was introduced that utilizes the spatial relationships among elements to dynamically incorporate models into a 3D base, enabling a multi-perspective view of site activities. Validated by simulated construction site experiments, this methodology showcased an impressive reconstruction accuracy reaching up to 95%, this underscores its significant potential in enhancing the efficiency of creating a dynamic digital twin model.

A New Methodology to Estimate the Early-Age Compressive Strength of Concrete before Demolding

Non-destructive testing has many advantages, such as the ability to obtain a large number of data without destroying existing structures. However, the reliability of the estimation accuracy and the limited range of applicable targets remain an issue. This study proposes a novel pin penetration test method to determine the early-age compressive strength of concrete before demolding. The timing of demolding and initial curing is determined according to the strength development of concrete. Therefore, it is important to determine the compressive strength at an early age before demolding at the actual construction site. The applicability of this strength estimation methodology at actual construction is investigated. Small test holes (12 mm in diameter) are prepared on the mold surface in real construction sites and mock-up specimens in advance. The pin is penetrated into these test holes to obtain the relationship between the compressive strength and the penetration depth. As a result, it is confirmed that the pin penetration test method is suitable for measuring the early-age compressive strength at the actual construction site. This allows the benchmark values for compressive strength, necessary to avoid early frost damage, to be directly verified on the concrete structural members at the construction site. For instance, the compressive strengths of greater than 5 MPa and 10 MPa can be confirmed by the penetration depths benchmark values of 8.0 mm and 6.7 mm or less, respectively.

Power saw noise levels during steel stud cutting tasks on commercial construction sites: a tool characterization from a worker exposure standpoint.

Construction framers who cut and install steel studs as part of their daily tasks are exposed to hazardous noise levels during their work shift in large part due to the power saws they use to cut steel studs. This investigation characterized the sound pressure levels of power saws used to cut steel studs on active construction sites. Further, the length of time it took to cut various studs on a construction site was investigated to understand worker exposure times to saw noise. In general, power saws used on the study sites to cut steel studs had a mean A-weighted equivalent continuous sound pressure level (LAeq) of 107.2 dB and a C-weighted peak sound pressure level (LCpeak) of 120.1 dB. Three of the saws-the chopsaw, the cut-off saw, and the grinder-had similar noise levels, whereas the cordless circular saw had higher noise levels. It took an average of 13.2 s to cut each stud, and workers in the study used power saws to cut steel studs for an average of 371.5 s per day. This average exposure time at the average recorded sound pressure levels (SPLs) suggests these saws can increase the risk of occupational noise-induced hearing loss, according to National Institute for Occupational Safety and Health (NIOSH) recommendations.

Monitoring the impacts of rainfall characteristics on sediment loss from road construction sites

Exposed soils associated with active construction sites provide opportunities for erosion and sediment transport during storm events, introducing risks associated with excess sediment to downstream infrastructure and aquatic biota. A better understanding of the drivers of sediment transport in construction site runoff is needed to improve the design and performance of erosion and sediment control measures (ESCMs). Eleven monitoring locations on 3 active road construction sites in central Ohio were established to characterize runoff quality from points of concentrated flow during storm events. Grab samples were analyzed for total suspended solids (TSS), turbidity, and particle size distribution (PSD). Median TSS concentrations and turbidity levels across all samples were 626 mg/L (range 25–28,600 mg/L) and 759 NTU (range 22–33,000 NTU), respectively. The median PSD corresponded to a silty clay loam, mirroring the soil texture of much of Ohio’s subsoils. TSS concentrations and turbidity were significantly positively correlated with the rainfall intensity 10 min prior to sample collection, suggesting that higher flow rates created greater shear stress on bare soil which resulted in more erosion. Conversely, rainfall duration was negatively correlated with particle size, indicating that prolonged moisture from rainfall promoted the dispersion of soil aggregates which mobilized smaller particles. Multivariable linear regression models revealed that higher rainfall intensities corresponded to higher turbidity values, while higher TSS concentrations were associated with higher rainfall intensities, depths, and durations. Results from this study highlight the importance of reducing raindrop impact and subsequent shear stress applied by concentrated flows through the use of ESCMs to limit sediment export from construction sites.

Style-Enhanced Transformer for Image Captioning in Construction Scenes.

Image captioning is important for improving the intelligence of construction projects and assisting managers in mastering construction site activities. However, there are few image-captioning models for construction scenes at present, and the existing methods do not perform well in complex construction scenes. According to the characteristics of construction scenes, we label a text description dataset based on the MOCS dataset and propose a style-enhanced Transformer for image captioning in construction scenes, simply called SETCAP. Specifically, we extract the grid features using the Swin Transformer. Then, to enhance the style information, we not only use the grid features as the initial detail semantic features but also extract style information by style encoder. In addition, in the decoder, we integrate the style information into the text features. The interaction between the image semantic information and the text features is carried out to generate content-appropriate sentences word by word. Finally, we add the sentence style loss into the total loss function to make the style of generated sentences closer to the training set. The experimental results show that the proposed method achieves encouraging results on both the MSCOCO and the MOCS datasets. In particular, SETCAP outperforms state-of-the-art methods by 4.2% CIDEr scores on the MOCS dataset and 3.9% CIDEr scores on the MSCOCO dataset, respectively.

Development and Application of Safety Protection Passageway Capable of Double Buffering and Double Protection

The main purpose of the safety protection passage is not only to provide psychological stability to pedestrians when they have to pass near a construction site in the city but also to protect against materials, parts, tools, and debris that may fall at the actual construction site. However, despite the fact that pedestrian safety passages are important temporary facilities that are directly related to the safety of citizens, in the case of existing passageways, only the shape of the frame is arbitrarily created using square pipes or square lumber at the construction site, and wood is placed on the top. Currently, the panels are assembled and used without safety verification. The safety passageway installed in this manner is easily destroyed by a light impact. It can neither perform its function nor guarantee the safety of pedestrians. The main purpose of this study is to provide psychological stability to pedestrians in pedestrian passageways near urban construction sites and to prevent damage caused by materials, parts, tools, and debris that may fall at actual construction sites. As a result of research and development, the ease of manufacturing, economic feasibility, and operability of the structure were confirmed through the production of a prototype of the structure. A structural review confirmed that the stress generated in the safety protection passage of the researched and developed system for the appropriate load of the falling object was within the allowable stress.

Improving single‐stage activity recognition of excavators using knowledge distillation of temporal gradient data

AbstractSingle‐stage activity recognition methods have been gaining popularity within the construction domain. However, their low per‐frame accuracy necessitates additional post‐processing to link the per‐frame detections. Therefore, limiting their real‐time monitoring capabilities is an indispensable component of the emerging construction of digital twins. This study proposes knowledge DIstillation of temporal Gradient data for construction Entity activity Recognition (DIGER), built upon the you only watch once (YOWO) method and improving its activity recognition and localization performance. Activity recognition is improved by designing an auxiliary backbone to exploit the complementary information in the temporal gradient data (transferred into YOWO using knowledge distillation), while localization is improved primarily through integration of complete intersection over union loss. DIGER achieved a per‐frame activity recognition accuracy of 93.6% and localization mean average precision at 50% of 79.8% on a large custom dataset, outperforming state‐of‐the‐art methods without requiring additional computation during inference, making it highly effective for real‐time monitoring of construction site activities.

Point cloud registration considering safety nets during scaffold installation using sensor fusion and deep learning

Accidents and fatalities during scaffolding work are significant concerns in the construction industry. Scaffold monitoring technology based on 3D reconstruction can offer a potential solution to prevent such fatalities. However, the practical application of this technology at actual construction sites faces a notable challenge due to the presence of safety nets. Safety nets hinder the acquisition of complete scaffold point clouds necessary for reconstruction. To address this issue, we propose a novel registration method for scaffold point clouds that considers safety nets, employing sensor fusion and deep learning techniques. The method consists of three steps: 1) LiDAR-camera calibration and SLAM-based point cloud data acquisition, 2) object detection and coordinate transformation, and 3) identification of scaffold installation stages and point cloud registration. The proposed method was verified to be effective in registering scaffold point clouds without safety nets.

Research on rural landscape garden planning and plantscape construction method based on digital twin technology under rural revitalization strategy

Abstract This paper integrates the landscape information model, designs the digital twin rural landscape architecture, and analyzes the advantages of the digital twin rural landscape model. The practical application of digital twin technology is examined from the planning and design stage to the construction stage. Considering the actual construction site layout and the consumption of construction materials, the NSGA-II algorithm is selected to optimize the dynamic layout of temporary facilities by combining multi-objective optimization theory. Using the digital twin to drive the dynamic layout of the construction site, a digital twin-driven construction site layout mechanism is proposed in combination with BIM technology. The actual construction scheduling tasks are used to analyze the feasibility of the construction site layout scheme generated using digital twin technology. Analyze the construction of rural landscape gardens planned using digital twin technology in terms of ecological, social, and economic benefits. The convergence minimum is achieved at 0.15 and 0.09 when comparing the number of iterations between the initialized layout and the digital twin-driven layout. The corresponding scheme reaches its optimal state during the construction stage and can provide the most suitable site arrangement scheme during that stage. The rural landscape garden planned by the digital twin technology can generate an economic return value of 71.756 yuan/m² per year, which can further promote rural revitalization.

A Case Study of Peat Ground Improvement by Vacuum Consolidation in Hokkaido, Japan

This paper presents the field performance of vacuum consolidation method on peat ground and some technical learning from the field trial. Peat is well known to be a soft soil which has particular characteristics, including extremely high compressibility and greatly low undrained shear strength. In case of an embankment building over peat ground, sliding failure and large settlement often occur due to the particular characteristics. For actual construction sites on peat ground, therefore, some kinds of ground improvement methods are commonly used. One of the methods is the vacuum consolidation method which can load vacuum pressure with the soft ground by vacuum pumps and prefabricated vertical drains to accelerate the consolidation and increases the strength of soft ground. Peat ground distributed widely in Hokkaido, the northernmost land of Japan. A full-scale trial construction of vacuum consolidation was conducted in a highway project over peat deposit in Hokkaido of Japan to reveal its performance. Although the undrained shear strength of peat ground at the trial construction site was approximately 10 kN/m2 and extremely low, a 10.7 m high embankment was successfully built in only 45 days. This experimental fact implies that the vacuum consolidation method has extremely high effects in improving the stability of peat ground. Based on a result of the trial construction, it also revealed that the increase of undrained shear strength of the peat ground using vacuum consolidation and the suitable spacing of prefabricated vertical drains for peat ground.

Towards Human–Robot Collaboration in Construction: Understanding Brickwork Production Rate Factors

This study explores the critical determinants impacting labor productivity in brickwork operations within the construction industry—a matter of academic and practical significance, particularly in the era of increasing human–robot collaboration. Through an extensive literature review on construction labor productivity, this study identifies factors affecting brickwork productivity. Data were collected from active construction sites during brick wall construction through on-site measurements and participatory observation, and the relative importance of these factors is determined using Principal Component Analysis (PCA)-factor analysis. The validity of the analysis is established through the Kaiser–Meyer–Olkin (KMO) test and Bartlett’s test of sphericity, with a KMO value of 0.544 and significance at the 0.05 significance level. The analysis reveals four principal components explaining 75.96% of the total variance. Notably, this study identifies the Euclidean distances for the top factors: weather (0.980), number of helpers (0.965), mason competency (0.934), and number of masons (0.772). Additionally, correlation coefficients were observed: wall area had the highest correlation (0.998), followed by wall length (0.853) and height (0.776). Interestingly, high correlations did not necessarily translate to high factor importance. These identified factors can serve as a foundation for predictive modeling algorithms for estimating production rates and as a guideline for optimizing labor in construction planning and scheduling, particularly in the context of human–robot collaboration.

Construction Activity Analysis of Workers Based on Human Posture Estimation Information

Identifying workers’ construction activities or behaviors can enable managers to better monitor labor efficiency and construction progress. However, current activity analysis methods for construction workers rely solely on manual observations and recordings, which consumes considerable time and has high labor costs. Researchers have focused on monitoring on-site construction activities of workers. However, when multiple workers are working together, current research cannot accurately and automatically identify the construction activity. This research proposes a deep learning framework for the automated analysis of the construction activities of multiple workers. In this framework, multiple deep neural network models are designed and used to complete worker key point extraction, worker tracking, and worker construction activity analysis. The designed framework was tested at an actual construction site, and activity recognition for multiple workers was performed, indicating the feasibility of the framework for the automated monitoring of work efficiency.

드론을 활용한 스마트 건설 안전기술 개발 및 실증연구

In the construction industry, the introduction of innovative safety measures is urgently required in the current trend of increasing deaths and economic losses due to continuous thinking. One of the major causes of this trend is that it relies on passive management systems that do not reflect the development of technology.
 In recognition of the potential of smart construction technology, this study has begun to integrate these innovations into existing safety management protocols. However, the initial review has found that the development and introduction of smart construction technologies in Korea are behind, and there are several areas where improvement and refinement are needed.
 In response to these challenges, we developed smart construction safety platform technology. This platform technology is designed to thoroughly analyze domestic and overseas smart safety technologies. One of the major features of this technology is the ability to monitor field activities in real-time to secure administrators and other personnel safety. Using smart IoT devices using drones and AI-based monitoring analytics systems, active measures can be provided. In addition to preventing construction workers from entering dangerous areas, they can quickly detect and respond to urgent situations.
 At the heart of this effort is to design efficient data flow mechanisms. Work has been done to ensure seamless communication and data exchange by integrating drones, central control systems, and platform technology itself. We tested the practicality and effectiveness of platforms at the construction site of Gwangmyeong-shiheung, and as a result, smart construction safety platform technology using drone proved robustness and reliability in the real environment.
 We will concentrate on further refinement of platform technology through this study. By collecting feedback from the actual construction site and integrating it into the system, it is estimated that smart safety construction platform technology using drones will stay at the forefront of the industry standard and can protect many lives from the construction site.

Site Characterisation, Deep Basement Support, Construction, and Deformation Control

Deep basement construction is characterised by a deformation challenge for the excavation pit and adjacent structures. Basement construction is an unavoidable problem in urban areas. A case is found in a Triumph Unit building block project, where a 14 m basement will be constructed near the existing structures. Conducting a site survey engineering analysis before the deep basement excavation is essential to guarantee safety during basement construction. Site survey engineering analysis is vital in recommending a suitable support structure for the basement pit during excavation. Therefore, this paper takes the Triumph Unit high-rise building basement excavation project as a practical application of site survey engineering analysis on the actual construction site. Geotechnical and groundwater characterisation were achieved through field and laboratory tests. The study revealed that the site was suitable for construction of bored piles as enclosure structure. It also recommended application of steel bracing material enhanced with a hydraulic servo system as basement excavation internal support structure. The recommended support structure is applied to the actual excavation. The excavation-induced deformation with respect to the recommended support structure application is strictly monitored and controlled. The measured project site results show the effectiveness of site survey engineering analysis in recommending a suitable deep basement excavation support system that controls the excavation-induced deformation desirably.

DESIGN-BUILT BAMBOO STRUCTURE USING MULTIPLE-MEMBER PRE-FABRICATED CONNECTORS

Bamboo as the structural material has become the trend to respond to sustainability, due to its outstanding structural properties and renewable aspect. Though bamboo architecture is seen throughout the world, but they are still varied from culture to culture, due to limited knowledge and advanced applications. In order to move this material forward for industrialization, standard system of creating bamboo structure should be established. The most challenge of bamboo structure is the connectors. Though the conventional style is elegant and crafty, but they require special skills and lengthy construction time. Using pre-fabricated connectors to expedite construction are not quite common. This potential to introduce pre-fabricated connectors and more complex bamboo structure is needed to explore further. This research then takes the design-built approach as the methodology. The process starts with designing a complex structure with multiple-member at column-foundation nodes. Pre-fabricated steel connectors are designed to host at least six members in a single node. Four nodes are designed in this 30 sq. m bamboo pavilion. Each member is made of two different bamboo formats; bundled bamboo culms and bundled bamboo splits. Pavilion frames then are assembled using designed connectors in actual construction site. The construction is carefully monitored and documented for their strength and feasibility. It is found that pre-fabricated connectors can simply put the construction together with simple tools and in efficient time. Multiple-member at column-foundation nodes is strong and possible for complex structure. They perform well and still hold the elegant integrity of bamboo architecture.

Unmanned Aerial Systems and Deep Learning for Safety and Health Activity Monitoring on Construction Sites.

Construction is a highly hazardous industry typified by several complex features in dynamic work environments that have the possibility of causing harm or ill health to construction workers. The constant monitoring of workers' unsafe behaviors and work conditions is considered not only a proactive but also an active method of removing safety and health hazards and preventing potential accidents on construction sites. The integration of sensor technologies and artificial intelligence for computer vision can be used to create a robust management strategy and enhance the analysis of safety and health data needed to generate insights and take action to protect workers on construction sites. This study presents the development and validation of a framework that implements the use of unmanned aerial systems (UASs) and deep learning (DL) for the collection and analysis of safety activity metrics for improving construction safety performance. The developed framework was validated using a pilot case study. Digital images of construction safety activities were collected on active construction sites using a UAS, and the performance of two different object detection deep-learning algorithms/models (Faster R-CNN and YOLOv3) for safety hardhat detection were compared. The dataset included 7041 preprocessed and augmented images with a 75/25 training and testing split. From the case study results, Faster R-CNN showed a higher precision of 93.1% than YOLOv3 (89.8%). The findings of this study show the impact and potential benefits of using UASs and DL in computer vision applications for managing safety and health on construction sites.

Environmental impact assessment of on-site and off-site construction logistics activities – A case study analysis from Norway

Construction site activities are one of the main contributors to GHG emissions in the construction industry. There are several on-going initiatives on finding low and zero emission solutions for reducing GHG emission from construction sites. The objective of this paper is to investigate the emission reduction potential from fossil and emission free on-site and off-site construction logistic activities based on actual data collected from a case study from Oslo. The paper firstly presents definitions and step wise approach for fossil free and emission free construction site activities. Then, GHG emission calculation from the logistic activities using LCA methods and scenario analysis to evaluate the environmental performance of fossil and emission free solutions considered in the selected case study. The results illustrated the GHG emission reduction potential from electrification of construction machineries and transport of material, collaboration between construction site for more efficient use and reuse of excavated masses, modal shift for transport of materials as well as the importance of clear description of the system boundary and background data. Availability of electric machinery, electrified means of transport and sufficient electricity supply, lack of requirements for low-emission material transport solutions, lack of data for LCA studies are identified as some challenges. Moreover, the study highlighted the potential contribution of increased demand for emission free solutions through public procurement to facilitate a change in the industry by overcoming these barriers.