An object recognition, tracking, and contextual reasoning-based video interpretation method for rapid productivity analysis of construction operations

Measuring the process of construction operations for productivity improvement remains a difficult task for most construction companies due to the manual effort required in most activity measurement methods. This paper proposed and described the elements, processes, and algorithms that comprise a computational and intelligent construction video interpretation method. A number of vision-based construction object recognition and tracking methods were evaluated to provide guidance for algorithm selection. A prototype system was developed to integrate the proposed video analysis processes and selected computer vision algorithms. Videos of construction operations were analyzed to validate the proposed method. Comparing to the traditional manual construction video analysis method, the proposed method provided a semi-automated video interpretation method. The new method enabled the interpretation of these videos into productivity information, such as working processes, cycle times, and delays, with an accuracy that was comparable to manual analysis, without the limitations of on-site human observation.     

Automated task-level activity analysis through fusion of real time location sensors and worker's thoracic posture data

Knowledge of workforce productivity and activity is crucial for determining whether a construction project can be accomplished on time and within budget. Significant work has been done on improving and assessing productivity and activity at task, project, or industry levels. Task level productivity and activity analysis are used extensively within the construction industry for various purposes, including cost estimating, claim evaluation, and day-to-day project management. The assessment is mostly performed through visual observations and after-the-fact analyses even though previous studies show automatic translation of operations data into productivity information and provide spatial information of resources for specific construction operations. An original approach is presented that automatically assesses labor activity. Using data fusion of spatio-temporal and workers' thoracic posture data, a framework was developed for identifying and understanding the worker's activity type over time. This information is used to perform automatic work sampling that is expected to facilitate real-time productivity assessment.     

Real-time resource location data collection and visualization technology for construction safety and activity monitoring applications

Data to field operations of construction resources (personnel, equipment, materials) is vast, but the effort of collecting, analyzing, and visualizing is hardly ever taken. One main reason that limits higher quality in project site management decision making especially in resource intensive and complex operations is access to real-time information and subsequent technology that enables effortless data collection, processing, and visualization. Although recent developments in remote data sensing and intelligent data processing supplement manual data recording and analyze practices, few data on visualization tools in construction exist that gather data from dynamic resources and stream it to a field-realistic virtual reality environment in real-time. State-of-the-art technology in the field of real-time data collection and visualization is reviewed. A novel framework is presented that explains the method of streaming data from real-time positioning sensors to a real-time data visualization platform. Three case studies are presented which highlight its methods for recording data and visualizing information of construction activities in a (1) simulated virtual construction site, (2) outdoor construction setting, and (3) worker training environment. The results demonstrate that important construction information related to both safety and activity in field operations can be automatically monitored and visualized in real-time, thus offering benefits such as increased situational awareness to workers, equipment operators, or decision makers anywhere on a construction project or from a remote location.     

Evaluation of image-based modeling and laser scanning accuracy for emerging automated performance monitoring techniques

Accurate and rapid assessment of the as-built status on any construction site provides the opportunity to understand the current performance of a project easily and quickly. Rapid project assessment further identifies discrepancies between the as-built and as-planned progress, and facilitates decision making on the necessary remedial actions. Currently, manual visual observations and surveying are the most dominant data capturing techniques but they are time-consuming, error-prone, and infrequent, making quick and reliable decision-making difficult. Therefore, research on new approaches that allow automatic recognition of as-built performance and visualization of construction progress is essential. This paper presents and compares two methods for obtaining point cloud models for detection and visualization of as-built status for construction projects: (1) A new method of automated image-based reconstruction and modeling of the as-built project status using unordered daily construction photo collections through analysis of Structure from Motion (SfM); (2) 3D laser scanning and analysis of the as-built dense point cloud models. These approaches provide robust means for recognition of progress, productivity, and quality on a construction site. In this paper, an overview of the newly developed automated image-based reconstruction approach and exclusive features which distinct it from other image-based or conventional photogrammetric techniques is presented. Subsequently the terrestrial laser scanning approach carried out for reconstruction and comparison of as-built scenes is presented. Finally the accuracy and usability of both of these techniques for metric reconstruction, automated production of point cloud models, 3D CAD shape modeling, and as-built visualizations is evaluated and compared on eight different case studies. It is shown that for precise defect detection or alignment tasks, image-based point cloud models may not be as accurate and dense as laser scanners' point cloud models. Nonetheless image-based point cloud models provide an opportunity to extract as-built semantic information (i.e., progress, productivity, quality and safety) through the content of the images, are easy to use, and do not need add burden on the project management teams by requiring expertise for data collection or analysis. Finally image-based reconstruction automatically provides photo alignment with point cloud models and enables image-based renderings which can remarkably impact automated performance monitoring and as-built visualizations.     

A model for automated monitoring of road construction

Monitoring and control of earthmoving operations is gaining an increasing interest. Manual monitoring and control of earthmoving operations have not yielded the expected results. Additionally, because manual monitoring is labor‐intensive, construction managers have to choose between monitoring based on rough estimates, or spending a lot of time collecting and processing data. The latter choice distracts them from many other important duties. The purpose of the present model is to automatically collect and process monitoring data providing the construction manager with real‐time control information. The model was developed for road construction. It uses GPS technology for automated data collection, logging the locations of all the earthmoving equipment while working on the project. Specially developed algorithms convert these locations to control information regarding productivity, duration (or progress) and actual consumption of materials. The model was implemented and tested for 3 weeks in a road construction project. The performance of four activities was measured by the model and compared to manual measurement of the same parameters. This comparison indicated that the model could reach a deviation of ±5%.     

Can project monitoring and control be fully automated?

An extended research programme has examined over the past two decades how productivity in construction projects can be improved through the development of models for project monitoring and control, which process automatically collected data on the actual project performance. Tests that were conducted with these models demonstrate that this approach can help overcome some of the limitations of existing manual methods. However, they also indicate that certain manually obtained data are still required in addition to the automatically collected data. A framework for semi-automated project monitoring and control is proposed, in which both manually and automatically collected data can be incorporated. This framework integrates the monitoring of projects with their control by taking into account the impact on productivity of existing deviations from the planned performance, and of the controlling actions that are proposed to deal with these deviations.     

A Petri net simulation model for virtual construction of earthmoving operations

A common and extended Petri net simulation framework for virtual construction of earthmoving operations is developed to simulate dynamic changes of workflow and information flow in the earthmoving construction process and illustrate the constraint relationship between various operational equipment and construction restrictions. The proposed framework considers factors that influence earthmoving operations including randomness of construction activities, individual preference of equipment scheduling, and constraint relationship between equipment and construction environment. With the given equipment availability and project indirect cost, the framework can predict construction situation, equipment utilization rate, estimated duration and cost to achieve visualized and intelligent scheduling of virtual construction process in earthmoving operations. The simulation process is conducted on the CPNTools platform. The data required by the research were collected on-site in an actual case. The randomness of construction activities in earthmoving operations and main factors influencing construction are simulated. The sensitivity analysis for the model is carried out. The study will provide technical support and a management basis for equipment scheduling of earthmoving operations.     

Automated content analysis for construction safety: A natural language processing system to extract precursors and outcomes from unstructured injury reports

In the United States like in many other countries throughout the globe, construction workers are more likely to be injured on the job than workers in any other industry. This poor safety performance is responsible for huge human and financial losses and has motivated extensive research. Unfortunately, safety improvement in construction has decelerated in the last decade and traditional safety programs have reached saturation. Yet major construction companies and federal agencies possess a wealth of empirical knowledge in the form of huge databases of digital construction injury reports. This knowledge could be used to better understand, predict, and prevent the occurrence of construction accidents. Unfortunately, due to the lack of a clear methodology and the high costs of manual large-scale content analysis, these valuable data have yet to be extracted and leveraged. Recently, researchers have proposed a framework allowing meaningful empirical data to be extracted from accident reports. However, the resource limitations inherent to manual content analysis still remain. The present study tested the proposition that manual content analysis of injury reports can be eliminated using natural language processing (NLP). This paper describes (1) the overall strategy and methodology used in developing the system, and specifically how key challenges with decoding unstructured reports were overcome; (2) how the system was built through an iterative process of coding and testing against manual content analysis results from a team of seven independent analysts; and (3) the implications and potential uses of the data extracted. The results indicate that the NLP system is capable of quickly and automatically scanning unstructured injury reports for 101 attributes and outcomes with over 95% accuracy. The main contribution of this research is to empower any organization to quickly obtain a large and highly reliable structured attribute and outcome data set from their databases of unstructured accident reports. Such structured data are a necessary prerequisite to the application of statistical modeling techniques, allowing the extraction of new safety knowledge and finally the amelioration of safety management.     

Simulation-based construction productivity forecast using Neural-Network-Driven Fuzzy Reasoning

Fuzzy models and Artificial Neural Network (ANN) systems are two well-known areas of soft-computing that have significantly helped researchers with decision-making under uncertainties. Uncertainty, an ever-present factor in construction projects, has made such intelligent systems very attractive to the construction industry. Estimating the productivity of construction operations, as a basic element of project planning and control, has become a remarkable target for forecasting models. A glimpse into this interdisciplinary field of research exposes the need for a system, that (1) models the effect of qualitative and quantitative variables on construction productivity with an improved accuracy of estimation and (2) has the ability to deal with both crisp and fuzzy input variables in one single framework. Neural-Network-Driven Fuzzy Reasoning (NNDFR), as one of the hybrid intelligent structures, displays a great potential for modeling datasets among which clear clusters are recognizable. The weakness of NNDFR in auto-tuning the design of fuzzy membership functions along with this model's insufficient attention to the optimization of number of clusters has created an area for further research. In this paper, the parameters (fuzzifier and number of clusters) of the proposed system are optimized by using Genetic Algorithm (GA) to fine-tune the system for the highest possible level of accuracy that can be exploited for productivity estimation. The proposed model is also capable of dealing with a combination of crisp and fuzzy input variables by using a hybrid modeling approach based on the application of the alpha-cut technique. The developed model helps researchers and practitioners use historical data to forecast the productivity of construction operations with a level of accuracy greater than what could be offered by traditional techniques.     

提升和创新项目生产力理论

文章阐述了项目生产力理论的起源,在解析项目生产力概念、内涵和特征的基础上构建了基于项目生产力理论的建设项目管理基本框架体系;提出了提升和创新项目生产力理论的3个着力点。从健全和完善建设工程质量和安全生产保障体系、大力推进以工程总承包为主流模式的建设工程生产组织方式变革、持续推进建筑节能减排、加强企业知识管理和全员素质培养、积极推动和促进“四化”建设,以及加强政府与行业协会联动等6个方面,研究了提升和创新项目生产力理论的主要内容;明确了提升和创新项目生产力理论的目标。     

Development of web-based system for safety risk early warning in urban metro construction

At present, underground urban metro construction accidents in China are rising with the rapid growth of urbanization and infrastructure investment. Real-time safety and risk management during urban metro construction has become extremely important but is very difficult, time-consuming and unreliable due to the lack of information and experienced managers. This paper presents the development and application of a web-based system for safety risk early warning in urban metro construction. A hybrid data fusion model based on multisource information (monitoring measurements, calculated predictions, and visual inspections) is employed to imitate human experts to give safety risk assessment and early warnings automatically. In addition, it has significantly improved information collection, sharing and communication by establishing a collaborative platform instead of traditional manual management. The system has been successfully applied to several metro construction projects and has perfected the safety management performance in the cities of Wuhan, Shenyang, Zhengzhou and Kunming in China.     

Construction equipment productivity estimation using artificial neural network model

Estimating equipment production rates is both an art and a science. An accurate prediction of the productivity of earthmoving equipment is critical for accurate construction planning and project control. Owing to the unique work requirements and changeable environment of each construction project, the influences of job and management factors on operation productivity are often very complex. Hence, construction productivity estimation, even for an operation with well‐known equipment and work methods, can be challenging. This study develops and compares two methods for estimating construction productivity of dozer operations (the transformed regression analysis, and a non‐linear analysis using neural network model). It is the hypothesis of this study that the proposed neural networks model may improve productivity estimation models because of the neural network's inherent ability to capture non‐linearity and the complexity of the changeable environment of each construction project. The comparison of results suggests that the non‐linear artificial neural network (ANN) has the potential to improve the equipment productivity estimation model.     

某基坑工程施工对邻近建筑物安全影响评估分析

本文结合工程案例,运用理论分析和数值模拟计算方法,进行了工程安全评估和论证。重点针对现场最不利工况,依据实测数据对比,提供提示和预警。通过计算和论证证明了基坑工程对周围环境的不利影响。该有限元分析方法能对其受影响的邻近建筑物进行安全保护措施参考,并可以确保基坑周围环境安全的施工控制要求,可预测、保证工程和环境安全。     

A framework for evaluating the safety performance of construction contractors

Improvements to contracting organisations’ safety standards could inevitably be helped by continuous monitoring and review of their safety performance. To achieve this, an objective Safety Performance Evaluation (SPE) framework is a prerequisite. Although various methods of SPE have been proposed, a more comprehensive SPE framework which takes into account factors pertinent to an organisation and its project has yet to be realised. In this paper, the importance of SPE factors is examined through a questionnaire survey conducted in Hong Kong. The results of the questionnaire survey are used to develop a SPE framework suitable for use in the construction industry and protocols for evaluating the safety performance at the organisational and project levels. Through this analytical framework, SPE scores can be computed which would facilitate the benchmarking process and various initiatives to improve the safety performance of construction contractors.     

Socioeconomic impact assessment of highly dense-urban construction projects

Dense-urban construction is reported to affect the social and economic welfare of surrounding residents and local businesses in various ways. However, research studies and practical methodologies aimed at assessing to what extent the choice of a construction plan that reduces such effect are very limited. The objective of this paper is to present the development of an automated assessment methodology to fill this research gap. To this end, two formulations are presented; one based on multi-attributed utility functions and the other based on monetary compensations for disruptions caused by construction operations. Both formulations assess the impacts of construction plans on (1) increased travel distance; (2) residents' relocation; (3) business loss; (4) business closure; and (5) noise inconvenience.The proposed automated methodology is implemented in five sequential phases and utilizes Geographical Information Systems (GIS) and Visual Basic Application (VBA). Using the proposed implementation, the two alternative formulations are applied to an infrastructure upgrading project in Cairo, Egypt that had five possible construction scenarios. While the two formulations resulted in the same preference order for the five scenarios, they exhibited different performance in terms of their (1) assessment relative values; (2) required input data and robustness; (3) ease of results interpretation; and (4) comprehensiveness and scalability.The developed framework shows promising results in terms of identifying and sorting the major root causes of the socioeconomic disruptions caused by dense urban construction. Results show that using the proposed methodology informs decision-making and planning at the early stages of a project, which in turn helps to reduce cost overruns and schedule delays.     

浅谈房屋建筑施工企业建筑业总产值的统计核算

建筑业总产值是指以货币表现的建筑业企业在一定时期内生产的建筑业产品和服务的总和,正确的统计方法要克服统计中重报、漏报、混淆概念等造成的总产值统计失真,通过进一步的分析,提出应当从认真读解报表制度、加强对原始数据的归集、整理、及时掌握工程进展、理清工程进度款与建筑业总产值的关系等方面入手,提高建筑业总产值统计的水平。     

Hierarchical evaluation of on-site environmental performance to enhance a green construction operation

The construction process generates multiple types of nuisances, such as noise, vibration, dust, etc., and it consumes natural resources. Therefore, efforts to improve environmental performance should be aimed not only at operating and maintaining built facilities but also at constructing them. The objective of this study is to develop an evaluation framework for measuring the environmental performance of a construction operation. The framework provides a dynamic and interactive process, which feeds back into continual monitoring and improvements in site operation. The study tried to minimise the adverse environmental impacts on construction sites, thereby enhancing green construction operations. Key performance indicators were identified in the evaluation model through the combined effort of an expert panel. A computerised prototype was developed to assist in applying the evaluation process. The environmental performance of a residential project was then appraised as a case study to demonstrate the applicability of the evaluation model. The proposed model can effectively quantify the environmental performance of the construction process and can be used as an on-site environmental management tool for green construction operations.     

Real-time analysis and prediction of shield cutterhead torque using optimized gated recurrent unit neural network

An accurate prediction of earth pressure balance (EPB) shield moving performance is important to ensure the safety tunnel excavation. A hybrid model is developed based on the particle swarm optimization (PSO) and gated recurrent unit (GRU) neural network. PSO is utilized to assign the optimal hyperparameters of GRU neural network. There are mainly four steps: data collection and processing, hybrid model establishment, model performance evaluation and correlation analysis. The developed model provides an alternative to tackle with time-series data of tunnel project. Apart from that, a novel framework about model application is performed to provide guidelines in practice. A tunnel project is utilized to evaluate the performance of proposed hybrid model. Results indicate that geological and construction variables are significant to the model performance. Correlation analysis shows that construction variables (main thrust and foam liquid volume) display the highest correlation with the cutterhead torque (CHT). This work provides a feasible and applicable alternative way to estimate the performance of shield tunneling.     

Ladars for construction assessment and update

Work at the National Institute of Standards and Technology (NIST) on laser radar imaging of a construction site is described. The objective of the NIST research is to make measurements required in a construction project quicker and cheaper than current practice and to do so without impacting existing operations. This can be done by developing techniques for real-time assessment and documentation in terms of 3-D as-built models of the construction process. Once developed, this technology may be used for other applications such as condition assessment of a hazardous environment where human intervention would be impossible.     

Integrating 3D laser scanning and photogrammetry for progress measurement of construction work

Progress reporting is an essential management function for successful delivery of construction projects. It relies on tangible data collected from construction job sites, which is then used to compare actual work performed to that planned. One method used to collect actual work data is 3D laser scanning, where the construction site is scanned at different times to generate data, which can then be used to estimate the quantities of work performed within the time interval considered between two successive scans. Photogrammetry is another method for data collection where the geometrical properties of an object on site are generated from its photo image. This paper presents a method, which integrates 3D scanning and photogrammetry in an effort to enhance the speed and accuracy of data collection from construction sites to support progress measurement and project control. The application of the proposed method is demonstrated using a building presently under construction.