Journal of Computing in Civil Engineering

Monitoring the productivity of construction equipment would help to improve construction productivity, control cost, and discover potential project issues. However, manual equipment productivity monitoring is labor-intensive and inefficient. In recent years, a large number of studies have been conducted to develop automatic methods for equipment productivity monitoring. Numerous technologies were used to estimate equipment operation time, calculate soil quantity, and analyze influence factors, among others. However, there is no recent review paper focusing on equipment productivity monitoring. This paper provides a comprehensive review of automated methods for earthmoving equipment productivity monitoring. A total of 119 related papers are reviewed and 88 papers are categorized based on the method of collecting productivity-related data. In addition, the benefits and limitations of different methods are compared in detail. Finally, a roadmap is proposed to illustrate a path forward for automatic equipment monitoring and productivity analysis. The review is expected to provide future directions that will support the development of full automation in productivity monitoring of construction equipment.

Developing deep neural network (DNN) models for computer vision applications for construction is challenging due to the shortage of training data. To address this issue, we proposed a novel data augmentation method that integrates a conditional generative adversarial networks (GANs) framework with a target classifier. The integrated architecture enables adversarial attack and defense during end-to-end training, thereby making it possible to generate effective images for the target classifier’s training. We trained and tested two image classification DNNs with and without data augmentation, where we confirmed the effectiveness of the proposed method: with the data augmentation, the classification accuracy improved by 4.2 percentage points, from 71.24% to 75.46%, with qualitatively improved feature extraction more focused on the target object. Given that the application areas of our method are open-ended, the result is noteworthy. The proposed method can help construction researchers offset the data insufficiency, which will contribute to having more accurate and scalable DNN-powered vision models in construction applications.

Fully automated building code compliance checking (ACC) requires accurate information extraction from both building information models (BIMs) and building code chapters, and equally (if not more) importantly, a precise matching between the two. Although research on information extraction has been extensively conducted for ACC, there is a lack of investigation of automated and practical information mapping between the extracted information, from BIMs to building code requirements. To address this gap, the authors proposed a new method for BIM model validation to validate an input Industry Foundation Classes (IFC) model with regard to building code concepts. This validation method was supported by creating invariant signatures of architecture, engineering, and construction (AEC) objects that capture the geometric nature of the objects. Target concepts from building codes are classified into four categories: (1) explicit concepts, (2) inferable concepts, (3) user-assisted concepts, and (4) system defaults. Identification algorithms are developed for all four categories based on the invariant signatures of AEC objects. An experiment was conducted to test the proposed method on validating five real commercial project models with selected concepts from a current building code. Compared with a manually developed gold standard, 99.8% precision and 99.6% recall were achieved. This demonstrates that the proposed method is promising in supporting information matching between BIMs and building code concepts for ACC purpose.

Road condition and quality are critical road maintenance and risk reduction factors. Most existing road monitoring systems include regular on-site surveys and maintenance. However, major roads in urban areas are generally complicated and have heavy traffic during the daytime, so such field investigation can be significantly limited. Moreover, any road work at nighttime can be risky and dangerous and incur excessive expenses. Based on a review of existing systems for monitoring road conditions, this study focuses on overcoming two unsolved challenges: the capacity of the monitoring range and the avoidance techniques to ensure traffic is not hindered. To solve these challenges, these paper proposes an integrated road monitoring system called Car-free Street Mapping (CfSM) using unmanned aerial vehicles (UAV), aerial mapping cameras, and deep learning (DL) algorithms. The use of the aerial mapping camera mounted on the UAV is to widen the monitoring viewing range, and general-purpose drones are used in this study rather than expensive special equipment. Since the drone-taken images include many passing vehicles that conceal the road surface from the camera vision, the DL model was applied to detect the vehicles and their shadows and then remove them from the images. To train the DL model, two image datasets were used: publicly available cars overhead with context (COWC) images and orthoimages additionally taken for the project to further improve the accuracy. The two datasets consist of 298,623 labeled objects on 9,331 images in total. The tests resulted in a mean average precision (mAP) of 89.57% for trucks, 95.77% for passenger vehicles, and 76.51% for buses. Finally, the object-removed images were composited into one whole car-free image. The CfSM was applied to two areas in Yeouido and Sangam-dong, Seoul, Korea. The car-free images in both regions show a spatial resolution of 10 mm and can be used for various purposes such as road maintenance and management and autonomous vehicle roadmaps.

The construction industry is information-intensive, and building information modeling (BIM) has been proposed as an information source for supporting decision making by construction project team members in the architecture, engineering, construction, and operation (AECO) industry. Because building information models contain more building data, further use of the aggregated building information to support construction and operation activities has become important. In Industry 4.0, similar-to-real-life virtual assistants, e.g., Apple’s Siri and Google Assistant, are becoming ever more popular. This research developed a query-answering (QA) system for BIM information extraction (IE) by using natural language processing (NLP) methods to build a virtual assistant for construction project team members. The architecture of the developed QA system for BIM IE consists of three major modules: natural language understanding, IE, and natural language generation. A Python-based prototype application was developed based on the architecture of the QA system for BIM IE to evaluate functionalities of the developed QA system using several BIM/industry foundation classes (IFC) models. Seven building information models and 127 test queries were utilized to evaluate the accuracy of the developed QA system for BIM IE. The experimental results indicated that the developed QA system for BIM IE achieved an 81.9 accuracy score. The developed NLP-based QA system for BIM is valid to provide relatively accurate answers based on natural language queries. The contributions of this research facilitate the development of virtual assistants in the AECO industry, and the architecture of the developed QA system can be extended to queries in other areas.

Point cloud data (PCD) have attracted attention in many disciplines, including civil engineering. However, big PCD have posed great challenges for conventional approaches using a single computer. Although many published studies have demonstrated distributed computing’s potential for large-scale data-intensive applications, this technology has not been applied widely in processing of big PCD due to a lack of methods for data management, visualization, and analysis. To strengthen the foundation of distributed computation in civil engineering, this study offers a solution to one of the obstacles presented in the previous studies, which was the visualization of big PCD. The practical result of this study is the introduction of B-EagleV, a cost-effective Hadoop-based solution for the visualization of big PCD in civil engineering with almost complete components of scalable storage, high-performance rendering, and interactive visualization. Through experiment results and demonstration, B-EagleV showed great promise for data management, progress monitoring, and survey conduction in the construction sector.

Despite the increased interest in automation and the expanded deployment of robots in the construction industry, using robots in a dynamic and unstructured working environment has caused safety concerns in operating construction robots. Improving human–robot interaction (HRI) can increase the adoption of robots on construction sites; for example, increasing trust in robots could help construction workers to accept new technologies. Confidence in operation (or self-efficacy), mental workload, and situational awareness are among other key factors that help such workers to remote operate robots safely. However, construction workers have very few opportunities to practice with robots to build trust, self-efficacy, and situational awareness, as well as resistance against increasing mental workload, before interacting with them on job sites. Virtual reality (VR) could afford a safer place to practice with the robot; thus, we tested if VR-based training could improve these four outcomes during the remote operation of construction robots. We measured trust in the robot, self-efficacy, mental workload, and situational awareness in an experimental study where construction workers remote-operated a demolition robot. Fifty workers were randomly assigned to either VR-based training or traditional in-person training led by an expert trainer. Results show that VR-based training significantly increased trust in the robot, self-efficacy, and situational awareness, compared to traditional in-person training. Our findings suggest that VR-based training can allow for significant increases in beneficial cognitive factors over more traditional methods and has substantial implications for improving HRI using VR, especially in the construction industry.

Modern roundabouts are popular intersection control designs in many countries and are increasingly popular in the United States. Roundabouts facilitate reduced vehicle delays with naturally optimized conflict resolution for turning traffic, which also reduces the risks of severe crashes. However, evaluating the roundabout capacity for multilane configurations can be challenging due to the randomized decision making to accept or reject a headway to enter the roundabout. In addition, considering the follow-up headway between two vehicles entering the roundabout from the same lane is critical to evaluate accurate roundabout capacity. Several manual techniques are popularly used to evaluate roundabout capacity using computer vision powered by multiple video cameras and observers. However, manual processing of videos with a narrow field of view (FoV) requires significant computational effort. Traditional techniques used in manual processing involve a complex two-step time stamp recording and interpreting the parameters required for capacity evaluation. In this case study, a one-step gap-based methodology is proposed to accurately measure the roundabout capacity parameters. In addition, a computer vision algorithm is developed to integrate with deep learning to detect and track vehicular traffic in a multilane roundabout. A software-defined technique is developed to process videos with wider FoV powered by unmanned aerial vehicles (UAVs) and evaluate roundabout capacity parameters, such as accept, reject, and follow-up headways. Furthermore, the mean critical headway is calculated using a maximum likelihood estimation method. The evaluated roundabout capacity parameters are compared with manual technique results, and the corresponding values are published in the current standards.