Search

This paper presents new metrics and methods for evaluating the quality of reality capture plans—commonly used to operate camera‐mounted unmanned aerial vehicles (UAVs) or ground rovers—for construction progress monitoring and inspection of as‐is conditions. Using 4D building information model (BIM) or 3D reality model as a priori, these metrics provide feedback on the quality of a plan (within a few minutes), accounting for resolution, visibility, accuracy, completeness of the capture, and satisfying battery capacity and line‐of‐sight requirements. A cloud‐based system is introduced to create and optimize UAV/rover missions in the context of prior model. Results from real‐world construction data sets demonstrate that the proposed metrics offer actionable insights into the accuracy and completeness of reality capture plans. Additionally, a capture plan—with a combination of canonical and noncanonical camera views—that satisfies the introduced metrics is statistically correlated with the quality of reconstructed reality. These metrics can improve computer‐vision progress monitoring and inspection methods that rely on the construction site's appearance and geometry. [ABSTRACT FROM AUTHOR]

Current construction still suffers from significant schedule delays and budget overruns due to inefficient and retroactive project controls programs. This paper developed a visual and virtual project control system that proactively promotes team-based planning and real-time communication of progress and schedule risk. The system benefits from the growth of visual data on construction sites and the increasing maturity level of building information modeling (BIM), to map the current state of production in 3D and expose waste. By modeling production trends, reliability in the future state of production is forecasted to highlight potential delay issues in a location-driven scheme. A visual 3D interface supports collaborative decision-making to eliminate root causes of waste, enables pull flows between people and information, decentralizes work tracking, and facilitates in-process quality control and hand-overs among contractors. This system was implemented on two projects to validate the underlying algorithms. Results show that the system's functional aspects improve transparency, accountability, and traceability in project execution, and streamline communications between the field and the office. Specifically, 30% PPC increase and four weeks project completion date advance have been observed. Limitations such as resistance to workflow changes could be further improved in the future through early system introduction. [ABSTRACT FROM AUTHOR]

Falls, struck-bys, and caught-in/betweens are among the most common types of fatal accidents on construction sites. Despite their significance, the majority of today's accident prevention programs react passively to situations in which workers or equipment enter predefined unsafe zones. To support systems that proactively prevent these accidents, this paper presents a path prediction model for workers and equipment. The model leverages the extracted video frames to predict upcoming worker and equipment motion trajectories on construction sites. Specifically, the model takes two-dimensional (2D) tracks of workers and equipment from visual data—based on computer vision methods for detection and tracking—and uses a long short-term memory (LSTM) encoder-decoder followed by a mixture density network (MDN) to predict their locations. A multihead prediction module is introduced to predict locations at different future times. The method is validated on an existing dataset, TrajNet, and a new dataset of 105 high-definition videos recorded over 30 days from a real-world construction site. On the TrajNet dataset, the proposed model significantly outperforms Social LSTM. On the new dataset, the presented model outperforms conventional time-series models and achieves average localization errors of 7.30, 12.71, and 24.22 pixels for 10, 20, and 40 future steps, respectively. The benefits and limitations of the method to worker and equipment path prediction are discussed. [ABSTRACT FROM AUTHOR]

Recent research efforts to improve information management on construction sites have focused on devising mobile augmented reality methods to provide on-demand access to project information and facilitate field reporting. To track position and orientation of the users, prior research focused on radio frequency based location tracking methods, fiduciary markers, or parallel visual tracking and mapping techniques. These methods have potential in providing fast information access to field personnel, yet their application heavily depends on preinstalled infrastructure, may suffer from accumulated drift errors, and in the case of visual methods do not typically scale well. Furthermore, these methods do not provide content authoring capability in three dimensions, which is necessary for reciprocal application of augmented reality for field reporting and asynchronous personnel-to-personnel communications. To overcome these limitations, this paper presents a scalable markerless and infrastructure-independent mobile augmented reality system for commodity smartphones and tablets, with client-server architecture and cloud computing basis, to facilitate both accessing to project information and conducting field reporting in three dimensions. The method relies on structure-from-motion point clouds generated from site images and/or videos to enable image-based localization and single-image based content authoring in three dimensions. By using mobile client devices with the proposed method, onsite personnel can associate field reports with two-dimensional (2D) patches from mobile images and store that information directly in the underlying three-dimensional (3D) point cloud model. In addition, the client-server architecture of the proposed system allows an onsite access to most updated project information and field reports as they are being documented on the server. The presented architecture also handles multiple onsite information retrieval and field reporting requests simultaneously. The overall system is validated on several indoor/outdoor work areas of three real-world construction projects with varying degrees of occlusions and lighting conditions. The experimental results show the potential of the proposed method in prompt field reporting in three dimensions, minimizing the time field personnel spent on accessing project information, and communicating with others to resolve an issue/conflict on the jobsite within 1-3 min. [ABSTRACT FROM AUTHOR]

Effective progress monitoring is crucial for successful construction project delivery. Visual data, comprising images and videos of construction operations, has emerged as a valuable source for gaining comprehensive insights into project status. While various vision-based methods have been developed for automated progress monitoring at the element level (e.g., columns, beams, floors, walls), challenges persist in achieving accurate schedule activity-level (e.g., formwork, reinforcement, concrete placement) progress tracking. Existing methods often struggle to report progress status beyond binary form (built/not built). To address these limitations, this research proposes a novel framework for precisely measuring the percent completion of activities associated with under-construction building elements. The framework is implemented through an Activity-level progress monitoring system (ALPMS). ALPMS takes the input of construction site images and a four-dimensional building information model (BIM) and outputs the activity-wise completion percentage required for updating project schedules. It creates as-built point clouds from images, compares them with the as-planned BIM, generates orthographic views of under-construction elements through projective transformation or neural radiance fields (NeRF), applies deep learning-based semantic segmentation for progress reasoning, and estimates completion percentages. Finally, the activity-level rich semantic information is transferred to the as-built point cloud and BIM for three-dimensional visualization of the progress status. When the framework was applied to two building construction projects, on average, the ALPMS could report the activity-wise completion percentages with <6% mean absolute error. Future research shall focus on automating the mapping of project schedule activities and activity-level progress details for timely schedule updates and prediction of project completion dates. • Activity percent complete measurement framework for outdoor and indoor construction monitoring. • Percentage completion estimation of schedule activities through semantic segmentation of orthographic view images. • Methodology for orthographic view synthesis through projective transformation and neural radiance field (NeRF). • 3D progress visualization through semantic segmentation of the as-built point cloud and color-coded BIM. • Semantic image segmentation dataset for activity level progress monitoring. [ABSTRACT FROM AUTHOR]

Today, computer vision object detection methods are used for safety inspections from site videos and images. These methods detect bounding boxes and use hand-made rules to enable personal protective equipment compliance checks. This paper presents a new method to improve the breadth and depth of vision-based safety compliance checking by explicitly classifying worker-tool interactions. A detection model is trained on a newly constructed image dataset for construction sites, achieving 52.9% average mean precision for 10 object categories and 89.4% average precision for detecting workers. Using this detector and new dataset, the proposed human-object interaction recognition model achieved 79.78% precision and 77.64% recall for hard hat checking; 79.11% precision and 75.29% recall for safety coloring checking. The new model also verifies hand protection for workers when tools are being used with 66.2% precision and 64.86% recall. The proposed model is superior in these checking tasks when compared with post-processing detected objects with hand-made rules, or applying detected objects only. • A learned Human-Object Interaction (HOI) recognition model is proposed for personal protective equipment compliance checking. • Final HOI recognition model is validated by hard hat, safety coloring, and hand protection checking. • Final HOI recognition model achieves higher precision and recall than using hand-made rules or detected objects only. [ABSTRACT FROM AUTHOR]