Activity-Based Data Fusion for Automated Progress Tracking of Construction Projects

Abstract

In recent years, many researchers have investigated automated progress tracking for construction projects. These efforts range from 2D photo feature extraction to 3D laser scanners and Radio Frequency Identification (RFID) tags. A multi-sensor data fusion model that would utilize multiple sources of information would provide a better alternative than a single-source model for tracking project progress. However, the existing fusion models are based on data fusion at the sensor and object levels, and therefore, are incapable of capturing critical information regarding non-structural trades and activities on a construction site, such as welding, inspection and installation activities. This paper presents an activity-based data fusion model, which incorporates an Ultra Wide Band (UWB) positioning system to track activities in a construction project. A field experimentation study on an industrial-type building construction project was conducted to validate the model presented in this research. The scope of the experimental program was limited to ductwork, HVAC, and piping activities on the project, but the model, experiments, and results are scalable to a complete construction project. A comparison of concrete, steel, and piping projects showed that for piping projects, where the asbuilt environment may be substantially different than as-designed models, the activity-based progress estimation model of this paper can be fused with existing object-based models to provide a more accurate and reliable progress estimate.