Worksite Object Characterization for Automatically Updating Building Information Models

Abstract

Automated data capture systems could significantly improve the efficiency and productivity of the architecture, engineering, construction and facility management (AEC/FM) industry. However, automatically collecting spatiotemporal information in an unstructured environment such as a construction site or a work place remains a time consuming and challenging task. This paper presents a new approach to automated data capture and processing, referred to as object characterization. In object characterization, the goal is to identify common objects in a scene and extract rich semantic information about those objects. A novel 2D-3D object detection algorithm is designed for detection and characterization of common worksite objects. The proposed system has applications in automated surveying and data collection, especially in applications which leverage unmanned aerial vehicles or mobile robots. To demonstrate this utility, the proposed system is deployed on a mobile robot and used to detect newly placed objects in a worksite environment.