A performance assessment of calibrated camera networks for construction site monitoring

  • Authors:

  • Itai Katz;Nicholas Scott;Kamel Saidi

  • Affiliations:

  • National Institute of Standards and Technology, Gaithersburg, MD;National Institute of Standards and Technology, Gaithersburg, MD;National Institute of Standards and Technology, Gaithersburg, MD

  • Venue:
  • PerMIS '08 Proceedings of the 8th Workshop on Performance Metrics for Intelligent Systems
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

Monitoring the status of construction activity is a key factor in maximizing efficiency and reducing cost on capital construction sites. In contrast to human inspection, an automated technology would provide more frequent updates. However, real-time construction site monitoring remains an elusive goal because of many factors including the environment's large size and dynamic behavior. Calibrated camera networks have recently been developed to enable smart environments, where the location of people and objects in the scene are updated in real-time. Despite a growing interest in this technology, a detailed performance analysis has not been conducted. In this paper, empirical results on the calibration and static 3D localization error are presented for a calibrated camera network prototype using four cameras. Using a total station to provide ground truth, the cameras are calibrated and points in the workspace are reconstructed in 3D by combining observations from each image plane. Results show that performance is well suited for localizing objects typically found on a construction site (although scaling errors have not yet been characterized).