Metrics and methods for evaluating model-driven reality capture plans

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.

Automated summary

This paper introduces new metrics and methods for evaluating the quality of reality capture plans, which provide feedback on resolution, visibility, accuracy, completeness, battery capacity, and line-of-sight requirements within a few minutes. Results from real-world construction data sets show that these metrics offer insights into the accuracy and completeness of reality capture plans, improving computer-vision progress monitoring and inspection methods relying on construction site appearance and geometry.