期刊
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING
卷 37, 期 1, 页码 55-72出版社
WILEY
DOI: 10.1111/mice.12693
关键词
-
类别
资金
- National Science Foundation (NSF) [1446765, 1544999]
- Directorate For Engineering
- Div Of Civil, Mechanical, & Manufact Inn [1446765] Funding Source: National Science Foundation
- Div Of Civil, Mechanical, & Manufact Inn
- Directorate For Engineering [1544999] Funding Source: National Science Foundation
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.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据