Off-campus UNL users: To download campus access dissertations, please use the following link to log into our proxy server with your NU ID and password. When you are done browsing please remember to return to this page and log out.

Non-UNL users: Please talk to your librarian about requesting this dissertation through interlibrary loan.

Point Cloud Assessment of Distributed Civil Systems

Yijun Liao, University of Nebraska - Lincoln


As remote sensing technologies have advanced in recent decades, various techniques have been introduced to collect high quality, accurate, and dense data efficiently that can be used for distributed civil system assessments. Within this dissertation, two remote sensing platforms, including an unpiloted or unmanned aerial system (UAS) and ground-based light detection and ranging (lidar) scanner, were used to generate point clouds. Compared to traditional methods, point clouds can be collected efficiently and economically, particularly in areas with limited accessibility. Digital assessments via point clouds provide objective, reliable results in both qualitative and quantitative analyses by using both RGB (red, green, blue) color and geometric features. The focus of this research is to develop robust assessment methodologies for distributed civil systems using point clouds. Specifically, the assessments include post-hurricane infrastructure damage classification, roadway performance evaluation, and post-tornado agricultural damage identification. Within the proposed methodologies, acquired datasets and computational results were quantitatively compared and validated with respect to ground truth measurements for error assessments. Deep learning algorithms enable automatic localization and classification of target objects by mining for features within a computer-based approach. Moreover, the inclusion of depth information common to point clouds improved the model performance and accuracy significantly compared to traditional 2D datasets. Developed models were analyzed to understand event characteristics (e.g., wind speed at the ground), damage distribution and severity, and civil engineering shortcomings, which can assist in systematic decision-making processes.

Subject Area

Civil engineering

Recommended Citation

Liao, Yijun, "Point Cloud Assessment of Distributed Civil Systems" (2020). ETD collection for University of Nebraska-Lincoln. AAI28258522.