An official website of the United States government
The integration of structure from motion (SFM) and unmanned aerial vehicle (UAV) technologies has allowed for the generation of very high-resolution three-dimensional (3D) point cloud data (up to millimeters) to detect and monitor surface changes. However, a bottleneck still exists in accurately and rapidly registering the point clouds at different times. The existing point cloud registration algorithms, such as the Iterative Closest Point (ICP) and the Fast Global Registration (FGR) method, were mainly developed for the registration of small and static point cloud data, and do not perform well when dealing with large point cloud data with potential changes over time. In particular, registering large data is computationally expensive, and the inclusion of changing objects reduces the accuracy of the registration. In this paper, we develop an AI-based workflow to ensure high-quality registration of the point clouds generated using UAV-collected photos. We first detect stable objects from the ortho-photo produced by the same set of UAV-collected photos to segment the point clouds of these objects. Registration is then performed only on the partial data with these stable objects. The application of this workflow using the UAV data collected from three erosion plots at the East Tennessee Research and Education Center indicates that our workflow outperforms the existing algorithms in both computational speed and accuracy. This AI-based workflow significantly improves computational efficiency and avoids the impact of changing objects for the registration of large point cloud data.
more »
« less
Processed data and the final point clouds for the historic masonry structures in Mayfield, Kentucky:RAPID: Mayfield, KY Post-Tornado Building Reconnaissance
The process of generating a comprehensive point cloud from the raw data collected at Mayfield involved three distinct steps. Firstly, Pix4D was utilized to process and analyze the data. This was followed by the utilization of Register 360 to further refine and align the collected data. Finally, Cyclone was used to complete the point cloud generation process, ensuring that the resulting point cloud was as detailed and accurate as possible. The combination of these three steps allowed for the creation of a comprehensive point cloud that could be utilized for a variety of applications, ranging from surveying and mapping to construction and design.Damage reconnaissance of historical buildings affected by tornado loading
more »
« less
- Award ID(s):
- 2222849
- PAR ID:
- 10484791
- Publisher / Repository:
- Designsafe-CI
- Date Published:
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Two project-based learning approaches were implemented in a 100-level information literacy class in the Mechanical Engineering program at a mid-Atlantic university. One approach, the treatment group, partnered engineering students with education students to develop and deliver engineering lessons that guide elementary school students through the engineering design process. In the second approach, the comparison group, engineering students were partnered with their engineering classmates to work on an engineering problem using the engineering design process. The two projects were designed to have similar durations and course point values. For both projects, teams were formed, and peer evaluations were completed, using the Comprehensive Assessment of Team Member Effectiveness (CATME) survey. This study examined how the two project-based learning approaches affected students' teamwork effectiveness. Data was collected from undergraduate engineering students assigned to groups in the comparison and treatment conditions from Fall 2019 to Fall 2022. Data was collected electronically through the CATME teammate evaluations and project reflections (treatment, n = 137; comparison, n = 112). CATME uses a series of questions assessed on a 5-point Likert scale. Quantitative analysis using Analysis of Variance (ANOVA) and Covariance (ANCOVA) showed that engineering students in the treatment group expected more quality, were more satisfied, and had more task commitment than engineering students working within their discipline. However, no statistically significant differences were observed for teamwork effectiveness categories such as contribution to the team’s work, interaction with teammates, keeping the team on track, and having relevant knowledge, skills, and abilities. This result suggests that engineering students who worked in interdisciplinary teams with an authentic audience (i.e., children) perceived higher quality in their projects and had higher levels of commitment to the task than their peers in the comparison group. A thematic analysis of the written reflections was conducted to further explain the results obtained for the three categories: expecting quality, satisfaction, and task commitment. The thematic analysis revealed that the treatment, or interdisciplinary, groups exhibited considerably more positive reflections than their comparison peers regarding the project in all three categories, supporting results obtained quantitatively.more » « less
-
Debugging in production cloud systems (or live debugging) is a critical yet challenging task for on-call developers due to the financial impact of cloud service downtime and the inherent complexity of cloud systems. Unfortunately, how debugging is performed, and the unique challenges faced in the production cloud environment have not been investigated in detail. In this paper, we perform the first fine-grained, observational study of 93 real-world debugging experiences of production cloud failures in 15 widely adopted open-source distributed systems including distributed storage systems, databases, computing frameworks, message passing systems, and container orchestration systems. We examine each debugging experience with a fine-grained lens and categorize over 1700 debugging steps across all incidents. Our study provides a detailed picture of how developers perform various diagnosis activities including failure reproduction, anomaly analysis, program analysis, hypothesis formulation, information collection and online experiments. Highlights of our study include: (1) Analyses of the taxonomies and distributions of both live debugging activities and the underlying reasons for hypothesis forking, which confirm the presence of expert debugging strategies in production cloud systems, and offer insights to guide the training of novice developers and the development of tools that emulate expert behavior. (2) The identification of the primary challenge in anomaly detection (or, observability) for end-to-end debugging: the collection of system-specific data (17.1% of data collected). In comparison, nearly all (96%) invariants utilized to detect anomalies are already present in existing monitoring tools. (3) The identification of the importance of online interventions (i.e., in-production experiments that alter system execution) for live debugging - they are performed as frequently as information collection - with an investigation of different types of interventions and challenges. (4) An examination of novel debugging techniques developers utilized to overcome debugging challenges inherent to or amplified in cloud systems, which offer insights for the development of enhanced debugging tools.more » « less
-
Human experience involvement in existing operations of airborne Light Detection and Ranging (LIDAR) systems and off-line processing of collected LIDAR data make the acquisition process of airborne LIDAR point cloud less adaptable to environment conditions. This work develops a deep reinforcement learning-enabled framework for adaptive airborne LIDAR point cloud acquisition. Namely, the optimization of the airborne LIDAR operation is modeled as a Markov decision process (MDP). A set of LIDAR point cloud processing methods are proposed to derive the state space, action space, and reward function of the MDP model. A DRL algorithm, Deep Q-Network (DQN), is used to solve the MDP. The DRL model is trained in a flexible virtual environment by using simulator AirSim. Extensive simulation demonstrates the efficiency of the proposed framework.more » « less
-
Beauregard, Melissa S; Budge, Aaron S (Ed.)Climate change has been playing a crucial role in altering the precipitation patterns in the southern USA. States like Mississippi, Louisiana, and Alabama have seen increased numbers of extreme events like hurricanes, storms, and heavy rainfall. Therefore, rainfall-induced landslides have been very common in recent years. In Mississippi, due to the prevalence of highly expansive clay soil, slope failure has brought about a huge financial burden for the authority. In order to create resiliency in highway embankments, regular monitoring and early detection of landslide risks are important. The objective of the current study is to evaluate the landslide behavior of highway slopes under changed climatic conditions. One highway slope near Grenada, Mississippi, was selected for the study. The slope has a history of shallow landslide. Remote sensing technology like Light Detection and Ranging (LiDAR) has been utilized to compare the topographical surfaces in different seasons. Electrical Resistivity Imaging (ERI) was performed, and seasonal variations in subsurface moisture contents were obtained from the ERI profiles. In addition, rainwater data of the site location from available open sources were collected. Perched water zones have been detected through the ERI images when there were events of extreme rainfall. A drone mounted with an advanced LiDAR scanning system has been utilized to detect any trend of slope movement in the study site. The LiDAR scan gathered dense point cloud data to construct 3D surfaces and produce topographic maps of the slope. The integration of ERI and LiDAR provides a comprehensive understanding of the climate resilience of highway slopes in the face of climate change.more » « less
