세미나

Degradation in various engineering systems is inevitable, and numerous automated technologies have been proposed to enable predictive maintenance and prevent sudden failures. Despite recent advances, automation of these real-world tasks has been limited thus far. This is partly due to the variety of data and the fundamental challenges associated with each domain. Extensive human involvement is still required at this time to perform procedures such as sensor installation, site visits, data organization, filtering, and ranking before executing analytical techniques, consequently, discouraging engineers from the widespread adoption of automated systems. The widespread availability of image sensors and sensor platforms (e.g., AR devices, UAV, UGV), along with their ease of use for a broad range of users and the pervasive accessibility of the internet as infrastructure, has significantly expanded the opportunities for replacing such human involvements. This study focuses on the development of techniques in remote sensing, integrating computer vision, artificial intelligence, digital twins, and visual analytics. These include the development of human interaction algorithms leveraging AR devices, control technologies for camera systems, and the optimization of super-resolution 3D reconstruction techniques. The automated capabilities developed in this research are adaptable to many engineering applications where remote sensing and monitoring are required throughout the lifecycle of the systems.