What is it about?
This work discusses the use of convolutional neural networks for surface surveillance and inspection of spacecraft or orbital structures in space. The focus is on non-destructive inspection, meaning that surfaces can be monitored and assessed without causing any damage to the object being examined. By applying computer vision and deep learning techniques to on-orbit inspection tasks, the study aims to improve the detection of surface defects, anomalies, or changes that may affect spacecraft safety and performance. Such methods can support autonomous or semi-autonomous monitoring in space missions, where manual inspection is difficult, costly, and risky.
Featured Image
Photo by NASA Hubble Space Telescope on Unsplash
Why is it important?
Reliable on-orbit inspection is essential for maintaining spacecraft health, extending mission life, and reducing operational risk. Deep learning-based inspection methods can help identify surface issues faster and more accurately than conventional manual approaches, while also supporting future autonomous servicing, maintenance, and debris-monitoring missions.
Perspectives
From our point of view, this research reflects the growing need to combine artificial intelligence with space technology in meaningful and practical ways. We see on-orbit inspection not only as a technical challenge, but also as an important step toward building more resilient and autonomous space systems. It is exciting to work on solutions that may help future missions become safer, smarter, and less dependent on human intervention in hazardous environments.
Sanjay Lakshminarayana
AGH University of Krakow
Read the Original
This page is a summary of: On-Orbit, Non-destructive Surface Surveillance and Inspection with Convolution Neural Network, January 2022, Springer Science + Business Media,
DOI: 10.1007/978-3-031-15784-4_22.
You can read the full text:
Contributors
The following have contributed to this page
