Date of Award

5-2024

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Aerospace, Physics, and Space Sciences

First Advisor

Madhur Tiwari

Second Advisor

Ratneshwar Jha

Third Advisor

Eric D. Swenson

Fourth Advisor

Seong Hyeon Hong

Abstract

In the era of burgeoning space exploration, the growing population of spacecraft heightens the inevitability of collisions. While traditional imagery remains effective for damage assessment, its lack of 3D representation of the object necessitates more advanced approaches. This research delves into cutting-edge methodologies, with a primary focus on leveraging machine learning and computer vision technologies to enhance the precision and efficiency of damage assessment by taking imagery of a space body and creating a 3D model. The study extensively investigates TransMVSNet, a neural network code employing classical computer vision techniques such as multi-vision stereo (MVS) and depth maps. This approach enables the construction of high-fidelity scene models based on motion dynamics [1]. Moving beyond traditional paradigms, the research explores Neural Radiance Fields (NeRF), an innovative solution that integrates positional encoding and ray integration for rapid and accurate scene reconstruction. NeRF demonstrates superior efficiency compared to conventional methods, significantly reducing reconstruction time while minimizing errors [2]. This paper aims to engage in a comprehensive analysis of advanced machine learning solutions in addressing the intricacies of space systems. By studying ways to implement machine learning and computer vision into satellite damage assessment.

Download

Share

COinS