PROJECT TITLE :

Satellite recognition and Pose Estimation using homeomorphic manifold analysis

ABSTRACT:

We have a tendency to propose a novel monocular vision-primarily based framework for each satellite recognition and pose estimation, using homeomorphic manifold analysis. We use a unified conceptual manifold to represent continuous cause variation of all satellites within the visual input area, learn nonlinear perform mapping from conceptual manifold representation to visual inputs, and decompose discrete category variation within the mapping coefficient space. Experimental results on a simulated image information set show the effectiveness and robustness of our approach.