Abstract
To estimate the pose of satellites in space, the docking ring component has strong rigid body characteristics and can provide a fixed circular feature, which is an important object. However, due to the need for additional constraints to estimate a single spatial circle pose on the docking ring, practical applications are greatly limited. In response to the above problems, this paper proposes a pose solution method based on a single spatial circle. First, the spatial circle is discretized into a set of 3D asymmetric specific sparse points, eliminating the strict central symmetry of the circle. Then, a two-stage pose estimation network, Hvnet, based on Hough voting is proposed to locate the 2D sparse points on the image. Finally, the position and orientation of the spatial circle are obtained by the Perspective-n-Point (PnP) algorithm. The effectiveness of the proposed method was verified through experiments, and the method was found to achieve good solution accuracy under a complex lighting environment.
Highlights
As a result of the rapid development of space technology, an increasing number of spacecraft have been launched into space, occupying limited orbital resources
This paper proposes a specific discrete point selection method, which discretizes the spatial circle into a set of 3D specific sparse points, eliminates the strict central symmetry of the circle, and handles the high fusion of the foreground and the background in the image under complex lighting conditions caused by many interference features
Aiming at docking rings that are common in space satellite pose estimation tasks, a pose estimation method based on a single spatial circle is proposed
Summary
As a result of the rapid development of space technology, an increasing number of spacecraft have been launched into space, occupying limited orbital resources. Miao and Zhu et al calculated two solutions of the spatial circle pose based on the projection of the spatial circle on the docking ring on the image. Liu and Xie et al proposed a method for estimating circular feature poses based on binocular stereo vision This method did not require other constraints, it had high requirements for the matching results of image features in two different cameras. The spatial circle position and orientation are derived and modeled to recover the pose of the target object from a single RGB image. OC is the camera center point, Q is the spatial circle with radius R on the target of the docking ring, OD is its center, and q is the Q projection on the image coordinate frame. The spatial circle is first discretized into a set of asymmetric specific sparse points
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
