Comparative assessment of techniques for initial pose estimation using monocular vision

• A comparative assessment of initial pose estimation techniques is performed.
• We focus on four state-of-the-art perspective-n-point solvers.
• A framework of assessment with test cases representing space imagery is presented.
• Accuracy of the PnP solvers is sub-optimal in the presence of feature outliers.
• Each solver׳s strength lay in separate regimes and calls for a synergy of strategies.

This work addresses the comparative assessment of initial pose estimation techniques for monocular navigation to enable formation-flying and on-orbit servicing missions. Monocular navigation relies on finding an initial pose, i.e., a coarse estimate of the attitude and position of the space resident object with respect to the camera, based on a minimum number of features from a three dimensional computer model and a single two dimensional image. The initial pose is estimated without the use of fiducial markers, without any range measurements or any apriori relative motion information. Prior work has been done to compare different pose estimators for terrestrial applications, but there is a lack of functional and performance characterization of such algorithms in the context of missions involving rendezvous operations in the space environment. Use of state-of-the-art pose estimation algorithms designed for terrestrial applications is challenging in space due to factors such as limited on-board processing power, low carrier to noise ratio, and high image contrasts. This paper focuses on performance characterization of three initial pose estimation algorithms in the context of such missions and suggests improvements.