Abstract
Recently, unsupervised domain adaptation in satellite pose estimation has gained increasing attention, aiming at alleviating the annotation cost for training deep models. To this end, we propose a self-training framework based on the domain-agnostic <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">geometrical constraints</i> . Specifically, we train a neural network to predict the 2D keypoints of a satellite and then use PnP to estimate the pose. The poses of target samples are regarded as latent variables to formulate the task as a minimization problem. Furthermore, we leverage fine-grained segmentation to tackle the information loss issue caused by abstracting the satellite as sparse keypoints. Finally, we iteratively solve the minimization problem in two steps: pseudo-label generation and network training. Experimental results show that our method adapts well to the target domain. Moreover, our method won the 1st place on the <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">sunlamp</monospace> task of the second international Satellite Pose Estimation Competition.
Published Version (
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