AstroPose: Astronaut pose estimation using a monocular camera during extravehicular activities

Abstract

With the completion of the Chinese space station, an increasing number of extravehicular activities will be executed by astronauts, which is regarded as one of the most dangerous activities in human space exploration. To guarantee the safety of astronauts and the successful accomplishment of missions, it is vital to determine the pose of astronauts during extravehicular activities. This article presents a monocular vision-based pose estimation method of astronauts during extravehicular activities, making full use of the available observation resources. First, the camera is calibrated using objects of known structures, such as the spacesuit backpack or the circular handrail outside the space station. Subsequently, the pose estimation is performed utilizing the feature points on the spacesuit. The proposed methods are validated both on synthetic and semi-physical simulation experiments, demonstrating the high precision of the camera calibration and pose estimation. To further evaluate the performance of the methods in real-world scenarios, we utilize image sequences of Shenzhou-13 astronauts during extravehicular activities. The experiments validate that camera calibration and pose estimation can be accomplished solely with the existing observation resources, without requiring additional complicated equipment. The motion parameters of astronauts lay the technological foundation for subsequent applications such as mechanical analysis, task planning, and ground training of astronauts.