Visual Tracking of Synthetic Space Platforms in Low Orbit Using International Space Station Video Stream and Rendered Earth Model

This paper presents a framework for simulating the visual tracking of low orbit space platforms such as satellites to be captured by a space manipulator system intended to conduct assembly, maintenance, or deorbiting operations. The video stream from the International Space Station, publicly available, is used as background for an animated overlay of the target platform moving within the field of view of the camera. A real-synthetic video is generated in Blender in different daytime observation conditions, allowing also the introduction of light sources for simulating the sun or its reflection of Earth's surface. Additionally, completely synthetic videos are created using a rendered model of the Earth, which allows for a variety of relative orientations for the camera. In order to illustrate the application of the developed framework with a particular visual tracking method, the Continuously Adaptive Mean-Shift (CAMShift) algorithm is evaluated considering a satellite platform as the target to be tracked with different approaching trajectories, illumination conditions, and background. The initial detection phase in dark scenes is enhanced introducing a Fast Line Detector (FLD) stage in a modified implementation, exploiting the linear segments typically found on satellites and solar panel arrays. The performance of the algorithm is evaluated in different conditions using the generated videos.