On-Orbit Image Processing for Efficient Resident Space Object (RSO) Data Collection

TSC is proposing the development and in-space testing of an image processing pipeline for use on Space Domain Awareness (SDA) satellites with minimal edge computing capabilities. The onboard pipeline will utilize state-of-the-art Computer Vision (CV) techniques to analyze imagery containing potential RSOs and isolate only the relevant sections for compression, storage, and downlink. TSC's CV pipeline will be optimized for short processing time and low power usage and use on existing flight hardware. TSC plans to demonstrate this pipeline in flight on the upcoming DROID.002 SDA spacecraft (launch date Oct 2023).  The proposed image processing pipeline will result in a significant reduction in the volume of data that needs to be handled by an SDA spacecraft following an imaging operation, thus reducing the power, data storage, and datalink resources required to deliver large quantities of high-quality RSO imagery to Department of the Air Force (DAF) and commercial customers.