Onboard Image Processing for Small Satellites

In general, the computational ability of spacecraft and satellites has lagged behind terrestrial computers by several generations. Moore's Law turns the supercomputers of yesterday into the laptops of today, but space computing remains relatively underpowered due to the harsh radiation environment and low risk-tolerance of most space missions. Space missions are generally low risk because of the high cost of components and launch. However, launch costs are drastically decreasing and innovations such as CubeSats are changing the risk equation. By accepting more risk and utilizing commercial of the shelf (COTS) parts, it is possible to cheaply build and launch extremely capable computing platforms into space. High performance satellites will be required for advanced interplanetary exploration due to latency challenges. The long transmission times between planets means satellites or robotic explorers need onboard processing to perform tasks in real-time. This paper explores one possible application that could be hosted onboard the next generation of high performance satellites, performing object classification on satellite imagery. Automation of satellite imagery processing is currently performed by servers or workstations on Earth, but this paper will show that those algorithms can be moved onboard satellites by using COTS components. First traditional computer vision techniques such as edge detection and sliding windows are used to detect possible objects on the open ocean. Then a modern neural network architecture is used to classify the object as a ship or not. This application is implemented on a Nvidia Jetson TX2 and measurements of the application's power use confirm that it fits within the Size Weight and Power (SWAP) requirements of SmallSats and possibly even CubeSats.