Computer Vision in Space Science Technology: Advancements and Applications

Computer Vision (CV)

Computer vision, being a sub-domain of Artificial Intelligence and Machine Learning, enables the systems and computers to derive meaningful information from digital images, videos and other visual inputs. The scientific discipline of computer vision is concerned with the theory behind artificial systems that extract information from images. The image data can take many forms, such as video sequences, views from multiple cameras, multi-dimensional data from a 3D scanner, 3D point clouds from LiDaR sensors, or medical scanning devices.

This digital Image processing technology has applications in various fields. These tasks range from industrial machine vision, to research in artificial intelligence for agriculture, health care, sports and computer robots for satellite missions.

The study of space science involves planet imagery, satellite tracking, satellite communication, exoplanet research, minimization of space junk and increasing the autonomy of space vehicles.

Computer vision plays a crucial role in each of these space technology applications which is worth mentioning and also opens up other areas of research in Space Technology like spacecraft docking and orbital maneuvering.

Computer Vision in Space Technology

Space environments are different concerning the image characteristics from terrestrial applications of Computer Vision. Additional problems are caused by environmental factors such as temperature and its variation, cosmic radiation and high acceleration and so on.

Computer vision tasks can be categorized using the real-time aspect and considering what kind of data is available. Vision tasks require certain skills such as:

1. Operational model — Computer Vision systems can be categorized to operate in different operational modes, similar to robots (direct, shared, autonomous).
2. Reliability — Expected reliability of information from a computer vision system and its performance is essential to the system designer and user.
3. Spectrum — some cameras operate in the visible part of the spectrum. Some may benefit from using infrared (IR) or tunable selective cameras that image only a narrow part of the spectrum.
4. 3D range, accuracy, speed, type — Three-dimensional information is important for robotic tasks and several related skills can be defined.
5. Object recognition — Detection of events and objects may use their geometrical and surface models, natural or artificial features in images.
6. Tracking (2D, 3D) — An ability to monitor an object's position in a 2D image or in a 3D external system.

Advancements and Applications of CV in Space Technology

Autonomy is a big part of achieving interplanetary goals. Both computer vision and deep learning can work together towards it, with computer vision algorithms capable of further improving autonomous performance.

Both computer vision and AI in space exploration reduce the time astronauts have to spend on repetitive tasks, improving their capabilities in execution, perception, information storage, retrieval, task planning, and more. Specifically, some of the computer vision tasks employed in space exploration are:

1. Satellite imagery information retrieval: Satellite Imagery provides an unprecedented way of capturing the surface of Earth which is widely used in Remote Sensing. The image captured by the satellite is then processed using a variety of Computer vision techniques where every part of the image is detected and essentially features are extracted. This facilitates scientists to build predictive models for specific remote sensing applications like natural disaster identification and prevention.
2. Spacecraft docking: Raven, a hybrid computing system, developed by NASA’s Goddard Space Flight Center, USA, helped to develop technologies that allow for spacecraft to dock autonomously and in real-time. Raven’s sensor which was the eyes worked alongside the Space-Cube processor which was the brain, and worked together to create an autopilot ability.
3. Autonomous precision landing: Using computer vision algorithms in aircraft, can help estimate a spacecraft’s relative position while descending. A landmark recognition-based algorithm can calculate the motion and relative positions. Similar computer vision algorithms play a major role in landing aircraft such as obstacle detection and avoidance, Routine testing and inspection, evacuation and mining, terrain map building and surveillance of the planet's surface.
4. Asteroid detection: Image processing technology in computer vision uses technologies such as image enhancement, image identification, Gaussian stretching and linear stretching to identify and classify new asteroids. In image processing, two-dimensional matched filters are often used to improve the signal-to-noise quality of X-ray findings. Legacy sensors and optics have improved detection sensitivity, allowing for the surveillance of near-Earth asteroids (NEA) of smaller sizes.
5. Self-Driving Rovers: Self-Driving reconnaissance vehicles have made many important discoveries, especially in the exploration of the Martian surface. Their vehicles can perceive their surroundings through computer vision technologies. Thus, they can pilot routes and transmit what they see in real-time to researchers around the world.
6. Tracking and surveillance of space debris: The Department of Defense’s Global Space Surveillance Network (SSN) tracks over 27,000 pieces of space debris, both artificial orbital debris and naturally occurring meteoroid debris. It’s vital to track them to prevent spacecraft from being damaged. Computer vision monitors the debris and finds ways to reduce it by Using real-time video analysis to monitor the operational activities of spacecraft. Detecting and tracking debris using computer vision models.Using pre-trained machine learning models to predict future dangers during missions.

In Conclusion, Computer Vision is hard and requires a big effort to start digging deep into that universe, but with Deep Learning methods, we can achieve state-of-the-art results on challenging computer vision problems in various applicational fields in this world.

Co-Authors :

Kaavya Shree, Shravani Upadhyay

Special Mention :

Bharathi Athinarayanan