AI imaging system for nanosats

November 10, 2021 // By Nick Flaherty
AI imaging system for nanosats
Teledyne 2V is working with the Centre Spatial Universitaire de Grenoble (CSUG) on an AI image analysis system for a CubeSat nanosatellite based on its quad core QlevEr board

Teledyne e2v is working with a French research group on an AI-based imaging system for small satellites.

The QlevEr Sat demo for a 6U CubeSat measures 10cm x 20cm x 30cm and uses the quad-core 1.8GHz Qormino QLS1046-Space processing module. This has four 64bit Arm Cortex A72 processor cores and 4GB of co-packaged DDR4 memory capacity. The imaging data is captured using a 16Mpixel Emerald CMOS image sensor also provided by Teledyne e2v.

The system will process the images on-board to build simplified binary maps of the areas before transmitting back from space, thereby significantly reducing the bandwidth overhead involved.

Large area images are firstly acquired by the QlevEr Sat system, then converted via the on-board processing resource with an advanced tailor-made artificial intelligence (AI) algorithm incorporated into it. The AI algorithm was specifically developed by the Multidisciplinary Institute in Artificial Intelligence (MIAI), to optimize execution on embedded targets.

The algorithm is used for applications such as deforestation tracking as the primary use case, but also for monitoring of volcanic activity, evaluation of damage caused by natural or manmade disasters, growth in urbanization, glacial movement analysis and oceanic investigation, as well as possible defence related tasks.

The modules are subjected to extensive qualification, screening and radiation characterization procedures covering the processor element itself and the accompanying DDR4 memory. The modules can cope with total ionizing dose (TID) levels above 100kRad and have single event latch-up (SEL) resilience beyond 60MeV.cm²/mg. An operational temperature range of -55°C to +125°C is also supported to ease integration into spacecraft.

“Integrating AI capabilities directly into CubeSats will dramatically reduce the amount of bandwidth needed for data transmission, which is clearly beneficial given the rising number of satellites now in orbit. This QlevEr Sat demo provides a radiation tolerant processing capability without taking up much PCB area,” states Tania McNamara, Project


Vous êtes certain ?

Si vous désactivez les cookies, vous ne pouvez plus naviguer sur le site.

Vous allez être rediriger vers Google.