Rugged embedded computing system for artificial intelligence (AI) and sensor processing introduced by Elma
Jetsys-5320 is for high-resolution sensor processing, movement tracking, automatic target recognition, threat location, and predictive maintenance.
FREMONT, Calif. – Elma Electronic in Fremont, Calif., is introducing the Jetsys-5320 rugged artificial intelligence (AI) embedded computing system for mobile data-intensive applications.
It provides complex general-purpose graphics processing unit (GPGPU) inference computing at the edge of the battlefield for AI and machine learning in intelligent video analytics, virtual reality, augmented reality, and unmanned vehicles.
The Jetsys-5320 increases visual intelligence throughout defense and transportation applications such as high-resolution sensor processing, movement tracking security systems, automatic target recognition, threat location detection, and condition-based monitoring and predictive maintenance.
Related: Embedded computing sensor and signal processing meets the SWaP test
At the heart of the JetSys-5320 is the NVIDIA Jetson TX2i system on module. Paired with a dual-core Denver 2 64-bit microprocessor, quad-core ARM A57 Complex, and 256 CUDA cores, NVIDIA’s Pascal architecture delivers 1.3 trillion floating point operations per second (TFLOPs) of performance.
The rugged embedded computing system also provides high-definition serial digital interface (HD-SDI), Gigabit Ethernet with Power-over-Ethernet, USB 3.0 interfaces for video capture, and mini PCI Express expansion slots. It operates in temperatures from -40 to 71 degrees Celsius, offers IP67-rated ingress protection, and meets MIL-STD-810G for harsh environments.
For more information contact Elma Electronic online at www.elma.com.