All News | Boards | Chips | Devices | Software | Archive | About | Contact | Subscribe
Follow LinuxGizmos:
Twitter Facebook Pinterest RSS feed
*   get email updates   *

Jetson-based sensor fusion kit features mmWave Radar

Mar 17, 2022 — by Eric Brown 1,260 views

Mistral’s “AI-SFK Lite” system runs Linux on its Jetson Xavier NX powered Neuron Base Board Basic with a 250GB SSD, GbE, HDMI 2.0, CAN, etc., and adds Mistral’s 77GHz mmWave Radar module and a CSI-based 8MP/4K camera.

Mistral announced a $1,450 AI-SFK Lite (AI-enabled Sensor Fusion Kit Lite) kit for AI, machine vision, and video analytics applications including edge camera with object detection and recognition, human activity recognition, smart retail, Industry 4.0, radar camera sensor fusion, robotics, and ADAS. The system is built around its Neuron Base Board Basic (NB-Basic) carrier board. The AI-SFK Lite uses the Jetson Xavier NX based version of the NB-Basic, which also supports the Jetson Nano.

AI-SFK Lite (left) and Neuron Base Board Basic with fan
(click images to enlarge)

When we covered the Neuron carrier in Oct. 2020, Mistral said there would be an optional mmWave module. Mistral’s 77GHz mmWave Radar Module comes standard with the AI-SFK Lite, which also adds an 8-megapixel camera and an enclosure.

Mistral says the AI-SFK Lite was launched in response to the global shortage of controller chipsets for GMSL and FPD Link interfaces. Mistral has a product page, but not a press release or shopping link, for a similar AI-SFK kit based on the Neuron Base Board Turbo. The Turbo model expands upon the base model’s 2-lane CSI interface to add a second 4-lane channel. It also provides FPD-Link III and GMSL camera support via FAKRA connectors. (Note that the enclosures are the same for the AI-SFK and AI-SFK Lite, as can be seen in the image above, which shows empty GMSL and FPD-Link III port holes.)


FPD-Link III can connect cameras and radar sensors via coaxial cables at up to 15 meters. The more advanced, SerDes-derived GMSL has a similar range and supports bi-directional data, power, and control without losing latency.

The mmWave Radar Module is based on TI’s mmWave radar sensors. The extremely high frequency, short wavelength mmWave technology operates at 30GHz and 300GHz to provide sub-mm range accuracy. The technology can penetrate heavy weather, as well as materials including, plastic, drywall, and clothing. mmWave not only detects objects but offers precise measurements of range, velocity, and angle. Mistral also offers some 60GHz models, but not with the Lite kit.

The camera module is from Leopard Imaging and is based on Sony’s iMX219 color sensor. The CSI-connected, 8MP/4K camera supports up to 21fps rates.

On the Neuron Base Board, AI algorithms running on the Jetson GPU and CUDA libraries can combine mmWave data with camera and sensor inputs to provide local intelligence. A Neural Development Kit integrates algorithms based on CUDA, cuDNN, and TensorRT from Nvidia’s Ubuntu-powered Jetpack SDK. The algorithms are optimized for sensor fusion using the board’s mmWave, camera, and attached sensors. Alternatively, you can load Ubuntu 18.04 “natively.”

Mistral 77GHz mmWave Radar Module (left) and AI-SFK Lite (image shows the Xavier NX module rather than NB-Basic board)
(click images to enlarge)

The AI-SFK Lite’s NB-Basic mainboard incorporates a Xavier NX with up to 8GB DDR4 and 16GB eMMC. Major ports include GbE with GigE support, HDMI 2.0 with audio, USB 3.1, and 2x USB 2.0. The NB-Basic is equipped with an M.2-based, 250GB SSD, as well as a WiFi/BT module.

Other features include an a CAN interface, UART debug, I2S header, and a GPIO header. There is a 12V/5A to 24V/2.5A input, a -20 to 85°C operating range, and various accessories. (For more details, see our Neuron Base Board report.)

Further information

The AI-SFK Lite is available for $1,450, with a lead time of 8-10 weeks. More information may be found in Mistral’s announcement (PDF), as well as the AI-SFK Lite shopping and product pages.

(advertise here)

Print Friendly, PDF & Email

Please comment here...