Here’s another one with AAEON VPC-3350AI AI edge computer powered by an Intel Atom X5 E3940 Apollo Lake processor, as well as two Myriad X VPUs for AI acceleration, and equipped with five Ethernet ports – four of which supporting PoE – to get video data from IP cameras or other networked video sources that makes it especially suitable as an AI network video recorder.
- SoC – Intel Atom X5-E3940 quad-core Apollo Lake processor @ 1.6 GHz / 1.8 GHz with 2 MB cache, 12 EU Intel UHD graphics; 9.5W TDP; Option for Celeron N4200/N3350 and X5-E3950)
- System Memory – Up to 8GB, DDR3L via 204-pin SODIMM socket
- Storage – 1x SATA port for 2.5″ drives
- AI Accelerator – 2x Intel Myriad X Vision Processing Unit (up to 4 Myriad X as an option)
- Video Output – 1x HDMI, 1 DisplayPort
- Audio – LINE out, MIC in
- 1x Gigabit Ethernet port
- 4x Ethernet ports with PoE (IEEE 802.3 at/af) support sharing 60W of power budget
- 2x Micro SIM slots (So there must also be an mPCIe socket for 4G/3G?)
- USB – 2x USB 3.2 Gen 1 ports
- Serial – 2x RS-232/422/485 ports (DB9)
- Expansion – 8-bit DIO with 4-ch digital input, 4-ch digital output
- Misc – Power & reset buttons, Power & HDD LEDs
- Power Supply – 12-24V DC via 3-[in terminal block
- Form Factor – Mobile NVR
- Dimension – 160 x 134 x 62mm (“Mobile NVR” form factor)
- Weight – 2.3 kg (gross)
- Temperature Range – Operating: -20°C ~ 60°C; storage: -40°C ~ 85°C
- Humidity – Storage: 10%~80% @40°C, non-condensing
- Vibration/Shock – MIL-STD-810G
- Certification – CE & FCC Class A
The device ships with a wall-mount bracket, a SATA cable, and a power cable for SATA. VPC-3350AI fanless network video recorder is capable of video processing speeds up to 210 FPS and 8 TOPs thanks to the two Myriad X VPUs integrated into the system when using GoogleNet. There’s no word about operating system support, but considering the edge computer should rely on Intel OpenVino toolkit both Windows and Linux should be supported.
VPC-3350AI AI network video recorder is especially suitable for license plate and facial recognition, advanced driver-assist systems (ADAS), as well as driver monitoring and behavior analysis for heavy vehicle operators.
Further information can be found on the product page.
Jean-Luc started CNX Software in 2010 as a part-time endeavor, before quitting his job as a software engineering manager, and starting to write daily news, and reviews full time later in 2011.
|Support CNX Software - Donate via PayPal or become a Patron on Patreon|