Ultra compact signage PC with vision processing units

1 FEBRUARY 2021

The IDS-310AI embedded PC from ICP Germany is an ultra-compact digital signage system that has been optimized for use in low-power AI applications. On the hardware side, the IDS-310AI is equipped with two Intel® Movidius™ Myriad™ X MA2485 VPUs, which provide excellent inference performance per watt, 16 SHAVES cores for AI calculations and native FP16 support. The IDS-310AI is further equipped with an Intel® Celeron® J3455 which has a maximum clock speed of 2.3GHz and a Thermal Design Power of 10 watts. Pre-installed are 8 GB DDR3L SO-DIMM memory as well as a 128GB SATA Disk on Module on which both the Windows 10 or Linux operating system as well as the user software find place. On the software side, the IDS-310AI supports the Intel® Open Source Toolkit “Open Visual Inference Neural Network Optimization” (OpenVINO™), and thus end-to-end acceleration for a variety of neural networks. OpenVINO™ enables CNN (convolutional neural network) based pre-trained models to be deployed at the edge with little effort. Training models such as AlexNet, GoogleNet, Tiny Yolo, Squeezenet, resNet and many more are supported by default and are easy and fast to implement. For connecting peripherals, the palm-sized embedded PC has two GbE LAN ports, one RS-232/422/485 with AFC functionality and three USB 3.2 interfaces. In addition, the IDS-310AI provides its user with three HDMI ports for image output with a maximum resolution of 3840×2160 pixels at 30Hz. The cooling concept of the IDS-310-AL does not require a fan, making it low-maintenance. The IDS-310AI can thus be operated in a temperature range from -20°C to +45°C. The IDS-310AI’s power consumption is reported to be a maximum of 31.2 watts at 12 volts DC. The compact size and the mounting options additionally offer a flexible range of applications to realize AI projects.

Specifications

  • Ultra compact embedded PC
  • Intel® Celeron® J3455 Apollo Lake SoC
  • Dual Intel® MovidiusTM MyriadTM X VPU for AI Deep Learning
  • 8GB DDR3L SO-DIMM memory
  • 3x HDMI 1.4b 4K
  • COM, Dual LAN GbE, USB 3.2
  • Extensions: M.2 and PCIe Mini Slots
  • Optional I/O: MicroSD slot, WiFi 802.11 a/b/g/n/ac, TPM2.0
  • Power input: 12VDC
  • Operating temperature: -20°C ~ +60°C
  • VESA or wall mounting

Applications

  • Digital signage
  • Visualization
  • Industrial PC
  • Deep Learning Inference System
  • Object Recognition
  • Face Recognition
  • AIoT Edge Computer
  • Smart Automation
  • Image Processing

ICP Deutschland

Leave a Reply

Your email address will not be published. Required fields are marked *

  • We use your personal data ONLY to respond to your comments/requests.
  • To receive responses that are appropriate to your requests, we may transfer your email address and your name to the author of the article.
  • For more information on our Privacy Policy and Personal Data Processing, please visit the page: Privacy Policy (GDPR) & Cookies.
  • If you have any questions or concerns regarding the way we process your personal data, you can contact our Data Protection Officer at: gdpr@esp2000.ro
  • Subscribe to our magazine newsletter