FPGA powered Corazon-AI gateway supports up to 8 IP cameras for video analytics

Earlier this year, we covered some video analytics solutions based on AAEON UP Xtreme Edge embedded computer combining an Intel Whiskey Lake processor with Intel Movidius Myriad X AI accelerator modules, as well as video management & analytics software solutions from Milestones & SAIMOS, or aotu.ai BrainFrame.

iWave Systems has now introduced a similar solution with Corazon-AI gateway capable of handling up to 8 IP cameras in real-time, but instead of relying on AI accelerators, the company leverages Xilinx Zynq Ultrascale+ Arm Cortex-A53/R5 FPGA MPSoC for AI inference.

Corazon-AI gateway specifications:

SoC – Xilinz Zynq Ultrascale+ ZU2, ZU3, ZU4 or ZU5 MPSoC
- Processing System (PS)
  - Quad/Dual Arm Cortex-A53 @ 1.5GHz, dual Cortex-R5 @ 600MHz
  - Arm Mali-400MP2 GPU @ 677MHz
  - H.264/H.265 Video Encoder/Decoder
- Programming Logic (PL)
  - Up to 256K Logic cells
  - PL GTH Transceivers x 4 @ 12.5 Gbps
System Memory
- 64bit, 2GB DDR4 with ECC for PS (upgradable)
- 32bit, 1GB DDR4 for PL (upgradable)
Storage – 8GB eMMC Flash (upgradable), EEPROM for MAC Address, optional MicroSD socket
Peripheral & features from PS
- Display I/F – DisplayPort video output
- Connectivity
  - Dual Gigabit Ethernet (RJ45)
  - 802.11b/g/n/ac WiFi 5 & Bluetooth 5.0 module with antenna connectors
- USB – 2x USB3.0 Type-A ports
- Expansion – M.2 Key B Connector with SATA/PCIe & USB3.0
- Debugging – UART Header, JTAG Header
- Misc – RTC Coin cell Header
Peripherals & feature PL GTH Transceivers (Note: no support for ZU3 & ZU2 MPSoC)
- Video
  - 4K HDMI output connector
  - 4K HDMI input connector
  - Optional 12G SDI input through BNC jack
  - Optional 12G SDI output through BNC jack
- Networking – 10G Ethernet through SFP+ connector
Power Supply – 12V input through 2.5mm Jack
Dimensions – 100 x 72mm (not for the gateway, but for iW-RainboW-G36S board instead)
Temperature Range – -40°C to +85°C (Industrial)

Corazon-AI HW & SW Architecture — HW & SW Architecture

The AI gateway runs the usual Petalinux distributions plus Vitis AI stack that includes pre-optimized deep learning models from mainstream frameworks such as Tensorflow, Caffe, Darknet, and PyTorch. You can run different CNN models (SSD, GoogleNet, Yolo v2/v3, Mobilenet..) on each camera simultaneously.

It even looks like 11 cameras could be connected to the systems as the company indicates the system can handle 8 IP Cameras up to
1080p, plus two USB3.0 Cameras and one SDI camera, but it’s unclear whether AI inference is possible on all eleven cameras in real-time. It does seem to work fairly well with eight cameras though.

Corazon-AI gateway is designed for machine learning and computer-vision based applications such as video surveillance, ADAS, smart parking, medical robotics, industrial automation, and augmented reality. iWave Systems promises 10+ years of availability for the solution. More details can be found on the product page.

Jean-Luc Aufranc (CNXSoft)

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.