Edge video processing platform features NXP i.MX 8M Plus, i.MX 93, or i.MX 95 SoC, supports up to 23 camera types

DAB Embedded AquaEdge is a compact computer based on NXP i.MX 8M Plus, i.MX 93, or i.MX 95 SoC working as an edge video processing platform and supporting 23 types of vision cameras with resolution from VGA up to 12MP, and global/rolling shutter.

The small edge computer features a gigabit Ethernet RJ45 jack with PoE to power the device. It is also equipped with a single GSML2 connector to connect a camera whose input can be processed by the built-in AI accelerator found in the selected NXP i.MX processors. Other external ports include a microSD card slot, a USB 3.0 Type-A port, and a mini HDMI port (for the NXP i.MX 8M Plus model only).

DAB Embedded AquaEdge video processing platform

DAB Embedded AquaEdge specifications:

  • SoC / Memory / Storage options
    • NXP i.MX 8M Plus
      • CPU – Quad-core Cortex-A53 processor @ 1.8GH, Arm Cortex-M7 real-time core
      • AI accelerator – 2.3 TOPS NPU
      • VPU
        • Encoder up to 1080p60 H.264, H.265
        • Decoder up to 1080p60 H.264, H.265
      • Memory – 2 to 8GB LPDDR4
      • Storage – 16 to 64GB eMMC flash
    • NXP i.MX93
      • CPU – Dual-core Cortex-A55 processor @ 1.7GHz, Arm Cortex-M33 low-power core
      • AI Accelerator – Arm Ethos-U65 microNPU
      • VPU – N/A
      • Memory – 1 to 2GB LPDDR4
      • Storage – 16 to 64GB eMMC flash
    • NXP i.MX95
      • CPU – Hexa-core Cortex-A55 processor @ 2.0GHz, Cortex-M33 real-time core, Cortex-M7  low-power safety controller
      • AI Accelerator – NXP eIQ Neutron NPU
      • VPU
        • Encoder up to 4K60 H.264, H.265; JPEG
        • Decoder up to 4K60 H.264, H.265; JPEG
      • Memory – 4-16 GB LPDDR5
      • Storage – 16-128 GB eMMC flash
  • Storage
    • microSD card slot with UHS capability
    • Optional NVMe SSD via M.2 Key-M socket
  • Video Output – Mini HDMI output with HDMI 2.0a capability (NXP i.MX 8M Plus only)
  • Camera – GMSL2 interface (6 Gbps) for an external camera up to 16 MP resolution
  • Networking
    • Gigabit Ethernet RJ45 jack with PoE option
    • WiFi 5 and Bluetooth 5.3 BLE (NXP i.MX93)
    • WiFi 6 and Bluetooth 5.3 BLE (NXP i.MX95)
    • Optional 5G cellular connectivity via M.2 socket (based on the announcement on LinkedIn)
  • USB – USB 3.0 Host port with 1A max output power
  • Expansion – M.2 Key-M socket (PCIe / USB 2.0)
  • Power Supply – PoE input
  • Power consumption
    • 10 W max (NXP i.MX 8M Plus)
    • 7.5 W max (NXP i.MX 93)
    • 15 W max (NXP i.MX 95)
  • Dimensions – 124 x 86.6 x 32.1 mm
Embedded Mini PC GSML2 camera connector
GMSL2 camera

The AquaEdge runs Linux with a Yocto-based file system containing all necessary components for the development of video processing applications. DAB Embedded also provides a “standard package” with video ISP (image vision processor) drivers, GStreamer for video streaming, a Web server, and a Rest API. The following Sony camera sensors are pre-calibrated for the edge devices: IMX462, IMX412, IMX900, IMX392,  IMX335,  and IMX415.

We’re also told MobileNet SSD, Yolov4-tiny, and TFLite AI models are supported out of the box in the provided Linux BSP for image classification, segmentation, and more. Sadly, the company did not release documentation or software publicly, but Tomeu Vizoso (who worked on the open-source Etnaviv NPU driver) mentions that the Arm Ethos NPU’s software stack is open source, including the compiler, enabling users to leverage the NPU for other scenarios such as transformer-based models. That’s valid for the NXP i.MX 93 SoC, but the NXP i.MX 95 relies on the drivers developed by NXP.

Axo2 GMSL2 camera with Sony IMX335 sensor
Axo2 GMSL2 camera with Sony IMX335 sensor

You’ll find more details about the AquaEdge video processing platform and supported camera on the DAB Embedded “shop” which doesn’t sell anything for now…

Share this:

Support CNX Software! Donate via cryptocurrencies, become a Patron on Patreon, or purchase goods on Amazon or Aliexpress

Radxa Orion O6 Armv9 mini-ITX motherboard
Subscribe
Notify of
guest
The comment form collects your name, email and content to allow us keep track of the comments placed on the website. Please read and accept our website Terms and Privacy Policy to post a comment.
0 Comments
oldest
newest
Boardcon CM3588 Rockchip RK3588 System-on-Module designed for AI and IoT applications