Machine Vision

Image acquisition and inference at the machine: camera interfaces feeding a compute module, often with an accelerator, and results sent over Ethernet.

  • Multi-protocolEdge AI, Ethernet, Embedded Linux, Arm architecture
  • Multi-manufacturer19 manufacturers in this selection
  • Built-in documentationDatasheets and linked resources
  • SupportHelp choosing and integrating

Architecture

Typical Machine Vision architecture

From the field to the uplink: each role of the chain and the product families that fill it.

Request a quote
  1. 1. Vision compute

    Embedded module with GPU or NPU.

    See the products
  2. 2. Inference accelerator

    M.2 or PCIe accelerator cards.

    See the products
  3. 3. Networking

    Ethernet uplink to the line controller.

    See the products

This is an architecture pattern, not a certified reference design. Verify every interface, rating and certification in the datasheets.

Use cases

Concrete problems this solution answers

All applications

Products

Products for a Machine Vision solution

Request a quote

Industries

Sectors that use these product families

All industries

Technologies and protocols

Compatibilities and standards

All technologies

Documentation and resources

Guides and documentation

  • SCG-5632 — Telnet COM Port Control OptionManual · Sollae Systems Open
  • SCG-5632 — TCP Server/Client modeManual · Sollae Systems Open
  • SCG-5632 — Serial cable datasheetDatasheet · Sollae Systems Open
  • SCG-5632 — Separator functionManual · Sollae Systems Open
All resources

Before choosing

What to verify

Camera interface (MIPI CSI, GigE Vision, USB) and bandwidth
Frame-rate versus inference latency
Trigger and I/O synchronisation with the line
Thermal limits in enclosed cabinets