MIPI embedded vision systems has deep learning
Custom-made Arm boards with mobile industry processor interface (MIPI) sensors are used by EyeVision Technology (EVT) to create compact embedded vision systems.
EyeVision also offers deep learning algorithms for these embedded vision platforms to enable precise surface inspection and number plate recognition applications.
The MIPI sensors are directly from the EVT hardware development and are available in different resolutions and models. They can be combined with Raspberry Pi 4 or Zero, Nvidia or Pine Arm boards.
The small form factor is particularly suitable for space-constrained applications. Adjustments can be exact to fit housing modifications.
The EyeVision deep learning algorithms run on EyeVision’s embedded vision systems. According to EyeVision, complex applications can be solved with only a few mouse clicks. The software has ready-to-use commands in the graphical user interface (GUI) with drag-and-drop programming for surface inspections and numberplate reading.
Surfaces can be inspected for cracks, scratches, rills, grout, inadequate machining surfaces without requiring complex configurations. The different error types are classified and the deep learning algorithm’s add-on can be integrated very quickly into the production process.
The operating system is Linux. Compatible communications interfaces are Profinet, Modbus, TCP/IP or UDP. In addition, the OPC UA interface allows for integration into the SCADA system.
