What is Embedded Vision?
Embedded Vision, essentially a term meaning that the image processing happens onboard a device.
It can be presented in a variety of formats and technologies butthe idea is to embed a solution so that it is running as efficiently as possible, in a compact format, typically on processors based on ARM or x86 architecture. The processing ‘result’ is often all that the system will output so minimising data bandwidth with the real-world and presenting only the core information required by the system.
Until now, embedded vision solutions have been focused on transport, logistics, medical and other non-manufacturing vision tasks, such as automated vehicle guidance. It is predicted these areas and similar will grow at an ever increasing pace as our world demands further more automation and data feedback on all aspects of our lives. It is also expected to have a major impact in the traditional machine vision market where specific inspection tasks can be realised more quickly and cost effectively than ever, with the use of embedded technology.
An embedded system consists of three main elements (aside from lighting and lenses);
Processor board – typically based on ARM or x86 , there are several popular options such as NVIDIA Jetson, Raspberry Pi, MicroZed, and ODRIOD. The MicroZed for example uses a Xilinx ZYNC SoC (System-on-chip) processor. This device integrates the software programmability of an ARM®-based processor with the hardware programmability of an FPGA, enabling key analytics and hardware acceleration while integrating CPU, DSP, ASSP, and mixed signal functionality on a single device.
Software – designed to run a specific task, highly efficiently. Depending on platform the skills required will include C/C++ , FGPA and DSP programming. The functions may be written from scratch or alternatively it is now possible to harness the power of third party processing libraries such as HALCON Embedded.
Sensor/Camera – a vision system requires an image! This can come from an off-the-shelf board level or compact camera designed to be feature rich and compact (such as Basler dart) or it may come from a customised sensor-interface solution (such as Pleora iPORT NTx series).
What are the benefits of Embedded Vision?
- Lean system design
- Light weight
- Cost-effective, because there is no unnecessary hardware
- Lower manufacturing costs
- Lower energy consumption
- Small footprint