AI (artificial intelligence) and vision systems sound like a perfect combination. Intel has recently announced the OpenVINO (Open Visual Inference and Neural Network Optimization) toolkit, which lets developers combine a graphics subsystem with the algorithms required to deployed a sophisticated AI/machine-learning platform at the Edge of the IoT.
The application areas for such a solution are too numerous to name – one is for traffic management. In addition to simply observing the traffic flow, the system can consider weather (current and future), time of day, holidays, unplanned events, and so on. With all that information, things like lane opening and closing, parking spot availability, traffic-light patterns, can be adjusted accordingly.
OpenVINO consists of Intel CPUs with integrated graphics. This allows the designer to adapt to almost any potential network or interface. The VPU can help maintain performance efficiency. A key decision which the system must make is what and where to send to the Cloud, verses handing at the Edge of the IoT (known as fog computing) – the latter is important for applications that need to operate in real-time. While sending information to the Cloud for processing can be quick and efficient, it is not suitable for real-time applications.
Richard Nass, Executive Vice-President of OpenSystems Media, wrote an article in Embedded Computing, covering AI/Vision Systems in greater detail.