Machine vision has been around for a long time. For example systems in manufacturing lines that easily detect varying quality. Once you take such system in a human environment like a or aim to understand a video the solution of these problems becomes more difficult. There have been considerable advances, but the general problem is still hard. Here is a new example from a company called Vitamin D Video, with a brain-based solution. ' ... In its current form, Vitamin D Video is targeted for video analytics and monitoring, but the underlying technology, called Hierarchical Temporal Memory, or HTM, is modeled on the human neocortex and is the stuff of AI-yet-to-come ... '.
This system is trained rather than programmed. We worked with several such systems and the results could be too narrowly focused. Like the manufacturing line example.
Subscribe to:
Post Comments (Atom)
No comments:
Post a Comment