SEMANTICALLY SUPPORTED OBJECT RECOGNITION TO PROVIDE KNOWLEDGE TRANSFER

摘要

Systems and methods for knowledge transfer using augmented reality. A stream of images from a camera, recorded in first-person perspective, is sent to a processor to analyze object types, their location on the frame and associated detection accuracy. The response from the processor is combined with information from a semantic data model stored in memory, that is then used to detect actions using an activity recognition engine. A structured set of work instructions is generated and stored in the memory for the task. The structured set of work instructions may then be used in learning mode to instruct new users and to give them feedback.