Anchor recognition in reality system
Abstract:
A control method, suitable for head-mounted devices located in a physical environment, includes following operations. Images of the physical environment are captured over time by the head-mounted devices. Candidate objects and object features of the candidate objects are extracted from the images. Local determinations are generated about whether each of the candidate objects is fixed or not. The object features and the local determinations are shared between the head-mounted devices. An updated determination is generated about whether each of the candidate objects is fixed or not according to the local determinations shared between the head-mounted devices.
Public/Granted literature
Information query
Patent Agency Ranking
0/0