Context-aware tagging for augmented reality environments

摘要

A method for tag-based search includes capturing an image, extracting a tag from the image, identifying a location associated with the captured image, and querying stored content for information that matches the location and the tag. Local storage is checked for the information first, and remote storage may be checked subsequently. Any located information may be used to augment the image. Information located in the remote storage may be saved in the local storage until it reaches a certain age, until it fails to be accessed for a threshold period of time, or until the location moves outside a threshold radius associated with a location of the information located in the remote storage.

主权项

1. A method for augmenting an image, the method comprising:
capturing an image using a mobile device; extracting a machine-readable label from the image; querying stored content for information that is associated with the machine-readable label, wherein the information includes non-location information; identifying a location associated with the mobile device; generating a tentative identification of an object depicted in the image, based at least in part on the information; producing a model of a statistical distribution of objects that share characteristics with the object and that are known to be present in the location associated with the system; inferring a probability that the tentative identification is correct, from the model of the statistical distribution; and augmenting the image by visually superimposing at least some of the information over the image, wherein the at least some of the information is related to the tentative identification, when the probability indicates that the tentative identification is likely to be correct, wherein at least one of: the extracting, the querying, or the augmenting is performed using a processor of the mobile device.