Virtual tagging detection for context awareness using computer vision

Abstract

A general concept on the use of computer vision in a way in which objects in the scene act as visual markers is presented, with special focus on its ability to increase the contextual awareness of a blind user with relation to its surroundings. A demonstration of the concept has been developed and is presented in this work. Having a rough estimation of user location and previous knowledge, from memory, of which visual features should be present in an environment, the recognition of visual elements in a scene validates and provides a trust indicator about the estimated spatial context of a blind user of an assistive orientation device, reducing the gap naturally imposed by his impairment.