Wearable Mobility Aid for Low Vision Using Scene Classification in a Markov Random Field Model Framework

Abstract

This article describes work on a novel approach to vision enhancement for people with severe visual impairments. This approach utilizes computer vision techniques to classify scene content so that visual enhancement of the scene can identify semantically important concepts. The mediated view of a scene presented to the user is in the form of a highly-saturated color image in which distinct colors represent important object types in the scene. The effectiveness of this scheme was demonstrated in a pilot study participated in by people with a range of visual impairments. The scene classification technique uses an artificial neural network classifier within the framework of a Markov random field model, and the accuracy and robustness of this technique using low quality video images from a hand-held camera is demonstrated.