Visual Localization of Key Positions for Visually Impaired People

TL;DR

This paper presents a visual localization algorithm that combines prior GNSS signals and multi-modal images to accurately identify key positions for visually impaired individuals, enhancing outdoor navigation precision.

Contribution

It introduces a robust and efficient visual localization method that leverages multi-modal images and prior GNSS data for improved accuracy at key outdoor positions.

Findings

Achieves higher localization accuracy at key outdoor positions.

Demonstrates effectiveness on wearable systems in real-world scenarios.

Outperforms traditional GNSS-based localization methods.

Abstract

On the off-the-shelf navigational assistance devices, the localization precision is limited to the signal error of global navigation satellite system (GNSS). During travelling outdoors, the inaccurately localization perplexes visually impaired people, especially at key positions, such as gates, bus stations or intersections. The visual localization is a feasible approach to improving the positioning precision of assistive devices. Using multiple image descriptors, the paper proposes a robust and efficient visual localization algorithm, which takes advantage of priori GNSS signals and multi-modal images to achieve the accurate localization of key positions. In the experiments, we implement the approach on the wearable system and test the performance of visual localization under practical scenarios.