Stereo Acoustic Perception based on Real Time Video Acquisition for Navigational Assistance

TL;DR

This paper presents a real-time video-based stereo acoustic navigation aid for the visually impaired, using object detection and sound cues to identify immediate obstacles efficiently.

Contribution

It introduces a novel real-time video processing algorithm that detects the most threatening obstacle and translates it into audio signals for navigation assistance.

Findings

Efficient obstacle detection algorithm outperforming previous methods

Real-time processing on a digital media processor

Effective audio feedback system for obstacle awareness

Abstract

A smart navigation system (an Electronic Travel Aid) based on an object detection mechanism has been designed to detect the presence of obstacles that immediately impede the path, by means of real time video processing. The algorithm can be used for any general purpose navigational aid. This paper is discussed, keeping in mind the navigation of the visually impaired, and is not limited to the same. A video camera feeds images of the surroundings to a Da- Vinci Digital Media Processor, DM642, which works on the video, frame by frame. The processor carries out image processing techniques whose result contains information about the object in terms of image pixels. The algorithm aims to select the object which, among all others, poses maximum threat to the navigation. A database containing a total of three sounds is constructed. Hence, each image translates to a beep, where every beep informs the navigator of the obstacles directly in front of him. This paper implements an algorithm that is more efficient as compared to its predecessors.