Date of Award

6-6-2019

Document Type

Thesis - SCU Access Only

Publisher

Santa Clara : Santa Clara University, 2019

Department

Computer Engineering

First Advisor

Behnam Dezfouli

Abstract

Navigating while visually impaired is extremely difficult. Without sight, people must rely on their other senses to navigate through life, mainly by way of hearing and touching (with their cane). Nonetheless, these senses cannot completely make up for the loss of vision. In this paper, we propose NavSense, an assistive device that supplements existing technology, and improves navigation in day to day life. NavSense provides near real-time object identification and context to the user through auditory feedback. This paper describes the testing procedures used and results gathered while identifying the best components for the system. NavSense is capable of providing accurate results quickly on low cost and energy efficient edge devices.

Share

COinS