An Embedded Real-time Object Alert System for Visually Impaired: A Monocular Depth Estimation based Approach through Computer Vision

TL;DR

This paper presents a real-time alert system for the visually impaired using monocular depth estimation and object detection, optimized for embedded devices to improve safety during urban navigation.

Contribution

It introduces a novel combined model for depth estimation and object detection optimized for embedded systems, enhancing real-time obstacle alert capabilities.

Findings

Achieved a lightweight real-time depth estimation and object detection model with mAP50 of 0.801.

Utilized transfer learning and quantization to optimize models for embedded deployment.

Proposed system effectively alerts visually impaired users of nearby objects to prevent accidents.

Abstract

Visually impaired people face significant challenges in their day-to-day commutes in the urban cities of Bangladesh due to the vast number of obstructions on every path. With many injuries taking place through road accidents on a daily basis, it is paramount for a system to be developed that can alert the visually impaired of objects at close distance beforehand. To overcome this issue, a novel alert system is proposed in this research to assist the visually impaired in commuting through these busy streets without colliding with any objects. The proposed system can alert the individual to objects that are present at a close distance. It utilizes transfer learning to train models for depth estimation and object detection, and combines both models to introduce a novel system. The models are optimized through the utilization of quantization techniques to make them lightweight and efficient, allowing them to be easily deployed on embedded systems. The proposed solution achieved a lightweight real-time depth estimation and object detection model with an mAP50 of 0.801.