Design, Development and Performance Analysis of Intelligent Virtual Assistive aid with Multi Sensor Fused Navigation for Visually Impaired People

Autor: Myneni Madhu Bala, D. N. Vasundhara, V K N S N Moorthy CH
Rok vydání: 2022
Popis: Wearable auxiliary devices’ research and innovations for visually impaired elderly people and blind are playing an attractive role. These inventions attempt to improve the quality of visually impaired people life. However, in spite of the promising research outcomes, the existing wearable aids has numerous weaknesses in terms of weight, feature limitations and cost. The main objective of this manuscript is to provide the detailed design of a novel lightweight wearable aid for visually impaired and blind people. The proposed research aims to design an intelligent virtual assistant that will guide for walking by detecting the environment around them. The framework proposed to develop the virtual assistant is a fusion of sensor based, vision based and smart application. The visual design components include obstacle detection, uneven surface detection, slope and downward steps detection, pothole detection and hallow object detection; location tracking, walking guide, image capturing and video recording. Based on the appearance of this prototype named as Blind's Apron. The invention focusses on parameters like reduction on size (quite handy) and light weight (comfortable to wear), and minimum user intervention (high end operations like switching on and off). All user interactions are friendly and affordable to everyone. The results obtained in this research assures a high end technical intervention with ease of use while comparing with the current working products in this field. These are demonstrated with many blindfolded subjects on visually impaired participants. Finally, the performance of the proposed virtual assistant tested in real-time and targeted people. The results are assured the proposed invention is light weight and in easily understandable instructions.
Databáze: OpenAIRE