Computer Vision-Based Assistive Technology for Blind and Visually Impaired People: A Deep Learning Approach

Author:

G.M. Roopa1,Prakash Chetana1,Pradeep N. 1

Affiliation:

1. Bapuji Institute of Engineering and Technology,Department of Computer Science and Engineering,Davangere – 577004, Visvesvaraya Technological University, Belagavi,India,590018,

Abstract

<b></b><b></b>According to the World Health Organization (WHO), a minimum of 2.2 billion individuals worldwide have impaired vision or are blind. In contrast to hereditary blindness, gained visual impairment is frequently identified as a result of aging, lifestyle habits, or hereditary influences. Aging-related presbyopia has the largest influence on visual impairment and is the second most prevalent cause of blindness globally, and the rate of acquired blindness is predicted to rise dramatically as life expectancy rises. When performing most of the everyday tasks that non-disabled individuals do, visually and blind people face several problems. Thus, assistive gadgets have been utilized to help the blind and visually impaired overcome physical, social, infrastructural, and accessibility hurdles to independence, allowing them to live engaged, creative, and fruitful life as equal members of society. The usage of assistance equipment has increased, and numerous electronic help devices have been produced in recent years, which have been superseded by traditional aid gear, such as white canes. Currently, ATs are created by integrating various types of sensors, cameras, or feedback channels that combine with various implementation methodologies to increase movement for the visually handicapped. Assistive systems based on computer vision or machine learning approaches have emerged, and as technology has advanced, so has assistive technology. Assistive technology is a priority in the field of education and rehabilitation for individuals with blindness or low vision because it “equalizes the ability to access, store, and retrieve information between sighted people and those with visual impairments”. Nowadays, technological advances are making a difference in their ability to overcome difficulties to some extent. Every day, they encounter a slew of challenges, the most significant of which are establishing one's position, determining one's heading and movement directions, and comprehending the placements of things. The goal of assistive technology is to boost impaired people's faith, comfort, security, independence, and quality of life by enhancing their mobility and decreasing their impairment.<b></b><b></b><br>

Publisher

BENTHAM SCIENCE PUBLISHERS

Reference28 articles.

1. Deng J.; Xuan X.; Wang W.; Li Z.; Yao H.; Wang Z.; A review of research on object detection based on deep learning. The 2020 International Seminar on Artificial Intelligence, Networking and Information Technology 2020

2. Liu L.; Ouyang W.; Wang X.; Fieguth P.; Chen J.; Liu X.; Pietikäinen M.; Deep Learning for Generic Object Detection: A Survey. Int J Comput Vis 2020,128(2),261-318

3. Wua X.; DoyenSahoob, Steven C.H.Hoiab “Recent advances in deep learning for object detection”. Neurocomputing 2020,243(21),125-132

4. Cao C.Y.; Zheng J.C.; Huang Y.Q.; Liu J.; Yang C.F.; Investigation of a Promoted You Only Look Once Algorithm and Its Application in Traffic Flow Monitoring. Appl Sci (Basel) 2019,9(17),3619

5. Hui J.; 2019,28

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3