THIRD EYE 360° Object Detection and Assistance for Visually Impaired People

Visual disability is a global issue. Visually impaired people confront several challenges every day. Many times, blindness affects a person’s ability to self-navigate in known or unknown environments. The difficulties faced by them and how they deal with themare largely known and explored. The system we developed is an idea to overcome the challenges of detecting objects in a known environment or room environment with the help of Artificial Intelligence. The idea is based on the approach to aid visually impaired people with voice assistance to detect objects of the surrounding using 360° view cameras. The proposed system uses a 360° view camera of the mobile phone to assist the user for detecting desired objects in the room environment and provide localization. Using this system, users can search for the desired objects by giving voice commands and can be assisted to the object location. When the user wants to search any object, he/she simply gives a voice command using NLP to the system. The system then identifies commands and extracts the object name to be searched. With the help of imageprocessing, first identifies and locates the object in surrounding and navigates the user to that object using a voice assistant.

Download Full-text

Efficient Multi-Object Detection and Smart Navigation Using Artificial Intelligence for Visually Impaired People

Entropy ◽

10.3390/e22090941 ◽

2020 ◽

Vol 22 (9) ◽

pp. 941

Author(s):

Rakesh Chandra Joshi ◽

Saumya Yadav ◽

Malay Kishore Dutta ◽

Carlos M. Travieso-Gonzalez

Keyword(s):

Artificial Intelligence ◽

Object Detection ◽

Real Time ◽

Visually Impaired ◽

Auditory Information ◽

Visually Impaired People ◽

Video Frames ◽

Average Accuracy ◽

Impaired People ◽

Impaired Person

Visually impaired people face numerous difficulties in their daily life, and technological interventions may assist them to meet these challenges. This paper proposes an artificial intelligence-based fully automatic assistive technology to recognize different objects, and auditory inputs are provided to the user in real time, which gives better understanding to the visually impaired person about their surroundings. A deep-learning model is trained with multiple images of objects that are highly relevant to the visually impaired person. Training images are augmented and manually annotated to bring more robustness to the trained model. In addition to computer vision-based techniques for object recognition, a distance-measuring sensor is integrated to make the device more comprehensive by recognizing obstacles while navigating from one place to another. The auditory information that is conveyed to the user after scene segmentation and obstacle identification is optimized to obtain more information in less time for faster processing of video frames. The average accuracy of this proposed method is 95.19% and 99.69% for object detection and recognition, respectively. The time complexity is low, allowing a user to perceive the surrounding scene in real time.

Download Full-text

Touching Blind Bodies: A Critical Inquiry into Pedagogical and Cultural Constructions of Visual Disability in the Nineteenth Century

10.3366/edinburgh/9781474400046.003.0014 ◽

2018 ◽

Author(s):

Heather Tilley ◽

Jan Eric Olsén

Keyword(s):

Nineteenth Century ◽

Visually Impaired ◽

Blind People ◽

Embodied Experience ◽

Visual Disability ◽

Visually Impaired People ◽

Educational Challenges ◽

Impaired People ◽

The Senses ◽

Cultural Constructions

Changing ideas on the nature of and relationship between the senses in nineteenth-century Europe constructed blindness as a disability in often complex ways. The loss or absence of sight was disabling in this period, given vision’s celebrated status, and visually impaired people faced particular social and educational challenges as well as cultural stereotyping as poor, pitiable and intellectually impaired. However, the experience of blind people also came to challenge received ideas that the visual was the privileged mode of accessing information about the world, and contributed to an increasingly complex understanding of the tactile sense. In this chapter, we consider how changing theories of the senses helped shape competing narratives of identity for visually impaired people in the nineteenth century, opening up new possibilities for the embodied experience of blind people by impressing their sensory ability, rather than lack thereof. We focus on a theme that held particular social and cultural interest in nineteenth-century accounts of blindness: travel and geography.

Download Full-text

Object Detection to Assist Visually Impaired People: A Deep Neural Network Adventure

Advances in Visual Computing - Lecture Notes in Computer Science ◽

10.1007/978-3-030-03801-4_44 ◽

2018 ◽

pp. 500-510 ◽

Cited By ~ 5

Author(s):

Fereshteh S. Bashiri ◽

Eric LaRose ◽

Jonathan C. Badger ◽

Roshan M. D’Souza ◽

Zeyun Yu ◽

...

Keyword(s):

Neural Network ◽

Object Detection ◽

Visually Impaired ◽

Deep Neural Network ◽

Visually Impaired People ◽

Impaired People

Download Full-text

An Enhanced Mobile Phone Dialler Application for Blind and Visually Impaired People

International Journal of Engineering & Technology ◽

10.14419/ijet.v2i4.1101 ◽

2013 ◽

Vol 2 (4) ◽

pp. 270 ◽

Cited By ~ 4

Author(s):

Rana Mohammad Yousef ◽

Omar Adwan ◽

Murad Abu-Leil

Keyword(s):

Mobile Phone ◽

Mobile Phones ◽

Visually Impaired ◽

Voice Recognition ◽

Blind And Visually Impaired ◽

Phone Calls ◽

Visually Impaired People ◽

Impaired People ◽

Windows Phone ◽

Innovative Concept

This paper presents the development of a new mobile phone dialler application which is designed to help blind and visually impaired people make phone calls. The new mobile phone dialler application is developed as a windows phone application to facilitate entering information to touch screen mobile phones by blind people. This application is advantageous through its innovative concept, its simplicity and its availability at an affordable cost. Feedback from users showed that this new application is easy to use and solves many problems of voice recognition applications such as inaccuracy, slowness and interpretation of unusual voices. In addition, this application has increased the users ability to dial phone numbers more independently and less stressfully.

Download Full-text