Assistive Technology for the Visually Impaired: Optimizing Frame Rate (Freshness) to Improve the Performance of Real-Time Objects Detection Application

Barakat, Basel; Steponenaite, Aiste; Lall, Gurprit S.; Arshad, Kamran; Wassell, Ian J.; Keates, Simeon

Abstract

It has been 100+ years since the world’s first commercial radio station started. This century witnessed several astonishing inventions (e.g. the computer, internet and mobiles) that have shaped the way we work and socialize. With the start of a new decade, it is evident that we are becoming more reliant on these new technologies as the majority of the world population relies on the new technology on a daily basis. As world’s population is becoming reliant on new technologies and we are shaping our lives around it, it is of paramount importance to consider those people who struggle in using the new technologies and inventions. In this paper, we are presenting an algorithm and a framework that helps partially sighted people to locate their essential belongings. The framework integrates state-of-the-art technologies from computer vision, speech recognition and communication queueing theory to create a framework that can be implemented on low computing power platforms. The framework verbally communicates with the users to identify the object they are aiming to find and then notify them when it is within the range.

Citation

Barakat, B., Steponenaite, A., Lall, G. S., Arshad, K., Wassell, I. J., & Keates, S. (2020, July). Assistive Technology for the Visually Impaired: Optimizing Frame Rate (Freshness) to Improve the Performance of Real-Time Objects Detection Application. Presented at 14th International Conference, UAHCI 2020, Held as Part of the 22nd HCI International Conference, HCII 2020, Copenhagen, Denmark

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 14th International Conference, UAHCI 2020, Held as Part of the 22nd HCI International Conference, HCII 2020
• Start Date: Jul 19, 2020
• End Date: Jul 24, 2020
• Online Publication Date: Jul 10, 2020
• Publication Date: 2020
• Deposit Date: Jul 24, 2020
• Publicly Available Date: Jul 11, 2021
• Publisher: Springer
• Pages: 479-492
• Series Title: Lecture Notes in Computer Science
• Series Number: 12189
• Series ISSN: 0302-9743
• Book Title: Universal Access in Human-Computer Interaction. Applications and Practice: Proceedings, Part II
• ISBN: 978-3-030-49107-9
• DOI: https://doi.org/10.1007/978-3-030-49108-6_34
• Public URL: http://researchrepository.napier.ac.uk/Output/2676268
• Related Public URLs: http://2020.hci.international/