An Assist System for Visually Impaired at Indoor Residential Environment using Faster-RCNN

Lin, Wei-Jen; Su, Mu-Chun; Cheng, Wei-Yin; Cheng, Wen-Yu

doi:10.1109/iiai-aai.2019.00231

Cited by 6 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lin et al [61] developed a system combining Deep Learning with a camera to assist visually impaired individuals in identifying objects in their surroundings. By using a smartphone application to inform VIPs about their location and the location of nearby objects, the goal was to create a safe and comfortable indoor environment for these individuals.…”

Section: T4 -Adls (Performing Activities Of Daily Life)mentioning

confidence: 99%

Intelligent Environments and Assistive Technologies For Assisting Visually Impairment People: A Systematic Literature Review

de Souza,

Francisco,

Tavares

et al. 2023

Preprint

View full text Add to dashboard Cite

Intelligent Environments (IE) refer to fisical spaces imbued with pervasive and seamless intelligence, created to proactively support individuals in their daily routines. Developments in technologies such as the Internet of Things (IoT) and Artificial Intelligence (AI) have taken these environments from theoretical notions to practical realities. Simultaneously, the field of Ambient Assisted Living (AAL) has made significant strides. Evolving from Assistive Technology (AT), AAL represents an application of IE that specifically seeks to enable individuals —especially those with disabilities or the elderly— to lead healthier, more independent, and dignified lives through the assistance of technology integrated within their living environments. The confluence of IE and AAL has led to the rise of innovative solutions aimed at enhancing the lives of individuals with special needs,such as the Visually Impaired People (VIP). This research presents a systematic literature review investigating the utilization of IE, underpinned by AAL principles, in supporting VIPs. Initially, a pool of 14,760 studies was obtained from 9 databases, all published up to December 2022. After applying specific inclusion and exclusion criteria, this pool was reduced to 101 articles. Each of these articles was reviewed, analyzed, and categorized into four functional and operating principle categories to address five research questions. The study proposes multiple taxonomies as an approach to holistically synthesize the various technologies and devices categorized in the reviewed articles. Emerging research challenges and trends in this domain are highlighted, with a substantial trend being the escalating use of Deep Learning (DL) techniques. These techniques have been pivotal in the development of systems focused on object detection, path recognition, and navigation for devices, particularly smartphones, geared towards enhancing the lives of VIPs.

show abstract

Section: T4 -Adls (Performing Activities Of Daily Life)mentioning

confidence: 99%