TY - GEN
T1 - Towards Seamless Sidewalk Navigation
T2 - 2nd International Conference on Advances in Smart Computing and Information Security, ASCIS 2023
AU - Rustamov, Zahiriddin
AU - Rustamov, Jaloliddin
AU - Parambil, Medha Mohan Ambali
AU - Ahmed, Soha Glal
AU - Turaev, Sherzod
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
PY - 2024
Y1 - 2024
N2 - Undeniably, visual impairment severely affects the quality of life and impacts many daily activities of visually impaired individuals. Visually impaired individuals have difficulty navigating on side-walks. There are many assistive tools available for navigational assistance for visually impaired individuals. The majority of assistive technologies for sidewalk navigation in visually impaired individuals rely on server-based models, introducing challenges of latency, data costs, and privacy. This research investigates on-device machine learning as an alternative, emphasizing real-time feedback and user experience. We assessed algorithms, including EfficientDet-Lite, SSD, and YOLOv4, optimizing them for mobile deployment. The resultant Android application, embedding the top-performing model, demonstrated the potential for immediate, server-independent feedback. This research not only bridges a notable gap in the literature but also paves the way for research on more accessible, immediate, and discreet navigation tools for the visually impaired community.
AB - Undeniably, visual impairment severely affects the quality of life and impacts many daily activities of visually impaired individuals. Visually impaired individuals have difficulty navigating on side-walks. There are many assistive tools available for navigational assistance for visually impaired individuals. The majority of assistive technologies for sidewalk navigation in visually impaired individuals rely on server-based models, introducing challenges of latency, data costs, and privacy. This research investigates on-device machine learning as an alternative, emphasizing real-time feedback and user experience. We assessed algorithms, including EfficientDet-Lite, SSD, and YOLOv4, optimizing them for mobile deployment. The resultant Android application, embedding the top-performing model, demonstrated the potential for immediate, server-independent feedback. This research not only bridges a notable gap in the literature but also paves the way for research on more accessible, immediate, and discreet navigation tools for the visually impaired community.
KW - assistive technologies
KW - machine learning
KW - obstacle detection
KW - sidewalk
KW - visually impaired
UR - http://www.scopus.com/inward/record.url?scp=85193567635&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85193567635&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-58604-0_26
DO - 10.1007/978-3-031-58604-0_26
M3 - Conference contribution
AN - SCOPUS:85193567635
SN - 9783031586033
T3 - Communications in Computer and Information Science
SP - 358
EP - 365
BT - Advancements in Smart Computing and Information Security - 2nd International Conference, ASCIS 2023, Revised Selected Papers
A2 - Rajagopal, Sridaran
A2 - Popat, Kalpesh
A2 - Meva, Divyakant
A2 - Bajeja, Sunil
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 7 December 2023 through 9 December 2023
ER -