J
Jayakanth Kunhoth
Researcher at Qatar University
Publications - 11
Citations - 174
Jayakanth Kunhoth is an academic researcher from Qatar University. The author has contributed to research in topics: Computer science & Usability. The author has an hindex of 2, co-authored 6 publications receiving 39 citations.
Papers
More filters
Journal ArticleDOI
Indoor positioning and wayfinding systems: a survey
TL;DR: This article reviews different computer vision-based indoor navigation and positioning systems along with indoor scene recognition methods that can aid the indoor navigation, and investigates and contrasts the different navigation systems in each category.
Journal ArticleDOI
Comparative analysis of computer-vision and BLE technology based indoor navigation systems for people with visual impairments
TL;DR: Examining the performance and usability of two computer-vision based systems and BLE-based systems for assistive systems for people with visual impairments shows that QRNav and CamNav system is more efficient than BLE based system in terms of accuracy and usability.
Journal ArticleDOI
Smartphone-based food recognition system using multiple deep CNN models
TL;DR: A smartphone-based system for recognizing the food dishes as well as fruits for children with visual impairments, and a new deep convolutional neural network model for food recognition using the fusion of two CNN architectures are proposed.
Journal ArticleDOI
CamNav: a computer-vision indoor navigation system
TL;DR: The techniques of the system that improve the recognition accuracy of an existing system that uses oriented FAST and rotated BRIEF as part of its location-matching procedure employ multiscale local binary pattern (MSLBP) features to recognize places.
Proceedings ArticleDOI
A vision-based zebra crossing detection method for people with visual impairments
Younes Akbari,Hanadi Hassen,Nandhini Subramanian,Jayakanth Kunhoth,Somaya Al-Maadeed,Wael K.M. Alhajyaseen +5 more
TL;DR: The use of multiple convolutional neural networks (CNNs) by utilizing wavelet transform subbands as inputs in which networks are trained to detect zebra crossing are introduced.