Deakin University
Browse

File(s) under permanent embargo

Navigational path detection for the visually impaired using fully convolutional networks

Version 2 2024-06-04, 02:20
Version 1 2018-07-29, 14:09
conference contribution
posted on 2024-06-04, 02:20 authored by K Saleh, RA Zeineldin, M Hossny, S Nahavandi, NA El-Fishawy
© 2017 IEEE. In this paper a novel approach for navigational path detection problem for the visually impaired was presented. A deep learning model based on state-of-the-art fully convolution neural networks have been proposed that can accurately semantically segment any navigational areas on pixel-wise level in different scenes without any prior assumptions about the environment of the scene such as textures or specific appearance cues. The proposed approach have been evaluated on two different publicly available dataset and have achieved a pixel accuracy of 91% over the testing images dataset. Furthermore, the performance of the proposed approach have been compared against other commonly used approach for the problem of predicting navigational areas in input RGB images, and the proposed approach outperformed it with more than 14%, 11% and 10% on the mean intersection over union, mean accuracy and pixel accuracy evaluation metrics respectively.

History

Pagination

1399-1404

Location

Banff, Canada

Start date

2017-10-05

End date

2017-10-08

ISBN-13

9781538616451

Language

eng

Publication classification

E1 Full written paper - refereed

Copyright notice

2017, IEEE

Title of proceedings

SMC 2017 : Proceedings of IEEE International Conference on Systems, Man, and Cybernetics

Event

Systems, Man, and Cybernetics. International Conference (2017 : Banff, Canada)

Publisher

IEEE

Place of publication

Piscataway, N.J.

Usage metrics

    Research Publications

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC