Obstacle Detection System for Navigation Assistance of Visually Impaired People Based on Deep Learning Techniques
Sensors · 01.06.2023 · 23 (11) · 5262
DOI: 10.3390/s23115262 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 01.06.2023. Verfasst von Yahia Said und 4 weiteren Autor:innen. Beteiligte Einrichtung: Remote Sensing Unit, College of Engineering, Northern Border University, Arar 91431, Saudi Arabia. Hauptthemen laut MEDLINE: Deep Learning, Persons with Visual Disabilities, Self-Help Devices, Sensory Aids. Die Arbeit wurde bisher 47-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: King Salman Center for Disability Research.
Abstract (Originalsprache)
Visually impaired people seek social integration, yet their mobility is restricted. They need a personal navigation system that can provide privacy and increase their confidence for better life quality. In this paper, based on deep learning and neural architecture search (NAS), we propose an intelligent navigation assistance system for visually impaired people. The deep learning model has achieved significant success through well-designed architecture. Subsequently, NAS has proved to be a promising technique for automatically searching for the optimal architecture and reducing human efforts for architecture design. However, this new technique requires extensive computation, limiting its wide use. Due to its high computation requirement, NAS has been less investigated for computer vision tasks, especially object detection. Therefore, we propose a fast NAS to search for an object detection framework by considering efficiency. The NAS will be used to explore the feature pyramid network and the prediction stage for an anchor-free object detection model. The proposed NAS is based on a tailored reinforcement learning technique. The searched model was evaluated on a combination of the Coco dataset and the Indoor Object Detection and Recognition (IODR) dataset. The resulting model outperformed the original model by 2.6% in average precision (AP) with acceptable computation complexity. The achieved results proved the efficiency of the proposed NAS for custom object detection.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Remote Sensing Unit, College of Engineering, Northern Border University, Arar 91431, Saudi Arabia.
- King Salman Center for Disability Research, Riyadh 11614, Saudi Arabia.
- Laboratory of Electronics and Microelectronics (LR99ES30), University of Monastir, Monatir 5019, Tunisia.
- College of Computer Sciences, King Khalid University, Abha 62529, Saudi Arabia.
- School of Computer Science, Umm Al-Qura University, Mecca 24382, Saudi Arabia.
- Department of Electrical Engineering, College of Engineering, Jouf University, Sakaka 72388, Saudi Arabia.
ORCID-Profile: Yahia Said, Marwan Ali Albahar, Ahmed Ben Atitallah, Yazan Ahmad Alsariera
Förderung
- King Salman Center for Disability Research
Zitieren
APA
Said, Y., Atri, M., Albahar, M. A., Ben Atitallah, A., & Alsariera, Y. A. (2023). Obstacle Detection System for Navigation Assistance of Visually Impaired People Based on Deep Learning Techniques. Sensors, 23(11), 5262. https://doi.org/10.3390/s23115262
Vancouver
Said Y, Atri M, Albahar MA, Ben Atitallah A, Alsariera YA. Obstacle Detection System for Navigation Assistance of Visually Impaired People Based on Deep Learning Techniques. Sensors. 2023;23(11):5262. doi:10.3390/s23115262
BibTeX
@article{Said2023,
author = {Said, Yahia and Atri, Mohamed and Albahar, Marwan Ali and Ben Atitallah, Ahmed and Alsariera, Yazan Ahmad},
title = {Obstacle Detection System for Navigation Assistance of Visually Impaired People Based on Deep Learning Techniques},
journal = {Sensors},
year = {2023},
volume = {23},
number = {11},
pages = {5262},
doi = {10.3390/s23115262}
}
EUVIMED