Skip to main content

An effective obstacle detection system using deep learning advantages to aid blind and visually impaired navigation

Author name : Ahmed Ben Atitallah
Publication Date : 2024-02-20
Journal Name : Ain Shams Engineering Journal

Abstract

Blind and visually impaired people face different challenges when navigating indoors and outdoors. In this context, we suggest developing an obstacle detection system based on a modified YOLO v5 neural network architecture. The suggested system is capable of recognizing and locating a set of landmark indoor and outdoor objects that are extremely useful for Blind and Visually Impaired (BVI) navigation aids. Training and evaluation experiments were conducted using two datasets: the IODR dataset for indoor object detection and the MS COCO dataset for outdoor object detection. We used several optimization strategies, such as model width scaling, quantization, and channel pruning, to guarantee that the suggested work is implemented in embedded devices in a lightweight manner. The proposed system was successful in achieving results that were extremely competitive in terms of processing time as well as the precision of obstacle detection

Keywords

Obstacle detection, Navigation Assistance, Visually Impaired, Deep Learning, Lightweight implementation

Publication Link

https://doi.org/10.1016/j.asej.2023.102387

Block_researches_list_suggestions

Suggestions to read

HIDS-IoMT: A Deep Learning-Based Intelligent Intrusion Detection System for the Internet of Medical Things
Ahlem . Harchy Ep Berguiga
Generalized first approximation Matsumoto metric
AMR SOLIMAN MAHMOUD HASSAN
Structure–Performance Relationship of Novel Azo-Salicylaldehyde Disperse Dyes: Dyeing Optimization and Theoretical Insights
EBTSAM KHALEFAH H ALENEZY
“Synthesis and Characterization of SnO₂/α-Fe₂O₃, In₂O₃/α-Fe₂O₃, and ZnO/α-Fe₂O₃ Thin Films: Photocatalytic and Antibacterial Applications”
Asma Arfaoui
Contact