A Blind Navigation Algorithm Based on The PPYOLO Model
Authors: 
Lin Zhao, Lihang ZhangAuthors Info & Claims
Lin Zhao, Lihang ZhangAuthors Info & ClaimsArticle No.: 35, Pages 1 - 5
Abstract
Abstract: This study aims to address challenges faced by visually impaired individuals in daily travel, such as inability to perceive traffic lights, navigate obstacles, and locate tactile pavings. The goal is to develop a specialized travel assistance algorithm for visually impaired individuals. After thorough research on existing technologies including GPS, IrDA, AI-assisted technology, mobile applications, and object recognition, and analyzing their limitations, we proposed a blind navigation algorithm based on the PP-YOLO model. This algorithm combines traffic sign recognition, object recognition, and tactile paving recognition to achieve multi-task image recognition. Through dataset preparation, data annotation, and parameter adjustment, the algorithm was implemented on portable devices like mobile phones and wearable devices. Laboratory verification and field testing confirmed that the algorithm provides accurate navigation guidance and ensures safety for visually impaired individuals during travel. With a frame rate of 8fps, the algorithm achieved a recognition rate of 96.3% within an 8m range on portable devices; in low-light environments, the object recognition accuracy within the same range reached 94%. Even at complex intersections with a width of 30m, the recognition rate was 85%. This research outcome presents an innovative technical solution for travel assistance technology for visually impaired individuals and offers new research ideas for similar studies. The PP-YOLO model was chosen for its superior speed and accuracy in object detection tasks, crucial for real-time navigation. The model was streamlined for use on portable devices through lightweight design and hardware acceleration features such as NPU and GPU. The challenge with this approach involves some risk of recognition errors, similar to those in autonomous driving technology. However, considering the slower walking speed of visually impaired individuals, the consequences of these errors are mitigated. Thus, the project provides an additional mobility option for visually impaired individuals, providing more freedom than without it.
References
[1]
Ma Wenjie, Zhang Xuanxiong. Research on Blind Path and Blind Path Obstacle Recognition Algorithm Based on Deep Learning [J/OL]. Electronic Science and Technology, 1-10 [2023-03-21]. https://doi.org/10.16180/j.cnki.issn1007-7820.2024.03.010.
[2]
Y. Yamanaka, E. Takaya, and S. Kurihara, Tactile Tile Detection Integrated with Ground Detection using an RGB-Depth Sensor [J], Proceedings of the 12th International Conference on Agents and Artificial Intelligence, Valletta, Malta, 2020, pp. 750–757.
[3]
Y. Ito, C. Premachandra, S. Sumathipala, H. W. H. Premachandra, and B. S. Sudantha, Tactile Paving Detection by Dynamic Thresholding Based on HSV Space Analysis for Developing a Walking Support System [J], IEEE Access, vol. 9, pp. 20358–20367, 2021.
[4]
R. C. Joshi, S. Yadav, M. K. Dutta, and C. M. Travieso-Gonzalez, Efficient Multi-Object Detection and Smart Navigation Using Artificial Intelligence for Visually Impaired People, Entropy [J], vol. 22, no. 9, p. 941, Aug. 2020.
[5]
A. R. See, B. G. Sasing, and W. D. Advincula, A Smartphone-Based Mobility Assistant Using Depth Imaging for Visually Impaired and Blind [J], Appl. Sci, vol. 12, no. 6, p. 2802, Mar. 2022.
[6]
D. Lee and J. Cho, Automatic Object Detection Algorithm-Based Braille Image Generation System for the Recognition of Real-Life Obstacles for Visually Impaired People, Sensors [J], vol. 22, no. 4, p. 1601, Feb. 2022.
[7]
Y. S. Taspinar and M. Selek, Complex Support System for Visually Impaired Individuals [J], PLUSBASE Akad Organ. VE DANISMANLIK LTDSTI, p. 1, Dec. 2022.
[8]
M. C. Ghilardi, R. C. O. Macedo, I. H. Manssour, "A new Approach for Automatic Detection of Tactile Paving Surfaces in Sidewalks" [J], Procedia Computer Science, Vol. 80, pp. 662-672, 2016.
[9]
H. S.AI-Khalifa, "Utilizing QR Code and Mobile Phones for Blinds and Visually Impaired People" [J], International Conference on Computers Helping People with Special Need, pp. 1065-1069, Jul. 2008.
[10]
Wei Tong, Yuan Lei. High Real-Time Blind Path Recognition Algorithm Based on Boundary Tracking [J]. Optics and Precision Engineering, 2017, 44(07): 676-684+750.
Index Terms
- A Blind Navigation Algorithm Based on The PPYOLO Model
Recommendations
A proposed indoor navigation system for blind individuals
iiWAS '11: Proceedings of the 13th International Conference on Information Integration and Web-based Applications and ServicesVisual impairment is one of the disabilities that could injure people congenitally or adventitiously. The number of individuals who suffer from visual impairment is increasing rapidly. Therefore, there is an urgent need to develop assistive technologies ...
Hacking Blind Navigation
CHI EA '19: Extended Abstracts of the 2019 CHI Conference on Human Factors in Computing SystemsIndependent navigation in unfamiliar and complex environments is a major challenge for blind people. This challenge motivates a multi-disciplinary effort in the CHI community aimed at developing assistive technologies to support the orientation and ...
Deep learning-based application for indoor wayfinding assistance navigation
AbstractThere is an increasing need to develop new adaptive technologies and new wayfinding assistance systems for blind and visually impaired persons in order to improve their daily lives. To address this need, we propose in this paper to develop a new ...
Comments
Information & Contributors
Information
Published In
December 2023
292 pages
ISBN:9798400709401
DOI:10.1145/3632314
Copyright © 2023 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 09 December 2023
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
ISIA 2023
ISIA 2023: 2023 International Conference on Intelligent Sensing and Industrial Automation
December 9 - 10, 2023
Virtual Event, China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 28Total Downloads
- Downloads (Last 12 months)20
- Downloads (Last 6 weeks)3
Reflects downloads up to 03 Mar 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format