Real-Time Obstacle Detection and Auditory Directional Guidance for the Visually Impaired on Mobile
Article Sidebar
Main Article Content
Abstract
Visually impaired individuals frequently encounter difficulties in perceiving their surrounding environment and identifying obstacles in close proximity. This research presents an Android application that functions as a Directional Guidance and Obstacle Alert System. The system utilizes the YOLOv8s (Small) algorithm combined with an input image resolution of 480x480 pixels and employs Half-Precision Quantization (Float16) to optimize processing efficiency on mobile device GPUs. The system operates by detecting objects and determining their relative position (Left, Center, or Right) with respect to the user through Geometric Estimation. Feedback is provided via a Text-to-Speech synthesis system. Experimental results demonstrate that the Float16 technique effectively reduces latency while maintaining high accuracy, making it a practical assistive tool.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
Z. Q. Zhao, P. Zheng, S. T. Xu and X. Wu, “Object Detection With Deep Learning: A Review,” IEEE Transactions on Neural Networks and Learning Systems, Vol. 30, No. 11, pp. 3212–3232, 2019.
S. Kumar, R. Singh and A. K. Singh, “Indoor and Outdoor Navigation System for Visually Impaired People Using Deep Learning,” 2021 6th International Conference on Communication and Electronics Systems (ICCES), Coimbatore, India, pp. 1024–1029, 2021.
J. Terven and D. Cordova-Esparza, “A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS,” Machine Learning and Knowledge Extraction, Vol. 5, No. 4, pp. 1680–1716, 2023.
Y. Wang, Z. Li and J. Liu, “Real-time Object Detection on Android Devices using TensorFlow Lite,” 2021 IEEE 4th International Conference on Electronics Technology (ICET), Chengdu, China, pp. 345–349, 2021.
A. Bewley, Z. Ge, L. Ott, F. Ramos and B. Upcroft, “Simple online and real-time tracking,” 2016 IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, USA, pp. 3464–3468, 2016.
H. S. Khare, P. Sharma and M. Sharma, “Monocular Distance Estimation for Visually Impaired People Using Deep Learning,” 2021 International Conference on Artificial Intelligence and Smart Systems (ICAIS), Coimbatore, India, pp. 1205–1210, 2021.
A. F. A. H. Al-Shamayleh et al., “Real-Time Object Detection System for Visually Impaired People Using YOLOv3 Algorithm,” 2020 11th International Conference on Information and Communication Systems (ICICS), Irbid, Jordan, pp. 130–135, 2020.
M. Sultana, A. Sufian and P. Dutta, “Wearable Object Detection System for the Blind with Audio Feedback,” 2020 IEEE Calcutta Conference (CALCON), Kolkata, India, pp. 42–46, 2020.
B. Kuriakose, R. Shrestha and F. E. Sandnes, “Automated mobility assistance for visually impaired using object detection,” 2022 13th International Conference on Computing Communication and Networking Technologies (ICCCNT), Kharagpur, India, pp. 1–6, 2022.
J. Bai, S. Liu and Z. Zhang, “Design of Audio Feedback for a Computer Vision-Based Travel Aid for the Blind,” IEEE Access, Vol. 10, pp. 45678–45689, 2022.
