Smart Wearable Vision-Assistance System for Visually Impaired Using Edge-Based Deep Learning

Harika B; Tulja Yerram; Manasa Katukuri; Rajesh Mitukula

doi:10.31127/tuje.1869785

Smart Wearable Vision-Assistance System for Visually Impaired Using Edge-Based Deep Learning

Abstract

Assistive technologies based on computer vision have a huge potential in improving mobility of visually impaired people. However, they are not very widely adopted because they depend on high-power processors, cloud access, or complicated sensor configurations. This paper outlines a low-cost and lightweight wearable vision-assist system that is completely edge-based and provides real-time information in the environment. The framework is constructed using the Raspberry Pi Zero 2W and a lightweight object detection model optimized to run on a monocular camera on the device using the Tensorflow Lite. The design proposed offers object identification, rough distance estimation, and spatial position (right, left, centre) with audio feedback in real-time to enhance MSIA both indoors and outdoors. Experimental analysis demonstrates a mean detection rate of 92%, spatial localization rate of 85% and audio feedback latency of below 2 seconds at a power consumption in the range of less than 5W. These findings indicate that implementing effective assistive vision systems on ultra-low-power embedded systems is achievable and can be used in practice as a portable solution for everyday use.

Keywords

References

Avitia, D., Baldwin, J., McFadden, I., Rowland, B., Rodriguez, P., & Pennington, C. G. (2024). Blindness and visual impairment. Make it Count, 1.
Etya’ale, D. (2023). Blindness and Vision Impairment. Global Health Essentials, 209–213. https://doi.org/10.1007/978-3-031-33851-9_31
Bourne, R., Price, H., Stevens, G., & GBD Vision Loss Expert Group, f. t. (2012). Global Burden of Visual Impairment and Blindness. Archives of Ophthalmology, 130(5). https://doi.org/10.1001/archophthalmol.2012.1032
Abdulhussein, D., & Abdul Hussein, M. (2022). WHO Vision 2020: Have We Done It? Ophthalmic Epidemiology, 30(4), 331–339. https://doi.org/10.1080/09286586.2022.2127784
(Ed.). (2022). Regional consultation on the WHO-UNICEF global report on assistive technology. Eastern Mediterranean Health Journal, 28(11), 847–848. https://doi.org/10.26719/2022.28.11.847
Doss, A. S. A., Lingampally, P. K., Nguyen, G. M. T., & Schilberg, D. (2023). A comprehensive review of wearable assistive robotic devices used for head and neck rehabilitation. Results in Engineering, 19, 101306. https://doi.org/10.1016/j.rineng.2023.101306
Simić, M., & Stojanović, G. M. (2024). Wearable device for personalized EMG feedback-based treatments. Results in Engineering, 23, 102472. https://doi.org/10.1016/j.rineng.2024.102472
Khasnabis, C., & Motsch, K. H. (2008). The participatory development of international guidelines for CBR. Leprosy Review, 79(1), 17–29. https://doi.org/10.47276/lr.79.1.17

Senjam, S. S., Manna, S., Kishore, J., et al. (2023). Assistive technology usage, unmet needs and barriers to access: A sub-population-based study in India. The Lancet Regional Health – Southeast Asia, 15, 100213. https://doi.org/10.1016/j.lansea.2023.100213
(Ed.). (2025). Accelerating access to assistive technology. https://doi.org/10.2471/b09433
Hicks, S. L., Wilson, I., Muhammed, L., Worsfold, J., Downes, S. M., & Kennard, C. (2013). A depth-based head-mounted visual display to aid navigation in partially sighted individuals. PLoS ONE, 8(7), e67695. https://doi.org/10.1371/journal.pone.0067695
The Smart Glasses Using Iot And Unity. (2021). Turkish Journal of Computer and Mathematics Education (TURCOMAT), 12(11), 4823-4830. https://doi.org/10.17762/turcomat.v12i11.6658
Kumar, A., Kumar, V., & Bhadauria, A. (2025). Real-time hybrid machine learning-based next-generation intrusion detection system for edge computing networks. Turkish Journal of Engineering, 9(3), 600–611. https://doi.org/10.31127/tuje.1630410
Ahmetovic, D., Gleason, C., Ruan, C., Kitani, K., Takagi, H., & Asakawa, C. (2016). NavCog: A navigational cognitive assistant for the blind. In Proceedings of the 18th International Conference on Human-Computer Interaction with Mobile Devices and Services (pp. 90–99).ACM https://doi.org/10.1145/2935334.2935361
Piccardi, L., et al. (2007). WearCam: A head-mounted wireless camera for monitoring gaze attention. In Proceedings of the IEEE RO-MAN Symposium (pp. 594–598). https://doi.org/10.1109/ROMAN.2007.4415154
Poggi, M., Nanni, L., & Mattoccia, S. (2015). Crosswalk recognition through point-cloud processing and deep learning suited to a wearable mobility aid. In New Trends in Image Analysis and Processing – ICIAP 2015 Workshops (LNCS 9281). Springer. https://doi.org/10.1007/978-3-319-23222-5_35
Niu, L., et al. (2017). A wearable assistive technology for the visually impaired with door-knob detection and real-time feedback. In Proceedings of the IEEE International Conference on Computer Vision Workshops. https://doi.org/10.1109/ICCVW.2017.177
Yang, K., et al. (2018). Unifying terrain awareness for the visually impaired through real-time semantic segmentation. Sensors, 18(5), 1506. https://doi.org/10.3390/s18051506
Yiğit, G. (2025a). Crowd detection: Leveraging YOLO for human recognition. Turkish Journal of Engineering, 9(3), 571–577. https://doi.org/10.31127/tuje.1627839
Bhavana, G., & Mitukula, R. (2025). A hybrid cluster-based energy-efficient routing framework for underwater wireless sensor networks. Turkish Journal of Engineering, 10(1), 244–251. https://doi.org/10.31127/tuje.1809878
Kadve, G., Chowdhury, A., Singh, V. K., & Pal, A. (2025). Engineering a multi-model fallback system for edge devices. Results in Engineering, 26, 105165. https://doi.org/10.1016/j.rineng.2025.105165
Alakuş, O., & Türkoğlu, İ. (2025). Analysis of explosion images obtained with high-speed camera with image processing and prediction of explosion loads. Turkish Journal of Engineering, 9(3), 479–489. https://doi.org/10.31127/tuje.1524358
Yiğit, G. (2025b). A comparative study of deep learning approaches for human action recognition. Turkish Journal of Engineering, 9(2), 281–289. https://doi.org/10.31127/tuje.1579795
Vinoth, K., & Sasikumar, P. (2024). Lightweight object detection in low-light conditions: Pixel-wise depth refinement and optimization. Results in Engineering, 23, 102510. https://doi.org/10.1016/j.rineng.2024.102510
Kadve, G., Chowdhury, A., Singh, V. K., & Pal, A. (2025). Engineering a multi model fallback system for edge devices. Results in Engineering, 26, 105165. https://doi.org/10.1016/j.rineng.2025.105165
Van, C. N., Tran, D.-N., Long, T. T., Thao, N. G. M., & Tran, D.-T. (2025). Hybrid feature selection for real-time road surface classification on low-end hardware: A machine learning approach. Results in Engineering, 27, 105693. https://doi.org/10.1016/j.rineng.2025.105693

Details

Primary Language

English

Subjects

Reinforcement Learning, Communications Engineering (Other)

Journal Section

Research Article

Authors

Harika B ^*
0009-0000-8542-1231
India

Tulja Yerram
0009-0000-7349-2649
India

Manasa Katukuri
0009-0002-5407-2635
India

Rajesh Mitukula
0000-0002-6365-4525
India

Publication Date

July 6, 2026

Submission Date

January 22, 2026

Acceptance Date

June 4, 2026

Published in Issue

Year 2026 Volume: 10 Number: 3

DOI

https://doi.org/10.31127/tuje.1869785

IZ

https://izlik.org/JA44TZ26FD

Cite

RIS / Bibtex

APA

B, H., Yerram, T., Katukuri, M., & Mitukula, R. (2026). Smart Wearable Vision-Assistance System for Visually Impaired Using Edge-Based Deep Learning. Turkish Journal of Engineering, 10(3), 1026-1033. https://doi.org/10.31127/tuje.1869785

AMA

1.B H, Yerram T, Katukuri M, Mitukula R. Smart Wearable Vision-Assistance System for Visually Impaired Using Edge-Based Deep Learning. TUJE. 2026;10(3):1026-1033. doi:10.31127/tuje.1869785

Chicago

B, Harika, Tulja Yerram, Manasa Katukuri, and Rajesh Mitukula. 2026. “Smart Wearable Vision-Assistance System for Visually Impaired Using Edge-Based Deep Learning”. Turkish Journal of Engineering 10 (3): 1026-33. https://doi.org/10.31127/tuje.1869785.

EndNote

B H, Yerram T, Katukuri M, Mitukula R (July 1, 2026) Smart Wearable Vision-Assistance System for Visually Impaired Using Edge-Based Deep Learning. Turkish Journal of Engineering 10 3 1026–1033.

IEEE

[1]H. B, T. Yerram, M. Katukuri, and R. Mitukula, “Smart Wearable Vision-Assistance System for Visually Impaired Using Edge-Based Deep Learning”, TUJE, vol. 10, no. 3, pp. 1026–1033, July 2026, doi: 10.31127/tuje.1869785.

ISNAD

B, Harika - Yerram, Tulja - Katukuri, Manasa - Mitukula, Rajesh. “Smart Wearable Vision-Assistance System for Visually Impaired Using Edge-Based Deep Learning”. Turkish Journal of Engineering 10/3 (July 1, 2026): 1026-1033. https://doi.org/10.31127/tuje.1869785.

JAMA

1.B H, Yerram T, Katukuri M, Mitukula R. Smart Wearable Vision-Assistance System for Visually Impaired Using Edge-Based Deep Learning. TUJE. 2026;10:1026–1033.

MLA

B, Harika, et al. “Smart Wearable Vision-Assistance System for Visually Impaired Using Edge-Based Deep Learning”. Turkish Journal of Engineering, vol. 10, no. 3, July 2026, pp. 1026-33, doi:10.31127/tuje.1869785.

Vancouver

1.Harika B, Tulja Yerram, Manasa Katukuri, Rajesh Mitukula. Smart Wearable Vision-Assistance System for Visually Impaired Using Edge-Based Deep Learning. TUJE. 2026 Jul. 1;10(3):1026-33. doi:10.31127/tuje.1869785