Edge-Deployed Smart Wearable Glasses with Vision-Ultrasonic Late Fusion and Audio Feedback for Assistive Navigation

Authors

  • M.Pradeep Shri Vishnu Engineering College for Women, India
  • Aruna Ajjarapu Malla Reddy (MR) Deemed to be University, India
  • M. Supriya Geethanjali College of Engineering and Technology, India
  • V. Jyothi Vardhaman College of Engineering, India
  • G. Vijaya Nirmala CVR College of Engineering, India
  • Radhika Peeriga Koneru Lakshmaiah Education Foundation, India
  • A. Athiraja Saveetha Engineering College, India
  • N. Rajeswaran School of Engineering Technology & AI, MNR University, India

DOI:

https://doi.org/10.55003/ETH.430403

Keywords:

Assistive Navigation, Wearable Edge AI, Object Detection, Ultrasonic Proximity Sensing, Late Fusion, Audio Feedback, Raspberry Pi

Abstract

This study presents a feasibility prototype of edge-deployed wearable glasses that combines camera-based object detection, ultrasonic proximity sensing, and bone-conduction audio feedback for visually impaired users. The revision narrows the contribution to system-level integration and evidence-controlled reporting rather than claiming a new object-detection architecture. The archived dataset records contain 3,250 public-source images and 550 independently captured live frames distributed across six operational classes. An Ultralytics YOLO detector was trained for 50 epochs at 416 × 416 resolution and executed on a Raspberry Pi 4. The retained training plot indicates approximately 0.49 mAP@0.5 and 0.21 mAP@0.5:0.95 at the final epoch; class-wise field results are reported separately because the original “accuracy” formulation was an IoU/Jaccard expression. The reported frame-processing time was 300 ms (approximately 3.3 FPS), which is adequate for static or slowly changing alerts but is not established as safe real-time navigation in dynamic traffic. Seven battery trials yielded 6.2–7.5 h of operation (mean 6.9 h). Preliminary feedback from 10 participants produced a mean overall rating of 4.4/5; because the archived package did not include participant-level responses or an ethics approval identifier, these observations are treated as formative usability evidence rather than clinical validation.

References

[1] World Health Organization. “Blindness and vision impairment.” who.int. https://www.who.int/news-room/ fact-sheets/detail/blindness-and-visual-impairment (Jul. 11, 2026).

[2] A. D. P. D. Santos, A. H. G. Suzuki, F. O. Medola, and A. Vaezipour, “A Systematic Review of Wearable Devices for Orientation and Mobility of Adults With Visual Impairment and Blindness,” IEEE Access, vol. 9, pp. 162306–162324, 2021, doi: 10.1109/ACCESS.2021.3132887.

[3] F. E. -z. El-Taher, A. Taha, J. Courtney, and S. McKeever, “A Systematic Review of Urban Navigation Systems for Visually Impaired People,” Sensors, vol. 21, no. 9, 2021, Art. no. 3103, doi: 10.3390/s21093103.

[4] M. Hersh, “Wearable Travel Aids for Blind and Partially Sighted People: A Review with a Focus on Design Issues,” Sensors, vol. 22, no. 14, 2022, Art. no. 5454, doi: 10.3390/s22145454.

[5] M. D. Messaoudi, B. -A. J. Menelas, and H. Mcheick, “Review of Navigation Assistive Tools and Technologies for the Visually Impaired,” Sensors, vol. 22, no. 20, 2022, Art. no. 7888, doi: 10.3390/s22207888.

[6] P. Theodorou, K. Tsiligkos, and A. Meliones, “Multi-Sensor Data Fusion Solutions for Blind and Visually Impaired: Research and Commercial Navigation Applications for Indoor and Outdoor Spaces,” Sensors, vol. 23, no. 12, 2023, Art. no. 5411, doi: 10.3390/s23125411.

[7] E. Casanova, D. Guffanti, and L. Hidalgo, “Technological Advancements in Human Navigation for the Visually Impaired: A Systematic Review,” Sensors, vol. 25, no. 7, 2025, Art. no. 2213, doi: 10.3390/s25072213.

[8] J. Bai, Z. Liu, Y. Lin, Y. Li, S. Lian, and D. Liu, “Wearable Travel Aid for Environment Perception and Navigation of Visually Impaired People,” Electronics, vol. 8, no. 6, 2019, Art. no. 697, doi: 10.3390/electronics8060697.

[9] Y. H. Lee and G. Medioni, “RGB-D camera based wearable navigation system for the visually impaired,” Computer Vision and Image Understanding, vol. 149, pp. 3–20, 2016, doi: 10.1016/j.cviu.2016.03.019.

[10] Z. Chen, X. Liu, M. Kojima, Q. Huang, and T. Arai, “A Wearable Navigation Device for Visually Impaired People Based on the Real-Time Semantic Visual SLAM System,” Sensors, vol. 21, no. 4, 2021, Art. no. 1536, doi: 10.3390/s21041536.

[11] H. Son and J. Weiland, “Wearable System to Guide Crosswalk Navigation for People With Visual Impairment,” Frontiers in Electronics, vol. 2, 2022, Art. no. 790081, doi: 10.3389/felec.2021.790081.

[12] F. Barontini, M. G. Catalano, L. Pallottino, B. Leporini, and M. Bianchi, “Integrating Wearable Haptics and Obstacle Avoidance for the Visually Impaired in Indoor Navigation: A User-Centered Approach,” IEEE Transactions on Haptics, vol. 14, no. 1, pp. 109–122, 2021, doi: 10.1109/TOH.2020.2996748.

[13] R. Jafri and M. M. Khan, “User-centered design of a depth data based obstacle detection and avoidance system for the visually impaired,” Human-centric Computing and Information Sciences, vol. 8, 2018, Art. no. 14, doi: 10.1186/s13673-018-0134-9.

[14] M. M. Bala, D. N. Vasundhara, A. Haritha, and CH. V. K. N. S. N. Moorthy, “Design, development and performance analysis of cognitive assisting aid with multi sensor fused navigation for visually impaired people,” Journal of Big Data, vol. 10, 2023, Art. no. 21, doi: 10.1186/s40537-023-00689-5.

[15] Z. Li, F. Han, and K. Zheng, “An RGB-D Camera-Based Wearable Device for Visually Impaired People: Enhanced Navigation with Reduced Social Stigma,” Electronics, vol. 14, no. 11, 2025, Art. no. 2168, doi: 10.3390/electronics14112168.

[16] A. Noor, H. Almukhalfi, A. Souza, and T. H. Noor, “Towards a Real-Time Indoor Object Detection for Visually Impaired Users Using Raspberry Pi 4 and YOLOv11: A Feasibility Study,” Computer Modeling in Engineering & Sciences, vol. 144, no. 3, pp. 3085–3111, 2025, doi: 10.32604/cmes.2025.068393.

[17] S. N. Katkade, R. R. Manza, and C. Pattebahadur, “YOLOv5-Based Object Detection System for Visually Impaired Individuals Using Raspberry Pi,” Artificial Intelligence and Applications, vol. 4, no. 2, pp. 256–264, 2025, doi: 10.47852/bonviewAIA52024434.

[18] A. Yang, N. Tamkittikhun, G. Hamilton-Fletcher, V. Ramdhanie, T. Vu, and M. Beheshti, “Evaluating the efficacy of UNav: A computer vision-based navigation aid for persons with blindness or low vision,” Assistive Technology, vol. 37, no. 6, pp. 459–473, 2025, doi: 10.1080/10400435.2024.2382113.

[19] B. Chaudary, S. Pohjolainen, S. Aziz, L. Arhippainen, and P. Pulli, “Teleguidance-based remote navigation assistance for visually impaired and blind people—usability and user experience,” Virtual Reality, vol. 27, pp. 141–158, 2023, doi: 10.1007/s10055-021-00536-z.

[20] T. -Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár, and C. L. Zitnick, “Microsoft COCO: Common Objects in Context,” in Proc. 13th European Conference on Computer Vision (ECCV 2014), Zurich, Switzerland, Sep. 6–12, 2014, pp. 740–755, doi: 10.1007/978-3-319-10602-1_48.

[21] A. Kuznetsova, H. Rom, N. Alldrin, J. Uijlings, I. Krasin, J. Pont-Tuset, S. Kamali, S. Popov, M. Malloci, A. Kolesnikov, T. Duerig, and V. Ferrari, “The Open Images Dataset V4,” International Journal of Computer Vision, vol. 128, no. 7, pp. 1956–1981, 2020, doi: 10.1007/s11263-020-01316-z.

Downloads

Published

2026-11-20

How to Cite

[1]
M.Pradeep, “Edge-Deployed Smart Wearable Glasses with Vision-Ultrasonic Late Fusion and Audio Feedback for Assistive Navigation”, Eng. & Technol. Horiz., vol. 43, no. 4, p. 430403, Nov. 2026.