Authors
Deepika Yadav
Department of Computer Science and Information Technology, Mahatma Jyotiba Phule Rohilkhand University, Bareilly , Uttar Pradesh, India
Hemant Yadav
Department of Computer Science and Engineering, Future University, Bareilly, Uttar Pradesh, India
Pooja Yadav
Department of Computer Science and Information Technology, Mahatma Jyotiba Phule Rohilkhand University, Bareilly , Uttar Pradesh, India

Abstract

In this study, an assistive navigation system is proposed for visually impaired pedestrians by combining object detection system You Only Look Once version 5 (YOLOv5), camera, Light Detection and Ranging (LiDAR) sensor, and voice feedback system based on Google Text-to-Speech (gTTS). The proposed system detects the objects around it, estimates the relative position of each object and delivers immediate audio guidance to facilitate safe navigation in urban areas. Using the annotated object detection data, the model was trained and evaluated and achieved a precision of 94.82%, recall of 69.82%, mean Average Precision at 0.5 of 91.57%, and mean Average Precision at 0.5–0.95 of 91.03%. The proposed framework integrates real-time visual perception with distance sensing and speechbased guidance, offering a continuous sense of the environment and enhancing mobility, safety, and user independence, unlike conventional assistive devices.

Keywords

Object Detection Assistive Technology Blind Navigation YOLO Algorithm Voice Integration Google Textto- Speech (gTTS) Pedestrian Safety Deep Learning

References

    World Health Organization. (2019). World report on vision: Executive summary. Accessed: 2026-07-15. Article

    Dongre A. (2020). Visual recognition-based system to assist blind persons. PhD thesis, National College of Ireland, Dublin. Article

    Chen Y., Shen J., & Sawada H. (2023). A wearable assistive system for the visually impaired using object detection, distance measurement and tactile presentation. Intelligence & Robotics, Vol. 3, Issue 3, pp. 420–435. Article

    Patel I., Kulkarni M., & Mehendale N. (2024). Review of sensor-driven assistive device technologies for enhancing navigation for the visually impaired. Multimedia Tools and Applications, Vol. 83, Issue 17, pp. 52171–52195. Article

    Srikanteswara R., Reddy M. C., Himateja M., & Kumar K. M. (2021). Object detection and voice guidance for the visually impaired using a smart app. Recent Advances in Artificial Intelligence and Data Engineering: Select Proceedings of AIDE 2020, pp. 133–144. Springer. Article

    Saravanan R., Nakkeeran R., & Baskar K. (2022). An assistive device based on recent deep learning approach for object detection integrated with audio guidance for visually impaired people. International Journal of Analytical and Experimental Modal Analysis.

    Tavakoli Y. A. (2024). Seeing with sound: Object detection and localization by YOLOv8 and audio feedback for blind individuals. Article

    Alrowais F., Almofarreh M., & Marzouk R. (2026). Enhanced pedestrian walkway object detection using deep learning and pelican optimization algorithm for assisting disabled persons. 16, Scientific Reports. Article

    Zou Z., Chen K., Shi Z., Guo Y., & Ye J. (2023). Object detection in 20 years: A survey. Proceedings of the IEEE, Vol. 111, Issue 3, pp. 257–276. Article

    Lee J., Cha K.-A., & Lee M. (2024). Multi-modal system for walking safety for the visually impaired: Multi-object detection and natural language generation. Applied Sciences, Vol. 14, Issue 17, p. 7643. Article

    Sheela K. S., Kingsly R. J., Bhalaji C.K., Selvalakshmi C.B., Radhika A. (2024). Traffic sign categorization using YOLO algorithm: Leveraging real-time object detection for improved road safety. 9th International Conference on Communication and Electronics Systems, pp. 1547–1553. Article

    Mathivanan P., Abishek N., et al. (2024). Computer vision empowered assistive technology for blind people. IEEE International Conference on Emerging Research in Computational Science, pp. 1–7. Article

    Gao W. (2024). YOLO-based gripping method for industrial robots. International Journal of Computer Applications in Technology, Vol. 75, Issue 1, pp. 48–57. Article

    Gui S., Song S., Qin R., & Tang Y. (2024). Remote sensing object detection in the deep learning era—a review. Remote Sensing, Vol. 16, Issue 2. Article

    Al Amin R., Hasan M., Wiese V., & Obermaisser, R. (2024). FPGA-based real-time object detection and classification system using YOLO for edge computing. IEEE Access, Vol. 12, pp. 73268–73278. Article

    Abdulhaq K., & Ahmed A. A. (2025). Real-time object detection and recognition in embedded systems using open-source computer vision frameworks. International Journal of Electrical Engineering and Sustainability, pp. 103–118. Article

    Tian J., Jin Q., Wang Y., Yang J., Zhang S., & Sun D. (2024). Performance analysis of deep learning-based object detection algorithms on COCO benchmark: A comparative study. Journal of Engineering and Applied Science, Vol. 71, Issue 1, p. 76. Article

    Saiveena K., & Praveen P. (2025). A hybrid deep learning approach for vehicle detection and image segmentation in autonomous driving. 2025 8th International Conference on Computing Methodologies and Communication, pp. 1289–1294. Article

    Li Y., & Feng L. (2026). Global-local collaborative learning: A dynamic and attentive framework for tiny object detection in aerial imagery. IEEE International Conference on Embedded Systems, Mobile Communication and Computing (EMC²), pp. 193–198. Article

    Kumar K., Sharma M., & Sharma R. (2026). A review of YOLO-based realtime fire detection models and applications. IEEE International Conference on Signal Processing and Electronics Design, pp. 96–101. Article

    Ganapathi I. I., Abdelhafez F. O., Velayudhan D., Habtie M. A., Karki H., Al Awadhi K. Y., Dias J., & Werghi N. (2025). Flare: Flare analysis and regression-based estimation. IEEE International Conference on Advances in Data-Driven Analytics and Intelligent Systems, pp. 1–6. Article

    Rahman W., Roy S., & Islam A. (2025). A comprehensive model for advanced road scene understanding: YOLO-CNN fusion for accurate road segmentation and object detection in varied conditions. PhD thesis, Brac University.

    Sun Y., Meng Y., Wang Q., Tang M., Shen T., & Wang Q. (2023). Visible and infrared image fusion for object detection: A survey. International Conference on Image, Vision and Intelligent Systems, pp. 236–248. Springer. Article

    Shabbir N., Ahmed R., Raza M. W., Zeb A., Elahi H., & Waheed H. (2025). Comparative performance and resource utilization analysis of OCR models for number plate recognition on Raspberry Pi 4. IEEE International Conference on Communication Technologies, pp. 1–6. Article

    Wang, J., Xie, Z., & Chen, M. (2025). An intelligent framework for micro-LED defect detection with deep learning. IEEE Sensors Journal, vol. 26, Issue 4, pp. 5749-5756. Article

    Redmon J., Divvala S., Girshick R., & Farhadi A. (2016). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788. Article

    Alagarsamy, S., Rajkumar, T. D., Syamala, K., Niharika, C. S., Rani, D. U., & Balaji, K. (2023). An real-time object detection method for visually impaired using machine learning. 2023 International Conference on Computer Communication and Informatics, pp. 1–6. Article

    Taiwo R., Bello I. T., Abdulai S. F., Yussif A.-M., Salami B. A., Saka A., & Zayed T. (2024). Generative AI in the construction industry: A state-of-the-art analysis. Article