Object Detection System for Visually Impaired People Using Yolo Technology

Author

K. Sujitha, Dr J Evangelin Deva Sheela

Abstract

 Visually impaired individuals often face challenges in perceiving nearby objects and maintaining awareness of their surrounding environment. This paper presents a low-cost, real-time object detection assistant that uses a webcam, computer vision, and speech output to provide environmental awareness. Live camera frames are processed using OpenCV and analysed using the YOLO-World object detection model. The system detects selected everyday obstacles, including persons, chairs, doors, vehicles, walls, and stairs. A priority mechanism ranks objects according to their position in the camera frame and relative bounding-box size, giving greater importance to objects located ahead of the user. Relative object size is used to provide an apparent proximity category: very close, near, or far. The most relevant obstacle is converted into a spoken alert using Windows Text-to-Speech, while a Streamlit dashboard displays the live frame, object labels, confidence scores, positions, and priority status. The work is designed as an accessible prototype that can run on a standard computer with a webcam and speaker. A structured evaluation protocol is included to measure detection performance, response time, and behaviour under different lighting conditions before journal submission.

Keywords

visual impairment, assistive technology, object detection, YOLO-World, OpenCV, text-to-speech, real-time computer vision

Full Text:

Download Paper PDF

References

[1] P. Kathiria, S. H. Mankad, J. Patel, M. Kapadia and N. Lakdawala, ‘Assistive Systems for Visually Impaired People: A Survey on Current Requirements and Advancements,’ Neurocomputing, vol. 606, 2024, Article 128284, doi: 10.1016/j.neucom.2024.128284.

[2] J. Redmon, S. Divvala, R. Girshick and A. Farhadi, ‘You Only Look Once: Unified, Real-Time Object Detection,’ Proceedings of CVPR, pp. 779-788, 2016.

[3] T. Cheng et al., ‘YOLO-World: Real-Time Open-Vocabulary Object Detection,’ Proceedings of CVPR, 2024.

[4] H. Najm, K. Elferjani and A. Alariyibi, ‘Assisting Blind People Using Object Detection with Vocal Feedback,’ arXiv:2401.01362, 2024.

[5] K. Bamane, S. Khaparde, H. Totala, Y. Singh and D. Ghule, ‘Design and Development of Android Application for Visually Impaired People Using Object Detection and Direction Prediction,’ International Journal of Novel Research and Development, vol. 9, no. 4, 2024.

[6] M. Joshna, J. T. Kumar, G. Yuvaraju, K. V. V. Reddy and V. S. P. Reddy, ‘Object Detection Tracking and Alert System for Visually Impaired Persons,’ Proceedings of ICRDICCT, pp. 45-49, 2025.

[7] A. Nabila, F. A. Soelistianto and I. Mahfudi, ‘Designing an Object Detection System as an Assistive Device for the Visually Impaired Based on YOLOv10 with Dual Camera,’ West Science Information System and Technology, vol. 3, no. 3, pp. 166-175, 2025.

[8] Ultralytics, ‘YOLO-World Model Documentation,’ accessed August 2026. Available: https://docs.ultralytics.com/models/yolo-world/

[9] M. M. Valipoor and A. de Antonio, “Recent trends in computer vision-driven scene understanding for VI/blind users: A systematic mapping,” Universal Access in the Information Society, 2022, doi: 10.1007/s10209-022-00868-w.

[10] K. Patel and B. Parmar, “Assistive device using computer vision and image processing for visually impaired; review and current status,” Disability and Rehabilitation: Assistive Technology, vol. 17, no. 3, pp. 290–297, 2022, doi: 10.1080/17483107.2020.1786731.

[11] A. Voulodimos, N. Doulamis, A. Doulamis and E. Protopapadakis, “Deep learning for computer vision: A brief review,” Computational Intelligence and Neuroscience, vol. 2018, Article 7068349, 2018, doi: 10.1155/2018/7068349.

[12] 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, doi: 10.1109/TNNLS.2018.2876865.

[13] G. Jocher, A. Chaurasia and J. Qiu, “Ultralytics YOLOv8,” version 8.0.0, Ultralytics, 2023. [Online]. Available: https://github.com/ultralytics/ultralytics

[14] R. Girshick, J. Donahue, T. Darrell and J. Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 580–587, 2014, doi: 10.1109/CVPR.2014.81.

[15] R. Girshick, “Fast R-CNN,” Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 1440–1448, 2015, doi: 10.1109/ICCV.2015.169.

[16] W. Liu et al., “SSD: Single shot multibox detector,” European Conference on Computer Vision (ECCV), pp. 21–37, 2016, doi: 10.1007/978-3-319-46448-0_2.

[17] N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection,” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), vol. 1, pp. 886–893, 2005, doi: 10.1109/CVPR.2005.177.

[18] A. Krizhevsky, I. Sutskever and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” Advances in Neural Information Processing Systems, vol. 25, 2012.

 

 

 

 

 

Share your valuable work from Social Media Buttons