19, June 2026

AI based campus assistant for visually impaired

VOLUME-12; ISSUE-6; JUNE-2026

Author(s): 1. Piyushchandra Vyas, 2. Shravani Trikolwar, 3. Sakshi Tonge, 4. Shrividya Polu, 5. Kshitij Turankar

Authors Affiliations:

1. Student, Department of Computer Science & Engineering, RCERT ,Chandrapur, India

2. Student, Department of Computer Science & Engineering, RCERT ,Chandrapur, India

3. Student, Department of Computer Science & Engineering, RCERT ,Chandrapur, India

4. Student, Department of Computer Science & Engineering, RCERT ,Chandrapur, India

5. Student, Department of Computer Science & Engineering, RCERT ,Chandrapur, India

DOIs:10.2015/IJIRMF/202606022     |     Paper ID: IJIRMF202606021


Abstract
Keywords
Cite this Article/Paper as
References

This paper presents an AI-driven campus assistant designed to enhance independence for the visually impaired on campus. At its core are three main components working together seamlessly as one single workflow: real-time on-the-fly object detection using YOLOv8, reading of text with EasyOCR, and spoken navigation through a route graph engine. All user interactions are simplified with a minimal Android UI, with all AI inference being carried out on a FastAPI backend. All information given back to the user is delivered by voice, with no reading necessary. Tests on the prototype have shown the feasibility of the method on commodity mobile devices with no extra hardware using entirely open-source technology, and will serve as a basis for future work such as custom campus model training, indoor accurate positioning, and better maps for navigation.

Visual Impairment, Campus Assistance, Object Detection, OCR, Android, YOLO, Accessibility

Mr. Piyushchandra S. Vyas,  Ms. Shravani P. Trikolwar, Ms. Sakshi Tonge, Ms. Shrividya Polu, Mr. Kshitij Turankar (2026); AI based campus assistant for visually impaired, International Journal for Innovative Research in Multidisciplinary Field, ISSN(O): 2455-0620, Vol-12, Issue-6, Available on –   https://www.ijirmf.com/

  1. World Health Organization (2019). World report on vision. Geneva, Switzerland: World Health Organization. Available: https://www.who.int/publications/i/item/9789241516570
  2. Redmon J., Divvala S., Girshick R., and Farhadi A. (2016), You Only Look Once: Unified, Real-Time Object Detection, Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 779–788. doi: 10.1109/CVPR.2016.91.
  3. Shi B., Bai X., and Yao C. (2017), An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(11), 2298–2304. doi: 10.1109/TPAMI.2016.2646371.
  4. Zhou X., Yao C., Wen H., Wang Y., Zhou S., He W., and Liang J. (2017), EAST: An Efficient and Accurate Scene Text Detector, Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). doi: 10.1109/CVPR.2017.283.
  5. Baek Y., Lee B., Han D., Yun S., and Lee H. (2019), Character Region Awareness for Text Detection, Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). doi: 10.1109/CVPR.2019.00955.
  6. JaidedAI (2020), EasyOCR [GitHub Repository]. Available: https://github.com/JaidedAI/EasyOCR
  7. Kuriakose B., Shrestha R., and Sandnes F. E. (2023), Exploring the User Experience of an AI-based Smartphone Navigation Assistant for People with Visual Impairments, Proc. 15th Biannual Conference of the Italian SIGCHI Chapter (CHItaly 2023), Torino, Italy.
  8. Li B., Munoz J. P., Rong X., Nguyen D., Chen J., Xiao W., and Yao Y. (2018), Vision-Based Mobile Indoor Assistive Navigation Aid for Blind People, IEEE Transactions on Mobile Computing, 18(3), 702–714.
Post Views: 67

Download Full Paper

Download PDF No. of Downloads:14 | No. of Views: 58