International Journal of Scientific Research and Engineering Development

This paper presents an intelligent assistive system designed to enhance the mobility and independence of visually impaired individuals through real-time object detection and audio feedback. The system leverages deep learning and computer vision techniques to identify objects in the user’s surroundings using a live video feed. A lightweight YOLOv4-tiny model is employed to ensure fast processing with acceptable accuracy on low-resource systems. Detected objects are converted into speech using a text-to-speech engine, enabling users to understand their environment without visual input. Experimental results show that the system performs efficiently in real-time scenarios, providing timely and useful auditory cues. This solution aims to bridge the gap between visually impaired users and their environment by offering an affordable and portable assistive technology.

Aishwarya Hosale, Tanvi Panse, Priyanka Kumbhar, Adil Doka, Akash Mendgudle,"Real-Time Object Detection with Audio Feedback for Visually Impaired People" International Journal of Scientific Research and Engineering Development, V9(3): Page(86-88) May-June 2026. ISSN: 2581-7175. www.ijsred.com. Published by Scientific and Academic Research Publishing.