<![CDATA[Visually impaired individuals often face significant challenges in navigating their environments due to limited access to visual information. To address this issue, we propose an assistive tool designed to operate on a PC. The focus of this research is on developing an efficient, lightweight object detection system to ensure real-time performance while maintaining compatibility with low-resource setups. The proposed system enhances the autonomy and accessibility of visually impaired individuals by providing audio descriptions of their surroundings through the processing of live-streaming video. The core of the system is an object detection module based on the state-of-the-art YOLO7 model, designed to identify multiple objects in real-time within the user's environment. The system processes video frames captured by a camera, identifies objects, and delivers the results as audio descriptions using the pyttsx3 text-to-speech library, ensuring offline functionality and robust performance. The system demonstrates satisfactory results, achieving inference speeds ranging from 0.12 to 1.14 seconds for object detection, as evaluated through quantitative metrics and subjective assessments. In conclusion, the proposed tool effectively aids visually impaired individuals by providing accurate and timely audio descriptions, thereby promoting greater independence and accessibility.]]>
Copyrights © 2025
