Open Access Open Access  Restricted Access Subscription Access

AI-Powered Object Detection

Rajaram Roopa Sri, Mungi Sai Akshaya, Dr V. Subba Ramaiah, Ms. S. Renuka, Dr. K Mahesh Kumar

Abstract


This paper presents an AI-powered Object Detection system designed to provide real-time environmental awareness using computer vision and machine learning techniques. The system captures live video input through a camera and processes each frame to perform object detection, text recognition using OCR, currency identification, and traffic light detection. It includes a direction and urgency analysis module to determine the position and importance of detected objects, enabling effective decision-making. A priority-based alert queue system is implemented to manage and deliver voice alerts using a text-to-speech engine without overlap. The system supports multiple modes such as walk mode, OCR mode, and currency mode, allowing flexible and context-awareoperation.Experimentalresultsdemonstratethatthe system performs efficiently in real-time scenarios with minimal delay, making it a practical and reliable assistive solution, particularly for visually impaired individuals.

Full Text:

PDF

References


J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2016.

R. Smith, “An Overview of the Tesseract OCR Engine,” in Proc. Int. Conf. Document Analysis and Recognition (ICDAR), 2007.

J. Redmon and A. Farhadi, “YOLOv3: An Incremental Improvement,” arXiv preprint arXiv:1804.02767, 2018.

A. Rosebrock, Practical Python and OpenCV. PyImageSearch, 2019.

D. Dakopoulos and N. G. Bourbakis, “Wearable Obstacle Avoidance Electronic Travel Aids for the Blind,” IEEE Trans. Systems, Man, and Cybernetics, 2010.

W. Liu et al., “SSD: Single Shot MultiBox Detector,” in Proc. Eur. Conf. Computer Vision (ECCV), 2016.

P. Viola and M. Jones, “Rapid Object Detection Using a Boosted Cascade of Simple Features,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2001.

“OpenCV Documentation,” [Online]. Available: https://opencv.org/


Refbacks

  • There are currently no refbacks.