Real-Time Object Detection with OpenCV and Python

• Author(s): Himanshu Rai; Vansh Khatana; Dr. Anuj Chandila; Prof. (Dr.) Sanjay Pachauri
• Paper ID: 1712260
• Page: 1851-1852
• Published Date: 25-11-2025
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 9 Issue 5 November-2025

Abstract

This paper presents a real-time object detection system using OpenCV and Python. The proposed model aims to achieve fast, accurate, and reliable identification of objects from a live video stream. The system utilizes deep learning–based pretrained architectures such as MobileNet-SSD and YOLO-tiny, known for their efficiency in real-time detection tasks. The workflow includes frame acquisition, preprocessing, blob formation, and inference using OpenCV’s DNN module. Results demonstrate that lightweight models can process video frames in real time on CPU hardware while maintaining good accuracy. This study highlights how computer vision and deep learning can support automation, surveillance, and human–computer interaction systems.

Keywords

Object Detection, OpenCV, Deep Learning, YOLO, MobileNet-SSD, Real-Time Detection.

Citations

IRE Journals:
Himanshu Rai, Vansh Khatana, Dr. Anuj Chandila, Prof. (Dr.) Sanjay Pachauri "Real-Time Object Detection with OpenCV and Python" Iconic Research And Engineering Journals Volume 9 Issue 5 2025 Page 1851-1852 https://doi.org/10.64388/IREV9I5-1712260

IEEE:
Himanshu Rai, Vansh Khatana, Dr. Anuj Chandila, Prof. (Dr.) Sanjay Pachauri "Real-Time Object Detection with OpenCV and Python" Iconic Research And Engineering Journals, 9(5) https://doi.org/10.64388/IREV9I5-1712260