Design And Implementation Of A Real-time Multi-object Detection And Tracking System Using Yolo26

Abstract

This Paper Presents The Development Of A Real-time Object Detection And Multi-object Tracking System Using The Ultralytics YOLO26 Model. The System Captures Live Video Through A Webcam And Processes Each Frame Using A Deep Learning-based Computer Vision Model To Detect Multiple Objects Simultaneously. The Detected Objects Are Highlighted With Bounding Boxes And Assigned Unique Tracking IDs To Maintain Their Identity Across Consecutive Frames. The System Is Implemented Using Python, OpenCV, And The PyTorch Framework. The Proposed Model Is Executed On CPU Hardware Without GPU Acceleration And Achieves An Average Processing Speed Of Approximately 18–25 Frames Per Second. Experimental Results Show That The System Can Detect Common Objects Such As Persons, Vehicles, And Everyday Items Effectively In Real Time. The Proposed Approach Provides A Cost-effective And Efficient Solution For Surveillance Systems, Smart Monitoring, And Intelligent Vision-based Applications.

Keywords