Using computer vision for an automated object tracking system

The article considers the use of computer vision technologies to automate the process of tracking objects in a video stream. The developed system that realizes the recognition, tracking, and characterization of moving objects using the YOLOv8 model is described. The system includes modules for disp...

Full description

Saved in:
Bibliographic Details
Main Authors: Н. Булботка, О. Польшакова
Format: Article
Language:English
Published: Igor Sikorsky Kyiv Polytechnic Institute 2025-02-01
Series:Adaptivni Sistemi Avtomatičnogo Upravlinnâ
Subjects:
Online Access:https://asac.kpi.ua/article/view/323655
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The article considers the use of computer vision technologies to automate the process of tracking objects in a video stream. The developed system that realizes the recognition, tracking, and characterization of moving objects using the YOLOv8 model is described. The system includes modules for displaying video, recognizing, tracking, and characterizing objects. The article describes the process of training the YOLOv8 model on specific data sets, as well as the application of algorithms for determining the speed of moving objects. The proposed solution allows analyzing the video stream in real time. The results confirm the compliance of the developed system with the requirements and its practical applicability in the areas of video surveillance, analysis of the behavior of objects, unmanned vehicles, and transportation systems. Ref. 8, fig. 8, tab. 3
ISSN:1560-8956
2522-9575