IJRTI
International Journal for Research Trends and Innovation
International Peer Reviewed & Refereed Journals, Open Access Journal
ISSN Approved Journal No: 2456-3315 | Impact factor: 8.14 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.14 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)

Call For Paper

For Authors

Forms / Download

Published Issue Details

Editorial Board

Other IMP Links

Facts & Figure

Impact Factor : 8.14

Issue per Year : 12

Volume Published : 11

Issue Published : 119

Article Submitted : 22653

Article Published : 8822

Total Authors : 23281

Total Reviewer : 825

Total Countries : 161

Indexing Partner

Licence

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Published Paper Details
Paper Title: AI Powered Real Time Vehicle Detection Using YOLOv8
Authors Name: Mohd Zahid , Mohd Yasir Azeem , Mohd Sultan , Omar Badar Shafeeque
Download E-Certificate: Download
Author Reg. ID:
IJRTI_209858
Published Paper Id: IJRTI2602085
Published In: Volume 11 Issue 2, February-2026
DOI:
Abstract: The sudden increase in the density of vehicles in urban areas has led to the need for advanced Intelligent Transportation Systems (ITS) that can perform high-speed, autonomous surveillance. The aim of this research is to design an efficient real-time vehicle detection system that fills the important gap in the literature related to the trade-off between computational speed and accuracy. Although the current state-of-the-art versions of object detection algorithms, such as YOLOv5, have achieved remarkable performance, there is a considerable gap in the literature related to their performance in high-density traffic conditions with overlapping objects (occlusions) and changing lighting conditions. Most of the current systems are sensitive to "anchor-box" sizes, which results in the incorrect localization of small-scale objects such as motorcycles or far-away vehicles. To fill this gap, the main aim of this research work is to apply and test the YOLOv8 (You Only Look Once, version 8) model, particularly concentrating on the anchor-free detection part and Task-Aligned Assigner to improve spatial precision. The approach consists of a multi-step process: data collection with a hybrid dataset of 16,990 labeled images, and intensive augmentation (mosaic and horizontal flip) to mimic adverse weather and night conditions. The model employs a customized CSPDarknet53 feature extractor and a decoupled head for classification and regression. The major findings of this research work show that the YOLOv8m (Medium) model reached a maximum Mean Average Precision of 98.96% in a controlled environment and 93.4% on various validation sets. Importantly, by optimizing the loss function hyperparameters, the model increased precision by 0.12% compared to the default settings, reaching 95.1%. The model also ensured a constant inference rate of 52 FPS on a mid-range GPU, meeting real-time constraints. The implications of this research are substantial for smart city infrastructure, as this research work provides a scalable solution for automatic tolling and traffic optimization. This research work proves that anchor-free models are effective in minimizing false negatives on congested roads, providing a robust platform for real-time traffic analysis.
Keywords: YOLOv8, Computer Vision, Real-Time Detection, Intelligent Transportation Systems (ITS), Deep Learning, CNN.
Cite Article: "AI Powered Real Time Vehicle Detection Using YOLOv8", International Journal for Research Trends and Innovation (www.ijrti.org), ISSN:2456-3315, Vol.11, Issue 2, page no.a627-a642, February-2026, Available :http://www.ijrti.org/papers/IJRTI2602085.pdf
Downloads: 000132
ISSN: 2456-3315 | IMPACT FACTOR: 8.14 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.14 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publication Details: Published Paper ID: IJRTI2602085
Registration ID:209858
Published In: Volume 11 Issue 2, February-2026
DOI (Digital Object Identifier):
Page No: a627-a642
Country: LUCKNOW, UTTAR PRADESH, INDIA
Research Area: Engineering
Publisher : IJ Publication
Published Paper URL : https://www.ijrti.org/viewpaperforall?paper=IJRTI2602085
Published Paper PDF: https://www.ijrti.org/papers/IJRTI2602085
Share Article:

Share Facebook Twitter Google+ Pinterest LinkedIn Email Tumblr WhatsApp Google Gmail

Click Here to Download This Article

Article Preview
Click Here to Download This Article
Major Indexing from www.ijrti.org
Google Scholar ResearcherID Thomson Reuters Mendeley : reference manager Academia.edu
arXiv.org : cornell university library Research Gate CiteSeerX DOAJ : Directory of Open Access Journals
DRJI Index Copernicus International Scribd DocStoc

ISSN Details

ISSN: 2456-3315
Impact Factor: 8.14 and ISSN APPROVED, Journal Starting Year (ESTD) : 2016

DOI (A digital object identifier)


Providing A digital object identifier by DOI.ONE
How to Get DOI?

Conference

Open Access License Policy

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License

Creative Commons License This material is Open Knowledge This material is Open Data This material is Open Content

Important Details

Join RMS/Earn 300
IJRTI

WhatsApp
Click Here

Indexing Partner
Copyright © 2026 - All Rights Reserved - IJRTI