Home / Current Issue / Paper 1716890
Real-Time Illegal Parking Detection System Using YOLOv8 and OCR
Subject area: Science,Engineering and Technology · Area of research: Computer Vision and AI
DOI: https://doi.org/10.64388/IREV9I10-1716890
Abstract
Illegal parking is a major problem in urban environments, causing traffic congestion, road blockages, and safety issues. Traditional monitoring methods rely heavily on manual inspection, which is inefficient and time-consuming. This paper presents a real-time illegal parking detection system using computer vision and deep learning techniques. The proposed system uses the YOLOv8 object detection model to identify vehicles from live CCTV feeds and determine whether they are parked in restricted zones. A time-based validation mechanism ensures accurate detection of violations. Additionally, an Optical Character Recognition (OCR) module extracts vehicle license plate numbers for identification. All violations are logged with timestamped images and location details. Experimental results show high accuracy of 96.5% and real-time performance at 28 FPS. The system is scalable, cost-effective, and suitable for smart city applications.
Keywords
Illegal Parking Detection, YOLOv8, Computer Vision, OCR, Smart City, Deep Learning
How to cite this paper
@article{1716890,
author = {Yash Ubale, Yash Raj, Yuvraj Nikam},
title = {Real-Time Illegal Parking Detection System Using YOLOv8 and OCR},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {10},
pages = {3340-3342},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1716890.pdf},
abstract = {Illegal parking is a major problem in urban environments, causing traffic congestion, road blockages, and safety issues. Traditional monitoring methods rely heavily on manual inspection, which is inefficient and time-consuming. This paper presents a real-time illegal parking detection system using computer vision and deep learning techniques. The proposed system uses the YOLOv8 object detection model to identify vehicles from live CCTV feeds and determine whether they are parked in restricted zones. A time-based validation mechanism ensures accurate detection of violations. Additionally, an Optical Character Recognition (OCR) module extracts vehicle license plate numbers for identification. All violations are logged with timestamped images and location details. Experimental results show high accuracy of 96.5% and real-time performance at 28 FPS. The system is scalable, cost-effective, and suitable for smart city applications.},
keywords = {Illegal Parking Detection, YOLOv8, Computer Vision, OCR, Smart City, Deep Learning},
month = {April},
doi = {https://doi.org/10.64388/IREV9I10-1716890}
}