YOLOv5-Based Electric Scooter Crackdown Platform

As the use of personal mobility (PM) devices continues to rise, regulatory violations have become more frequent, highlighting the need for technological solutions to ensure efficient enforcement. This study addresses these challenges by proposing an AI-based enforcement platform. The system integrat...

Full description

Saved in:
Bibliographic Details
Main Authors: Seung-Hyun Lee, Sung-Hyun Oh, Jeong-Gon Kim
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/6/3112
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850204371577470976
author Seung-Hyun Lee
Sung-Hyun Oh
Jeong-Gon Kim
author_facet Seung-Hyun Lee
Sung-Hyun Oh
Jeong-Gon Kim
author_sort Seung-Hyun Lee
collection DOAJ
description As the use of personal mobility (PM) devices continues to rise, regulatory violations have become more frequent, highlighting the need for technological solutions to ensure efficient enforcement. This study addresses these challenges by proposing an AI-based enforcement platform. The system integrates the You Only Look Once version 5 (YOLOv5) object detection model, a deep-learning-based framework, with Global Positioning System (GPS) location data, Raspberry Pi 5, and Amazon Web Services (AWS) for data processing and web-based implementation. The YOLOv5 model was deployed in two configurations: one for detecting electric scooter usage and another for identifying legal violations. The system utilized AWS Relational Database Service (RDS), Simple Storage Service (S3), and Elastic Compute Cloud (EC2) to store violation records and host web applications. The detection performance was evaluated using mean average precision (mAP) metrics. The electric scooter detection model achieved mAP50 and mAP50-95 scores of 99.5 and 99.457, respectively. Meanwhile, the legal violation detection model attained mAP50 and mAP50-95 scores of 99.5 and 81.813, indicating relatively lower accuracy for fine-grained violation detection. This study presents a practical technological platform for monitoring regulatory compliance and automating fine enforcement for shared electric scooters. Future improvements in object detection accuracy and real-time processing capabilities are expected to enhance the system’s overall reliability.
format Article
id doaj-art-81b7ca2689f74f1cb6b976e6d768da3f
institution OA Journals
issn 2076-3417
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-81b7ca2689f74f1cb6b976e6d768da3f2025-08-20T02:11:18ZengMDPI AGApplied Sciences2076-34172025-03-01156311210.3390/app15063112YOLOv5-Based Electric Scooter Crackdown PlatformSeung-Hyun Lee0Sung-Hyun Oh1Jeong-Gon Kim2Department of Electronic Engineering, Tech University of Korea, Siheung-si 15297, Republic of KoreaDepartment of Electronic Engineering, Tech University of Korea, Siheung-si 15297, Republic of KoreaDepartment of Electronic Engineering, Tech University of Korea, Siheung-si 15297, Republic of KoreaAs the use of personal mobility (PM) devices continues to rise, regulatory violations have become more frequent, highlighting the need for technological solutions to ensure efficient enforcement. This study addresses these challenges by proposing an AI-based enforcement platform. The system integrates the You Only Look Once version 5 (YOLOv5) object detection model, a deep-learning-based framework, with Global Positioning System (GPS) location data, Raspberry Pi 5, and Amazon Web Services (AWS) for data processing and web-based implementation. The YOLOv5 model was deployed in two configurations: one for detecting electric scooter usage and another for identifying legal violations. The system utilized AWS Relational Database Service (RDS), Simple Storage Service (S3), and Elastic Compute Cloud (EC2) to store violation records and host web applications. The detection performance was evaluated using mean average precision (mAP) metrics. The electric scooter detection model achieved mAP50 and mAP50-95 scores of 99.5 and 99.457, respectively. Meanwhile, the legal violation detection model attained mAP50 and mAP50-95 scores of 99.5 and 81.813, indicating relatively lower accuracy for fine-grained violation detection. This study presents a practical technological platform for monitoring regulatory compliance and automating fine enforcement for shared electric scooters. Future improvements in object detection accuracy and real-time processing capabilities are expected to enhance the system’s overall reliability.https://www.mdpi.com/2076-3417/15/6/3112artificial intelligence (AI)object detectionpersonal mobility (PM)You Only Look Once version 5 (YOLOv5)Amazon Web Services (AWS)
spellingShingle Seung-Hyun Lee
Sung-Hyun Oh
Jeong-Gon Kim
YOLOv5-Based Electric Scooter Crackdown Platform
Applied Sciences
artificial intelligence (AI)
object detection
personal mobility (PM)
You Only Look Once version 5 (YOLOv5)
Amazon Web Services (AWS)
title YOLOv5-Based Electric Scooter Crackdown Platform
title_full YOLOv5-Based Electric Scooter Crackdown Platform
title_fullStr YOLOv5-Based Electric Scooter Crackdown Platform
title_full_unstemmed YOLOv5-Based Electric Scooter Crackdown Platform
title_short YOLOv5-Based Electric Scooter Crackdown Platform
title_sort yolov5 based electric scooter crackdown platform
topic artificial intelligence (AI)
object detection
personal mobility (PM)
You Only Look Once version 5 (YOLOv5)
Amazon Web Services (AWS)
url https://www.mdpi.com/2076-3417/15/6/3112
work_keys_str_mv AT seunghyunlee yolov5basedelectricscootercrackdownplatform
AT sunghyunoh yolov5basedelectricscootercrackdownplatform
AT jeonggonkim yolov5basedelectricscootercrackdownplatform