From Stationary to Nonstationary UAVs: Deep-Learning-Based Method for Vehicle Speed Estimation

The development of smart cities relies on the implementation of cutting-edge technologies. Unmanned aerial vehicles (UAVs) and deep learning (DL) models are examples of such disruptive technologies with diverse industrial applications that are gaining traction. When it comes to road traffic monitori...

Full description

Saved in:
Bibliographic Details
Main Authors: Muhammad Waqas Ahmed, Muhammad Adnan, Muhammad Ahmed, Davy Janssens, Geert Wets, Afzal Ahmed, Wim Ectors
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Algorithms
Subjects:
Online Access:https://www.mdpi.com/1999-4893/17/12/558
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846106291979681792
author Muhammad Waqas Ahmed
Muhammad Adnan
Muhammad Ahmed
Davy Janssens
Geert Wets
Afzal Ahmed
Wim Ectors
author_facet Muhammad Waqas Ahmed
Muhammad Adnan
Muhammad Ahmed
Davy Janssens
Geert Wets
Afzal Ahmed
Wim Ectors
author_sort Muhammad Waqas Ahmed
collection DOAJ
description The development of smart cities relies on the implementation of cutting-edge technologies. Unmanned aerial vehicles (UAVs) and deep learning (DL) models are examples of such disruptive technologies with diverse industrial applications that are gaining traction. When it comes to road traffic monitoring systems (RTMs), the combination of UAVs and vision-based methods has shown great potential. Currently, most solutions focus on analyzing traffic footage captured by hovering UAVs due to the inherent georeferencing challenges in video footage from nonstationary drones. We propose an innovative method capable of estimating traffic speed using footage from both stationary and nonstationary UAVs. The process involves matching each pixel of the input frame with a georeferenced orthomosaic using a feature-matching algorithm. Subsequently, a tracking-enabled YOLOv8 object detection model is applied to the frame to detect vehicles and their trajectories. The geographic positions of these moving vehicles over time are logged in JSON format. The accuracy of this method was validated with reference measurements recorded from a laser speed gun. The results indicate that the proposed method can estimate vehicle speeds with an absolute error as low as 0.53 km/h. The study also discusses the associated problems and constraints with nonstationary drone footage as input and proposes strategies for minimizing noise and inaccuracies. Despite these challenges, the proposed framework demonstrates considerable potential and signifies another step towards automated road traffic monitoring systems. This system enables transportation modelers to realistically capture traffic behavior over a wider area, unlike existing roadside camera systems prone to blind spots and limited spatial coverage.
format Article
id doaj-art-a7f34ff172c34674bda6d06c6a7fcfda
institution Kabale University
issn 1999-4893
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Algorithms
spelling doaj-art-a7f34ff172c34674bda6d06c6a7fcfda2024-12-27T14:05:13ZengMDPI AGAlgorithms1999-48932024-12-01171255810.3390/a17120558From Stationary to Nonstationary UAVs: Deep-Learning-Based Method for Vehicle Speed EstimationMuhammad Waqas Ahmed0Muhammad Adnan1Muhammad Ahmed2Davy Janssens3Geert Wets4Afzal Ahmed5Wim Ectors6UHasselt, Transportation Research Institute (IMOB), Martelarenlaan 42, 3500 Hasselt, BelgiumUHasselt, Transportation Research Institute (IMOB), Martelarenlaan 42, 3500 Hasselt, BelgiumDepartment of Urban and Infrastructure Engineering, NED University of Engineering and Technology, Karachi 75270, PakistanUHasselt, Transportation Research Institute (IMOB), Martelarenlaan 42, 3500 Hasselt, BelgiumUHasselt, Transportation Research Institute (IMOB), Martelarenlaan 42, 3500 Hasselt, BelgiumInstitute of Transportation Studies, University of Leeds, Leeds LS2 9JT, UKUHasselt, Transportation Research Institute (IMOB), Martelarenlaan 42, 3500 Hasselt, BelgiumThe development of smart cities relies on the implementation of cutting-edge technologies. Unmanned aerial vehicles (UAVs) and deep learning (DL) models are examples of such disruptive technologies with diverse industrial applications that are gaining traction. When it comes to road traffic monitoring systems (RTMs), the combination of UAVs and vision-based methods has shown great potential. Currently, most solutions focus on analyzing traffic footage captured by hovering UAVs due to the inherent georeferencing challenges in video footage from nonstationary drones. We propose an innovative method capable of estimating traffic speed using footage from both stationary and nonstationary UAVs. The process involves matching each pixel of the input frame with a georeferenced orthomosaic using a feature-matching algorithm. Subsequently, a tracking-enabled YOLOv8 object detection model is applied to the frame to detect vehicles and their trajectories. The geographic positions of these moving vehicles over time are logged in JSON format. The accuracy of this method was validated with reference measurements recorded from a laser speed gun. The results indicate that the proposed method can estimate vehicle speeds with an absolute error as low as 0.53 km/h. The study also discusses the associated problems and constraints with nonstationary drone footage as input and proposes strategies for minimizing noise and inaccuracies. Despite these challenges, the proposed framework demonstrates considerable potential and signifies another step towards automated road traffic monitoring systems. This system enables transportation modelers to realistically capture traffic behavior over a wider area, unlike existing roadside camera systems prone to blind spots and limited spatial coverage.https://www.mdpi.com/1999-4893/17/12/558UAVdronetraffic monitoringcomputer visionYOLO
spellingShingle Muhammad Waqas Ahmed
Muhammad Adnan
Muhammad Ahmed
Davy Janssens
Geert Wets
Afzal Ahmed
Wim Ectors
From Stationary to Nonstationary UAVs: Deep-Learning-Based Method for Vehicle Speed Estimation
Algorithms
UAV
drone
traffic monitoring
computer vision
YOLO
title From Stationary to Nonstationary UAVs: Deep-Learning-Based Method for Vehicle Speed Estimation
title_full From Stationary to Nonstationary UAVs: Deep-Learning-Based Method for Vehicle Speed Estimation
title_fullStr From Stationary to Nonstationary UAVs: Deep-Learning-Based Method for Vehicle Speed Estimation
title_full_unstemmed From Stationary to Nonstationary UAVs: Deep-Learning-Based Method for Vehicle Speed Estimation
title_short From Stationary to Nonstationary UAVs: Deep-Learning-Based Method for Vehicle Speed Estimation
title_sort from stationary to nonstationary uavs deep learning based method for vehicle speed estimation
topic UAV
drone
traffic monitoring
computer vision
YOLO
url https://www.mdpi.com/1999-4893/17/12/558
work_keys_str_mv AT muhammadwaqasahmed fromstationarytononstationaryuavsdeeplearningbasedmethodforvehiclespeedestimation
AT muhammadadnan fromstationarytononstationaryuavsdeeplearningbasedmethodforvehiclespeedestimation
AT muhammadahmed fromstationarytononstationaryuavsdeeplearningbasedmethodforvehiclespeedestimation
AT davyjanssens fromstationarytononstationaryuavsdeeplearningbasedmethodforvehiclespeedestimation
AT geertwets fromstationarytononstationaryuavsdeeplearningbasedmethodforvehiclespeedestimation
AT afzalahmed fromstationarytononstationaryuavsdeeplearningbasedmethodforvehiclespeedestimation
AT wimectors fromstationarytononstationaryuavsdeeplearningbasedmethodforvehiclespeedestimation