YOLO-RTUAV: Towards Real-Time Vehicle Detection through Aerial Images with Low-Cost Edge Devices

Object detection in aerial images has been an active research area thanks to the vast availability of unmanned aerial vehicles (UAVs). Along with the increase of computational power, deep learning algorithms are commonly used for object detection tasks. However, aerial images have large variations,...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Hong Vin Koay, Joon Huang Chuah, Chee-Onn Chow, Yang-Lang Chang, Keh Kok Yong
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	object detection deep learning aerial imaging real-time detection Science Q
Acceso en línea:	https://doaj.org/article/fac6d570a1b34a55a1fd799b620df404
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:fac6d570a1b34a55a1fd799b620df404
record_format	dspace
spelling	oai:doaj.org-article:fac6d570a1b34a55a1fd799b620df4042021-11-11T18:49:44ZYOLO-RTUAV: Towards Real-Time Vehicle Detection through Aerial Images with Low-Cost Edge Devices10.3390/rs132141962072-4292https://doaj.org/article/fac6d570a1b34a55a1fd799b620df4042021-10-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/21/4196https://doaj.org/toc/2072-4292Object detection in aerial images has been an active research area thanks to the vast availability of unmanned aerial vehicles (UAVs). Along with the increase of computational power, deep learning algorithms are commonly used for object detection tasks. However, aerial images have large variations, and the object sizes are usually small, rendering lower detection accuracy. Besides, real-time inferencing on low-cost edge devices remains an open-ended question. In this work, we explored the usage of state-of-the-art deep learning object detection on low-cost edge hardware. We propose YOLO-RTUAV, an improved version of YOLOv4-Tiny, as the solution. We benchmarked our proposed models with various state-of-the-art models on the VAID and COWC datasets. Our proposed model can achieve higher mean average precision (mAP) and frames per second (FPS) than other state-of-the-art tiny YOLO models, especially on a low-cost edge device such as the Jetson Nano 2 GB. It was observed that the Jetson Nano 2 GB can achieve up to 12.8 FPS with a model size of only 5.5 MB.Hong Vin KoayJoon Huang ChuahChee-Onn ChowYang-Lang ChangKeh Kok YongMDPI AGarticleobject detectiondeep learningaerial imagingreal-time detectionScienceQENRemote Sensing, Vol 13, Iss 4196, p 4196 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	object detection deep learning aerial imaging real-time detection Science Q
spellingShingle	object detection deep learning aerial imaging real-time detection Science Q Hong Vin Koay Joon Huang Chuah Chee-Onn Chow Yang-Lang Chang Keh Kok Yong YOLO-RTUAV: Towards Real-Time Vehicle Detection through Aerial Images with Low-Cost Edge Devices
description	Object detection in aerial images has been an active research area thanks to the vast availability of unmanned aerial vehicles (UAVs). Along with the increase of computational power, deep learning algorithms are commonly used for object detection tasks. However, aerial images have large variations, and the object sizes are usually small, rendering lower detection accuracy. Besides, real-time inferencing on low-cost edge devices remains an open-ended question. In this work, we explored the usage of state-of-the-art deep learning object detection on low-cost edge hardware. We propose YOLO-RTUAV, an improved version of YOLOv4-Tiny, as the solution. We benchmarked our proposed models with various state-of-the-art models on the VAID and COWC datasets. Our proposed model can achieve higher mean average precision (mAP) and frames per second (FPS) than other state-of-the-art tiny YOLO models, especially on a low-cost edge device such as the Jetson Nano 2 GB. It was observed that the Jetson Nano 2 GB can achieve up to 12.8 FPS with a model size of only 5.5 MB.
format	article
author	Hong Vin Koay Joon Huang Chuah Chee-Onn Chow Yang-Lang Chang Keh Kok Yong
author_facet	Hong Vin Koay Joon Huang Chuah Chee-Onn Chow Yang-Lang Chang Keh Kok Yong
author_sort	Hong Vin Koay
title	YOLO-RTUAV: Towards Real-Time Vehicle Detection through Aerial Images with Low-Cost Edge Devices
title_short	YOLO-RTUAV: Towards Real-Time Vehicle Detection through Aerial Images with Low-Cost Edge Devices
title_full	YOLO-RTUAV: Towards Real-Time Vehicle Detection through Aerial Images with Low-Cost Edge Devices
title_fullStr	YOLO-RTUAV: Towards Real-Time Vehicle Detection through Aerial Images with Low-Cost Edge Devices
title_full_unstemmed	YOLO-RTUAV: Towards Real-Time Vehicle Detection through Aerial Images with Low-Cost Edge Devices
title_sort	yolo-rtuav: towards real-time vehicle detection through aerial images with low-cost edge devices
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/fac6d570a1b34a55a1fd799b620df404
work_keys_str_mv	AT hongvinkoay yolortuavtowardsrealtimevehicledetectionthroughaerialimageswithlowcostedgedevices AT joonhuangchuah yolortuavtowardsrealtimevehicledetectionthroughaerialimageswithlowcostedgedevices AT cheeonnchow yolortuavtowardsrealtimevehicledetectionthroughaerialimageswithlowcostedgedevices AT yanglangchang yolortuavtowardsrealtimevehicledetectionthroughaerialimageswithlowcostedgedevices AT kehkokyong yolortuavtowardsrealtimevehicledetectionthroughaerialimageswithlowcostedgedevices
_version_	1718431741873487872

YOLO-RTUAV: Towards Real-Time Vehicle Detection through Aerial Images with Low-Cost Edge Devices

Ejemplares similares