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,...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | Article |
Published: |
MDPI
2021
|
Subjects: | |
Online Access: | http://eprints.um.edu.my/28122/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.um.eprints.28122 |
---|---|
record_format |
eprints |
spelling |
my.um.eprints.281222022-07-25T04:05:18Z http://eprints.um.edu.my/28122/ YOLO-RTUAV: Towards real-time vehicle detection through aerial images with low-cost edge devices Koay, Hong Vin Chuah, Joon Huang Chow, Chee-Onn Chang, Yang-Lang Yong, Keh Kok TK Electrical engineering. Electronics Nuclear engineering 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. MDPI 2021-11 Article PeerReviewed Koay, Hong Vin and Chuah, Joon Huang and Chow, Chee-Onn and Chang, Yang-Lang and Yong, Keh Kok (2021) YOLO-RTUAV: Towards real-time vehicle detection through aerial images with low-cost edge devices. Remote Sensing, 13 (21). ISSN 2072-4292, DOI https://doi.org/10.3390/rs13214196 <https://doi.org/10.3390/rs13214196>. 10.3390/rs13214196 |
institution |
Universiti Malaya |
building |
UM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Malaya |
content_source |
UM Research Repository |
url_provider |
http://eprints.um.edu.my/ |
topic |
TK Electrical engineering. Electronics Nuclear engineering |
spellingShingle |
TK Electrical engineering. Electronics Nuclear engineering Koay, Hong Vin Chuah, Joon Huang Chow, Chee-Onn Chang, Yang-Lang Yong, Keh Kok 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 |
Koay, Hong Vin Chuah, Joon Huang Chow, Chee-Onn Chang, Yang-Lang Yong, Keh Kok |
author_facet |
Koay, Hong Vin Chuah, Joon Huang Chow, Chee-Onn Chang, Yang-Lang Yong, Keh Kok |
author_sort |
Koay, Hong Vin |
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 |
publishDate |
2021 |
url |
http://eprints.um.edu.my/28122/ |
_version_ |
1739828439634935808 |
score |
13.160551 |