Cover Image

Real-time vehicle counting using custom YOLOv8n and DeepSORT for resource-limited edge devices

Recently, there has been a significant increase in the use of deep learning and low-computing edge devices for analysis of video-based systems, particularly in the field of intelligent transportation systems (ITS). One promising application of computer vision techniques in ITS is in the dev...

Full description

Saved in:
Bibliographic Details
Main Authors: Saadeldin, Abuelgasim, Rashid, Muhammad Mahbubur, Shafie, Amir Akramin, Hasan, Tahsin Fuad
Format: Article
Language:English
English
Published: Universitas Ahmad Dahlan 2024
Subjects:
TE177 Roadside development. Landscaping
Online Access:http://irep.iium.edu.my/110556/7/110556_Real-time%20vehicle%20counting%20using%20custom%20YOLOv8n.pdf
http://irep.iium.edu.my/110556/13/110556_Real-time%20vehicle%20counting%20using%20custom%20YOLOv8n_SCOPUS.pdf
http://irep.iium.edu.my/110556/
http://telkomnika.uad.ac.id/index.php/TELKOMNIKA/article/view/25096/11804
http://doi.org/10.12928/telkomnika.v22i1.25096
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.iium.irep.110556
record_format dspace
spelling my.iium.irep.1105562024-02-27T08:50:50Z http://irep.iium.edu.my/110556/ Real-time vehicle counting using custom YOLOv8n and DeepSORT for resource-limited edge devices Saadeldin, Abuelgasim Rashid, Muhammad Mahbubur Shafie, Amir Akramin Hasan, Tahsin Fuad TE177 Roadside development. Landscaping Recently, there has been a significant increase in the use of deep learning and low-computing edge devices for analysis of video-based systems, particularly in the field of intelligent transportation systems (ITS). One promising application of computer vision techniques in ITS is in the development of low- computing and accurate vehicle counting systems that can be used to eliminate dependence on external cloud computing resources. This paper proposes a compact, reliable and real-time vehicle counting solution which can be deployed on low-computational requirement edge computing devices. The system makes use of a custom-built vehicle detection algorithm based on the you only look once version 8 nano (YOLOv8n), combined with a deep association metric (DeepSORT) object tracking algorithm and an efficient vehicle counting method for accurate counting of vehicles in highway scenes. The system is trained to detect, track and count four distinct vehicle classeses, namely: car, motorcycle, bus, and truck. The proposed system was able to achieve an average vehicle detection mean average precision (mAP) score of 97.5%, a vehicle counting accuracy score of 96.8% and an average speed of 19.4 frames per second (FPS), all while being deployed on a compact Nvidia Jetson Nano edge-computing device. The proposed system outperforms other previously proposed tools in terms of both accuracy and speed. Universitas Ahmad Dahlan 2024-01-25 Article PeerReviewed application/pdf en http://irep.iium.edu.my/110556/7/110556_Real-time%20vehicle%20counting%20using%20custom%20YOLOv8n.pdf application/pdf en http://irep.iium.edu.my/110556/13/110556_Real-time%20vehicle%20counting%20using%20custom%20YOLOv8n_SCOPUS.pdf Saadeldin, Abuelgasim and Rashid, Muhammad Mahbubur and Shafie, Amir Akramin and Hasan, Tahsin Fuad (2024) Real-time vehicle counting using custom YOLOv8n and DeepSORT for resource-limited edge devices. Telkomnika (Telecommunication Computing Electronics and Control), 22 (1). pp. 1-9. ISSN 1693-6930 E-ISSN 2087-278X http://telkomnika.uad.ac.id/index.php/TELKOMNIKA/article/view/25096/11804 http://doi.org/10.12928/telkomnika.v22i1.25096
institution Universiti Islam Antarabangsa Malaysia
building IIUM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider International Islamic University Malaysia
content_source IIUM Repository (IREP)
url_provider http://irep.iium.edu.my/
language English
English
topic TE177 Roadside development. Landscaping
spellingShingle TE177 Roadside development. Landscaping
Saadeldin, Abuelgasim
Rashid, Muhammad Mahbubur
Shafie, Amir Akramin
Hasan, Tahsin Fuad
Real-time vehicle counting using custom YOLOv8n and DeepSORT for resource-limited edge devices
description Recently, there has been a significant increase in the use of deep learning and low-computing edge devices for analysis of video-based systems, particularly in the field of intelligent transportation systems (ITS). One promising application of computer vision techniques in ITS is in the development of low- computing and accurate vehicle counting systems that can be used to eliminate dependence on external cloud computing resources. This paper proposes a compact, reliable and real-time vehicle counting solution which can be deployed on low-computational requirement edge computing devices. The system makes use of a custom-built vehicle detection algorithm based on the you only look once version 8 nano (YOLOv8n), combined with a deep association metric (DeepSORT) object tracking algorithm and an efficient vehicle counting method for accurate counting of vehicles in highway scenes. The system is trained to detect, track and count four distinct vehicle classeses, namely: car, motorcycle, bus, and truck. The proposed system was able to achieve an average vehicle detection mean average precision (mAP) score of 97.5%, a vehicle counting accuracy score of 96.8% and an average speed of 19.4 frames per second (FPS), all while being deployed on a compact Nvidia Jetson Nano edge-computing device. The proposed system outperforms other previously proposed tools in terms of both accuracy and speed.
format Article
author Saadeldin, Abuelgasim
Rashid, Muhammad Mahbubur
Shafie, Amir Akramin
Hasan, Tahsin Fuad
author_facet Saadeldin, Abuelgasim
Rashid, Muhammad Mahbubur
Shafie, Amir Akramin
Hasan, Tahsin Fuad
author_sort Saadeldin, Abuelgasim
title Real-time vehicle counting using custom YOLOv8n and DeepSORT for resource-limited edge devices
title_short Real-time vehicle counting using custom YOLOv8n and DeepSORT for resource-limited edge devices
title_full Real-time vehicle counting using custom YOLOv8n and DeepSORT for resource-limited edge devices
title_fullStr Real-time vehicle counting using custom YOLOv8n and DeepSORT for resource-limited edge devices
title_full_unstemmed Real-time vehicle counting using custom YOLOv8n and DeepSORT for resource-limited edge devices
title_sort real-time vehicle counting using custom yolov8n and deepsort for resource-limited edge devices
publisher Universitas Ahmad Dahlan
publishDate 2024
url http://irep.iium.edu.my/110556/7/110556_Real-time%20vehicle%20counting%20using%20custom%20YOLOv8n.pdf
http://irep.iium.edu.my/110556/13/110556_Real-time%20vehicle%20counting%20using%20custom%20YOLOv8n_SCOPUS.pdf
http://irep.iium.edu.my/110556/
http://telkomnika.uad.ac.id/index.php/TELKOMNIKA/article/view/25096/11804
http://doi.org/10.12928/telkomnika.v22i1.25096
_version_ 1792146438826754048
score 13.211869

Similar Items