Cover Image

Lightweight CNN model: Automated vehicle detection in aerial images

Efficient vehicle detection has played an important role in Intelligent Transportation Systems (ITS) in smart cities. With the development of the Convolutional Neural Network (CNN) for objection detection, new applications have been designed to enable on-road vehicle detection algorithms. Therefore,...

Full description

Saved in:
Bibliographic Details
Main Authors: Momin, Md Abdul, Junos, Mohamad Haniff, Khairuddin, Anis Salwa Mohd, Abu Talip, Mohamad Sofian
Format: Article
Published: SPRINGER LONDON LTD 2023
Subjects:
TK Electrical engineering. Electronics Nuclear engineering
TR Photography
Online Access:http://eprints.um.edu.my/39488/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.um.eprints.39488
record_format eprints
spelling my.um.eprints.394882024-06-10T03:14:09Z http://eprints.um.edu.my/39488/ Lightweight CNN model: Automated vehicle detection in aerial images Momin, Md Abdul Junos, Mohamad Haniff Khairuddin, Anis Salwa Mohd Abu Talip, Mohamad Sofian TK Electrical engineering. Electronics Nuclear engineering TR Photography Efficient vehicle detection has played an important role in Intelligent Transportation Systems (ITS) in smart cities. With the development of the Convolutional Neural Network (CNN) for objection detection, new applications have been designed to enable on-road vehicle detection algorithms. Therefore, this work aims to further improve the conventional CNN model for real-time detection on low-cost embedded hardware. In this study, a lightweight CNN model is proposed based on YOLOv4 Tiny to detect vehicles from the VEDAI dataset. In the proposed method, one additional scale feature map is added to make a total of three prediction boxes in the architecture. Then, the output image size of the second and third prediction boxes are upscaled in order to improve detection accuracy in detecting small size vehicles in the aerial images. The proposed model has been evaluated on NVIDIA Geforce 940MX GPU-based computer, Google Collab (TESLA K80) and Jetson Nano. Based on the experimental results, this study has demonstrated that the proposed model achieved better mean average precision (mAP) compared to the conventional YOLOv4 Tiny and previous works. SPRINGER LONDON LTD 2023-06 Article PeerReviewed Momin, Md Abdul and Junos, Mohamad Haniff and Khairuddin, Anis Salwa Mohd and Abu Talip, Mohamad Sofian (2023) Lightweight CNN model: Automated vehicle detection in aerial images. SIGNAL IMAGE AND VIDEO PROCESSING, 17 (4). pp. 1209-1217. ISSN 1863-1703, DOI https://doi.org/10.1007/s11760-022-02328-7 <https://doi.org/10.1007/s11760-022-02328-7>. 10.1007/s11760-022-02328-7
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
TR Photography
spellingShingle TK Electrical engineering. Electronics Nuclear engineering
TR Photography
Momin, Md Abdul
Junos, Mohamad Haniff
Khairuddin, Anis Salwa Mohd
Abu Talip, Mohamad Sofian
Lightweight CNN model: Automated vehicle detection in aerial images
description Efficient vehicle detection has played an important role in Intelligent Transportation Systems (ITS) in smart cities. With the development of the Convolutional Neural Network (CNN) for objection detection, new applications have been designed to enable on-road vehicle detection algorithms. Therefore, this work aims to further improve the conventional CNN model for real-time detection on low-cost embedded hardware. In this study, a lightweight CNN model is proposed based on YOLOv4 Tiny to detect vehicles from the VEDAI dataset. In the proposed method, one additional scale feature map is added to make a total of three prediction boxes in the architecture. Then, the output image size of the second and third prediction boxes are upscaled in order to improve detection accuracy in detecting small size vehicles in the aerial images. The proposed model has been evaluated on NVIDIA Geforce 940MX GPU-based computer, Google Collab (TESLA K80) and Jetson Nano. Based on the experimental results, this study has demonstrated that the proposed model achieved better mean average precision (mAP) compared to the conventional YOLOv4 Tiny and previous works.
format Article
author Momin, Md Abdul
Junos, Mohamad Haniff
Khairuddin, Anis Salwa Mohd
Abu Talip, Mohamad Sofian
author_facet Momin, Md Abdul
Junos, Mohamad Haniff
Khairuddin, Anis Salwa Mohd
Abu Talip, Mohamad Sofian
author_sort Momin, Md Abdul
title Lightweight CNN model: Automated vehicle detection in aerial images
title_short Lightweight CNN model: Automated vehicle detection in aerial images
title_full Lightweight CNN model: Automated vehicle detection in aerial images
title_fullStr Lightweight CNN model: Automated vehicle detection in aerial images
title_full_unstemmed Lightweight CNN model: Automated vehicle detection in aerial images
title_sort lightweight cnn model: automated vehicle detection in aerial images
publisher SPRINGER LONDON LTD
publishDate 2023
url http://eprints.um.edu.my/39488/
_version_ 1802977488807133184
score 13.211869

Similar Items