Automatic Target Detection from Satellite Imagery Using Machine Learning.

Tahir, A; Munawar, HS; Akram, J; Adil, M; Ali, S; Kouzani, AZ; Mahmud, MAP

Automatic Target Detection from Satellite Imagery Using Machine Learning.

Tahir, A Munawar, HS Akram, J Adil, M Ali, S Kouzani, AZ Mahmud, MAP

Permalink

Publisher:: MDPI
Publication Type:: Journal Article
Citation:: Sensors (Basel), 2022, 22, (3), pp. 1147
Issue Date:: 2022-02-02

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download full textAdobe PDF (5.46 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Tahir, A
dc.contributor.author	Munawar, HS
dc.contributor.author	Akram, J
dc.contributor.author	Adil, M
dc.contributor.author	Ali, S
dc.contributor.author	Kouzani, AZ
dc.contributor.author	Mahmud, MAP
dc.date.accessioned	2023-05-01T01:11:36Z
dc.date.available	2022-01-31
dc.date.available	2023-05-01T01:11:36Z
dc.date.issued	2022-02-02
dc.identifier.citation	Sensors (Basel), 2022, 22, (3), pp. 1147
dc.identifier.issn	1424-8220
dc.identifier.issn	1424-8220
dc.identifier.uri	http://hdl.handle.net/10453/170145
dc.description.abstract	Object detection is a vital step in satellite imagery-based computer vision applications such as precision agriculture, urban planning and defense applications. In satellite imagery, object detection is a very complicated task due to various reasons including low pixel resolution of objects and detection of small objects in the large scale (a single satellite image taken by Digital Globe comprises over 240 million pixels) satellite images. Object detection in satellite images has many challenges such as class variations, multiple objects pose, high variance in object size, illumination and a dense background. This study aims to compare the performance of existing deep learning algorithms for object detection in satellite imagery. We created the dataset of satellite imagery to perform object detection using convolutional neural network-based frameworks such as faster RCNN (faster region-based convolutional neural network), YOLO (you only look once), SSD (single-shot detector) and SIMRDWN (satellite imagery multiscale rapid detection with windowed networks). In addition to that, we also performed an analysis of these approaches in terms of accuracy and speed using the developed dataset of satellite imagery. The results showed that SIMRDWN has an accuracy of 97% on high-resolution images, while Faster RCNN has an accuracy of 95.31% on the standard resolution (1000 × 600). YOLOv3 has an accuracy of 94.20% on standard resolution (416 × 416) while on the other hand SSD has an accuracy of 84.61% on standard resolution (300 × 300). When it comes to speed and efficiency, YOLO is the obvious leader. In real-time surveillance, SIMRDWN fails. When YOLO takes 170 to 190 milliseconds to perform a task, SIMRDWN takes 5 to 103 milliseconds.
dc.format	Electronic
dc.language	eng
dc.publisher	MDPI
dc.relation.ispartof	Sensors (Basel)
dc.relation.isbasedon	10.3390/s22031147
dc.rights	info:eu-repo/semantics/openAccess
dc.subject	0301 Analytical Chemistry, 0502 Environmental Science and Management, 0602 Ecology, 0805 Distributed Computing, 0906 Electrical and Electronic Engineering
dc.subject.classification	Analytical Chemistry
dc.subject.mesh	Algorithms
dc.subject.mesh	Machine Learning
dc.subject.mesh	Neural Networks, Computer
dc.subject.mesh	Satellite Imagery
dc.subject.mesh	Software
dc.subject.mesh	Algorithms
dc.subject.mesh	Software
dc.subject.mesh	Satellite Imagery
dc.subject.mesh	Machine Learning
dc.subject.mesh	Neural Networks, Computer
dc.subject.mesh	Algorithms
dc.subject.mesh	Machine Learning
dc.subject.mesh	Neural Networks, Computer
dc.subject.mesh	Satellite Imagery
dc.subject.mesh	Software
dc.title	Automatic Target Detection from Satellite Imagery Using Machine Learning.
dc.type	Journal Article
utslib.citation.volume	22
utslib.location.activity	Switzerland
utslib.for	0301 Analytical Chemistry
utslib.for	0502 Environmental Science and Management
utslib.for	0602 Ecology
utslib.for	0805 Distributed Computing
utslib.for	0906 Electrical and Electronic Engineering
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Science
utslib.copyright.status	open_access	*
dc.date.updated	2023-05-01T01:11:30Z
pubs.issue	3
pubs.publication-status	Published online
pubs.volume	22
utslib.citation.issue	3

Abstract:

Object detection is a vital step in satellite imagery-based computer vision applications such as precision agriculture, urban planning and defense applications. In satellite imagery, object detection is a very complicated task due to various reasons including low pixel resolution of objects and detection of small objects in the large scale (a single satellite image taken by Digital Globe comprises over 240 million pixels) satellite images. Object detection in satellite images has many challenges such as class variations, multiple objects pose, high variance in object size, illumination and a dense background. This study aims to compare the performance of existing deep learning algorithms for object detection in satellite imagery. We created the dataset of satellite imagery to perform object detection using convolutional neural network-based frameworks such as faster RCNN (faster region-based convolutional neural network), YOLO (you only look once), SSD (single-shot detector) and SIMRDWN (satellite imagery multiscale rapid detection with windowed networks). In addition to that, we also performed an analysis of these approaches in terms of accuracy and speed using the developed dataset of satellite imagery. The results showed that SIMRDWN has an accuracy of 97% on high-resolution images, while Faster RCNN has an accuracy of 95.31% on the standard resolution (1000 × 600). YOLOv3 has an accuracy of 94.20% on standard resolution (416 × 416) while on the other hand SSD has an accuracy of 84.61% on standard resolution (300 × 300). When it comes to speed and efficiency, YOLO is the obvious leader. In real-time surveillance, SIMRDWN fails. When YOLO takes 170 to 190 milliseconds to perform a task, SIMRDWN takes 5 to 103 milliseconds.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/170145