Automatic Target Detection from Satellite Imagery Using Machine Learning
Article
Article Title | Automatic Target Detection from Satellite Imagery Using Machine Learning |
---|---|
ERA Journal ID | 34304 |
Article Category | Article |
Authors | Tahir, Arsalan, Munawar, Hafiz Suliman, Akram, Junaid, Adil, Muhammad, Ali, Shehryar, Kouzani, Abbas Z. and Mahmud, M. A. Parvez |
Journal Title | Sensors |
Journal Citation | 22 (3), pp. 1-22 |
Article Number | 1147 |
Number of Pages | 22 |
Year | 2022 |
Publisher | MDPI AG |
Place of Publication | Switzerland |
ISSN | 1424-8220 |
1424-8239 | |
Digital Object Identifier (DOI) | https://doi.org/10.3390/s22031147 |
Web Address (URL) | https://www.mdpi.com/1424-8220/22/3/1147 |
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 com-prises 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. |
Keywords | Deep learning; Faster RCNN; Satellite images; SIMRDWN; SSD; YOLO |
Byline Affiliations | National University of Sciences and Technology, Pakistan |
University of New South Wales | |
Superior University, Pakistan | |
University of Sydney | |
Deakin University | |
Library Services |
https://research.usq.edu.au/item/w755w/automatic-target-detection-from-satellite-imagery-using-machine-learning
Download files
66
total views40
total downloads3
views this month4
downloads this month