2022
DOI: 10.3390/s22031147
|View full text |Cite
|
Sign up to set email alerts
|

Automatic Target Detection from Satellite Imagery Using Machine Learning

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 … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
12
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
6
4

Relationship

2
8

Authors

Journals

citations
Cited by 40 publications
(12 citation statements)
references
References 90 publications
0
12
0
Order By: Relevance
“…Among them, the YOLO ( 27) series and single-shot detector (SSD) (45) are typical representations of one-stage detection, and the faster region-based convolutional neural network (faster-RCNN) ( 46) is a typical representation of a two-stage detection model. Tahir et al previously reported that the faster-RCNN had a higher accuracy (95.31%) than YOLO (94.2%) and SSD (84.61%) in satellite imagery to detect objects; however, YOLO is an obvious leader in terms of speed and efficiency (47). Alkentar et al indicated that SSD had good detection ability but a high false positive ratio for drone detection.…”
Section: Discussionmentioning
confidence: 99%
“…Among them, the YOLO ( 27) series and single-shot detector (SSD) (45) are typical representations of one-stage detection, and the faster region-based convolutional neural network (faster-RCNN) ( 46) is a typical representation of a two-stage detection model. Tahir et al previously reported that the faster-RCNN had a higher accuracy (95.31%) than YOLO (94.2%) and SSD (84.61%) in satellite imagery to detect objects; however, YOLO is an obvious leader in terms of speed and efficiency (47). Alkentar et al indicated that SSD had good detection ability but a high false positive ratio for drone detection.…”
Section: Discussionmentioning
confidence: 99%
“…However, they cannot deal with large quantities of datasets. The limitation of traditional ML methods is that they cannot learn more complex features and cannot deal with the complex information within images, such as background pavement with different lighting [7,26].…”
Section: Traditional Machine Learning (Ml) Methodsmentioning
confidence: 99%
“…Munawar et al [51] wrote an overview of the use of disruptive technologies to move towards automated disaster prediction and forecasting. Tahir et al [52] created a satellite image dataset by using a convolutional neural network-based framework to perform object detection. Qadir et al [53] analyzed various metaheuristic algorithms for pre-disaster assessment and realize the function of UAV path optimization.…”
Section: Assessment and Measurement Of Waterlogging Resiliencementioning
confidence: 99%