Next Article in Journal
Land Subsidence Response to Different Land Use Types and Water Resource Utilization in Beijing-Tianjin-Hebei, China
Next Article in Special Issue
Improved Winter Wheat Spatial Distribution Extraction from High-Resolution Remote Sensing Imagery Using Semantic Features and Statistical Analysis
Previous Article in Journal
Discriminative Feature Learning Constrained Unsupervised Network for Cloud Detection in Remote Sensing Imagery
Previous Article in Special Issue
A Coarse-to-Fine Network for Ship Detection in Optical Remote Sensing Images
Open AccessArticle

Comparative Research on Deep Learning Approaches for Airplane Detection from Very High-Resolution Satellite Images

1
Geomatics Engineering Department, Istanbul Technical University, ITU Ayazaga Campus, Civil Engineering Faculty, Sariyer, 34469 Istanbul, Turkey
2
Institute of Informatics, Satellite Communication and Remote Sensing Program, Istanbul Technical University, ITU Ayazaga Campus, Institute of Informatics Building, Sariyer, 34469 Istanbul, Turkey
*
Author to whom correspondence should be addressed.
Remote Sens. 2020, 12(3), 458; https://doi.org/10.3390/rs12030458
Received: 18 December 2019 / Revised: 26 January 2020 / Accepted: 30 January 2020 / Published: 1 February 2020
Object detection from satellite images has been a challenging problem for many years. With the development of effective deep learning algorithms and advancement in hardware systems, higher accuracies have been achieved in the detection of various objects from very high-resolution (VHR) satellite images. This article provides a comparative evaluation of the state-of-the-art convolutional neural network (CNN)-based object detection models, which are Faster R-CNN, Single Shot Multi-box Detector (SSD), and You Look Only Once-v3 (YOLO-v3), to cope with the limited number of labeled data and to automatically detect airplanes in VHR satellite images. Data augmentation with rotation, rescaling, and cropping was applied on the test images to artificially increase the number of training data from satellite images. Moreover, a non-maximum suppression algorithm (NMS) was introduced at the end of the SSD and YOLO-v3 flows to get rid of the multiple detection occurrences near each detected object in the overlapping areas. The trained networks were applied to five independent VHR test images that cover airports and their surroundings to evaluate their performance objectively. Accuracy assessment results of the test regions proved that Faster R-CNN architecture provided the highest accuracy according to the F1 scores, average precision (AP) metrics, and visual inspection of the results. The YOLO-v3 ranked as second, with a slightly lower performance but providing a balanced trade-off between accuracy and speed. The SSD provided the lowest detection performance, but it was better in object localization. The results were also evaluated in terms of the object size and detection accuracy manner, which proved that large- and medium-sized airplanes were detected with higher accuracy. View Full-Text
Keywords: convolutional neural networks (CNNs); end-to-end detection; transfer learning; remote sensing; single shot multi-box detector (SSD); You Look Only Once-v3 (YOLO-v3); Faster RCNN convolutional neural networks (CNNs); end-to-end detection; transfer learning; remote sensing; single shot multi-box detector (SSD); You Look Only Once-v3 (YOLO-v3); Faster RCNN
Show Figures

Graphical abstract

MDPI and ACS Style

Alganci, U.; Soydas, M.; Sertel, E. Comparative Research on Deep Learning Approaches for Airplane Detection from Very High-Resolution Satellite Images. Remote Sens. 2020, 12, 458. https://doi.org/10.3390/rs12030458

AMA Style

Alganci U, Soydas M, Sertel E. Comparative Research on Deep Learning Approaches for Airplane Detection from Very High-Resolution Satellite Images. Remote Sensing. 2020; 12(3):458. https://doi.org/10.3390/rs12030458

Chicago/Turabian Style

Alganci, Ugur; Soydas, Mehmet; Sertel, Elif. 2020. "Comparative Research on Deep Learning Approaches for Airplane Detection from Very High-Resolution Satellite Images" Remote Sens. 12, no. 3: 458. https://doi.org/10.3390/rs12030458

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop