Abstract
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.
Original language | English |
---|---|
Article number | 458 |
Journal | Remote Sensing |
Volume | 12 |
Issue number | 3 |
DOIs | |
Publication status | Published - 1 Feb 2020 |
Bibliographical note
Publisher Copyright:© 2020 by the authors.
Funding
This research received no external funding., Authors acknowledge the support of Istanbul Technical University-Center for Satellite Communications and Remote Sensing (ITU-CSCRS) by providing the Pleiades satellite images.
Funders | Funder number |
---|---|
Istanbul Technical University-Center for Satellite Communications and Remote Sensing |
Keywords
- Convolutional neural networks (CNNs)
- End-to-end detection
- Faster RCNN
- Remote sensing
- Single shot multi-box detector (SSD)
- Transfer learning
- You Look Only Once-v3 (YOLO-v3)