Advertisement

Airport and Ship Target Detection on Satellite Images Based on YOLO V3 Network

  • Ren YingEmail author
Conference paper
  • 17 Downloads
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 657)

Abstract

Airplane and ship play a very important role in both civil life and military operations. It is a meaningful to detect airplane and ship around the world through remote sensing images. Target recognition algorithms based on deep learning technology are proven to be effective and gradually replacing traditional algorithms. This paper builds a target detection system based on NVIDIA TX2 development platform and YOLO V3 algorithm and focuses on both the ship and airplane targets. The training data comes from image fragments generated by satellites such as Jilin No. 1, DigitalGlobe, and Planet. The label of each target includes a bounding box and category information. The image processing method such as rotation and noise is added to increase the robustness of the trained YOLO V3 network for different sensors and atmosphere. The training of the input image takes about 3 days on an NVIDIA Titan X GPU. At test time, we partition testing images of arbitrary size into cutouts with a fixed size of 1 k × 1 k and run each cutout through our trained model to find ships and airplanes. The experimental results show that the F1-score values of the airport and the ship are 91.48% and 93.89%, respectively, and the detection speed of one cutout on NVIDIA TX2 development platform is about 0.56 s.

Keywords

Target detection Deep learning YOLO V3 Satellite images Training data 

References

  1. 1.
    Girshick R (2015) Fast R-CNN. In: IEEE conference on computer vision and pattern recognition, pp 1440–1448Google Scholar
  2. 2.
    He KM, Gkioxari G, Dollar P et al (2018) Mask R-CNN. In: IEEE conference on computer vision and pattern recognition, pp 1–12Google Scholar
  3. 3.
    Liu W, Anguelov D, Erhan D, et al (2016) SSD: signal shot multibox detector. In: IEEE conference on computer vision and pattern recognition, pp 21–37Google Scholar
  4. 4.
    Redmon J, Farhadi A (2018) YOLO V3: an incremental improvement. In: IEEE conference on computer vision and pattern recognition, pp 1–6Google Scholar
  5. 5.
    Redmon J, Farhadi A (2017) YOLO9000: better, faster, stronger. In: IEEE conference on computer vision and pattern recognition, pp 6517–6525Google Scholar
  6. 6.
    Redmon J, Divvala S, Girshick R, Farhadi A (2015) You only look once: unified, real-time object detection. arXiv:1506.02640

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.Chang Guang Satellite Technology Co., Ltd.ChangchunChina

Personalised recommendations