Ship detection in SAR images based on deep convolutional neural network

被引：4
|
作者：
Yang L. [1 ]
Su J. [1 ]
Li X. [1 ]
机构：
[1] College of Nuclear Engineering, Rocket Force University of Engineering, Xi'an
来源：
Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics | 2019年 / 41卷 / 09期
关键词：
Deep convolutional neural network; Ship detection; Single shot multibox detector (SSD) detection algorithm;
D O I：
10.3969/j.issn.1001-506X.2019.09.11
中图分类号：
学科分类号：
摘要：
Aiming at the problems that the detection accuracy of ship detection in synthetic aperture radar (SAR) images is susceptible to speckle noise, and traditional algorithms only extract the underlying features and the generalization is poor, this paper proposes a ship detection algorithm based on deep convolutional neural network. First, the current single shot multibox detector (SSD) detection algorithm is applied to the field of SAR image ship detection, and its limitations are pointed out. Next, improved detection methods based on SSD are proposed, including context information fusion and transfer model learning. Finally, the experimental results on the open ship dataset show that, compared with the original SSD detection algorithm, the proposed method not only improves the target detection accuracy, but also ensures the efficiency of the algorithm. © 2019, Editorial Office of Systems Engineering and Electronics. All right reserved.
引用
收藏
页码：1990 / 1997
页数：7
相关论文
共 29 条
  • [1] Lowe D.G., Distinctive image features from scale-invariant keypoints, International Journal of Computer Vision, 60, 2, pp. 91-110, (2004)
  • [2] Dalal N., Triggs B., Histograms of oriented gradients for human detection, Proc.of the IEEE Computer Society International Conference on Computer Vision & Pattern Recognition, pp. 886-893, (2005)
  • [3] Stagliano D., Lupidi A., Berizzi F., Ship detection from SAR images based on CFAR and wavelet transform, Proc.of the Tyrrhenian Workshop on Advances in Radar and Remote Sensing, pp. 53-58, (2012)
  • [4] Zhai L., Li Y., Su Y., Ship detection method based on anomaly detection and double-layer screening mechanism for SAR images, Computer Engineering, 43, 4, pp. 244-250, (2017)
  • [5] He J., Wang Y., Liu H., Et al., A novel automatic PolSAR ship detection method based on superpixel-level local information measurement, IEEE Geoscience & Remote Sensing Letters, 15, 3, pp. 384-388, (2018)
  • [6] Gui G., Sheng G., He J., Et al., Ship detection using compact polarimetric SAR based on the notch filter, IEEE Trans.on Geoscience & Remote Sensing, 56, 9, pp. 5380-5393, (2018)
  • [7] Deng J., Zhang Z., Eyben F., Et al., Autoencoder-based unsupervised domain adaptation for speech emotion recognition, IEEE Signal Processing Letters, 21, 9, pp. 1068-1072, (2014)
  • [8] Shim V.A., Tan K.C., Chia J.Y., An investigation on sampling technique for multi-objective restricted Boltzmann machine, Proc.of the IEEE Congress on Evolutionary Computation, pp. 1-8, (2010)
  • [9] Krizhevsky A., Sutskever I., Hinton G.E., Imagenet classification with deep convolutional neural networks, Proc.of the Advances in Neural Information Processing Systems, pp. 1097-1105, (2012)
  • [10] Ballester P., Araujo R.M., On the performance of GoogLeNet and AlexNet applied to sketches, Proc.of the 30th AAAI Conference on Artificial Intelligence, pp. 1124-1128, (2016)
123