An improved Capsule and its application in target recognition of SAR images

被引：0
作者：
Zhang P. [1 ,2 ,3 ,4 ,5 ]
Luo H. [1 ,2 ,4 ,5 ]
Ju M. [1 ,2 ,3 ,4 ,5 ]
Hui B. [1 ,2 ,4 ,5 ]
Chang Z. [1 ,2 ,4 ,5 ]
机构：
[1] Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang
[2] Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang
[3] University of Chinese Academy of Sciences, Beijing
[4] Key Laboratory of Opto-Electronic Information Processing, Chinese Academy of Sciences, Shenyang
[5] The Key Lab of Image Understanding and Computer Vision, Shenyang, 110016, Liaoning Province
来源：
Hongwai yu Jiguang Gongcheng/Infrared and Laser Engineering | 2020年 / 49卷 / 05期
关键词：
Brain-like calculation; Capsule network; Complete instantiation; Convolutional neural networks; Target recognition;
D O I：
10.3788/IRLA20201010
中图分类号：
学科分类号：
摘要：
In order to solve the problem that the Capsule network increases the amount of calculation and the number of parameters increases sharply with the input picture, the Capsule network is improved and the improved Capsule network is used in SAR automatic target recognition (SAR-ATR). In this paper, based on the mechanism of brain visual cortex processing information in hierarchical structure and column form, the idea of complete instantiation was proposed, and the brain-like calculation was used to improve the Capsule network. The specific method was to use multiple convolution layers to achieve hierarchical processing. The number of convolution kernels used in each layer increases with the depth of the hierarchy, which made the extracted abstract features gradually increase. In the PrimaryCaps layer, the Capsule vector consisted of all the feature maps output by the last layer of the convolutional layer, so that the Capsule unit contained all the features of the target part or the whole to achieve full instantiation of the target. On the SAR-ATR, a comparison experiment was performed with the Capsule network, the traditional target recognition algorithm and the target recognition algorithm based on the classical convolutional neural network. The experimental results show that the improved Capsule network training parameters and calculations are greatly reduced, and the training speed is greatly improved, and the recognition accuracy on the SAR image data set is increased by 0.37 and 1.96-8.96 percentage points compared with the Capsule network and the first two methods respectively. © 2020, Editorial Board of Journal of Infrared and Laser Engineering. All right reserved.
引用
收藏
相关论文
共 14 条
[1]  
Yang N., Nan L., Zhang D., Et al., Research on image interpretation based on deep learning, Infrared and Laser Engineering, 47, 2, (2018)
[2]  
Cohen T., Welling M., Group equivariant convolutional networks, International Conference on Machine Learning, pp. 2990-2999, (2016)
[3]  
Cohen T.S., Geiger M., Kohler J., Et al., Spherical cnns, (2018)
[4]  
Sabour S., Frosst N., Hinton G.E., Dynamic routing between Capsules, Computer Vision and Pattern Recognition, pp. 1-11, (2017)
[5]  
Sabour S., Frosst N., Hinton G., Matrix capsules with EM routing, 6th International Conference on Learning Representations, pp. 1-15, (2018)
[6]  
Hinton G.E., Krizhevsky A., Wang S.D., Transforming auto-encoders, International Conference on Artificial Neural Networks, pp. 44-51, (2011)
[7]  
Srinivas U., Monga V., Raj R.G., SAR automatic target recognition using discriminative graphical models, IEEE Transactions on Aerospace and Electronic Systems, 50, 1, pp. 591-606, (2014)
[8]  
Ding J., Chen B., Liu H., Et al., Convolutional neural network with data augmentation for SAR target recognition, IEEE Geoscience and Remote Sensing Letters, 13, 3, pp. 364-368, (2016)
[9]  
Morgan D.A.E., Deep convolutional neural networks for ATR from SAR imagery, Algorithms for Synthetic Aperture Radar Imagery XXII, 9475, (2015)
[10]  
O'Sullivan J.A., DeVore M.D., Kedia V., Et al., SAR ATR performance using a conditionally Gaussian model, IEEE Transactions on Aerospace and Electronic Systems, 37, 1, pp. 91-108, (2001)
12