首页 > 论文 > 激光与光电子学进展 > 55卷 > 11期(pp:111504--1)

基于深度学习的极光序列自动分类方法

Aurora Sequence Classification Based on Deep Learning

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

提出一种基于深度学习的极光序列分类方法,有效结合卷积神经网络(CNN)特征丰富的空间域信息和长短时记忆(LSTM)网络捕捉序列信息的优势,并利用极光的属性对CNN添加反馈约束调节使特征更契合极光图像。在中国北极黄河站的全天空成像仪(ASI)极光图像数据库上进行有监督的极光序列分类研究和无监督的极光事件检测,实验结果表明本文方法能有效用于极光序列的表征,为海量极光序列的自动分类提供了可能性。

Abstract

An aurora sequence classification method based on deep learning is proposed. It combines the rich spatial domain information and the sequence information corresponding to the advantages of convolutional neural network (CNN) features and long short-term memory (LSTM) network. In addition, aurora attributes employed as feedback constraints to the CNN make features more suitable for aurora images. Supervised aurora sequence classification and unsupervised aurora event detection are performed on the Chinese Yellow River Station All-Sky Imager (ASI) dataset. The experiment shows that our method can characterize aurora sequences effectively and can be able to implement automatic classification for massive aurora sequences.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391

DOI:10.3788/lop55.111504

所属栏目:机器视觉

基金项目:国家自然科学基金(61571353)

收稿日期:2018-04-15

修改稿日期:2018-05-09

网络出版日期:2018-05-29

作者单位    点击查看

张浩:南京邮电大学通信与信息工程学院, 江苏 南京 210003
陈昌红:南京邮电大学通信与信息工程学院, 江苏 南京 210003

联系人作者:陈昌红(chenchh@njupt.edu.cn); 张浩(ztqup666@outlook.com);

【1】Wang Q, Liang J, Hu Z J, et al. Spatial texture based automatic classification of dayside aurora in all-sky images[J]. Journal of Atmospheric and Solar-Terrestrial Physics, 2010, 72(5): 498-508.

【2】Yang Q J, Hu Z J. An automatic auroral classification method based on morphological characteristics[J]. Scientia Sinica (Terrae), 2017, 47(2): 252-260.
杨秋菊, 胡泽骏. 一种基于形态特征的极光自动分类方法[J]. 中国科学: 地球科学, 2017, 47(2): 252-260.

【3】Han B, Qiu W L. Aurora images classification via features salient coding[J]. Journal of Xidian University, 2013, 40(6): 180-186.
韩冰, 仇文亮. 一种特征显著性编码的极光图像分类方法[J]. 西安电子科技大学学报, 2013, 40(6): 180-186.

【4】Han B, Jia Z H, Gao X B. Improved PCANet for aurora images classification[J]. Journal of Xidian University, 2017, 44(1): 83-88.
韩冰, 贾中华, 高新波. 改进的主成分分析网络极光图像分类方法[J]. 西安电子科技大学学报, 2017, 44(1): 83-88.

【5】Yang Q J, Liang J M, Hu Z J, et al. Auroral sequence representation and classification using hidden Markov models[J]. IEEE Transactions on Geoscience and Remote Sensing, 2012, 50(12): 5049-5060.

【6】Xu B, Chen C, Gan Z, et al. Aurora sequences classification and aurora events detection based on hidden conditional random fields[C]∥Chinese Conference on Pattern Recognition, Springer Singapore, 2016: 404-415.

【7】Han B, Song Y, Gao X, et al. Dynamic aurora sequence recognition using Volume Local Directional Pattern with local and global features[J]. Neurocomputing, 2016, 184: 168-175.

【8】Song Y T, Han B, Gao X B. Tensor based dynamic textures model for aurora sequences classification[J]. Journal of Nanjing University (Natural Science), 2016, 52(1): 184-193.
宋亚婷, 韩冰, 高新波. 基于张量动态纹理模型的极光视频分类[J]. 南京大学学报(自然科学版), 2016, 52(1): 184-193.

【9】Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks[C]∥Advances in Neural Information Processing Systems, 2012: 1097-1105.

【10】Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.

【11】Matsukawa T, Suzuki E. Person re-identification using CNN features learned from combination of attributes[C]∥International Conference on Pattern Recognition, IEEE, 2017: 2428-2433.

【12】Simonyan K, Zisserman A. Two-stream convolutional networks for action recognition in videos[C]∥International Conference on Neural Information Processing Systems, MIT Press, 2014: 568-576.

【13】Donahue J, Hendricks L A, Guadarrama S, et al. Long-term recurrent convolutional networks for visual recognition and description[C]∥IEEE Conference on Computer Vision and Pattern Recognition, 2015: 2625-2634.

【14】Ye G L, Sun S Y, Gao K J, et al. Nighttime pedestrian detection based on faster region convolution neural network[J]. Laser & Optoelectronics Progress, 2017, 54(8): 081003.
叶国林, 孙韶媛, 高凯珺, 等. 基于加速区域卷积神经网络的夜间行人检测研究[J]. 激光与光电子学进展, 2017, 54(8): 081003.

【15】Zou Y B, Zhou W L, Chen X Z. Research of laser vision seam detection and tracking system based on depth hierarchical feature[J]. Chinese Journal of Lasers, 2017, 44(4): 0402009.
邹焱飚, 周卫林, 陈向志. 基于深度分层特征的激光视觉焊缝检测与跟踪系统研究[J]. 中国激光, 2017, 44(4): 0402009.

【16】Xu L, Zhao H T, Sun S Y. Monocular infrared image depth estimation based on deep convolutional neural networks[J]. Acta Optica Sinica, 2016, 36(7): 0715002.
许路, 赵海涛, 孙韶媛. 基于深层卷积神经网络的单目红外图像深度估计[J].光学学报, 2016, 36(7): 0715002.

【17】Wu S C, Zhao H T, Sun S Y. Depth estimation from monocular infrared video based on bi-recursive convolutional neural network[J]. Acta Optica Sinica, 2017, 37(12): 1215003.
吴寿川, 赵海涛, 孙韶媛. 基于双向递归卷积神经网络的单目红外视频深度估计[J]. 光学学报, 2017, 37(12): 1215003.

【18】Xu Y, Lu Y. Adaptive weighted fusion: A novel fusion approach for image classification[J]. Neurocomputing, 2015, 168: 566-574.

【19】Deng J, Dong W, Socher R, et al. ImageNet: a large-scale hierarchical image database[C]∥IEEE Conference on Computer Vision and Pattern Recognition, 2009: 248-255.

【20】Hu Z J, Yang H, Huang D, et al. Synoptic distribution of dayside aurora: multiple-wavelength all-sky observation at Yellow River Station in Ny-lesund, Svalbard[J]. Journal of Atmospheric and Solar-Terrestrial Physics, 2009, 71(8): 794-804.

【21】Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[C]∥International Conference on Learning Representations, 2015: 1-14.

【22】Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift[C]∥International Conference on Machine Learning, 2015: 448-456.

【23】Kingma D P, Ba J. Adam: a method for stochastic optimization[C]∥3rd International Conference for Learning Representations, 2015.

【24】Wang Q, Hu H Q, Hu Z J, et al. A method for detecting the change of auroral activities based on the all-sky image sequence[J]. Chinese Journal of Geophysics, 2015, 58(9): 3038-3047.
王倩, 胡红桥, 胡泽骏, 等. 基于全天空图像的极光活动变化检测方法研究[J]. 地球物理学报, 2015, 58(9): 3038-3047.

引用该论文

Zhang Hao,Chen Changhong. Aurora Sequence Classification Based on Deep Learning[J]. Laser & Optoelectronics Progress, 2018, 55(11): 111504

张浩,陈昌红. 基于深度学习的极光序列自动分类方法[J]. 激光与光电子学进展, 2018, 55(11): 111504

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF