首页 > 论文 > 激光与光电子学进展 > 54卷 > 10期(pp:102801--1)

结合最小噪声分离变换和卷积神经网络的高分辨影像分类方法

High Resolution Image Classification Method Combining with Minimum Noise Fraction Rotation and Convolution Neural Network

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

摘要

针对传统浅层机器学习方法应用于高分辨影像分类时存在的问题, 提出了结合最小噪声分离变换和卷积神经网络的高分辨率影像分类方法。采用最小噪声分离分析非监督训练初始化卷积神经网络, 为提高训练速度, 使用线性修正函数作为神经网络的激活函数; 利用概率最大化采样原则减少池化过程中影像特征的缺失, 并将下采样后影像特征输入Softmax分类器进行分类。采用所提分类方法对典型地区的影像进行分类实验, 并与支持向量机和人工神经网络分类方法的分类结果进行对比。结果表明, 所提分类方法的分类精度明显高于另两种分类方法的分类精度, 并能充分挖掘高分辨遥感影像的空间信息。

Abstract

Aiming at the problems of traditional shallow machine learning methods applied to high resolution image classification, we propose a high resolution image classification method combining with minimum noise fraction (MNF) rotation and convolution neural networks (CNN). MNF is used to analyze the initial unsupervised pre-training CNN. Linear correction function is adopted as the activation function of the neural network to increase the training speed. In order to reduce the missing of image features in the process of the pool, the sampled image features are put into Softmax classifier under the principle of maximizing sampling probability. Experimental image of typical regions is selected and classified by using the proposed classification method, and the classification results are compared with those of support vector machines classification method and artificial neural network classification method. The results show that the classification accuracy of the proposed method is superior to the shallow machine learning classification methods, and can fully excavate the spatial information of high resolution remote sensing images.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:P237

DOI:10.3788/lop54.102801

所属栏目:遥感与传感器

基金项目:国家重点研发计划(2016YFC0803100)、国家自然科学基金(41101452)、高等学校博士学科点专项科研基金(20112121120003)、辽宁省教育厅科研项目(LJYL010)

收稿日期:2017-05-23

修改稿日期:2017-06-06

网络出版日期:--

作者单位    点击查看

陈 洋:辽宁工程技术大学测绘与地理科学学院, 辽宁 阜新 123000中国测绘科学研究院, 北京 100830
范荣双:中国测绘科学研究院, 北京 100830
王竞雪:辽宁工程技术大学测绘与地理科学学院, 辽宁 阜新 123000
吴增林:辽宁工程技术大学测绘与地理科学学院, 辽宁 阜新 123000
孙汝星:辽宁工程技术大学测绘与地理科学学院, 辽宁 阜新 123000

联系人作者:陈洋(874153187@qq.com)

备注:陈 洋(1991-), 男, 硕士研究生,主要从事影像分割、地物信息智能提取方面的研究。

【1】Cheriyadat A M. Unsupervised feature learning for aerial scene classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(1): 439-451.

【2】Luo B, Zhang L. Robust autodual morphological profiles for the classification of high-resolution satellite images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(2): 1451-1462.

【3】Huang X, Zhang L. An SVM ensemble approach combining spectral, structural, and semantic features for the classification of high-resolution remotely sensed imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2013, 51(1): 257-272.

【4】Han J, Zhang D, Cheng G, et al. Object detection in optical remote sensing images based on weakly supervised learning and high-level feature learning[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(6): 3325-3337.

【5】Liu Dawei, Han Ling, Han Xiaoyong. High spatial resolution remote sensing image classification based on deep learning[J]. Acta Optica Sinica, 2016, 36(4): 0428001.
刘大伟, 韩玲, 韩晓勇. 基于深度学习的高分辨率遥感影像分类研究[J]. 光学学报, 2016, 36(4): 0428001.

【6】Wu Yiquan, Tao Feixiang. Multispectral and panchromatic image fusion based on improved projected gradient NMF in NSST domain[J]. Acta Optica Sinica, 2015, 35(4): 0410005.
吴一全, 陶飞翔. 改进投影梯度NMF的NSST域多光谱与全色图像融合[J]. 光学学报, 2015, 35(4): 0410005.

【7】Chen Yang, Fan Rongshuang, Wang Jingxue, et al. Segmentation of high-resolution remote sensing image combining phase consistency with watershed transformation[J]. Laser & Optoelectronics Progress, 2017, 54(9): 092803.
陈洋, 范荣双, 王竞雪, 等. 结合相位一致和分水岭变换的高分辨率遥感影像分割方法[J]. 激光与光电子学进展, 2017, 54(9): 092803.

【8】Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks[C]. Proceedings of the 25th International Conference on Neural Information Processing Systems, 2012: 1097-1105.

【9】Ranzato M A, Fergus R, Kavukcuoglu K, et al. Learning invariant features through topographic filter maps[C]. IEEE Conference on Computer Vision and Pattern Recognition, 2009: 1605-1612.

【10】Ciresan D C, Meier U, Gambardella L M, et al. Convolutional neural network committees for handwritten character classification[C]. Proceedings of the 2011 International Conference on Document analysis and Recognition, 2011: 1135-1139.

【11】Kim Y. Convolutional neural networks for sentence classification[Z/OL]. (2014-09-03)[2017-00-00]. http://xueshu.baidu.com/s wd=paperuri%3A%287ea81182039becbb82a22aaae8099c15%29&filter=sc_long_sign&tn=SE_xueshusource_2kduw22v&sc_vurl=http%3A%2F%2Farxiv.org%2Fabs%2F1408.5882&ie=utf-8&sc_us=17214068522800736720.

【12】Ciresan D C, Meier U, Masci J, et al. Flexible, high performance convolutional neural networks for image classification[C]. Proceedings of the 22nd International Joint Conference on Artificial Intelligence, 2011: 1237-1242.

【13】Xiao Jinsheng, Liu Enyu, Zhu Li, et al. Improved image super-resolution algorithm based on convolutional neural network[J]. Acta Optica Sinica, 2017, 37(3): 0318011.
肖进胜, 刘恩雨, 朱力, 等. 改进的基于卷积神经网络的图像超分辨率算法[J]. 光学学报, 2017, 37(3): 0318011.

【14】Maggiori E, Tarabalka Y, Charpiat G, et al. Convolutional neural networks for large-scale remote-sensing image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(2): 645-657.

【15】Du Y, Bourlai T, Dawson J. Automated classification of mislabeled near-infrared left and right iris images using convolutional neural networks[C]. IEEE 8th International Conference on Biometrics Theory, Applications and Systems, 2016: 16555730.

引用该论文

Chen Yang,Fan Rongshuang,Wang Jingxue,Wu Zenglin,Sun Ruxing. High Resolution Image Classification Method Combining with Minimum Noise Fraction Rotation and Convolution Neural Network[J]. Laser & Optoelectronics Progress, 2017, 54(10): 102801

陈 洋,范荣双,王竞雪,吴增林,孙汝星. 结合最小噪声分离变换和卷积神经网络的高分辨影像分类方法[J]. 激光与光电子学进展, 2017, 54(10): 102801

被引情况

【1】陈洋,范荣双,王竞雪,陆婉芸,朱红,楚清源. 基于深度学习的资源三号卫星遥感影像云检测方法. 光学学报, 2018, 38(1): 128005--1

【2】方旭,王光辉,杨化超,刘慧杰,闫立波. 结合均值漂移分割与全卷积神经网络的高分辨遥感影像分类. 激光与光电子学进展, 2018, 55(2): 22802--1

【3】何志超,赵龙章,陈闯. 用于人脸表情识别的多分辨率特征融合卷积神经网络. 激光与光电子学进展, 2018, 55(7): 71503--1

【4】刘坤,苏彤,王典. 基于模糊不变卷积神经网络的遥感飞机识别. 激光与光电子学进展, 2018, 55(8): 82001--1

【5】宓保宏,洪文学,宋佳霖,吴士明,孟辉. 基于红外热成像技术与BP神经网络的心肌缺血预诊断方法研究. 激光与光电子学进展, 2019, 56(1): 11101--1

【6】王书宇,陶声祥,杨钒,艾磊. 基于卷积神经网络的激光距离选通式成像目标识别. 激光与光电子学进展, 2019, 56(2): 21001--1

【7】王民,樊潭飞,贠卫国,王稚慧. PFWG改进的CNN多光谱遥感图像分类. 激光与光电子学进展, 2019, 56(3): 31003--1

【8】裴亮,刘阳,谭海,高琳. 基于改进的全卷积神经网络的资源三号遥感影像云检测. 激光与光电子学进展, 2019, 56(5): 52801--1

【9】刘芳,王鑫,路丽霞,黄光伟,王洪娟. 基于稀疏编码和卷积神经网络的地貌图像分类. 光学学报, 2019, 39(4): 410001--1

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