[1]刘玉华,陈建国.基于深度学习的高光谱图像多标签分类算法[J].福建工程学院学报,2018,16(03):264-270.[doi:10.3969/j.issn.1672-4348.2018.03.012]
 LIU Yuhua,CHEN Jianguo.A multi-label classification algorithm for hyperspectral image based on deep learning[J].Journal of FuJian University of Technology,2018,16(03):264-270.[doi:10.3969/j.issn.1672-4348.2018.03.012]
点击复制

基于深度学习的高光谱图像多标签分类算法()
分享到:

《福建工程学院学报》[ISSN:2097-3853/CN:35-1351/Z]

卷:
第16卷
期数:
2018年03期
页码:
264-270
栏目:
出版日期:
2018-06-25

文章信息/Info

Title:
A multi-label classification algorithm for hyperspectral image based on deep learning
作者:
刘玉华陈建国
福建工程学院应用技术学院
Author(s):
LIU Yuhua CHEN Jianguo
Institute of Applied Technology, Fujian University of Technology
关键词:
图像分类 高光谱图像 深度学习 自动编码器 逻辑回归
Keywords:
image classification hyperspectral image deep learning automatic encoder logic regression.
分类号:
TP311.1
DOI:
10.3969/j.issn.1672-4348.2018.03.012
文献标志码:
A
摘要:
提出一种基于深度学习的高光谱图像多标签分类算法。采用深度学习算法中的堆叠降噪自动编码器方法对每个像素的深层特征进行抽取,该方法可以有效表现高维特征空间中的非线性混合像素。使用多标签逻辑回归方法为每个像素预测并分配多个类标签。通过对合成数据和实际高光谱数据的大量对比实验,实验结果表明:该算法能够有效地为高光谱图像的像素精确地分配多类标签。
Abstract:
A multi-label classification algorithm was proposed for hyperspectral images based on deep learning. The deep features of each pixel were extracted by the Stacked Denoising Auto-Encoder(SDAE) method of deep learning, which could effectively represent the nonlinear mixed pixels in a high-dimensional feature space. In addition, a multi-label logical regression method was used to predict and assign multiple class labels for each pixel. The experimental results on the synthetic and actual hyperspectral image datasets show that the proposed algorithm can accurately assign multiple class labels to the pixels of hyperspectral images.

参考文献/References:

[1] 崔宾阁,吴子宾,秦学川,等.基于改进标签传播算法的高光谱图像半监督分类[J].山东科技大学学报,2016,35(6):101-107.
[2] 舒速.基于分水岭分割的高光谱图像分类算法研究[D].南京:南京师范大学,2015.
[3] COVERT M,HART P E. Nearest neighbor pattern classification[J]. IEEE Transactions on Information Theory, 1967, 13(1):21-27.
[4] CHAPELLE O, HAFFNER P, VAPNIK V N. Support vector machines for histogram-based image classification[J]. IEEE Transactions on Neural Networks, 1999, 10(5): 1055-1064.
[5] 邢晨.基于深度学习的高光谱遥感图像分类[D].武汉:中国地质大学,2016.
[6] LIANG H, LI Q. Hyperspectral imagery classification using sparse representations of convolutional neural network features[J]. Remote Sensing, 2016, 8(2): 1-16.
[7] 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): 298-306.
[8] 王曙.深度学习算法研究及其在图像分类上的应用[D].南京:南京邮电大学,2016.
[9] 高耀东,侯凌燕,杨大利.基于多标签学习的卷积神经网络的图像标注方法[J].计算机应用,2017,37(1): 228-232.
[10] 陈智.基于卷积神经网络的多标签场景分类[D].济南:山东大学,2015.
[11] CHEN Xing, MA Li, YANGXiaoquan. Stacked denoise autoencoder based feature extraction and classification for hyperspectral images[J]. Journal of Sensors, 2016(2): 112-119.
[12] 尹宝才,王文通,王立春.深度学习研究综述[J].北京工业大学学报,2015(1):48-59.
[13] 胡文瑜,蔡文培.数据挖掘取样方法的衡量与选用研究[J].福建工程学院学报,2011,9(4):351-356.
[14] HU W, HUANG Y, LI W. Deep convolutional neural networks for hyperspectral image classification[J]. Journal of Sensors, 2015(2): 21-28.
[15] READ J, PEREZ-CRUZF Perez-Cruz. Deep learning for multi-label classification[J]. Machine Learning, 2014, 85(3): 333-359.
[16] 王宪保,何文秀,王辛刚,等.基于堆叠降噪自动编码器的胶囊缺陷检测方法[J].计算机科学,2016,43(2):64-67.
[17] VIKTOR S, STEVEN V. Hyperspectral image Classification with convolutional neural networks[C]. Proceedings of the 23rd ACM International Conference on Multimedia (MM’15). 2015:1159-1162.
[18] PaginaDel Usuario.Grupo de InteligenciaComputacional. Universidad del Pais Vasco[Z/OL]. http:∥www.ehu.eus/ccwintco/index.php?title=Conjuntos_de_datos_3D. 2008.
[19] BAUMGARDNERMF, BIEHLL, LANDGREBEDA.Landgrebe. Band AVIRIS Hyperspectral Image Data Set[Z/OL]. https:∥purr.purdue.edu/publications/1947. 1992.
[20] FOSTERD H, Amano K, FOSTERMJ.Hyperspectral Images of Natural Scenes[Z/OL]. http:∥personalpages.manchester.ac.uk/staff/d.h.foster/Hyperspectral_images_of_natural_scenes_02.html.2002.

更新日期/Last Update: 2018-06-25