收稿：2019-06-10，
纸质出版：2020-04-07
移动端阅览
高光谱遥感技术在环境监测、应急保障、精细地物提取等方面有着广泛的应用，随着高分五号高光谱数据的正式发布，高光谱遥感技术将发挥更重要的作用。遥感影像分类作为高光谱遥感影像信息处理的重要部分，已成为当前研究重点。本文针对传统多级联森林深度学习中模型复杂、无法利用基分类器差异信息、对类间差异较小的样本无法正确区分等不足，提出了一种改进的多级联森林深度学习模型，在模型框架中，分别采用了随机森林和旋转森林作为基分类器，并引入逻辑回归分类器作为判别器用于训练层扩展。相较于传统的深度神经网络，改进的多级联森林深度网络超参数较少且能够自适应确定训练层，更方便进行模型优化。实验采用了高分五号数据集及两个公开的高光谱数据集(Indian Pines数据集及Pavia University数据集)进行精度评定，同时选择了传统分类器支持向量机、深度置信网等模型作为对比分析。实验结果表明，改进的多级联森林深度学习模型能有效地进行高光谱遥感影像分类，且较传统的分类方法精度有所提升。
With the release of GF-5 hyperspectral data
hyperspectral remote sensing plays an increasingly important role in environmental monitoring
emergency management
and object extraction. Classification is the primary problem of hyperspectral image applications. Some cascade forest models have been proposed to overcome the limitations of traditional deep neural networks
such as requiring excessive training samples and optimization of a large number of hyperparameters. Traditional cascade forest models have several disadvantages
such as (1) high model complexity
(2) homogeneous base classifiers
and (3) inability to discriminate the similar spectrum. In this study
a novel classification approach based on cascade forest is proposed to solve the above drawbacks.
The proposed improved cascade forest is an accumulation of layers
and each layer consists of two decision tree forests and a logistic regression classifier. Compared with traditional models
the number of forests in the improved method is reduced from four to two with the same accuracy and efficiency. Meanwhile
the original completely random tree forest is replaced by an efficient rotation forest to improve the diversity. The logistic regression classifier is added to determine the separating hyperplane among similar spectra. The number of layers is determined by the accuracy of validation set.
The proposed method is implemented on three hyperspectral datasets (GF-5
Indian Pines
and Pavia University datasets). DBN
SVM
RoF
RF
and original cascade forest are selected as the contrast methods. Experimental results on three different real hyperspectral datasets confirms the superiority of the proposed method
especially on the Indian Pines dataset
which has a similar spectrum. The improved cascade model can combine multiple classification results from different base classifiers to obtain the final results through the logistic regression classifier
and the quadratic discriminant process of the logistic regression classifier can effectively improve the classification accuracy. The impacts of the number of trees on the final results are discussed. The proposed model obtains the best performance with optimal parameters. Although the single training time is long
the insensitivity of model parameters immensely improves the training efficiency.
Compared with DNN
the improved cascade forest has the following advantages: (1) adaptive to determine the number of layers on the basis of the classification accuracy
(2) few hyperparameters are required in the improved cascade forest
making it easy to optimize the structure
and (3) each forest is independently trained because the training process do not have backpropagation
thereby accelerating the improved cascade forest by the CPU.
Breiman L . 1996 . Stacked regressions . Machine Learning , 24 ( 1 ): 49 - 64 [ DOI: 10.1007/BF00117832 http://dx.doi.org/10.1007/BF00117832 ]
Cao X H , Wen L , Ge Y M , Zhao J and Jiao L C . 2019 . Rotation-based deep forest for hyperspectral imagery classification . IEEE Geoscience and Remote Sensing Letters , 16 ( 7 ): 1105 - 1109 [ DOI: 10.1109/LGRS.2019.2892117 http://dx.doi.org/10.1109/LGRS.2019.2892117 ]
Chen Y S , Lin Z H , Zhao X , Wang G and Gu Y F . 2014 . Deep learning-based classification of hyperspectral data . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 7 ( 6 ): 2094 - 2107 [ DOI: 10.1109/jstars.2014.2329330 http://dx.doi.org/10.1109/jstars.2014.2329330 ]
Clarke B . 2003 . Comparing Bayes model averaging and stacking when model approximation error cannot be ignored . Journal of Machine Learning Research , 4 ( 4 ): 683 - 712 [ DOI: 10.1162/153244304773936090 http://dx.doi.org/10.1162/153244304773936090 ]
Du P J , Xia J S , Xue Z H , Tan K , Su H J and Bao R . 2016 . Review of hyperspectral remote sensing image classification . Journal of Remote Sensing , 20 ( 2 ): 236 - 256
杜培军 , 夏俊士 , 薛朝辉 , 谭琨 , 苏红军 , 鲍蕊 . 2016 . 高光谱遥感影像分类研究进展 . 遥感学报 , 20 ( 2 ): 236-256 ） [ DOI: 10.11834/jrs.20165022 http://dx.doi.org/10.11834/jrs.20165022 ]
Feng W and Bao W X . 2017 . Weight-based rotation forest for hyperspectral image classification . IEEE Geoscience and Remote Sensing Letters , 14 ( 11 ): 2167 - 2171 [ DOI: 10.1109/LGRS.2017.2757043 http://dx.doi.org/10.1109/LGRS.2017.2757043 ]
Ham J , Chen Y C , Crawford M M and Ghosh J . 2005 . Investigation of the random forest framework for classification of hyperspectral data . IEEE Transactions on Geoscience and Remote Sensing , 43 ( 3 ): 492 - 501 [ DOI: 10.1109/TGRS.2004.842481 http://dx.doi.org/10.1109/TGRS.2004.842481 ]
Hu J , Tan K and Wu L X . 2015 . An improved hyperspectral image clasification algorithm based on multinomial logistic regression . Remote Sensing Technology and Application , 30 ( 1 ): 135 - 139
胡俊 , 谭琨 , 吴立新 . 2015 . 一种基于多项式逻辑回归高光谱影像分类方法的改进 . 遥感技术与应用 , 30 ( 1 ): 135-139 ） [ DOI: 10.11873/j.issn.1004-0323.2015.1.0135 http://dx.doi.org/10.11873/j.issn.1004-0323.2015.1.0135 ]
Jiao Q J , Zhang B , Liu J G and Liu L Y . 2014 . A novel two-step method for winter wheat-leaf chlorophyll content estimation using a hyperspectral vegetation index . International Journal of Remote Sensing , 35 ( 21 ): 7363 - 7375 [ DOI: 10.1080/2150704X.2014.968681 http://dx.doi.org/10.1080/2150704X.2014.968681 ]
Li J , Bioucas-Dias J M and Plaza A . 2012 . Spectral–spatial hyperspectral image segmentation using subspace multinomial logistic regression and Markov random fields . IEEE Transactions on Geoscience and Remote Sensing , 50 ( 3 ): 809 - 823 [ DOI: 10.1109/TGRS.2011.2162649 http://dx.doi.org/10.1109/TGRS.2011.2162649 ]
Li J J , Xi B B , Li Y S , Du Q and Wang K Y . 2018 . Hyperspectral classification based on texture feature enhancement and deep belief networks . Remote Sensing , 10 ( 3 ): 396 [ DOI: 10.3390/rs10030396 http://dx.doi.org/10.3390/rs10030396 ]
Li X K , Wang J N , Zhang L F , Wu T X , Yang H , Liu K and Jiang H L . 2014 . A combined object-based segmentation and support vector machines approach for classification of Tiangong-1 hyperspectral image. Journal of Remote Sensing, 18(zl): 107 - 115
李雪轲 , 王晋年 , 张立福 , 吴太夏 , 杨杭 , 刘凯 , 姜海玲 . 2014 . 面向对象规则和支持向量机的天宫一号高光谱影像分类.遥感学报,18(z1): 107 - 115 ） [DOI: 10.11834/jrs.2014z16]
Liu Z , Tang B , He X F , Qiu Q C and Liu F . 2017 . Class-specific random forest with cross-correlation constraints for spectral–spatial hyperspectral image classification . IEEE Geoscience and Remote Sensing Letters , 14 ( 2 ): 257 - 261 [ DOI: 10.1109/LGRS.2016.2637561 http://dx.doi.org/10.1109/LGRS.2016.2637561 ]
Melgani F and Bruzzone L . 2004 . Classification of hyperspectral remote sensing images with support vector machines . IEEE Transactions on Geoscience and Remote Sensing , 42 ( 8 ): 1778 - 1790 [ DOI: 10.1109/TGRS.2004.831865 http://dx.doi.org/10.1109/TGRS.2004.831865 ]
Moser G and Serpico S B . 2013 . Combining support vector machines and Markov random fields in an integrated framework for contextual image classification . IEEE Transactions on Geoscience and Remote Sensing , 51 ( 5 ): 2734 - 2752 [ DOI: 10.1109/TGRS.2012.2211882 http://dx.doi.org/10.1109/TGRS.2012.2211882 ]
Pal M . 2005 . Random forest classifier for remote sensing classification . International Journal of Remote Sensing , 26 ( 1 ): 217 - 222 [ DOI: 10.1080/01431160412331269698 http://dx.doi.org/10.1080/01431160412331269698 ]
Paoletti M E , Haut J M , Plaza J and Plaza A . 2018 . A new deep convolutional neural network for fast hyperspectral image classification . ISPRS Journal of Photogrammetry and Remote Sensing , 145 : 120 - 147 [ DOI: 10.1016/j.isprsjprs.2017.11.021 http://dx.doi.org/10.1016/j.isprsjprs.2017.11.021 ]
Rodríguez J J , Kuncheva L I and Alonso C J . 2006 . Rotation forest: a new classifier ensemble method . IEEE Transactions on Pattern Analysis and Machine Intelligence , 28 ( 10 ): 1619 - 1630 [ DOI: 10.1109/TPAMI.2006.211 http://dx.doi.org/10.1109/TPAMI.2006.211 ]
Seewald A K . 2002 . How to make stacking better and faster while also taking care of an unknown weakness // Proceedings of the Nineteenth International Conference on Machine Learning . San Francisco : Morgan Kaufmann : 554 - 561
Tan K , Li E Z , Du Q and Du P J . 2014 . An efficient semi-supervised classification approach for hyperspectral imagery . ISPRS Journal of Photogrammetry and Remote Sensing , 97 : 36 - 45 [ DOI: 10.1016/J.ISPRSJPRS.2014.08.003 http://dx.doi.org/10.1016/J.ISPRSJPRS.2014.08.003 ]
Xia J S , Du P J , He X Y and Chanussot J . 2014 . Hyperspectral remote sensing image classification based on rotation forest . IEEE Geoscience and Remote Sensing Letters , 11 ( 1 ): 239 - 243 [ DOI: 10.1109/LGRS.2013.2254108 http://dx.doi.org/10.1109/LGRS.2013.2254108 ]
Xu J H , Shen Y , Liu P F and Xiao L . 2018 . Hyperspectral image classification combining kernel sparse multinomial logistic regression and TV-L 1 error rejection. Acta Electronica Sinica , 46 ( 1 ): 175 - 184
徐金环 , 沈煜 , 刘鹏飞 , 肖亮 . 2018 . 联合核稀疏多元逻辑回归和TV-l1错误剔除的高光谱图像分类算法 . 电子学报 , 46 ( 1 ): 175-184 ） [ DOI: 10.3969/j.issn.0372-2112.2018.01.024 http://dx.doi.org/10.3969/j.issn.0372-2112.2018.01.024 ]
Zhang B . 2016 . Advancement of hyperspectral image processing and information extraction . Journal of Remote Sensing , 20 ( 5 ): 1062 - 1090
张兵 . 2016 . 高光谱图像处理与信息提取前沿 . 遥感学报 , 20 ( 5 ): 1062-1090 ） [ DOI: 10.11834/jrs.20166179 http://dx.doi.org/10.11834/jrs.20166179 ]
Zhang B , Chen Z C , Zheng L F , Tong Q X , Liu Y N , Yang Y D and Xue Y Q . 2004 . Object detection based on feature extraction from hyperspectral imagery and convex cone projection transform . Journal of Infrared and Millimeter Waves , 23 ( 6 ): 441 - 445, 450
张兵 , 陈正超 , 郑兰芬 , 童庆禧 , 刘银年 , 杨一德 , 薛永祺 . 2004 . 基于高光谱图像特征提取与凸面几何体投影变换的目标探测 . 红外与毫米波学报 , 23 ( 6 ): 441 - 445 , 450 ） [ DOI: 10.3321/j.issn:1001-9014.2004.06.010 http://dx.doi.org/10.3321/j.issn:1001-9014.2004.06.010 ]
Zhang L P and Li J Y . 2016 . Development and prospect of sparse representation-based hyperspectral image processing and analysis . Journal of Remote Sensing , 20 ( 5 ): 1091 - 1101
张良培 , 李家艺 . 2016 . 高光谱图像稀疏信息处理综述与展望 . 遥感学报 , 20 ( 5 ): 1091-1101 ） [ DOI: 10.11834/jrs.20166050 http://dx.doi.org/10.11834/jrs.20166050 ]
Zhang L P , Zhang L F and Du B . 2016 . Deep learning for remote sensing data: a technical tutorial on the state of the art . IEEE Geoscience and Remote Sensing Magazine , 4 ( 2 ): 22 - 40 [ DOI: 10.1109/MGRS.2016.2540798 http://dx.doi.org/10.1109/MGRS.2016.2540798 ]
Zhang Y Q , Cao G , Li X S and Wang B S . 2018 . Cascaded random forest for hyperspectral image classification . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 11 ( 4 ): 1082 - 1094 [ DOI: 10.1109/JSTARS.2018.2809781 http://dx.doi.org/10.1109/JSTARS.2018.2809781 ]
Zhao S H , Liu S H , Wu D , Wu Y T and Liu Q Q . 2018 . Potential application analysis of GF-5 satellite in ecology and environment fields . Spacecraft Recovery and Remote Sensing , 39 ( 3 ): 115 - 120
赵少华 , 刘思含 , 吴迪 , 吴艳婷 , 刘芹芹 . 2018 . " 高分五号"卫星生态环境领域应用前景 . 航天返回与遥感 , 39 ( 3 ): 115-120 ） [ DOI: 10.3969/j.issn.1009-8518.2018.03.013 http://dx.doi.org/10.3969/j.issn.1009-8518.2018.03.013 ]
Zhou Z H and Feng J . 2017 . Deep forest: towards an alternative to deep neural networks // Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence . Melbourne, Australia : IJCAI : 3553 - 3559 [ DOI: 10.24963/ijcai.2017/497 http://dx.doi.org/10.24963/ijcai.2017/497 ]
Zhu L , Chen Y S , Ghamisi P and Benediktsson J A . 2018 . Generative adversarial networks for hyperspectral image classification . IEEE Transactions on Geoscience and Remote Sensing , 56 ( 9 ): 5046 - 5063 [ DOI: 10.1109/TGRS.2018.2805286 http://dx.doi.org/10.1109/TGRS.2018.2805286 ]
相关作者
相关机构
京公网安备11010802024621
