具有分类器机制的高光谱图像特征提取方法

邢长达; 汪美玲; 徐雍倡; 王志胜

doi:10.11834/jrs.20233065

遥感智能解译 | 浏览量 : 0 下载量: 575 CSCD: 0

R-PDF
PDF
导出
分享
收藏
专辑

具有分类器机制的高光谱图像特征提取方法
Classifier mechanism embedded feature-extraction method for hyperspectral images
2024年28卷第2期页码：511-527
纸质出版日期： 2024-02-07 ，
DOI： 10.11834/jrs.20233065
稿件说明：

移动端阅览

邢长达，汪美玲，徐雍倡，王志胜.2024.具有分类器机制的高光谱图像特征提取方法.遥感学报，28（2）： 511-527

Xing C D，Wang M L，Xu Y C and Wang Z S.2024. Classifier mechanism embedded feature-extraction method for hyperspectral images. National Remote Sensing Bulletin， 28（2）：511-527
邢长达，汪美玲，徐雍倡，王志胜.2024.具有分类器机制的高光谱图像特征提取方法.遥感学报，28（2）： 511-527 DOI： 10.11834/jrs.20233065.

Xing C D，Wang M L，Xu Y C and Wang Z S.2024. Classifier mechanism embedded feature-extraction method for hyperspectral images. National Remote Sensing Bulletin， 28（2）：511-527 DOI： 10.11834/jrs.20233065.

摘要

高光谱图像分类是图像解译任务的重要技术之一，已经在遥感观测、智慧医疗等诸多领域得到广泛的应用。本质上，高光谱图像分类由特征提取与基于分类器的标签预测这两阶段操作组成。现有分类方法在特征提取时，大多不考虑分类器的影响，会导致提取的特征与所用分类器之间的兼容性较差，难免出现预测结果差的情况。针对此问题，本文提出具有分类器机制的高光谱图像特征提取方法，保证特征提取与分类器之间的兼容性，使特征能更易于被分类器准确计算，改善分类预测结果。本文给出了两种具有分类器机制的高光谱图像特征提取模型的形式：（1）以稀疏表示和支持向量机为例，将支持向量机特性集成到稀疏表示形式中，建立了能够与支持向量机分类器相兼容的SRS特征提取模型；（2）以深度自编码网络与softmax函数为例，将softmax分类器特性嵌入到深度自编码网络中，构建能与softmax分类器相兼容的DAES特征提取模型。为获得SRS和DAES模型的解，本文还给出了对应的求解策略与优化过程。在遥感高光谱图像和医学高光谱图像数据上开展实验验证，结果表明，本文SRS和DAES算法具有明显的有效性和优越性，在高光谱图像分类指标OA（Overall Accuracy）、AA（Average Accuracy）、Kappa上分别提升约5.03%、5.13%、7.30%。

Abstract

As an important technique in image interpretation

hyperspectral image (HSI) classification is extensively used in many fields

such as remote-sensing observation and intelligent medical service. HSI classification may comprise label prediction based on feature extraction and based on classifiers. Although deep learning can directly obtain the classification results by one step

which is achieved by the end-to-end network structure from data input to classification result output

they are actually viewed as a direct cascade of both feature extraction based on deep networks (such as deep autoencoder and convolutional neural network) and classifiers (such as softmax and logistic regression). Most current classification approaches do not consider the influence of classifiers on feature extraction

which may cause the incompatibility between the extracted features and the used classifier. This incompatibility is reflected in the poor matching relationship between the classifier model and its input feature data

leading to poor prediction results.Method To remedy such deficiency

this paper presents a novel kind of HSI feature-extraction methods embedded by the classifier mechanism

which can ensure the compatibility between feature extraction and the used classifier. Thus

the features can be more easily calculated by classifier accurately

and classification prediction results can be improved. Two specific forms are given in this paper. 1) The sparse representation (SR)feature-extraction model compatible with Support Vector Machine (SVM) classifier is built

which embeds the SVM property into the SR. 2) The deep autoencoder (DAE) feature-extraction model compatible with softmax classifier is constructed

which integrates the softmax function into DAE network. We also provide the optimization strategy to obtain the optimal solutions of the SR and DAE models.Results The proposed SR and DAE models are experimentally evaluated on the remote-sensing HSI data and medical HSI data. The experiments consist of parameter analysis

algorithm comparison

ablation study

and convergence analysis. According to the parameter analysis

we validate that the values of important parameters have obvious impact on the performance of our methods and successfully select the best values of these parameters. As suggested by the algorithm comparison

the proposed methods achieve better classification performance than some state-of-the-art approaches

which have obvious effectiveness and superiority. The overall accuracy

average accuracy

and Kappa indices in the HSI classification task are

on average

higher by 5.03%

5.13%

and 7.30%

respectively. An ablation study is conducted to demonstrate the effectiveness of the compatibility between feature extraction and the bedded classifiers for the performance improvement of HSI classification. Convergence analysis indicates that the designed optimization-solution strategy can meet the application requirements of reliability and rapidity.Conclusion The proposed SR and DAE methods realize good compatibility between feature extraction and classifiers. Accordingly

the extracted features can be better calculated by classifiers

and more competitive classification performance can be achieved.

关键词

高光谱图像分类特征提取分类器机制稀疏表示深度自编码网络

Keywords

hyperspectral image classificationfeature extractionclassifier mechanismsparse representationdeep autoencoder network

references

Bai J, Lu J W, Xiao Z, Chen Z and Jiao L C. 2022. Generative adversarial networks based on transformer encoder and convolution block for hyperspectral image classification. Remote Sensing, 14(14): 3426 [DOI: 10.3390/rs14143426http://dx.doi.org/10.3390/rs14143426]

Benediktsson J A, Palmason J A and Sveinsson J R. 2005. Classification of hyperspectral data from urban areas based on extended morphological profiles. IEEE Transactions on Geoscience and Remote Sensing, 43(3): 480-491 [DOI: 10.1109/TGRS.2004.842478http://dx.doi.org/10.1109/TGRS.2004.842478]

Benediktsson J A, Pesaresi M and Amason K. 2003. Classification and feature extraction for remote sensing images from urban areas based on morphological transformations. IEEE Transactions on Geoscience and Remote Sensing, 41(9): 1940-1949 [DOI: 10.1109/TGRS.2003.814625http://dx.doi.org/10.1109/TGRS.2003.814625]

Cao X Y, Yao J, Xu Z B and Meng D Y. 2020. Hyperspectral image classification with convolutional neural network and active learning. IEEE Transactions on Geoscience and Remote Sensing, 58(7): 4604-4616 [DOI: 10.1109/TGRS.2020.2964627http://dx.doi.org/10.1109/TGRS.2020.2964627]

Chen Y, Nasrabadi N M and Tran T D. 2011. Hyperspectral image classification using dictionary-based sparse representation. IEEE Transactions on Geoscience and Remote Sensing, 49(10): 3973-3985 [DOI: 10.1109/TGRS.2011.2129595http://dx.doi.org/10.1109/TGRS.2011.2129595]

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.2014.2329330http://dx.doi.org/10.1109/JSTARS.2014.2329330]

Chen Y S, Zhao X and Jia X P. 2015. Spectral-spatial classification of hyperspectral data based on deep belief network. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8(6): 2381-2392 [DOI: 10.1109/JSTARS.2015.2388577http://dx.doi.org/10.1109/JSTARS.2015.2388577]

Chen Z, Wu X J and Kittler J. 2020. Low-rank discriminative least squares regression for image classification. Signal Processing, 173: 107485 [DOI: 10.1016/j.sigpro.2020.107485http://dx.doi.org/10.1016/j.sigpro.2020.107485]

Dong Y N, Liu Q W, Du B and Zhang L P. 2022. Weighted feature fusion of convolutional neural network and graph attention network for hyperspectral image classification. IEEE Transactions on Image Processing, 31: 1559-1572 [DOI: 10.1109/TIP.2022.3144017http://dx.doi.org/10.1109/TIP.2022.3144017]

Fang L Y, Liu G Y, Li S, Ghamisi P T and Benediktsson J A. 2019. Hyperspectral image classification with squeeze multibias network. IEEE Transactions on Geoscience and Remote Sensing, 57(3): 1291-1301 [DOI: 10.1109/TGRS.2018.2865953http://dx.doi.org/10.1109/TGRS.2018.2865953]

Fang L Y, Wang C, Li S T and Benediktsson J A. 2017. Hyperspectral image classification via multiple-feature-based adaptive sparse representation. IEEE Transactions on Instrumentation and Measurement, 66(7): 1646-1657 [DOI: 10.1109/TIM.2017.2664480http://dx.doi.org/10.1109/TIM.2017.2664480]

Fei B W, Akbari H and Halig L V. 2012. Hyperspectral imaging and spectral-spatial classification for cancer detection//Proceedings of the 5th International Conference on Biomedical Engineering and Informatics. Chongqing: IEEE: 62-64 [DOI: 10.1109/BMEI.2012.6513047http://dx.doi.org/10.1109/BMEI.2012.6513047]

Gao H M, Zhu M, Cao X Y, Li C M, Liu Q and Xu P P. 2023. A micro-hyperspectral image classification method of gallbladder cancer based on multi-scale fusion attention mechanism. Journal of Image and Graphics, 28(4): 1173-1185

高红民, 朱敏, 曹雪莹, 李臣明, 刘芹, 许佩佩. 2023. 多尺度融合注意力机制的胆囊癌显微高光谱图像分类. 中国图象图形学报, 28(4): 1173-1185 [DOI: 10.11834/jig.211201http://dx.doi.org/10.11834/jig.211201]

Ghamisi P, Plaza J, Chen Y S, Li J and Plaza A J. 2017. Advanced spectral classifiers for hyperspectral images: a review. IEEE Geoscience and Remote Sensing Magazine, 5(1): 8-32 [DOI: 10.1109/MGRS.2016.2616418http://dx.doi.org/10.1109/MGRS.2016.2616418]

He Z, Liu L, Deng R R and Shen Y. 2016. Low-rank group inspired dictionary learning for hyperspectral image classification. Signal Processing, 120: 209-221 [DOI: 10.1016/j.sigpro.2015.09.004http://dx.doi.org/10.1016/j.sigpro.2015.09.004]

Hu W, Huang Y Y, Wei L, Zhang F and Li H C. 2015. Deep convolutional neural networks for hyperspectral image classification. Journal of Sensors, 2015: 258619 [DOI: 10.1155/2015/258619http://dx.doi.org/10.1155/2015/258619]

Jia S, Deng B, Zhu J S, Jia X P and Li Q Q. 2018. Local binary pattern based hyperspectral image classification with superpixel guidance. IEEE Transactions on Geoscience and Remote Sensing, 56(2): 749-759 [DOI: 10.1109/TGRS.2017.2754511http://dx.doi.org/10.1109/TGRS.2017.2754511]

Li W and Du Q. 2014. Gabor-filtering-based nearest regularized subspace for hyperspectral image classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(4): 1012-1022 [DOI: 10.1109/JSTARS.2013.2295313http://dx.doi.org/10.1109/JSTARS.2013.2295313]

Li W, Lü M, Chen T H, Chu Z Y and Tao R. 2021. Application of a hyperspectral image in medical field: a review. Journal of Image and Graphics, 26(8): 1764-1785

李伟, 吕蒙, 陈天虹, 楚照耀, 陶然. 2021. 高光谱图像在生物医学中的应用. 中国图象图形学报, 26(8): 1764-1785 [DOI: 10.11834/jig.210191http://dx.doi.org/10.11834/jig.210191]

Li Y S, Tang H J, Xie W X and Luo W H. 2022a. Multidimensional local binary pattern for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 60: 5505113 [DOI: 10.1109/TGRS.2021.3069505http://dx.doi.org/10.1109/TGRS.2021.3069505]

Li Z Y, Huang H, Zhang Z and Shi G Y. 2022b. Manifold-based multi-deep belief network for feature extraction of hyperspectral image. Remote Sensing, 14(6): 1484 [DOI: 10.3390/rs14061484http://dx.doi.org/10.3390/rs14061484]

Liang X J, Zhang Y and Zhang J P. 2021. Relative water content retrieval and refined classification of hyperspectral images based on a symbiotic neural network. National Remote Sensing Bulletin, 25(11): 2283-2302

梁雪剑, 张晔, 张钧萍. 2021. 高光谱图像相对含水量反演引导的精细分类. 遥感学报, 25(11): 2283-2302 [DOI: 10.11834/jrs.20219359http://dx.doi.org/10.11834/jrs.20219359]

Liao W Z, Bellens R, Pizurica A, Philips W and Pi Y G. 2012. Classification of hyperspectral data over urban areas using directional morphological profiles and semi-supervised feature extraction. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 5(4): 1177-1190 [DOI: 10.1109/JSTARS.2012.2190045http://dx.doi.org/10.1109/JSTARS.2012.2190045]

Nie J T, Zhang L, Wei W, Yan Q S, Ding C, Chen G C and Zhang Y N. 2023. A survey of hyperspectral image super-resolution method. Journal of Image and Graphics, 28(6): 1685-1697

聂江涛, 张磊, 魏巍, 闫庆森, 丁晨, 陈国超, 张艳宁. 2023. 高光谱图像超分辨率重建技术研究进展. 中国图象图形学报, 28(6): 1685-1697 [DOI: 10.11834/jig.230038http://dx.doi.org/10.11834/jig.230038]

Parikh N and Boyd S. 2014. Proximal algorithms. Foundations and Trends® in Optimization, 1(3): 127-239 [DOI: 10.1561/2400000003http://dx.doi.org/10.1561/2400000003]

Scholkopf B, Locatello F, Bauer S, Ke N R, Kalchbrenner N, Goyal A and Bengio Y. 2021. Toward causal representation learning. Proceedings of the IEEE, 109(5): 612-634 [DOI: 10.1109/JPROC.2021.3058954http://dx.doi.org/10.1109/JPROC.2021.3058954]

Tan S B and Wang Y F. 2007. Combining error-correcting output codes and model-refinement for text categorization//Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. Amsterdam: ACM: 699-700 [DOI: 10.1145/1277741.1277865http://dx.doi.org/10.1145/1277741.1277865]

Wei X L, Li W, Zhang M M and Li Q L. 2019. Medical hyperspectral image classification based on end-to-end fusion deep neural network. IEEE Transactions on Instrumentation and Measurement, 68(11): 4481-4492 [DOI: 10.1109/TIM.2018.2887069http://dx.doi.org/10.1109/TIM.2018.2887069]

Wei X P, Yu X C, Zhang P Q, Zhi L and Yang F. 2020. CNN with local binary patterns for hyperspectral images classification. National Remote Sensing Bulletin, 24(8): 1000-1009

魏祥坡, 余旭初, 张鹏强, 职露, 杨帆. 2020. 联合局部二值模式的CNN高光谱图像分类. 遥感学报, 24(8): 1000-1009 [DOI: 10.11834/jrs.20208333http://dx.doi.org/10.11834/jrs.20208333]

Wu Y F, Yang X H, Plaza A, Qiao F, Gao L R, Zhang B and Cui Y B. 2016. Approximate computing of remotely sensed data: SVM hyperspectral image classification as a case study. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9(12): 5806-5818 [DOI: 10.1109/JSTARS.2016.2539282http://dx.doi.org/10.1109/JSTARS.2016.2539282]

Xing C D, Duan C W, Wang Z S and Wang M L. 2023. Binary feature learning with local spectral context-aware attention for classification of hyperspectral images. Pattern Recognition, 134: 109123 [DOI: 10.1016/j.patcog.2022.109123http://dx.doi.org/10.1016/j.patcog.2022.109123]

Xing C D, Wang M L, Dong C, Duan C W and Wang Z S. 2020. Joint sparse-collaborative representation to fuse hyperspectral and multispectral images. Signal Processing, 173: 107585 [DOI: 10.1016/j.sigpro.2020.107585http://dx.doi.org/10.1016/j.sigpro.2020.107585]

Xing C D, Wang M L, Wang Z S, Duan C W and Liu Y L. 2022. Diagonalized low-rank learning for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 60: 5507812 [DOI: 10.1109/TGRS.2021.3085672http://dx.doi.org/10.1109/TGRS.2021.3085672]

Xu Y H, Du B, Zhang F and Zhang L P. 2018. Hyperspectral image classification via a random patches network. ISPRS Journal of Photogrammetry and Remote Sensing, 142: 344-357 [DOI: 10.1016/j.isprsjprs.2018.05.014http://dx.doi.org/10.1016/j.isprsjprs.2018.05.014]

Xue Z H and Zhang Y J. 2022. Supervised hashing with RBF kernel and convolution for hyperspectral image classification. National Remote Sensing Bulletin, 26(4): 722-738

薛朝辉, 张瑜娟. 2022. 基于卷积核哈希学习的高光谱图像分类. 遥感学报, 26(4): 722-738 [DOI: 10.11834/jrs.20220359http://dx.doi.org/10.11834/jrs.20220359]

Zhang H Y, Li J Y, Huang Y C and Zhang L P. 2014. A nonlocal weighted joint sparse representation classification method for hyperspectral imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(6): 2056-2065 [DOI: 10.1109/JSTARS.2013.2264720http://dx.doi.org/10.1109/JSTARS.2013.2264720]

Zhang S, Sun B, Li S T and Kang X D. 2021. Noise estimation of hyperspectral image in the spatial and spectral dimensions. National Remote Sensing Bulletin, 25(5): 1108-1123

章硕, 孙斌, 李树涛, 康旭东. 2021. 空间与光谱维度的高光谱图像噪声估计. 遥感学报, 25(5): 1108-1123 [DOI: 10.11834/jrs.20210337http://dx.doi.org/10.11834/jrs.20210337]

Zhang X R, Weng P, Feng J, Zhang E L and Hou B. 2013. Spatial-spectral classification based on group sparse coding for hyperspectral image//Proceedings of the 2013 IEEE International Geoscience and Remote Sensing Symposium. Melbourne: IEEE: 1745-1748 [DOI: 10.1109/IGARSS.2013.6723134http://dx.doi.org/10.1109/IGARSS.2013.6723134]

文章被引用时，请邮件提醒。

提交

生成式对抗网络的高光谱遥感图像分类方法研究

高光谱图像滚动引导递归滤波与地物分类

小样本的高光谱图像降噪与分类

极化合成孔径雷达遥感地物分类研究进展