浏览全部资源
扫码关注微信
收稿：2020-12-30，
修回：2021-4-29，
录用：2021-5-5，
纸质出版：2021-08-16
移动端阅览
目的
2
目前高光谱图像决策融合方法主要采用以多数票决（majority vote，MV）为代表的硬决策融合和以对数意见池（logarithmic opinion pool，LOGP）为代表的软决策融合策略。由于这些方法均使用统一的权重系数进行决策融合，没有对子分类器各自的分类性能进行评估而优化分配权重系数，势必会影响最终的分类精度。针对该问题，本文对多数票决和对数意见池融合策略进行了改进，提出了面向高光谱图像分类的自适应决策融合方法。
方法
2
根据相关系数矩阵对高光谱图像进行波段分组，对每组波段进行空谱联合特征提取；利用高斯混合模型（Gaussian mixture model，GMM）或支持向量机（support vector machine，SVM）分类器对各组空谱联合特征进行分类；最后，采用本文研究的两种基于权重系数优化分配的自适应融合策略对子分类器的分类结果进行决策融合，使得分类精度低的波段组和异常值对最终分类结果的影响达到最小。
结果
2
对两个公开的高光谱数据集分别采用多种特征和两种分类器组合进行实验验证。实验结果表明，在相同特征和分类器条件下，本文提出的自适应多数票决策融合策略（adjust majority vote，adjustMV）、自适应对数意见池决策融合策略（adjust logarithmic opinion pool，adjustLOGP）比传统的MV决策融合策略、LOGP决策融合策略对两个数据集的分类精度均有大幅度提高。Indian Pines数据集上，adjustMV算法的分类精度比相应的MV算法平均提高了1.2%，adjustLOGP算法的分类精度比相应的LOGP算法平均提高了7.38%；Pavia University数据集上，adjustMV算法的分类精度比相应的MV算法平均提高了2.1%，adjustLOGP算法的分类精度比相应的LOGP算法平均提高了4.5%。
结论
2
本文提出的自适应权重决策融合策略为性能较优的子分类器（即对应于分类精度高的波段组）赋予较大的权重，降低了性能较差的子分类器与噪声波段对决策融合结果的影响，从而大幅度提高分类精度。所研究的决策融合策略的复杂度和计算成本均较低，在噪声环境中具有更强的鲁棒性，同时在一定程度上解决了高光谱图像分类应用中普遍存在的小样本问题。
Objective
2
Hyperspectral imagery contains rich spectral and spatial information and transforms remote sensing technology from qualitative to quantitative analysis. It can be widely used in geological prospecting
precision agriculture
ecology environment
and urban remote sensing. However
classification and recognition applications have many difficulties because hyperspectral image has large amount of data
multiple bands
and strong correlation between bands. In particular
the "Hughes" phenomenon caused by the decline in classification accuracy with the increase in data complexity when the number of training samples is limited needs to be addressed. Research on feature extraction and classification algorithm for hyperspectral image has become an important task in hyperspectral data processing to fully utilize the advantages of hyperspectral remote sensing technology and overcome the disadvantages caused by the large number of bands. Multi-classifier system with band-selection dimensionality reduction is effective for hyperspectral image classification
particularly when the size of the training dataset is small. The usual methods of decision fusion strategies at present are hard decision fusion represented by majority vote (MV) and soft decision fusion represented by logarithmic opinion pool (LOGP). These methods use the unified weight coefficient for decision fusion without evaluating the respective classification performance of sub-classifiers and optimizing the allocation of weight coefficients
which will inevitably affect the classification results. Two adaptive decision fusion strategies are studied in this work on the basis of MV and LOGP to solve this problem
and a multi-classifier system is designed for hyperspectral image classification.
Method
2
The correlation between adjacent bands of hyperspectral image usually appears in groups
the intra-band correlation is strong
and the inter-band correlation is weak. Thus
band selection is used for dimensionality reduction
and band grouping is utilized to feed features to multi-classifiers. Specifically
the hyperspectral data are grouped according to the correlation coefficient matrix. Then
spatial-spectral features are extracted for the bands with strong correlation in each group. Gabor and local binary pattern (LBP) features are proven to be suitable and powerful for hypershectral image(HSI) classification. The former is oriented to global features
and the latter is oriented to local features. These features are investigated for the proposed multi-classifier system. Apart from principal component analysis
two advanced local protection dimensionality reduction methods
namely
locality-preserving nonnegative matrix factorization (LPNMF) and locality fisher discriminant analysis (LFDA)
are also used in the proposed system. LPNMF aims to find a low-dimensional subspace and use its single element to represent the categories of ground objects for effectively protecting the diverse local structures of the original hyperspectral image. LFDA is suitable for dimensionality reduction of multi-model data
which can protect the local information between adjacent pixels by linear spectrum. Next
Gaussian mixture model (GMM) classifiers or support vector machine (SVM) classifiers are used to classify each group of features. Finally
the adjustMV decision fusion strategy and adjustLOGP decision fusion strategy are designed
which are based on the weight coefficient optimization allocation for sub-classifiers. They minimize the effect of band groups and abnormal values with low classification accuracy on the final classification results.
Result
2
Multiple features and two classifiers are executed crosswise for classification to verify the effectiveness of the proposed decision fusion strategies and multi-classifier system. Experiments are conducted on two public hyperspectral datasets
namely
the Indian Pines and Pavia University datasets. Experimental results show that the classification accuracies of the adjustMV strategy for Indian Pines and Pavia University datasets are improved by 1.02% and 3.39%
respectively
when Gabor features and GMM classifiers are used for MV decision fusion. When LBP features and SVM classifiers are used for MV decision fusion
the accuracies of the adjustMV strategy for Indian Pines and Pavia University datasets are improved by 1.32% and 0.82%
respectively. GMM classifiers followed by LFDA
LPNMF
or Gabor features
as three basic lines
are conducted into adjustLOGP strategy. For Indian Pines dataset
three adjustLOGP-based algorithms drive higher classification accuracies (18.54%
5.14%
and 2.87%) than three LOGP-based algorithms. For Pavia University dataset
three adjustLOGP-based algorithms drive higher classification accuracies (2.06%
5.81%
and 6.99%) than three LOGP based algorithms. Experiments are also conducted on the two datasets with different numbers of training samples and different powers of noise. The proposed adaptive decision fusion strategies still have better classification performance
even in situations of small sample size and environments with noise. It also has better stability by computing the standard deviations from 20 trails. When the number of training samples is 70
the classification accuracies of the two proposed decision fusion strategies on the Indian Pines and Pavia University datasets have 1.97% and 1.03% improvements compared with the unified weight fusion strategies. When the number of training samples is 30
the classification accuracies of the two proposed decision fusion strategies on the Indian Pines and Pavia University datasets have 4.91% and 3.55% improvements. Gaussian noise is added to the two hyperspectral datasets to further study the robustness of the improved strategies. The classification accuracies of 10 decision fusion algorithms are compared in the case that the signal-to-noise ratio(SNR) of noised datasets is 20 dB. Clearly
five adjustMV-based and adjustLOGP-based strategies are superior to the MV-based and LOGP-based strategies in the noise environment.
Conclusion
2
Two adaptive decision fusion strategies and a multi-classifier system are proposed for hyperspectral image classification in this study. The proposed decision fusion strategies consider allocating different weights with higher reliability to sub-classifiers according to their classification performance. The proposed adjustMV can cast a more important vote to obtain a final decision
and the proposed adjustLOGP has a higher probability of a posteriori to increase the probability of a correct decision. The proposed strategies have low complexity
but they can greatly improve the classification accuracy and possess better stability
even under situations of small sample size and environments with noise.
Cao X Y, Yao J, Fu X Y, Bi H X and Hong D F. 2021. An enhanced 3-D discrete wavelet transform for hyperspectral image classification. IEEE Geoscience and Remote Sensing Letters, 18(6): 1104-1108[DOI:10.1109/LGRS.2020.2990407]
Du Q, Zhang L P, Zhang B, Tong X H, Du P J and Chanussot J. 2013. Foreword to the special issue on hyperspectral remote sensing: theory, methods, and applications. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 6(2): 459-465[DOI:10.1109/JSTARS.2013.2257422]
Hou Q L, Wang Y J, Jing L and Chen H B. 2019. Linear discriminant analysis based on kernel-based possibilistic c-means for hyperspectral images. IEEE Geoscience and Remote Sensing Letters, 16(8): 1259-1263[DOI:10.1109/LGRS.2019.2894470]
Huang L H, Chen C, Li W and Qian D. 2016. Remote sensing image scene classification using multi-scale completed local binary patterns and fisher vectors. Remote Sensing, 8(6): #483[DOI:10.3390/rs8060483]
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.2017.2754511]
Jia S, Lin Z J, Deng B, Zhu J S and Li Q Q. 2020. Cascade superpixel regularized Gabor feature fusion for hyperspectral image classification. IEEE Transactions on Neural Networks and Learning Systems, 31(5): 1638-1652[DOI:10.1109/TNNLS.2019.2921564]
Jiang J J, Ma J Y, Chen C, Wang Z Y, Cai Z H and Wang L Z. 2018. SuperPCA: a superpixelwise PCA approach for unsupervised feature extraction of hyperspectral imagery. IEEE Transactions on Geoscience and Remote Sensing, 56(8): 4581-4593[DOI:10.1109/TGRS.2018.2828029]
Li W, Chen C, Su H J and Du Q. 2015. Local binary patterns and extreme learning machine for hyperspectral imagery classification. IEEE Transactions on Geoscience and Remote Sensing, 53(7): 3681-3693[DOI:10.1109/TGRS.2014.2381602]
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.2013.2295313]
Li W, Prasad S, Fowler J E and Bruce L M. 2012. Locality-preserving dimensionality reduction and classification for hyperspectral image analysis. IEEE Transactions on Geoscience and Remote Sensing, 50(4): 1185-1198[DOI:10.1109/TGRS.2011.2165957]
Luo R B and Pi Y G. 2014. Supervised neighborhood preserving embedding feature extraction of hyperspectral imagery. Acta Geodaetica et Cartographica Sinica, 43(5): 508-513, 528
骆仁波, 皮佑国. 2014. 有监督的邻域保留嵌入的高光谱遥感影像特征提取. 测绘学报, 43(5): 508-513, 528[DOI:10.13485/j.cnki.11-2089.2014.0079]
Makantasis K, Karantzalos K, Doulamis A and Doulamis N. 2015. Deep supervised learning for hyperspectral data classification through convolutional neural networks//2015 IEEE International Geoscience and Remote Sensing Symposium. Milan, Italy: IEEE: 4959-4962[ DOI: 10.1109/IGARSS.2015.7326945 http://dx.doi.org/10.1109/IGARSS.2015.7326945 ]
Pan C, Jia X P, Li J and Gao X B. 2020. Adaptive edge preserving maps in Markov random fields for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing: #9258970[DOI:10.1109/TGRS.2020.3035642]
Prasad S and Bruce L M. 2008. Decision fusion with confidence-based weight assignment for hyperspectral target recognition. IEEE Transactions on Geoscience and Remote Sensing, 46(5): 1448-1456[DOI:10.1109/TGRS.2008.916207]
Pu H Y, Chen Z, Wang B and Jiang G M. 2014. A novel spatial-spectral similarity measure for dimensionality reduction and classification of hyperspectral imagery. IEEE Transactions on Geoscience and Remote Sensing, 52(11): 7008-7022[DOI:10.1109/TGRS.2014.2306687]
Qiu Y F, Wang X P, Wang C Y and Meng L G. 2019. Hyperspectral image classification based on cascaded multi-classifiers. Journal of Image and Graphics, 24(11): 2021-2034
邱云飞, 王星苹, 王春艳, 孟令国. 2019. 应用级联多分类器的高光谱图像分类. 中国图象图形学报, 24(11): 2021-2034[DOI:10.11834/jig.190047]
Wang J Y, Wang X Y, Zhang K, Madani K and Sabourin C. 2018. Morphological band selection for hyperspectral imagery. IEEE Geoscience and Remote Sensing Letters, 15(8): 1259-1263[DOI:10.1109/LGRS.2018.2830795]
Ye Z, Bai L and Nian Y J. 2016. Hyperspectral image classification algorithm based on Gabor feature and locality-preserving dimensionality reduction. Acta Optica Sinica, 36(10): #1028003
叶珍, 白璘, 粘永健. 2016. 基于Gabor特征与局部保护降维的高光谱图像分类算法. 光学学报, 36(10): #1028003[DOI:10.3788/AOS201636.1028003]
Ye Z, Dong R, Bai L, Jin C X and Nian Y J. 2020. Hyperspectral image classification based on segmented local binary patterns. Sensing and Imaging, 21(1): #15[DOI:10.1007/s11220-020-0274-7]
Ye Z, Fowler J E and Bai L. 2017. Spatial-spectral hyperspectral classification using local binary patterns and Markov random fields. Journal of Applied Remote Sensing, 11(3): #035002[DOI:10.1117/1.JRS.11.035002]
Ye Z, Prasad S, Li W, Fowler J E and He M Y. 2014. Classification based on 3-D DWT and decision fusion for hyperspectral image analysis. IEEE Geoscience and Remote Sensing Letters, 11(1): 173-177[DOI:10.1109/LGRS.2013.2251316]
Yin Y P, Wei L and Liu W J. 2020. Ensemble extreme learning machine with cumulative variation quotient for hyperspectral image classification. Journal of Image and Graphics, 25(5): 1053-1068
尹玉萍, 魏林, 刘万军. 2020. 融合累积变异比和集成超限学习机的高光谱图像分类. 中国图象图形学报, 25(5): 1053-1068[DOI:10.11834/jig.190379]
相关作者
相关机构
京公网安备11010802024621
