Robust discriminative broad learning system for hyperspectral image classification

Abstract

With the advantages of simple structure and fast training speed, broad learning system (BLS) has attracted attention in hyperspectral images (HSIs). However, BLS cannot make good use of the discriminative information contained in HSI, which limits the classification performance of BLS. In this paper, we propose a robust discriminative broad learning system (RDBLS). For the HSI classification, RDBLS introduces the total scatter matrix to construct a new loss function to participate in the training of BLS, and at the same time minimizes the feature distance within a class and maximizes the feature distance between classes, so as to improve the discriminative ability of BLS features. RDBLS inherits the advantages of the BLS, and to a certain extent, it solves the problem of insufficient learning in the limited HSI samples. The classification results of RDBLS are verified on three HSI datasets and are superior to other comparison methods.

References

[1] LeeM A, YaoH, et al.. Determining the effects of storage on cotton and soybean leaf samples for hyperspectral analysis[J]. IEEE journal of selected topics in applied earth observations and remote sensing, 2014, 7(6):2562-2570

[2] MaheshS, JayasD S, PaliwalJ, et al.. Hyperspectral imaging to classify and monitor quality of agricultural materials[J]. Journal of stored products research, 2015, 61: 17-26

[3] LiuR, NingX, CaiW, et al.. Multiscale dense cross-attention mechanism with covariance pooling for hyperspectral image scene classification[J]. Mobile information systems, 2021, 2021: 1-15

[4] MelganiF, BruzzoneL. Classification of hyperspectral remote sensing images with support vector machines[J]. IEEE transactions on geoscience and remote sensing, 2004, 42(8):1778-1790

[5] WangM, GaoK, WangL, et al.. A novel hyperspectral classification method based on C5.0 decision tree of multiple combined classifiers[C], 2012, New York, IEEE: 373-376

[6] MookambigaA, GomathiV. Kernel eigenmaps based multiscale sparse model for hyperspectral image classification[J]. Signal processing: image communication, 2021, 99: 116416

[7] ChenY, JiangH, LiC, et al.. Deep feature extraction and classification of hyperspectral images based on convolutional neural networks[J]. IEEE transactions on geoscience and remote sensing, 2016, 54(10):6232-6251

[8] HeM, LiB, ChenH. Multi-scale 3D deep convolutional neural network for hyperspectral image classification[C], 2017, New York, IEEE: 3904-3908

[9] QinA, ShangZ, TianJ, et al.. Spectral-spatial graph convolutional networks for semisupervised hyperspectral image classification[J]. IEEE geoscience and remote sensing letters, 2018, 16(2):241-245

[10] ChenC L, LiuZ. Broad learning system: an effective and efficient incremental learning system without the need for deep architecture[J]. IEEE transactions on neural networks and learning systems, 2017, 29(1):10-24

[11] KongY, WangX, ChengY, et al.. Hyperspectral imagery classification based on semi-supervised broad learning system[J]. Remote sensing, 2018, 10(5):685

[12] MaY, LiuZ, ChenC L P. Multiscale random convolution broad learning system for hyperspectral image classification[J]. IEEE geoscience and remote sensing letters, 2021, 19: 1-5

[13] ZhaoG, WangX, KongY, et al.. Spectral-spatial joint classification of hyperspectral image based on broad learning system[J]. Remote sensing, 2021, 13(4):583

[14] MiaoY, ChenM, YuanY, et al.. Hyperspectral imagery classification via random multigraphs ensemble learning[J]. IEEE journal of selected topics in applied earth observations and remote sensing, 2021, 15: 641-653

[15] ZhouY, PengJ, ChenC L P. Extreme learning machine with composite kernels for hyperspectral image classification[J]. IEEE journal of selected topics in applied earth observations and remote sensing, 2014, 8(6):2351-2360

[16] LiC, LiS, KangX, et al.. Gabor filtering based deep network for hyperspectral image classification[C], 2017, New York, IEEE: 17414009