Robust Hyperspectral Image Classification by Multi-Layer Spatial-Spectral Sparse Representations

Abstract

Sparse representation (SR)-driven classifiers have been widely adopted for hyperspectral image (HSI) classification, and many algorithms have been presented recently. However, most of the existing methods exploit the single layer hard assignment based on class-wise reconstruction errors on the subspace assumption; moreover, the single-layer SR is biased and less stable due to the high coherence of the training samples. In this paper, motivated by category sparsity, a novel multi-layer spatial-spectral sparse representation (mlSR) framework for HSI classification is proposed. The mlSR assignment framework effectively classifies the test samples based on the adaptive dictionary assembling in a multi-layer manner and intrinsic class-dependent distribution. In the proposed framework, three algorithms, multi-layer SR classification (mlSRC), multi-layer collaborative representation classification (mlCRC) and multi-layer elastic net representation-based classification (mlENRC) for HSI, are developed. All three algorithms can achieve a better SR for the test samples, which benefits HSI classification. Experiments are conducted on three real HSI image datasets. Compared with several state-of-the-art approaches, the increases of overall accuracy (OA), kappa and average accuracy (AA) on the Indian Pines image range from 3.02% to 17.13%, 0.034 to 0.178 and 1.51% to 11.56%, respectively. The improvements in OA, kappa and AA for the University of Pavia are from 1.4% to 21.93%, 0.016 to 0.251 and 0.12% to 22.49%, respectively. Furthermore, the OA, kappa and AA for the Salinas image can be improved from 2.35% to 6.91%, 0.026 to 0.074 and 0.88% to 5.19%, respectively. This demonstrates that the proposed mlSR framework can achieve comparable or better performance than the state-of-the-art classification methods.

Intelligent Object Recognition of Urban Water Bodies Based on Deep Learning for Multi-Source and Multi-Temporal High Spatial Resolution Remote Sensing Imagery

“…The method of deep learning effectively adds semantic information to the sample making process, which can effectively improve the case segmentation of ground objects. Over the last decades, several relevant deep learning methods that combine the spatial and the spectral information to extract spatial-spectral features have been proposed [39][40][41][42][43][44][45][46][47][48][49][50][51]. It is now commonly accepted that spatial-spectral-based methods can significantly improve the classification performance.…”

The Comparison of Fusion Methods for HSRRSI Considering the Effectiveness of Land Cover (Features) Object Recognition Based on Deep Learning

“…Over the last decades, a number of relevant methods have been proposed by combining the spatial and the spectral information to extract spatial-spectral features [7][8][9][10][11][12][13][14][15][16][17][18][19]. In a recent study, Cheng propose a unified metric learning-based framework to alternately learn discriminative spectral-spatial features; they further designed a new objective function that explicitly embeds a metric learning regularization term into SVM (Support Vector Machine) training, which is used to learn a powerful spatial-spectral feature representation by fusing spectral features and deep spatial features, and achieved state-of-the-art results [20].…”

Remote Sensing Images Stripe Noise Removal by Double Sparse Regulation and Region Separation

“…However, the output of sensing images often suffers from stripe-like noise, which seriously degrades the image's visual quality and also yields a negative influence on high-level application, such as target detection and data classification [4][5][6][7]. Due to the inconsistent responses of detectors and the imperfect calibration of amplifiers, the gain and offset of true signals are various, producing stripe noise on Moderate Resolution Imaging spectrometer (MODIS) data and hyperspectral images.…”