Recent advances in spectral-spatial classification of hyperspectral images are presented in this paper. Several techniques are investigated for combining both spatial and spectral information. Spatial information is extracted at the object (set of pixels) level rather than at the conventional pixel level. Mathematical morphology is first used to derive the morphological profile of the image, which includes characteristics about the size, orientation, and contrast of the spatial structures present in the image. Then, the morphological neighborhood is defined and used to derive additional features for classification. Classification is performed with support vector machines (SVMs) using the available spectral information and the extracted spatial information. Spatial postprocessing is next investigated to build more homogeneous and spatially consistent thematic maps. To that end, three presegmentation techniques are applied to define regions that are used to regularize the preliminary pixel-wise thematic map. Finally, a multiple-classifier (MC) system is defined to produce relevant markers that are exploited to segment the hyperspectral image with the minimum spanning forest algorithm. Experimental results conducted on three real hyperspectral images with different spatial and spectral resolutions and corresponding to various contexts are presented. They highlight the importance of spectral-spatial strategies for the accurate classification of hyperspectral images and validate the proposed methods.

/pdf/advances-in-spectral-spatial-classification-of-hyperspectral-vlt2ik4ef1.pdf

Advances in Spectral-Spatial Classification of Hyperspectral Images

Recent research has shown that using spectral–spatial information can considerably improve the performance of hyperspectral image (HSI) classification. HSI data is typically presented in the format of 3D cubes. Thus, 3D spatial filtering naturally offers a simple and effective method for simultaneously extracting the spectral–spatial features within such images. In this paper, a 3D convolutional neural network (3D-CNN) framework is proposed for accurate HSI classification. The proposed method views the HSI cube data altogether without relying on any preprocessing or post-processing, extracting the deep spectral–spatial-combined features effectively. In addition, it requires fewer parameters than other deep learning-based methods. Thus, the model is lighter, less likely to over-fit, and easier to train. For comparison and validation, we test the proposed method along with three other deep learning-based HSI classification methods—namely, stacked autoencoder (SAE), deep brief network (DBN), and 2D-CNN-based methods—on three real-world HSI datasets captured by different sensors. Experimental results demonstrate that our 3D-CNN-based method outperforms these state-of-the-art methods and sets a new record.

/pdf/spectral-spatial-classification-of-hyperspectral-imagery-36x1sx3gn4.pdf

Spectral-spatial classification of hyperspectral imagery with 3D convolutional neural network

Imaging spectroscopy, also known as hyperspectral imaging, has been transformed in the last four decades from being a sparse research tool into a commodity product available to a broad user community. Specially, in the last 10 years, a large number of new techniques able to take into account the special properties of hyperspectral data have been introduced for hyperspectral data processing, where hyperspectral image classification, as one of the most active topics, has drawn massive attentions. Spectral–spatial hyperspectral image classification can achieve better classification performance than its pixel-wise counterpart, since the former utilizes not only the information of spectral signature but also that from spatial domain. In this paper, we provide a comprehensive overview on the methods belonging to the category of spectral–spatial classification in a relatively unified context. First, we develop a concept of spatial dependency system that involves pixel dependency and label dependency, with two main factors: neighborhood covering and neighborhood importance. In terms of the way that the neighborhood information is used, the spatial dependency systems can be classified into fixed, adaptive, and global systems, which can accommodate various kinds of existing spectral–spatial methods. Based on such, the categorizations of single-dependency, bilayer-dependency, and multiple-dependency systems are further introduced. Second, we categorize the performings of existing spectral–spatial methods into four paradigms according to the different fusion stages wherein spatial information takes effect, i.e., preprocessing-based, integrated, postprocessing-based, and hybrid classifications. Then, typical methodologies are outlined. Finally, several representative spectral–spatial classification methods are applied on real-world hyperspectral data in our experiments.

Recent Advances on Spectral–Spatial Hyperspectral Image Classification: An Overview and New Guidelines

This paper reviewed major remote sensing image classification techniques, including pixel-wise, sub-pixel-wise, and object-based image classification methods, and highlighted the importance of incorporating spatio-contextual information in remote sensing image classification. Further, this paper grouped spatio-contextual analysis techniques into three major categories, including 1) texture extraction, 2) Markov random fields (MRFs) modeling, and 3) image segmentation and object-based image analysis. Finally, this paper argued the necessity of developing geographic information analysis models for spatial-contextual classifications using two case studies.

https://www.tandfonline.com/doi/pdf/10.5721/EuJRS20144723

A Review of Remote Sensing Image Classification Techniques: the Role of Spatio-contextual Information

Hyperspectral remote sensing imagery contains rich information on spectral and spatial distributions of distinct surface materials. Owing to its numerous and continuous spectral bands, hyperspectral data enable more accurate and reliable material classification than using panchromatic or multispectral imagery. However, high-dimensional spectral features and limited number of available training samples have caused some difficulties in the classification, such as overfitting in learning, noise sensitiveness, overloaded computation, and lack of meaningful physical interpretability. In this paper, we propose a hyperspectral feature extraction and pixel classification method based on structured sparse logistic regression and 3-D discrete wavelet transform (3D-DWT) texture features. The 3D-DWT decomposes a hyperspectral data cube at different scales, frequencies, and orientations, during which the hyperspectral data cube is considered as a whole tensor instead of adapting the data to a vector or matrix. This allows the capture of geometrical and statistical spectral-spatial structures. After the feature extraction step, sparse representation/modeling is applied for data analysis and processing via sparse regularized optimization, which selects a small subset of the original feature variables to model the data for regression and classification purpose. A linear structured sparse logistic regression model is proposed to simultaneously select the discriminant features from the pool of 3D-DWT texture features and learn the coefficients of the linear classifier, in which the prior knowledge about feature structure can be mapped into the various sparsity-inducing norms such as lasso, group, and sparse group lasso. Furthermore, to overcome the limitation of linear models, we extended the linear sparse model to nonlinear classification by partitioning the feature space into subspaces of linearly separable samples. The advantages of our methods are validated on the real hyperspectral remote sensing data sets.

/pdf/hyperspectral-image-classification-based-on-structured-1xd3fehett.pdf

Hyperspectral Image Classification Based on Structured Sparse Logistic Regression and Three-Dimensional Wavelet Texture Features

An adaptive Markov random field (MRF) approach is proposed for classification of hyperspectral imagery in this letter. The main feature of the proposed method is the introduction of a relative homogeneity index for each pixel and the use of this index to determine an appropriate weighting coefficient for the spatial contribution in the MRF classification. In this way, overcorrection of spatially high variation areas can be avoided. Support vector machines are implemented for improved class modeling and better estimate of spectral contribution to this approach. Experimental results of a synthetic hyperspectral data set and a real hyperspectral image demonstrate that the proposed method works better on both homogeneous regions and class boundaries with improved classification accuracy.

Adaptive Markov Random Field Approach for Classification of Hyperspectral Imagery

A novel multi-scale superpixel-based spectral–spatial classification MS-SSC approach is proposed for hyperspectral images in this study. Superpixels are considered as the basic processing units for spectral–spatial-based classification. The use of multiple scales allows the capturing of local spatial structures of various sizes. The proposed technique consists of three steps. In the first step, hierarchical superpixel segmentations are performed from fine to coarse scales for the original hyperspectral image and the spectral information of each superpixel is used for classification at each scale. In the second step, each single scale superpixel-based classification is improved by combining with the segmentations at a higher level. Finally, the multi-scale classification is achieved via decision fusion. Experimental results are presented for two hyperspectral images and compared with recently advanced pixel-wise and pixel-based spectral–spatial classification approaches. The experiments demonstrate that the proposed method works effectively on the homogeneous regions and is also able to preserve the small local spatial structures in the image.

Multi-scale superpixel spectral–spatial classification of hyperspectral images

This letter presents a new technique for clustering hyperspectral images that exploits neighborhood-constrained spatial information. The main feature of the proposed method is the introduction of a neighborhood homogeneity index (NHI) and the use of this index to measure the spatial homogeneity in a local area. A new similarity measurement integrates NHI and spectral information using an adaptive distance norm for clustering. The performance of the proposed neighborhood-constrained-clustering algorithm was assessed through a synthetic image and a real hyperspectral image and compared with those obtained by advanced spectral-spatial clustering algorithms. Experimental results show that the proposed scheme gives better performances.

Hyperspectral Imagery Clustering With Neighborhood Constraints

In classifying very high spatial resolution (VHR) hyperspectral imagery, intra-class variation often adversely affects classification accuracy, mainly due to a low signal-to-noise ratio (SNR) and high spatial heterogeneity. To address this problem, this article develops a neighbourhood-constrained k-means (NC-k-means) algorithm by incorporating the pure neighbourhood index into the traditional k-means algorithm. The performance of the NC-k-means algorithm was assessed through a series of simulated images and a real hyperspectral image. The results indicate that the classification accuracy of NC-k-means algorithm is consistently better than that of the traditional k-means algorithm, in particular for the images with significant spatial autocorrelations among neighbouring pixels.

A neighbourhood-constrained k-means approach to classify very high spatial resolution hyperspectral imagery

Markov random field (MRF) provides a useful model for integrating contextual information into remote sensing image classification. However, there are two limitations when using the conventional MRF model in hyperspectral image classification. First, the maximum likelihood classifier used in MRF to estimate the spectral-based probability needs accurate estimation of covariance matrix for each class, which is often hard to obtain with a small number of training samples for hyperspectral imagery. Second, a fixed spatial neighboring impact parameter for all pixels causes overcorrection of spatially high variation areas and makes class boundaries blurred. This paper presents an improved method for integrating a support vector machine (SVM) and Markov random field to classify the hyperspectral imagery. An adaptive spatial neighboring impact parameter is assigned to each pixel according to its spatial contextualcorrelation.Experimentalresultsofahyperspectralimageshowthattheclassification accuracyfromtheproposedmethodhasbeenimprovedcomparedtothosefromtheconventional MRF model and pixel-wise classifiers including the maximum likelihood classifier and SVM

http://gis.geog.queensu.ca/PublicationPDFs/2011_JARS_Shanshan.pdf

Man Peng

Papers

Adaptive Markov Random Field Approach for Classification of Hyperspectral Imagery

Multi-scale superpixel spectral–spatial classification of hyperspectral images

Hyperspectral Imagery Clustering With Neighborhood Constraints

A neighbourhood-constrained k-means approach to classify very high spatial resolution hyperspectral imagery

Adaptive support vector machine and Markov random field model for classifying hyperspectral imagery