Anna Chlingaryan

A Novel Spectral Unmixing Method Incorporating Spectral Variability Within Endmember Classes

Some spectral unmixing methods incorporate endmember variability within endmember classes. It is, however, uncertain whether these methods work well when endmember spectra do not completely describe the variability that exists within endmember classes. This paper proposes a novel spectral unmixing method, Spectral Unmixing within a multi-task Gaussian Process framework (SUGP), which is more resistant to problems caused by the use of a small number of endmember spectra. SUGP models the latent function between spectra and abundances in a training set and predicts abundances from a given pixel spectrum. SUGP is different from existing methods in that it incorporates all spectra within each endmember class to estimate abundances within a probabilistic framework. Using simulated data, SUGP was compared with existing linear unmixing methods and was found to be superior in determining the number of endmember classes within each pixel and in estimating abundances. It was also more effective in cases where a small number of spectra within endmember classes were specified and was more resistant to the effects of spectral noise. Methods were applied to the hyperspectral imagery of a mine wall and to imagery acquired over Cuprite, Nevada. Abundance maps generated by SUGP were consistent with the validated reference maps. SUGP opens up possibilities for estimating accurate abundances under conditions where endmember variability is present and where endmember spectra incompletely describe the true variability of each endmember class.

Incorporating Spatial Information and Endmember Variability Into Unmixing Analyses to Improve Abundance Estimates

Incorporating endmember variability and spatial information into spectral unmixing analyses is important for producing accurate abundance estimates. However, most methods do not incorporate endmember variability with spatial regularization. This paper proposes a novel 2-step unmixing approach, which incorporates endmember variability and spatial information. In step 1, a probability distribution representing abundances is estimated by spectral unmixing within a multi-task Gaussian process framework (SUGP). In step 2, spatial information is incorporated into the probability distribution derived by SUGP through an a priori distribution derived from a Markov random field (MRF). The proposed method (SUGP-MRF) is different to the existing unmixing methods because it incorporates endmember variability and spatial information at separate steps in the analysis and automatically estimates parameters controlling the balance between the data fit and spatial smoothness. The performance of SUGP-MRF is compared with the existing unmixing methods using synthetic imagery with precisely known abundances and real hyperspectral imagery of rock samples. Results show that SUGP-MRF outperforms the existing methods and improves the accuracy of abundance estimates by incorporating spatial information.

Unsupervised feature learning for illumination robustness

The illumination conditions of a scene create intra-class variability in outdoor visual data, degrading the performance of high-level algorithms. Using only the image, and with hyper-spectral data as a case study, this paper proposes a deep learning approach to learn illumination invariant features from the data in an unsupervised manner. The proposed approach incorporates a similarity measure, the Spectral Angle, that is relatively insensitive to brightness into the cost function of a Stacked Auto-Encoder so that an illumination invariant mapping is learned from the input data to the hidden layer. Experiments using synthetic and real imagery show that this novel feature learning approach produces a more illumination invariant representation of the data, improving the results of a high-level algorithm (clustering) under such conditions.

A Novel Endmember Bundle Extraction and Clustering Approach for Capturing Spectral Variability Within Endmember Classes

Spectral variability, unrelated to the purity of endmembers, can change the geometry of the dataspace and affect conventional methods used to identify endmembers. Several methods have been developed to identify and extract endmember bundles representing the spectral variability within each endmember class. These methods, however, operate on the geometry of the dataspace. In addition, they commonly use k-means clustering that requires a priori the number of endmember classes present in a scene and may fail to group endmember spectra representing spectral variability within each class. This paper introduces a novel approach, spectral curve-based endmember extraction (SCEE), which allows for the extraction and clustering of multiple spectra representing spectral variability within endmember classes. The significant differences between SCEE and conventional methods are: i) SCEE is based on the shape of a spectral curve, not the geometry of the data simplex; and ii) SCEE extracts multiple endmember bundle candidates representing a particular class, without a priori knowledge of the number of endmember classes in a scene. Once multiple endmember bundle candidates are identified, they are automatically grouped by sequential pairwise clustering in order to determine the final number of endmember classes. The performance of SCEE is compared with that of other state-of-the-art endmember bundle extraction methods using simulated data and hyperspectral imagery of a mine pit and Cuprite. Results showed that multiple endmember bundles identified by SCEE gave better matches with spectral variability of reference spectra than those by other methods and were better able to encompass the range of variability within each class.

Multiple endmember spectral unmixing within a multi-task framework

A novel spectral unmixing technique is presented which addresses the problem of spectral variability within each endmember class and determines endmember types present in each pixel. The proposed unmixing method is a multi-task framework, based on Multi-task Gaussian Process (MTGP). The Unmixing within a MTGP framework (UMTGP) is different to conventional unmixing approaches in that it assumes that spectral variation exists within each endmember class. Using synthetic and real data, the fractional abundances estimated by the UMTGP are compared with conventional methods such as Fully Constrained Least Squares (FCLS) and Multiple Endmember Spectral Mixture Analysis (MESMA). Hyperspectral data acquired from field-based platforms are used for evaluation because intra-class spectral variability is commonly large in these datasets. The results show that the UMTGP outperforms FCLS in terms of estimating fractional abundance and provides better estimates than MESMA, especially when a small number of endmember spectra for each class are available.

Machine learning approaches for crop yield prediction and nitrogen status estimation in precision agriculture: A review

Abstract Accurate yield estimation and optimised nitrogen management is essential in agriculture. Remote sensing (RS) systems are being more widely used in building decision support tools for contemporary farming systems to improve yield production and nitrogen management while reducing operating costs and environmental impact. However, RS based approaches require processing of enormous amounts of remotely sensed data from different platforms and, therefore, greater attention is currently being devoted to machine learning (ML) methods. This is due to the capability of machine learning based systems to process a large number of inputs and handle non-linear tasks. This paper discusses research developments conducted within the last 15 years on machine learning based techniques for accurate crop yield prediction and nitrogen status estimation. The paper concludes that the rapid advances in sensing technologies and ML techniques will provide cost-effective and comprehensive solutions for better crop and environment state estimation and decision making. More targeted application of the sensor platforms and ML techniques, the fusion of different sensor modalities and expert knowledge, and the development of hybrid systems combining different ML and signal processing techniques are all likely to be part of precision agriculture (PA) in the near future.

Spectral curve-based endmember extraction method

Most commonly-used methods to determine the number of endmembers and to extract endmember spectra are affected by spectral variability caused by variations in illumination or the physical characteristics of materials. This paper proposes a novel endmember extraction method which can consider the spectral variability. The proposed method, a Spectral Curve-based Endmember Extraction (SCEE) method can automatically extract multiple endmember spectra per class and determine the number of endmember classes. SCEE is validated using the hyperspectral imagery of rock samples of known composition. Results are compared with Hyperspectral Signal identification by minimum error (HySime) and Vertex Component Analysis (VCA). Results show that SCEE can successfully extract multiple endmember spectra per class and determine the number of endmember classes.

Pretraining for Hyperspectral Convolutional Neural Network Classification

Convolutional neural networks (CNNs) have been shown to be a powerful tool for image classification. Recently, they have been adopted into the remote sensing community with applications in material classification from hyperspectral images. However, CNNs are time-consuming to train and often require large amounts of labeled training data. The widespread use of CNNs in the image processing and computer vision communities has been facilitated by the networks that have already been trained on large amounts of data. These pretrained networks can be used to initialize networks for new tasks. This transfer of knowledge makes it far less time-consuming to train a new classifier and reduces the need for a large labeled data set. This concept of transfer learning has not yet been fully explored by those using CNNs to train material classifiers from hyperspectral data. This paper provides an insight into training hyperspectral CNN classifiers by transferring knowledge from well labeled data sets to data sets that are less well labeled. It is shown that these CNNs can transfer between completely different domains and sensing platforms, and still improve classification performance. The application of this work is in the training of material classifiers of data acquired from field-based platforms, by transferring knowledge from publicly accessible airborne data sets. Factors, such as training set size, CNN architectures, and the impact of filter width and wavelength interval, are studied.

Automated Multi-class Classification of Remotely Sensed Hyperspectral Imagery Via Gaussian Processes with a Non-stationary Covariance Function

The ability to automatically classify hyperspectral imagery is of fundamental economic importance to the mining industry. A method of automated multi-class classification based on multi-task Gaussian processes (MTGPs) is proposed for classification of remotely sensed hyperspectral imagery. It is proved that because of the illumination invariance of the hyperspectral curves, the covariance function of the Gaussian process (GPs) has to be non-stationary. To enable multi-class classification of the hyperspectral imagery, a non-stationary multi-task observation angle-dependent covariance function is derived. In order to test MTGP, it was applied to data acquired in the laboratory and also in field. First, the MTGP was applied to hyperspectral imagery acquired under artificial light from samples of rock of known mineral composition. Data from a high-resolution field spectrometer are used to train the GPs. Second, the MTGP was applied to imagery of a vertical rock wall acquired under natural illumination. Spectra from hyperspectral imagery acquired in the laboratory are used to train the GPs. Results were compared with those obtained using the spectral angle mapper (SAM). In laboratory imagery, MTGP outperformed SAM across several metrics, including overall accuracy (MTGP: 0.96–0.98; SAM: 0.91–0.93) and the kappa coefficient of agreement (MTGP: 0.95–0.97; SAM: 0.88–0.91). MTGP applied to hyperspectral imagery of the rock wall gave broadly similar results to those from SAM; however, there were important differences. Some rock types were confused by SAM, but not by MTGP. Comparison of classified imagery with ground truth maps showed that MTGP outperformed SAM.