Spectral and Spatial Classification of Hyperspectral Images Based on Random Multi-Graphs

A Deep Stochastic Adaptive Fourier Decomposition Network for Hyperspectral Image Classification

Deep learning-based hyperspectral image (HSI) classification methods have recently shown excellent performance, however, there are two shortcomings that need to be addressed. One is that deep network training requires a large number of labeled images, and the other is that deep network needs to learn a large number of parameters. They are also general problems of deep networks, especially in applications that require professional techniques to acquire and label images, such as HSI and medical images. In this paper, we propose a deep network architecture (SAFDNet) based on the stochastic adaptive Fourier decomposition (SAFD) theory. SAFD has powerful unsupervised feature extraction capabilities, so the entire deep network only requires a small number of annotated images to train the classifier. In addition, we use fewer convolution kernels in the entire deep network, which greatly reduces the number of deep network parameters. SAFD is a newly developed signal processing tool with solid mathematical foundation, which is used to construct the unsupervised deep feature extraction mechanism of SAFDNet. Experimental results on three popular HSI classification datasets show that our proposed SAFDNet outperforms other compared state-of-the-art deep learning methods in HSI classification.

Stacking-Based Ensemble Learning Method for Multi-Spectral Image Classification

Higher dimensionality, Hughes phenomenon, spatial resolution of image data, and presence of mixed pixels are the main challenges in a multi-spectral image classification process. Most of the classical machine learning algorithms suffer from scoring optimal classification performance over multi-spectral image data. In this study, we propose stack-based ensemble-based learning approach to optimize image classification performance. In addition, we integrate the proposed ensemble learning with XGBoost method to further improve its classification accuracy. To conduct the experiment, the Landsat image data has been acquired from Bishoftu town located in the Oromia region of Ethiopia. The current study’s main objective was to assess the performance of land cover and land use analysis using multi-spectral image data. Results from our experiment indicate that, the proposed ensemble learning method outperforms any strong base classifiers with 99.96% classification performance accuracy.

Improved Active Deep Learning for Semi-Supervised Classification of Hyperspectral Image

Hyperspectral image (HSI) data classification often faces the problem of the scarcity of labeled samples, which is considered to be one of the major challenges in the field of remote sensing. Although active deep networks have been successfully applied in semi-supervised classification tasks to address this problem, their performance inevitably meets the bottleneck due to the limitation of labeling cost. To address the aforementioned issue, this paper proposes a semi-supervised classification method for hyperspectral images that improves active deep learning. Specifically, the proposed model introduces the random multi-graph algorithm and replaces the expert mark in active learning with the anchor graph algorithm, which can label a considerable amount of unlabeled data precisely and automatically. In this way, a large number of pseudo-labeling samples would be added to the training subsets such that the model could be fine-tuned and the generalization performance could be improved without extra efforts for data manual labeling. Experiments based on three standard HSIs demonstrate that the proposed model can get better performance than other conventional methods, and they also outperform other studied algorithms in the case of a small training set.

Bagging and Boosting Ensemble Classifiers for Classification of Multispectral, Hyperspectral and PolSAR Data: A Comparative Evaluation

In recent years, several powerful machine learning (ML) algorithms have been developed for image classification, especially those based on ensemble learning (EL). In particular, Extreme Gradient Boosting (XGBoost) and Light Gradient Boosting Machine (LightGBM) methods have attracted researchers’ attention in data science due to their superior results compared to other commonly used ML algorithms. Despite their popularity within the computer science community, they have not yet been well examined in detail in the field of Earth Observation (EO) for satellite image classification. As such, this study investigates the capability of different EL algorithms, generally known as bagging and boosting algorithms, including Adaptive Boosting (AdaBoost), Gradient Boosting Machine (GBM), XGBoost, LightGBM, and Random Forest (RF), for the classification of Remote Sensing (RS) data. In particular, different classification scenarios were designed to compare the performance of these algorithms on three different types of RS data, namely high-resolution multispectral, hyperspectral, and Polarimetric Synthetic Aperture Radar (PolSAR) data. Moreover, the Decision Tree (DT) single classifier, as a base classifier, is considered to evaluate the classification’s accuracy. The experimental results demonstrated that the RF and XGBoost methods for the multispectral image, the LightGBM and XGBoost methods for hyperspectral data, and the XGBoost and RF algorithms for PolSAR data produced higher classification accuracies compared to other ML techniques. This demonstrates the great capability of the XGBoost method for the classification of different types of RS data.

Data Augmentation and Spectral Structure Features for Limited Samples Hyperspectral Classification

For both traditional classification and current popular deep learning methods, the limited sample classification problem is very challenging, and the lack of samples is an important factor affecting the classification performance. Our work includes two aspects. First, the unsupervised data augmentation for all hyperspectral samples not only improves the classification accuracy greatly with the newly added training samples, but also further improves the classification accuracy of the classifier by optimizing the augmented test samples. Second, an effective spectral structure extraction method is designed, and the effective spectral structure features have a better classification accuracy than the true spectral features.

Efficient Unsupervised Classification of Hyperspectral Images Using Voronoi Diagrams and Strong Patterns

Hyperspectral images (HSIs) are a powerful tool to classify the elements from an area of interest by their spectral signature. In this paper, we propose an efficient method to classify hyperspectral data using Voronoi diagrams and strong patterns in the absence of ground truth. HSI processing consumes a great deal of computing resources because HSIs are represented by large amounts of data. We propose a heuristic method that starts by applying Parafac decomposition for reduction and to construct the abundances matrix. Furthermore, the representative nodes from the abundances map are searched for. A multi-partition of these nodes is found, and based on this, strong patterns are obtained. Then, based on the hierarchical clustering of strong patterns, an optimum partition is found. After strong patterns are labeled, we construct the Voronoi diagram to extend the classification to the entire HSI.

Spatial Spectral Band Selection for Enhanced Hyperspectral Remote Sensing Classification Applications

Despite the numerous band selection (BS) algorithms reported in the field, most if not all have exhibited maximal accuracy when more spectral bands are utilized for classification. This apparently disagrees with the theoretical model of the ‘curse of dimensionality’ phenomenon, without apparent explanations. If it were true, then BS would be deemed as an academic piece of research without real benefits to practical applications. This paper presents a spatial spectral mutual information (SSMI) BS scheme that utilizes a spatial feature extraction technique as a preprocessing step, followed by the clustering of the mutual information (MI) of spectral bands for enhancing the efficiency of the BS. Through the SSMI BS scheme, a sharp ’bell’-shaped accuracy-dimensionality characteristic that peaks at about 20 bands has been observed for the very first time. The performance of the proposed SSMI BS scheme has been validated through 6 hyperspectral imaging (HSI) datasets (Indian Pines, Botswana, Barrax, Pavia University, Salinas, and Kennedy Space Center (KSC)), and its classification accuracy is shown to be approximately 10% better than seven state-of-the-art BS schemes (Saliency, HyperBS, SLN, OCF, FDPC, ISSC, and Convolution Neural Network (CNN)). The present result confirms that the high efficiency of the BS scheme is essentially important to observe and validate the Hughes’ phenomenon in the analysis of HSI data. Experiments also show that the classification accuracy can be affected by as much as approximately 10% when a single ‘crucial’ band is included or missed out for classification.

Dimensionality Reduction of Hyperspectral Images Based on Improved Spatial-Spectral Weight Manifold Embedding

Due to the spectral complexity and high dimensionality of hyperspectral images (HSIs), the processing of HSIs is susceptible to the curse of dimensionality. In addition, the classification results of ground truth are not ideal. To overcome the problem of the curse of dimensionality and improve classification accuracy, an improved spatial-spectral weight manifold embedding (ISS-WME) algorithm, which is based on hyperspectral data with their own manifold structure and local neighbors, is proposed in this study. The manifold structure was constructed using the structural weight matrix and the distance weight matrix. The structural weight matrix was composed of within-class and between-class coefficient representation matrices. These matrices were obtained by using the collaborative representation method. Furthermore, the distance weight matrix integrated the spatial and spectral information of HSIs. The ISS-WME algorithm describes the whole structure of the data by the weight matrix constructed by combining the within-class and between-class matrices and the spatial-spectral information of HSIs, and the nearest neighbor samples of the data are retained without changing when embedding to the low-dimensional space. To verify the classification effect of the ISS-WME algorithm, three classical data sets, namely Indian Pines, Pavia University, and Salinas scene, were subjected to experiments for this paper. Six methods of dimensionality reduction (DR) were used for comparison experiments using different classifiers such as k-nearest neighbor (KNN) and support vector machine (SVM). The experimental results show that the ISS-WME algorithm can represent the HSI structure better than other methods, and effectively improves the classification accuracy of HSIs.

Novel Semi-Supervised Hyperspectral Image Classification Based on a Superpixel Graph and Discrete Potential Method

Hyperspectral image (HSI) classification plays an important role in the automatic interpretation of the remotely sensed data. However, it is a non-trivial task to classify HSI accurately and rapidly due to its characteristics of having a large amount of data and massive noise points. To address this problem, in this work, a novel, semi-supervised, superpixel-level classification method for an HSI was proposed based on a graph and discrete potential (SSC-GDP). The key idea of the proposed scheme is the construction of the weighted connectivity graph and the division of the weighted graph. Based on the superpixel segmentation, a weighted connectivity graph is constructed usingthe weighted connection between a superpixel and its spatial neighbors. The generated graph is then divided into different communities/sub-graphs by using a discrete potential and the improved semi-supervised Wu–Huberman (ISWH) algorithm. Each community in the weighted connectivity graph represents a class in the HSI. The local connection strategy, together with the linear complexity of the ISWH algorithm, ensures the fast implementation of the suggested SSC-GDP method. To prove the effectiveness of the proposed spectral–spatial method, two public benchmarks, Indian Pines and Salinas, were utilized to test the performance of our proposal. The comparative test results confirmed that the proposed method was superior to several other state-of-the-art methods.

A Novel Hyperspectral Image Classification Pattern Using Random Patches Convolution and Local Covariance

Today, more and more deep learning frameworks are being applied to hyperspectral image classification tasks and have achieved great results. However, such approaches are still hampered by long training times. Traditional spectral–spatial hyperspectral image classification only utilizes spectral features at the pixel level, without considering the correlation between local spectral signatures. Our article has tested a novel hyperspectral image classification pattern, using random-patches convolution and local covariance (RPCC). The RPCC is an effective two-branch method that, on the one hand, obtains a specified number of convolution kernels from the image space through a random strategy and, on the other hand, constructs a covariance matrix between different spectral bands by clustering local neighboring pixels. In our method, the spatial features come from multi-scale and multi-level convolutional layers. The spectral features represent the correlations between different bands. We use the support vector machine as well as spectral and spatial fusion matrices to obtain classification results. Through experiments, RPCC is tested with five excellent methods on three public data-sets. Quantitative and qualitative evaluation indicators indicate that the accuracy of our RPCC method can match or exceed the current state-of-the-art methods.

A Deep Learning-Based Approach for Automated Yellow Rust Disease Detection from High-Resolution Hyperspectral UAV Images

Yellow rust in winter wheat is a widespread and serious fungal disease, resulting in significant yield losses globally. Effective monitoring and accurate detection of yellow rust are crucial to ensure stable and reliable wheat production and food security. The existing standard methods often rely on manual inspection of disease symptoms in a small crop area by agronomists or trained surveyors. This is costly, time consuming and prone to error due to the subjectivity of surveyors. Recent advances in unmanned aerial vehicles (UAVs) mounted with hyperspectral image sensors have the potential to address these issues with low cost and high efficiency. This work proposed a new deep convolutional neural network (DCNN) based approach for automated crop disease detection using very high spatial resolution hyperspectral images captured with UAVs. The proposed model introduced multiple Inception-Resnet layers for feature extraction and was optimized to establish the most suitable depth and width of the network. Benefiting from the ability of convolution layers to handle three-dimensional data, the model used both spatial and spectral information for yellow rust detection. The model was calibrated with hyperspectral imagery collected by UAVs in five different dates across a whole crop cycle over a well-controlled field experiment with healthy and rust infected wheat plots. Its performance was compared across sampling dates and with random forest, a representative of traditional classification methods in which only spectral information was used. It was found that the method has high performance across all the growing cycle, particularly at late stages of the disease spread. The overall accuracy of the proposed model (0.85) was higher than that of the random forest classifier (0.77). These results showed that combining both spectral and spatial information is a suitable approach to improving the accuracy of crop disease detection with high resolution UAV hyperspectral images.

3-D Convolution-Recurrent Networks for Spectral-Spatial Classification of Hyperspectral Images

Nowadays, 3-D convolutional neural networks (3-D CNN) have attracted lots of attention in the spectral-spatial classification of hyperspectral imageries (HSI). In this model, the feed-forward processing structure reduces the computational burden of 3-D structural processing. However, this model as a vector-based methodology cannot analyze the full content of the HSI information, and as a result, its features are not quite discriminative. On the other hand, convolutional long short-term memory (CLSTM) can recurrently analyze the 3-D structural data to extract more discriminative and abstract features. However, the computational burden of this model as a sequence-based methodology is extremely high. In the meanwhile, the robust spectral-spatial feature extraction with a reasonable computational burden is of great interest in HSI classification. For this purpose, a two-stage method based on the integration of CNN and CLSTM is proposed. In the first stage, 3-D CNN is applied to extract low-dimensional shallow spectral-spatial features from HSI, where information on the spatial features are less than that of the spectral information; consequently, in the second stage, the CLSTM, for the first time, is applied to recurrently analyze the spatial information while considering the spectral one. The experimental results obtained from three widely used HSI datasets indicate that the application of the recurrent analysis for spatial feature extractions makes the proposed model robust against different spatial sizes of the extracted patches. Moreover, applying the 3-D CNN prior to the CLSTM efficiently reduces the model’s computational burden. The experimental results also indicated that the proposed model led to a 1% to 2% improvement compared to its counterpart models.

An Efficient Clustering Method for Hyperspectral Optimal Band Selection via Shared Nearest Neighbor

A hyperspectral image (HSI) has many bands, which leads to high correlation between adjacent bands, so it is necessary to find representative subsets before further analysis. To address this issue, band selection is considered as an effective approach that removes redundant bands for HSI. Recently, many band selection methods have been proposed, but the majority of them have extremely poor accuracy in a small number of bands and require multiple iterations, which does not meet the purpose of band selection. Therefore, we propose an efficient clustering method based on shared nearest neighbor (SNNC) for hyperspectral optimal band selection, claiming the following contributions: (1) the local density of each band is obtained by shared nearest neighbor, which can more accurately reflect the local distribution characteristics; (2) in order to acquire a band subset containing a large amount of information, the information entropy is taken as one of the weight factors; (3) a method for automatically selecting the optimal band subset is designed by the slope change. The experimental results reveal that compared with other methods, the proposed method has competitive computational time and the selected bands achieve higher overall classification accuracy on different data sets, especially when the number of bands is small.

Classification of Crops, Pastures, and Tree Plantations along the Season with Multi-Sensor Image Time Series in a Subtropical Agricultural Region

Timely and efficient land-cover mapping is of high interest, especially in agricultural landscapes. Classification based on satellite images over the season, while important for cropland monitoring, remains challenging in subtropical agricultural areas due to the high diversity of management systems and seasonal cloud cover variations. This work presents supervised object-based classifications over the year at 2-month time-steps in a heterogeneous region of 12,000 km2 in the Sao Paulo region of Brazil. Different methods and remote-sensing datasets were tested with the random forest algorithm, including optical and radar data, time series of images, and cloud gap-filling methods. The final selected method demonstrated an overall accuracy of approximately 0.84, which was stable throughout the year, at the more detailed level of classification; confusion mainly occurred among annual crop classes and soil classes. We showed in this study that the use of time series was useful in this context, mainly by including a small number of highly discriminant images. Such important images were eventually distant in time from the prediction date, and they corresponded to a high-quality image with low cloud cover. Consequently, the final classification accuracy was not sensitive to the cloud gap-filling method, and simple median gap-filling or linear interpolations with time were sufficient. Sentinel-1 images did not improve the classification results in this context. For within-season dynamic classes, such as annual crops, which were more difficult to classify, field measurement efforts should be densified and planned during the most discriminant window, which may not occur during the crop vegetation peak.