Hyperspectral image (HSI) clustering is very important in remote sensing applications. However, most graph-based clustering models are not suitable for dealing with large HSI due to their computational bottlenecks: the construction of the similarity matrix W, the eigenvalue decomposition of the graph Laplacian matrix L, and k-means or other discretization procedures. To solve this problem, we propose a novel approach, scalable graph-based clustering with nonnegative relaxation (SGCNR), to cluster the large HSI. The proposed SGCNR algorithm first constructs an anchor graph and then adds the nonnegative relaxation term. With this, the computational complexity can be reduced to O(ndłog m+nK²+nKc+K³), compared with traditional graph-based clustering algorithms that need at least O(n²d+n²K) or O(n²d+n³), where n, d, m, K, and c are, respectively, the number of samples, features, anchors, classes, and nearest neighbors. In addition, the SGCNR algorithm can directly obtain the clustering indicators, without resort to k-means or other discretization procedures as traditional graph-based clustering algorithms have to do. Experimental results on several HSI data sets have demonstrated the efficiency and effectiveness of the proposed SGCNR algorithm.

Graph neural network (GNN) has recently gained increasing attention in the hyperspectral image (HSI) classification. Compared with convolutional neural network (CNN), GNN can effectively relieve the scarcity of labeled data. In our method, we first perform feature learning on large-scale irregular regions through GNN and then extract local spatial–spectral features at the pixel level. Besides, we incorporate edge convolution (EdgeConv) into GNN to adaptively capture the interrelationship of the representative descriptors and fully exploit the discriminative features on graph. Experiments on several HSI datasets show that our method can achieve better classification performance compared with the state-of-the-art HSI classification methods.

Hyperspectral anomaly detection (HAD) has drawn a significant attention of late due to its importance in many military and civilian applications. In this article, a fast hyperspectral anomaly detector that combines multiple features and isolation forest is proposed. This approach, which is based on the assumption that the anomalous pixels are more susceptible to isolation than the background pixels, consists of two main parts. First, the spectral, Gabor, extended morphological profile (EMP) and extended multiattribute profile (EMAP) features are extracted from the hyperspectral image (HSI). Next, the isolation forest of each feature is constructed using the subsampling strategy. This combination of multiple features can exploit both the spectral and spatial information of the HSI, thereby improving the anomaly detection performance significantly. Compared with eight state-of-the-art HAD methods, the experimental results on four real hyperspectral data sets demonstrate that the performance of our proposed approach is quite competitive in terms of detection accuracy and running time.

As the captured information in our real word is very scare and labeling sample is time cost and expensive, semisupervised learning (SSL) has an important application in computer vision and machine learning. Among SSL approaches, a graph-based SSL (GSSL) model has recently attracted much attention for high accuracy. However, for most traditional GSSL methods, the large-scale data bring higher computational complexity, which acquires a better computing platform. In order to dispose of these issues, we propose a novel approach, bipartite GSSL normalized (BGSSL-normalized) method, in this paper. This method consists of three parts. First, the bipartite graph between the original data and the anchor points is constructed, which is parameter-insensitive, scale-invariant, naturally sparse, and simple operation. Then, the label of the original data and anchors can be inferred through the graph. Besides, we extend our algorithm to handle out-of-sample for large-scale data by the inferred label of anchors, which not only retains good classification result but also saves a large amount of time. The computational complexity of BGSSL-normalized can be reduced to O(ndm+nm²), which is a significant improvement compared with traditional GSSL methods that need O(n²d+n³), where n, d, and m are the number of samples, features, and anchors, respectively. The experimental results on several publicly available data sets demonstrate that our approaches can achieve better classification accuracy with less time costs.