Most existing techniques consider hyperspectral anomaly detection (HAD) as background modeling and anomaly search problems in the spatial domain. In this article, we model the background in the frequency domain and treat anomaly detection as a frequency-domain analysis problem. We illustrate that spikes in the amplitude spectrum correspond to the background, and a Gaussian low-pass filter performing on the amplitude spectrum is equivalent to an anomaly detector. The initial anomaly detection map is obtained by the reconstruction with the filtered amplitude and the raw phase spectrum. To further suppress the nonanomaly high-frequency detailed information, we illustrate that the phase spectrum is critical information to perceive the spatial saliency of anomalies. The saliency-aware map obtained by phase-only reconstruction (POR) is used to enhance the initial anomaly map, which realizes a significant improvement in background suppression. In addition to the standard Fourier transform (FT), we adopt the quaternion FT (QFT) for conducting multiscale and multifeature processing in a parallel way, to obtain the frequency domain representation of the hyperspectral images (HSIs). This helps with robust detection performance. Experimental results on four real HSIs validate the remarkable detection performance and excellent time efficiency of our proposed approach when compared to some state-of-the-art anomaly detection methods.

Hyperspectral images (HSIs) often contain irregular ground cover with mixed spectral features and noise, which makes it challenging to identify the ground cover using only pixel features, superpixel features, or a combination of both. To alleviate the above problem, this paper proposes a superpixel-pixel-subpixel multilevel network (SPSM), which compensates for the insufficiencies of the different levels and decrease the information loss. For arbitrary irregular regions, superpixel features are simulated as network nodes using a graph convolutional network (GCN) to capture the spatial texture structure of the HSI, which improves the smooth classification results of local regions while facilitating the identification of different vegetation features in the region. Additionally, the global attention module (GAM) learns local regular regions based on pixel-level features to extend the global interactive representation capability and reduce information loss. To overcome spectral mixing and enhance material discrimination, the normalized attention module (NAM) is used to suppress unimportant subpixel information and identify and remove irrelevant details, thereby improving the identification of critical features that differentiate different materials. Finally, the three features are fused to build a SPSM classification framework to improve robustness to overfitting, reduce computational complexity, and facilitate target recognition. Experimental results on four HSI datasets demonstrate that the method is more capable of recognizing detailed features than other advanced comparison methods.

The fusion of spectral–spatial features based on deep learning has become the focus of research in hyperspectral image (HSI) classification. However, previous deep frameworks based on spectral–spatial fusion usually performed feature aggregation only at the branch ends. Furthermore, only first-order statistical features are considered in the fusion process, which is not conducive to improving the discrimination of spectral–spatial features. This article proposes a global–local hierarchical weighted fusion end-to-end classification architecture. The architecture includes two subnetworks for spectral classification and spatial classification. For the spectral subnetwork, two band-grouping strategies are designed, and bidirectional long short-term memory is used to capture spectral context information from global to local perspectives. For the spatial subnetwork, a pooling strategy based on local attention is combined to construct a global–local pooling fusion module to enhance the discriminability of spatial features learned by a convolutional neural network. For the fusion stage, a hierarchical weighting fusion mechanism is developed to obtain the nonlinear relationship between both spectral and spatial features. The experimental results on four real HSI datasets and a GF-5 satellite dataset demonstrate that the method proposed is more competitive in terms of accuracy and generalization.

Superpixel segmentation is a powerful tool that can effectively utilize spectral and spatial information for hyperspectral image (HSI) classification. In this paper, we propose a new HSI classification method via superpixel and correlation coefficient (CC) representation (SCCR), where CC is a powerful metric to assess similarity among pixels. Considering the correlation among pixels within each superpixel, the superpixel region is viewed as the neighborhood of a test sample that can better exploit the spatial structure information of HSI. In the proposed method, recursive filtering is first used to extract features for hyperspectral data analysis. Then, based on the $k$ -nearest neighbors theory, the CC between each test sample and each class of training samples can be jointly calculated by the $k$ most relevant pixels in the neighborhood, which effectively reduces the effect of the mixed samples from different classes on the classification accuracy. Finally, the class label of each test sample is determined by which class presents the maximum CC. The experimental results demonstrate that the proposed SCCR improves classification performance compared to other well-known classification methods.

Hyperspectral images (HSIs) contain many levels of spatial structures, and thus, feature extraction techniques have been broadly studied in hyperspectral data processing to mine its structural information while preserving strong edge details. However, spatial characteristics in different scales unavoidably mix and overlap, which makes separation among pixels very difficult and yields misclassification. This article proposes a feature extraction method by using multitask superpixel-based auxiliary learning (MSAL) that consists of two main stages. We first design a novel multitask learning (MTL) model from the perspective of task input by constructing a set of auxiliary feature cubes as inputs. Under the MTL framework, the spatial information and edge information are refined in the superpixel-based auxiliary learning feature extraction stage. Specifically, the auxiliary rolling guidance features are extracted from auxiliary cubes via rolling guidance filter, which can remove the unwanted structure. Then, the spatial feature within superpixels is refined by applying structure density-based weighted operation, and the edge feature is stacked with the superpixel auxiliary features to supply the edge information. Finally, the obtained feature cubes are fed into a pixelwise classifier, and a weighted decision rule is introduced to optimize the initial results by utilizing the inherent relation between auxiliary cubes. Experimental results demonstrate that the MSAL can significantly improve the quality of the extraction feature and outperform other state-of-the-art approaches in terms of classification accuracies.

Remote sensing object detection (RSOD) is crucial for various monitoring and measurement applications due to its non-contact, large-scale and real-time observation, such as autonomous driving, scene awareness, and environmental surveillance. Despite significant advances driven by deep neural networks, RSOD faces challenges such as directional ambiguity, scale variations, and densely packed tiny objects, limiting its effectiveness in diverse scenarios. To address these challenges, we explore a novel end-to-end deep RSOD method, termed Gradual Semantic Interaction Network (GSINet). Specifically, we first design a Gradual Semantic Information Interaction Structure (GSIIS), which integrates contextual information across network layers from shallow to deep, enhancing semantic comprehension and detection precision. Second, we propose a novel Dual Attention Mechanism (DAM) that integrates our proposed Adaptive Context Feature Fusion Module (ACFFM) with Bi-Level Routing Attention (BRA) to optimize feature representation, ACFFM enhances context-aware feature fusion by capturing both local and global information, whereas BRA routes attention across different scales, together, they enhance tiny object detection in remote sensing images by reducing background interference and improving feature discrimination. Finally, we utilize the normalized Wasserstein distance (NWD) in place of the traditional Intersection over Union (IoU) metric to better manage object scale variations and location deviations. The extensive experimental evaluation on three public datasets demonstrates that the proposed method exhibits superior performance compared to state-of-the-art detectors, especially in detecting tiny objects. In particular, GSINet achieves a mean average precision (mAP) of 86.7% on the DIOR dataset, 95.01% on the NWPU VHR-10 dataset, and 96.7% on the RSOD dataset