Hyperspectral imagery with very high spectral resolution provides a new insight for subtle nuances identification of similar substances. However, hyperspectral target detection faces significant challenges of intraclass dissimilarity and interclass similarity due to the unavoidable interference caused by atmosphere, illumination, and sensor noise. In order to effectively alleviate these spectral inconsistencies, this paper proposes a novel target detection method without strict assumptions on data distribution based on an unconstrained linear mixture model and deep learning. Our proposed detector firstly reduces interference via a specifically designed deep-learning-based hierarchical denoising autoencoder, and then carries out accurate detection with a two-step subspace projection, aiming at background suppression and target enhancement. Additionally, to generate representative background and reliable target samples required in the detection procedure, an efficient spatial-spectral unified endmember extraction method has been developed. Performance comparison with several state-of-the-art detection methods and further analysis on four real-world hyperspectral images demonstrate the effectiveness and efficiency of our proposed target detector.

Recently, convolutional neural networks (CNNs) have attracted enormous attention in pattern recognition and demonstrated excellent performance in hyperspectral image (HSI) classification. However, high-dimensional HSI dataset versus limited training samples is easy to cause the over-fitting phenomenon in deep neural networks. Additionally, the intraclass distance of the embedding features extracted through the softmax-based CNNs may be greater than that of the interclass, which makes it difficult to further improve the classification accuracy. To address these issues, this paper proposes a deep prototypical network with hybrid residual attention (DPN-HRA), which can effectively investigate the spectral-spatial information in HSI. Specifically, in order to improve the generalization capability of the model, feature extraction with a hybrid residual attention module is presented to enhance the critical spectral-spatial features and suppress the useless ones in the classification task. Furthermore, a novel discriminant distance-based cross-entropy loss (D²CEL) is proposed to increase the intraclass compactness, so as to obtain more superior results. Extensive experiments on three benchmark datasets are carried out to convincingly evaluate the proposed framework. With the generation of optimal prototypes representing each class and more discriminative embedding features, encouraging classification results are achieved compared with state-of-the-art methods.

Target detection plays a core issue in hyperspectral remote sensing, but faces serious challenges of how to deal with the spatial and spectral redundancies and spectral variations. In this article, a novel network block is developed, called RFT-MSA block (abbreviated as RM), which includes the region-of-interest (RoI) feature transformation (RFT) and the multiscale-spectral-attention (MSA) module as to reduce the spatial and spectral redundancies simultaneously and provide strong discrimination. Furthermore, a deep spatial-spectral network (DSSN) is presented by stacking several RM and deconvolutional (DC) blocks for hyperspectral target detection in an unsupervised manner, and a feature loss term is investigated to simultaneously restrict the target to be sparse and minimize the energy of the background. The proposed algorithm mainly consists of three steps. First, an RoI map is detected using a classical detector (no statistic assumption is needed) with an edge-preserving filter. Then, the hyperspectral image (HSI) and the corresponding RoI map are considered as inputs to the DSSN for extracting the spatial and spectral feature of interest (SSFI). Finally, we apply the nearest neighbors (NNs) to the SSFI for detection-map refinement. The experimental results on one synthetic and three real HSIs demonstrate that the proposed algorithm outperforms other benchmark approaches in detection performance and robustness. In addition, further analysis also demonstrates the effectiveness of the proposed RM block.

Deep learning-based hyperspectral target detection (HTD) is potentially hindered by the limited training samples and sensor-dependent transferability. To address this issue, we propose a novel semisupervised domain adaptive few-shot learning (SDAFL) model to adaptively transfer similarity/dissimilarity measurement from source domain with sufficient labeled samples to target domain in an adversarial manner, where source data and target data can be collected by different sensors, i.e., sensor-independent. In order to alleviate negative transfer, residual channel attention (RCA) and weighted domain adaptation (WDA) are used to automatically select representative features and assign easy-transferred samples with higher priority. In addition, we adopt modulated deformable convolution (MDConv) to make the receptive field fit image spatial structure and also introduce a discriminatively boosted loss (DBL) function based on the prior known target signature to further enhance feature distinction, where intraclass similarity is improved, while interclass similarity is suppressed. After extracting discriminative features through the SDAFL model, guided filter and t-distribution kernel are jointly used for spatial–spectral target detection (S ² TD). It should be noted that only the spectral signature of the desired object is needed in the target domain. Experimental results and analysis on three real hyperspectral images (HSIs) verify the efficiency and superiority of our proposed sensor-independent hyperspectral target detection (SIHTD) method compared with other algorithms.

Unsupervised autoencoders (AEs) have been demonstrated effectively to achieve robust performance in hyperspectral feature extraction. However, one-dimension inputs of AE cannot get precise detection due to spatial information loss. And the improved convolutional AEs (CAEs) perform outstandingly in microscopic spatial-spectral details learning, but lack macroscopic contextual information, which can provide meaningful sizes and shapes for target detection. To address this issue, a three-dimensional (3-D) macro-micro convolutional AE network is proposed to preserve both macro and micro information in this article. Furthermore, to make it easier to optimize, residual learning is induced for refining the network, and forming a novel 3-D macro-micro residual AE (3-D-MMRAE). For feature extraction, 3-D-MMRAE aggregates features from a macro branch and a micro branch, capturing discriminative and valuable structures. In addition, a promising loss combined with similarity measurement and distance constraint is proposed to improve the discriminative capacity and refine the reconstruction process. At last, the extracted features are fed to a novel hierarchical radial basis function (hRBF) detector for target preservation and background suppression. Extensive experiments and analysis on several classic hyperspectral benchmarks demonstrate that the macro-micro features have superior capacity of distinction, and our proposed 3-D-MMRAE detector outperforms several state-of-the-art detectors.