Panchromatic (PAN) images contain abundant spatial information that is useful for earth observation, but always suffer from low-resolution ( LR) due to the sensor limitation and large-scale view field. The current super-resolution (SR) methods based on traditional attention mechanism have shown remarkable advantages but remain imperfect to reconstruct the edge details of SR images. To address this problem, an improved SR model which involves the self-attention augmented Wasserstein generative adversarial network ( SAA-WGAN) is designed to dig out the reference information among multiple features for detail enhancement. We use an encoder-decoder network followed by a fully convolutional network (FCN) as the backbone to extract multi-scale features and reconstruct the High-resolution (HR) results. To exploit the relevance between multi-layer feature maps, we first integrate a convolutional block attention module (CBAM) into each skip-connection of the encoder-decoder subnet, generating weighted maps to enhance both channel-wise and spatial-wise feature representation automatically. Besides, considering that the HR results and LR inputs are highly similar in structure, yet cannot be fully reflected in traditional attention mechanism, we, therefore, designed a self augmented attention (SAA) module, where the attention weights are produced dynamically via a similarity function between hidden features; this design allows the network to flexibly adjust the fraction relevance among multi-layer features and keep the long-range inter information, which is helpful to preserve details. In addition, the pixel-wise loss is combined with perceptual and gradient loss to achieve comprehensive supervision. Experiments on benchmark datasets demonstrate that the proposed method outperforms other SR methods in terms of both objective evaluation and visual effect.
Anomaly detection has become an important topic in Hyperspectral Imagery (HSI) analysis in the last two decades with the advantage of detecting the targets surrounding in diverse backgrounds without prior knowledge. HSIs usually have complex and redundant spectral signals due to the complicated land-cover distribution. Generally, it is difficult to estimate the background accurately, and distinguish the anomaly targets. The performances of traditional algorithms are difficult to meet the requirements. In this paper, we propose a novel anomalous component extraction framework for hyperspectral anomaly detection based on Independent Component Analysis (ICA) and Orthogonal Subspace Projection (OSP). In the proposed method, the brightest anomalous component is extracted to initialize the projection vector, by which the performance of ICA can be improved greatly. Moreover, the Independent Component (IC) containing the most abnormal information can be obtained according to the vector. Besides, The OSP algorithm is applied to suppress the background components in the remaining data. Then the data are iteratively processed by ICA to extract the anomalous component subtly. Therefore, in the initialization process, the possible situation of detecting the pixels in the same position can be effectively avoided, and the interference of the last iteration procedure can be cut down greatly, helping to optimize the detection. Finally, the experimental results show that the proposed framework achieves a superior performance compared to some of the state-of-the-art methods in the field of anomaly detection.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.