Deep learning-based methods have presented a promising performance in the task of hyperspectral imagery classification (HSIC). However, recent methods usually are considered HSIC as a patchwise image classification problem and addressed it by giving a single label to the patch surrounding a pixel. In this letter, we propose a new semantic segmentation network that can directly label each pixel in an end-to-end manner. Compared with patchwise models, our method can significantly improve training effectiveness and reduce some manual parameters. Another challenge in HSIC is that the spatial resolution of hyperspectral imagery is relatively low; in that case, the pooling operation may result in resolution and coverage loss. To address this issue, we introduce dilated convolution to our model and construct a dilated semantic segmentation network (DSSNet). Different from some existing works, DSSNet is specially designed for HSIC without complicated architecture, and no pretrained models are required. The joint spatial-spectral information can be extracted via an end-to-end manner and, thus, avoid various preprocessing or postprocessing operations. Experiments on two public data sets have demonstrated the effectiveness of our improvements compared with some of the latest deep learning-based HSIC models.

Recently, feature pyramid has been widely exploited in remote sensing detectors, which greatly alleviates the problem arising from scale variation across objects in remote sensing images. However, these object detectors with feature pyramid give insufficient consideration that objects in remote sensing images usually maintain symmetrical shape. To address this issue, we propose an anchor-free-based detector called Centerness-Aware Network (CANet), which could capture the symmetrical shape of objects in remote sensing images. The kernel structure of CANet is a new Centerness-Aware Model (CAM) that contains three components: Multiscale Centerness Descriptor (MSCD), Centerness Detection Head (CDH), and Feature Selective Module (FSM). Considering that symmetrical objects will maintain a rigid appearance around their center region, three components are integrated into the feature pyramid to extract and utilize the features around the center region. More precisely, the MSCD is embedded into the feature pyramid and highlights the center of current objects through the attention mechanism. Guided by the MSCD, the CDH could accurately capture the center of objects by per-pixel prediction. Furthermore, the FSM is connected to the CDH, which guides the CDH to adaptively select the optimal feature level from the pyramidal features. The selected feature level could describe the best semantic information around the center region, which helps the network progressively fit the symmetrical shape of remote sensing objects. Besides, we also design the hybrid loss function to effectively train CAM in the end-to-end way. The experiments show that our network is competitive with some state-of-the-art detection networks.

The accurate prediction for the tropical cyclone (TC) intensity is a recognised challenge. Researchers usually develop dynamical models to address this task. However, since the TC intensity is highly influenced by various factors such as ocean and atmosphere conditions, it is difficult to build the very model which can explicitly describe the mechanism of TC. A new idea is developed, utilising the massive historical observation data by a deep learning approach, to conduct a completely data‐driven TC intensity prediction model. All the TC intensity and track data which have been observed in Western North Pacific since 1949 are collected, and recurrent neural network for TC intensity prediction is constructed. In general, their motivation as well as novelty is to develop a data‐driven approach instead of empirical models. There are very few researches similar to their exploratory work. The proposed method has presented 5.1 m s error in 24 h prediction, which is better than some widely used dynamical models and is close to subjective prediction.

Deep-learning-based methods have attracted increasing attention on hyperspectral unmixing, where the transformer models have shown promising performance. However, recently proposed deep-learning-based hyperspectral unmixing methods usually tend to directly apply visual models, while ignoring the characteristics of hyperspectral imagery. In this article, we propose a novel double-aware transformer for hyperspectral Unmixing (UnDAT), which aims at simultaneously exploiting the region homogeneity and spectral correlation of hyperspectral imagery. One of the major assumptions of UnDAT is that hyperspectral remote-sensing images involve many homogeneous regions. Pixels inside a homogeneous region usually present similar spectral features, and the edge pixels are just the reverse. Another observation is that the pixel spectra are continuous and correlated. Based on the above assumption and observation, we construct the UnDAT by developing two modules: Score-based homogeneous-aware (SHA) module and the spectral group-aware (SGA) module. In the SHA module, a feature map rearrangement (FMR) approach is proposed to split the shallow feature maps from a linear encoder into an ordered homogeneous map (HomoMap) and an edge map and develop a homogenous region-aware strategy for deep feature representation. In the SGA module, the dependency among neighboring bands is described by dividing the hyperspectral image into multiple spectral groups and calculating the spectral similarity among bands within each group. Experiments on both real and synthetic datasets indicate the effectiveness of our model. We will publish the code of our approach if the article has the honor to be accepted.

Sparse hyperspectral unmixing has attracted increasing investigations during the past decade. Recent research has indicated that library pruning algorithms can significantly improve the unmixing accuracies by reducing the mutual coherence of the spectral library. Inspired by the good performance of library pruning, in this article we propose a new hyperspectral unmixing algorithm which integrates the idea of library pruning and sparse representation. An obvious challenge for pruning algorithms is that the real endmembers must be preserved after pruning. Unfortunately, recent proposed pruning algorithms, such as multiple signal classification are actually prepruning strategies, which cannot guarantee that the endmembers exactly exist in the selected spectral subset when the image noise is strong. To overcome this difficulty, we develop a simultaneous optimization approach which involves the pruning operation into the optimization process. Compared with existing prepruning-based unmixing methods, the proposed algorithm can gradually compress the search space of sparse representation, which may relieve the loss of spectral information caused by the rapid compression of the library. Instead of simply designing a regularizer, in this article we utilize a multiobjective-based framework where reconstruction error, sparsity error, and the pruning projection function are considered as three parallel objectives, so as to avoid the manually settings of regularization parameters. Moreover, we have provided theoretical analysis and proof for the reasonability of our pruning objective. Experiments on synthetic hyperspectral data may indicate the superiority of the proposed method under high-noise conditions.

In remote sensing images, the backgrounds of objects include crucial contextual information that may contribute to distinguishing objects. However, there are at least two issues that should be addressed: not all the backgrounds are beneficial, and object information may be suppressed by backgrounds. To address these problems, in this paper, we propose the contextual bidirectional enhancement (CBD-E) method to simultaneously remove unexpected background information and enhance objects features. CBD-E integrates the features of different background regions sequentially in two directions. On the one hand, a gate function is used to filter out unexpected information in the background and thus improve the recall of detection. On the other hand, a spatial-group-based visual attention mechanism is adopted to enhance the features of objects to reduce the false alarm. The gate function provides an approach to selecting meaningful information in the background, while the spatial-group-based visual attention mechanism enhances the information control ability of the gate function. In the experiments, we have validated the effectiveness of both the gate function and the visual attention mechanism and further demonstrated that the proposed contextual fusion strategy performs well on two published data sets.