High-dimensional and complex spectral structures make the clustering of hyperspectral images (HSI) a challenging task. Subspace clustering is an effective approach for addressing this problem. However, current subspace clustering algorithms are primarily designed for a single view and do not fully exploit the spatial or textural feature information in HSI. In this study, contrastive multi-view subspace clustering of HSI was proposed based on graph convolutional networks. Pixel neighbor textural and spatial-spectral information were sent to construct two graph convolutional subspaces to learn their affinity matrices. To maximize the interaction between different views, a contrastive learning algorithm was introduced to promote the consistency of positive samples and assist the model in extracting robust features. An attention-based fusion module was used to adaptively integrate these affinity matrices, constructing a more discriminative affinity matrix. The model was evaluated using four popular HSI datasets: Indian Pines, Pavia University, Houston, and Xu Zhou. It achieved overall accuracies of 97.61%, 96.69%, 87.21%, and 97.65%, respectively, and significantly outperformed state-of-the-art clustering methods. In conclusion, the proposed model effectively improves the clustering accuracy of HSI. Our implementation is available at https://github.com/GuanRX/CMSCGC.

Sparse unmixing, as a semisupervised unmixing method, has attracted extensive attention. The process of sparse unmixing involves treating the mixed pixels of hyperspectral imagery as a linear combination of a small number of spectral signatures (endmembers) in a standard spectral library, associated with fractional abundances. Over the past ten years, to achieve a better performance, sparse unmixing algorithms have begun to focus on the spatial information of hyperspectral images. However, less accurate spatial information greatly limits the performance of the spatial-regularization-based sparse unmixing algorithms. In this article, to overcome this limitation and obtain more reliable spatial information, a novel sparse unmixing algorithm named superpixel-based reweighted low-rank and total variation (SUSRLR-TV) is proposed to enhance the performance of the traditional spatial-regularization-based sparse unmixing approaches. In the proposed approach, superpixel segmentation is adopted to consider both the spatial proximity and the spectral similarity. In addition, a low-rank constraint is enforced on the objective function as pixels within each superpixel have the same endmembers and similar abundance values, and they naturally satisfy the low-rank constraint. Differing from the traditional nuclear norm, a reweighted nuclear norm is used to achieve a more efficient and accurate low-rank constraint. Meanwhile, low-rank consideration is also used to enhance the spatial continuity and suppress the effects of random noise. Furthermore, TV regularization is introduced to promote the smoothness of the abundance maps. Experiments on three simulated data sets, as well as a well-known real hyperspectral imagery data set, confirm the superior performance of the proposed method in both the qualitative assessment and the quantitative evaluation, compared with the state-of-the-art sparse unmixing methods.

High-resolution remote sensing (HRRS) image scene classification has attracted an enormous amount of attention due to its wide application in a range of tasks. Due to the rapid development of deep learning (DL), models based on convolutional neural network (CNN) have made competitive achievements on HRRS image scene classification because of the excellent representation capacity of DL. The scene labels of HRRS images extremely depend on the combination of global information and information from key regions or locations. However, most existing models based on CNN tend only to represent the global features of images or overstate local information capturing from key regions or locations, which may confuse different categories. To address this issue, a key region or location capturing method called key filter bank (KFB) is proposed in this article, and KFB can retain global information at the same time. This method can combine with different CNN models to improve the performance of HRRS imagery scene classification. Moreover, for the convenience of practical tasks, an end-to-end model called KFBNet where KFB combined with DenseNet-121 is proposed to compare the performance with existing models. This model is evaluated on public benchmark data sets, and the proposed model makes better performance on benchmarks than the state-of-the-art methods.

Due to the trade-off of temporal resolution and spatial resolution, spatiotemporal image-fusion uses existing high-spatial-low-temporal (HSLT) and high-temporal-low-spatial (HTLS) images as prior knowledge to reconstruct high-temporal-high-spatial (HTHS) images. However, some existing spatiotemporal image-fusion algorithms ignore the issue that the spatial information of HTLS images is insufficient to support the acquisition of spatial information, which leads to the unsatisfactory accuracy of the fusion result. To introduce more spatial information, the algorithm in this article uses Cycle-generative adversarial networks (GANs) to simulate the change process of two HSLT images at k-1 and k+1, and to generate some simulated images between k-1 and k+1. Then, the generated images are selected under the help of HTLS images, and the selected ones are then enhanced with wavelet transform. Finally, the image with spatial information is introduced into the Flexible Spatiotemporal DAta Fusion (FSDAF) framework to improve the performance of spatiotemporal image-fusion. Extensive experiments on two real data sets demonstrate that our proposed method outperforms current state-of-the-art spatiotemporal image-fusion methods.

Sub-meter high-resolution remote sensing (HRRS) image land cover classification could provide significant help for urban monitoring, management, and planning. Deep learning-based models have achieved remarkable performance in many land cover classification tasks through end-to-end supervised learning. However, the excellent performance of deep learning-based models relies heavily on a large number of well-annotated samples, which is impossible in practical land cover classification scenarios. Additionally, the training set could contain all of the different land cover types. To overcome these problems, in this paper a semi-supervised multiple-CNN ensemble learning method, namely the Semi-MCNN, is proposed to solve the land cover classification problem in Shenzhen city. Considering the lack of labelled samples, a semi-supervised learning strategy was adopted to leverage large amounts of unlabelled data. In the proposed approach, an automatic sample selection strategy called an ensembled teacher model dataset generation (EMDG) was adopted to select samples and generate a dataset from large amounts of unlabelled data automatically. To tackle the error-propagation problem, an important strategy was adopted to correct the errors by pretraining on the selected unlabelled data and finetuning on the labelled data. Moreover, the semi-supervised strategy together with the multi-CNN ensemble strategy were integrated into an end-to-end architecture. This could significantly improve the generalisation ability of the semi-supervised model, as well as improve the classification accuracy. Experiments were conducted on Shenzhen's land cover data (ShenzhenLC) and two other public remote sensing datasets. These experiments confirmed the superior performance of the proposed semi-MCNN compared to the state-of-the-art land cover classification models.

Mapping population distribution at fine spatial scales is significant and fundamental for resource utilization, assessment of city disaster, environmental regulation, and urbanization. Multisource data produced by remote and social sensing have been widely used to disaggregate census information to map population distributions at fine resolution. However, it is challenging to achieve accurate high-spatial-resolution population mapping by combining multisource data and considering geographic spatial heterogeneity. The existing approaches do not consider global and local spatial information simultaneously, resulting in low accuracy. This article proposes a multimodel fusion neural network for estimating fine-resolution population estimates from multisource data. Our approach takes into account the local spatial information and global information of each geographic unit. Specifically, a first-order space matrix of a geographic unit is used to characterize its local spatial information. We propose a multimodel neural network, which combines a convolutional neural network and a multilayer perceptron (MLP) model to estimate a fine-resolution population mapping. Using Shenzhen, China, as the experimental setting, a population distribution map was generated at a 100-m spatial resolution. The model was quantitatively validated by showing that it captured the relationship between the estimated population and the census population at the township level (R ² =0.77) more accurately than the WorldPop dataset (R ² =0.51) and the MLP-based model (R ² =0.63). Qualitatively, the proposed model can identify differences in population density in densely populated areas and some remote population clusters more accurately than the WorldPop population dataset.