Super-resolution (SR) technology is an important way to improve spatial resolution under the condition of sensor hardware limitations. With the development of deep learning (DL), some DL-based SR models have achieved state-of-the-art performance, especially the convolutional neural network (CNN). However, considering that remote sensing images usually contain a variety of ground scenes and objects with different scales, orientations, and spectral characteristics, previous works usually treat important and unnecessary features equally or only apply different weights in the local receptive field, which ignores long-range dependencies; it is still a challenging task to exploit features on different levels and reconstruct images with realistic details. To address these problems, an attention-based generative adversarial network (SRAGAN) is proposed in this article, which applies both local and global attention mechanisms. Specifically, we apply local attention in the SR model to focus on structural components of the earth’s surface that require more attention, and global attention is used to capture long-range interdependencies in the channel and spatial dimensions to further refine details. To optimize the adversarial learning process, we also use local and global attentions in the discriminator model to enhance the discriminative ability and apply the gradient penalty in the form of hinge loss and loss function that combines $L1$ pixel loss, $L1$ perceptual loss, and relativistic adversarial loss to promote rich details. The experiments show that SRAGAN can achieve performance improvements and reconstruct better details compared with current state-of-the-art SR methods. A series of ablation investigations and model analyses validate the efficiency and effectiveness of our method.

Super-resolution (SR) is able to improve the spatial resolution of remote sensing images, which is critical for many practical applications such as fine urban monitoring. In this paper, a new single-image SR method, deep gradient-aware network with image-specific enhancement (DGANet-ISE) was proposed to improve the spatial resolution of remote sensing images. First, DGANet was proposed to model the complex relationship between low- and high-resolution images. A new gradient-aware loss was designed in the training phase to preserve more gradient details in super-resolved remote sensing images. Then, the ISE approach was proposed in the testing phase to further improve the SR performance. By using the specific features of each test image, ISE can further boost the generalization capability and adaptability of our method on inexperienced datasets. Finally, three datasets were used to verify the effectiveness of our method. The results indicate that DGANet-ISE outperforms the other 14 methods in the remote sensing image SR, and the cross-database test results demonstrate that our method exhibits satisfactory generalization performance in adapting to new data.

Pixel-based and object-oriented processing of Chinese HJ-1-A satellite imagery (resolution 30 m) acquired on 23 July 2009 were utilized for classification of a study area in Budapest, Hungary. The pixel-based method (maximum likelihood classifier for pixel-level method (MLCPL)) and two object-oriented methods (maximum likelihood classifier for object-level method (MLCOL) and a hybrid method combining image segmentation with the use of a maximum likelihood classifier at the pixel level (MLCPL)) were compared. An extension of the watershed segmentation method was used in this article. After experimenting, we chose an optimum segmentation scale. Classification results showed that the hybrid method outperformed MLCOL, with an overall accuracy of 90.53%, compared with the overall accuracy of 77.53% for MLCOL. Jeffries–Matusita distance analysis revealed that the hybrid method could maintain spectral separability between different classes, which explained the high classification accuracy in mixed-cover types compared with MLCOL. The classification result of the hybrid model is preferred over MLCPL in geographical or landscape ecological research for its accordance with patches in landscape ecology, and for continuity of results. The hybrid of image segmentation and pixel-based classification provides a new way to classify land-cover types, especially mixed land-cover types, using medium-resolution images on a regional, national, or global basis.

International audienceUrban areas are major places where intensive interactions between human and the natural system occur. Urban vegetation is a major component of the urban ecosystem, and urban residents benefit substantially from urban green spaces. To measure urban green spaces, remote sensing is an established tool due to its capability of monitoring urban vegetation quickly and continuously. In this study: (1) a Building’s Proximity to Green spaces Index (BPGI) was proposed as a measure of building’s neighbouring green spaces; (2) LiDAR data and multispectral remotely sensed imagery were used to automatically extract information regarding urban buildings and vegetation; (3) BPGI values for all buildings were calculated based on the extracted data and the proximity and adjacency of buildings to green spaces; and (4) two districts were selected in the study area to examine the relationships between the BPGI and different urban environments. Results showed that the BPGI could be used to evaluate the proximity of residents to green spaces at building level, and there was an obvious disparity of BPGI values and distribution of BPGI values between the two districts due to their different urban functions (i.e., downtown area and residential area). Since buildings are the major places for residents to live, work and entertain, this index may provide an objective tool for evaluating the proximity of residents to neighbouring green spaces. However, it was suggested that proving correlations between the proposed index and human health or environmental amenity would be important in future research for the index to be useful in urban planning

Many researchers have used simulation to study the cognitive processes that underlie the decision‐making skills of expert athletes. However, we have seen that these studies used an explicit‐memory paradigm that does not uncover the processes responsible for the emergence of decisions made during a game. They have primarily been concerned with describing elementary operations rather than with identifying the nature of the processes involved. We therefore chose a priming paradigm, in an attempt to identify the decision‐making processes implemented during a simulated game. The results showed that the nature of the processing depended on the characteristics of the decision‐making task being considered. When the task required a one‐step decision, low‐level processes were utilized; when it required a series of planned actions, expert players implemented high‐level processes.