Search

The integration of remote sensing object counting in the Mobile Edge Computing (MEC) environment is of crucial significance and practical value. However, the presence of significant background interference in remote sensing images poses a challenge to accurate object counting, as the results are easily affected by background noise. Additionally, scale variation within remote sensing images presents a further difficulty, as traditional counting methods face challenges in adapting to objects of different scales. To address these challenges, we propose a selective spatial‐frequency pyramid network (SSFPNet). Specifically, the SSFPNet consists of two core modules, namely the pyramid attention (PA) module and the hybrid feature pyramid (HFP) module. The PA module accurately extracts target regions and eliminates background interference by operating on four parallel branches. This enables more precise object counting. The HFP module is introduced to fuse spatial and frequency domain information, leveraging scale information from different domains for object counting, so as to improve the accuracy and robustness of counting. Experimental results on RSOC, CARPK, and PUCPR+ benchmark datasets demonstrate that the SSFPNet achieves state‐of‐the‐art performance in terms of accuracy and robustness. [ABSTRACT FROM AUTHOR]

Super-resolution (SR) technology plays a crucial role in improving the spatial resolution of remote sensing images so as to overcome the physical limitations of spaceborne imaging systems. Although deep convolutional neural networks have achieved promising results, most of them overlook the advantage of self-similarity information across different scales and high-dimensional features after the upsampling layers. To address the problem, we propose a hybrid-scale hierarchical transformer network (HSTNet) to achieve faithful remote sensing image SR. Specifically, we propose a hybrid-scale feature exploitation module to leverage the internal recursive information in single and cross scales within the images. To fully leverage the high-dimensional features and enhance discrimination, we designed a cross-scale enhancement transformer to capture long-range dependencies and efficiently calculate the relevance between high-dimension and low-dimension features. The proposed HSTNet achieves the best result in PSNR and SSIM with the UCMecred dataset and AID dataset. Comparative experiments demonstrate the effectiveness of the proposed methods and prove that the HSTNet outperforms the state-of-the-art competitors both in quantitative and qualitative evaluations. [ABSTRACT FROM AUTHOR]

Object counting is a fundamental task in remote sensing analysis. Nevertheless, it has been barely studied compared with object counting in natural images due to the challenging factors, e.g., background clutter and scale variation. This paper proposes a triple attention and scale-aware network (TASNet). Specifically, a triple view attention (TVA) module is adopted to remedy the background clutter, which executes three-dimension attention operations on the input tensor. In this case, it can capture the interaction dependencies between three dimensions to distinguish the object region. Meanwhile, a pyramid feature aggregation (PFA) module is employed to relieve the scale variation. The PFA module is built in a four-branch architecture, and each branch has a similar structure composed of dilated convolution layers to enlarge the receptive field. Furthermore, a scale transmit connection is introduced to enable the lower branch to acquire the upper branch's scale, increasing the output's scale diversity. Experimental results on remote sensing datasets prove that the proposed model can address the issues of background clutter and scale variation. Moreover, it outperforms the state-of-the-art (SOTA) competitors subjectively and objectively. [ABSTRACT FROM AUTHOR]

With Graph: Figure 3 (a) Mean vertical displacement velocities throughout the NCP derived from the Sentinel-1A (S1A) data by using persistent scatterer interferometric synthetic aperture radar (PS-InSAR), (b) statistics of the subsidence rates at persistent scatterer (PS) points, (c) changes in the area with subsidence over 50 mm from 2016 to 2018, and (d) changes in the maximum subsidence rates from 2016 to 2018: PP, CP, and LP represent the piedmont alluvial-proluvial plain, central alluvial-lacustrine plain, and littoral plain, respectively. Replace Graph: Figure 3 (a) Mean vertical displacement velocities throughout the NCP derived from the Sentinel-1A (S1A) data by using persistent scatterer interferometric synthetic aperture radar (PS-InSAR), (b) statistics of the subsidence rates at persistent scatterer (PS) points, (c) changes in the area with subsidence over 50 mm from 2016 to 2018, and (d) changes in the maximum subsidence rates from 2016 to 2018: PP, CP, and LP represent the piedmont alluvial-proluvial plain, central alluvial-lacustrine plain, and littoral plain, respectively. Recent Ground Subsidence in the North China Plain, China, Revealed by Sentinel-1A Datasets. [Extracted from the article]

Remote sensing (RS) image dehazing holds significant importance in enhancing the quality and information extraction capability of RS imagery. The enhancement in image dehazing quality has progressively advanced alongside the evolution of convolutional neural network (CNN). Due to the fixed receptive field of CNN, there is insufficient utilization of contextual information on haze features in multi-scale RS images. Additionally, the network fails to adequately extract both local and global information of haze features. In addressing the above problems, in this paper, we propose an RS image dehazing network based on multi-scale large kernel convolution and hybrid attention (MKHANet). The network is mainly composed of multi-scale large kernel convolution (MSLKC) module, hybrid attention (HA) module and feature fusion attention (FFA) module. The MSLKC module fully fuses the multi-scale information of features while enhancing the effective receptive field of the network by parallel multiple large kernel convolutions. To alleviate the problem of uneven distribution of haze and effectively extract the global and local information of haze features, the HA module is introduced by focusing on the importance of haze pixels at the channel level. The FFA module aims to boost the interaction of feature information between the network's deep and shallow layers. The subjective and objective experimental results on on multiple RS hazy image datasets illustrates that MKHANet surpasses existing state-of-the-art (SOTA) approaches. The source code is available at https://github.com/tohang98/MKHA_Net. • Multi-scale large kernel convolution is introduced to enhance the effective receptive field. • Hybrid attention is used to enhance the extraction of features. • The feature fusion attention is used to enhance the interaction between different levels of the network layers. [ABSTRACT FROM AUTHOR]

Land subsidence is the ground surface response to underground space development, utilization and evolution. Presently, land subsidence has developed into a global, comprehensive and interdisciplinary complex systems problem. More than half a century has passed since the discovery of subsidence in the Beijing Plain in the 1960s. In this study, we investigate the land subsidence in the Beijing Plain over the period of 2003–2015 using ENVISAT ASAR and RADARSAT-2 interferometric datasets and the small baseline subset interferometric synthetic aperture radar (SBAS-InSAR) technique. Furthermore, we introduced the data field model and index-based built-up index (IBI) to obtain the dynamic and static load information of the Beijing Plain. Then, based on a machine learning method, we selected the gradient lifting decision tree (GBDT) model to quantitatively analyze the contributions of groundwater level change, compressible deposit thickness and dynamic and static loads to land subsidence. The results showed that the maximum land subsidence rate was 122 and 141 mm/year in 2003–2010 and 2010–2015, respectively. Comparisons between the SBAS-InSAR results and leveling measurements showed that the minimum absolute error achieved was only 0.2 mm/year. We suggest that the groundwater exploitation in the third confined aquifer has greater impacts on land subsidence in the Beijing Plain than the other factors. The land subsidence likely occurred in compressible deposit thicknesses exceeding 90 m. Moreover, we found that the compressible thickness and groundwater level contributions to land subsidence exceeded 60%. Our results provide a scientific basis for the regulation and control of regional land subsidence. Unlabelled Image • The causes of land subsidence in Beijing Plain are complex. • The maximum land subsidence rate is 122 and 141 mm/year in 2003–2010 and 2010–2015. • The dynamic load by using a spatial data mining method of data field model. • The third confined aquifer groundwater has greater impacts on land subsidence. • Compressible thickness and groundwater contribution to land subsidence exceed 60%. [ABSTRACT FROM AUTHOR]