Air traffic systems are of great significance to our society. However, air traffic systems are extremely complicated since an air traffic system encompasses many components which could evolve over time. It is therefore challenging to analyze the evolution dynamics of air traffic systems. In this paper we propose a graph perspective to trace the spatial-temporal evolutions of air traffic systems. Different to existing studies which are model-driven and only focus on certain properties of an air traffic system, in this paper we propose a data-driven perspective and analyze a couple of properties of an air traffic system. Specifically, we model air traffic systems with both unweighted and weighted graphs with respect to real-world traffic data. We then analyze the evolution dynamics of the constructed graphs in terms of nodal degrees, degree distributions, traffic delays, causality between graph structures and traffic delays, and system resilience under airport failures. To validate the effectiveness of the proposed approach, a case study on the American air traffic systems with respect to 12-month traffic data is carried out. It is found that the structures and traffic mobilities of the American air traffic systems do not evolve significantly over time, which leads to the stable distributions of the traffic delays as evidenced by a causality analysis. It is further found that the American
Compressive sensing (CS) technology is introduced into space optical remote sensing image acquisition stage, which could make wireless image sensor network node quickly and accurately obtain images in the case of two constraints of limited battery power and expensive sensor costs. On this basis, in order to further improve the quality of CS image reconstruction, we propose fused features and perceptual loss encoder-decoder residual network (FFPL-EDRNet) for image reconstruction. FFPL-EDRNet consists of a convolution layer and a reconstruction network. We train FFPL-EDRNet end-to-end, thus greatly simplifying the pre-processing and post-processing process and eliminating the block effect of reconstructed images. The reconstruction network is based on residual network, which introduces multiscale feature extraction, multi-scale feature combination and multi-level feature combination. Feature fusion integrates low-level information with high-level information to reduce reconstruction error. The perceptual loss function based on pretrained InceptionV3 uses the weighted mean square error to define the loss value between the reconstructed image feature and the label image feature, which makes the reconstructed image more semantically similar to label image. In the measurement procedure, we use convolution to achieve block compression measurement, so as to obtain full image measurements. For image reconstruction, we firstly use a deconvolution layer to initially reconstruct the image and then use the residual network to refine the initial reconstructed image. The experimental results show that: in the case of measurement rates (MRs) of 0.25, 0.10, 0.04 and 0.01, the peak signal-to-noise ratio (PSNR) = 27.502, 26.804, 24.593, 21.359 and structural similarity (SSIM) = 0.842, 0.816, 0.720, 0.568 of the reconstructed images obtained by FFPL-EDRNet. Therefore, Our FFPL-EDRNet could enhance the quality of image reconstruction.
The compressive sensing (CS)-based optical remote sensing (ORS) imaging system have been verified the feasibility of through numerical simulation experiments, which can reduce the demand for sampling equipment, effectively reduce sampling data, save storage space, and reduce transmission costs. However, it needs to reconstruct the original scene when facing the task of ship detection. The scene reconstruction process of CS is computationally expensive, high memory demanding, and timeconsuming. In response to this problem, this paper proposes an innovation pipeline to perform ship detection tasks, i.e., directly performing ship detection on CS measurements obtained by the imaging system, which avoids the process of scene reconstruction. To achieve the ship detection of CS measurements in the pipeline, we design a CNN-based algorithm, CS-CenterNet, which jointly optimizes the scene compression sampling phase and the measurements' ship detection phase. CS-CenterNet is divided into convolution measurement layer (CML), optimized hourglass network (OHgN), and optimized three-branch head network (OTBHN). Firstly, CML without bias or activation function simulates the block compression sampling process in CS-based ORS imaging system, which performs convolutional coding on the scene to obtain the measurements. Secondly, OHgN extracts highresolution feature information of measurements. Finally, OTBHN performs heat-map prediction, center-point offset prediction, and width-height prediction. We test the performance of CS-CenterNet using the HRSC2016 and LEVIR datasets. The experimental results show that the algorithm can achieve highaccuracy ship detection based on CS measurements of ORS scenes.
Convolutional neural networks (CNNs) have attracted significant attention as a commonly used method for hyperspectral image (HSI) classification in recent years; however, CNNs can only be applied to Euclidean data and have difficulties in dealing with relationships due to their limitations of local feature extraction. Each pixel of a hyperspectral image contains a set of spectral bands that are correlated and interact with each other, and the methods used to process Euclidean data cannot effectively obtain these correlations. In contrast, the graph convolutional network (GCN) can be used in non-Euclidean data but usually leads to over-smoothing and ignores local detail features due to the need for superpixel segmentation processing to reduce computational effort. To overcome the above problems, we constructed a fusion network based on the GCN and CNN which contains two branches: a graph convolutional network based on superpixel segmentation and a convolutional network with an added attention mechanism. The graph convolutional branch can extract the structural features and capture the relationships between the nodes, and the convolutional branch can extract detailed features in the local fine region. Owing to the fact that the features extracted from the two branches are different, the classification performance can be improved by fusing the complementary features extracted from the two branches. To validate the proposed algorithm, experiments were conducted on three widely used datasets, namely Indian Pines, Pavia University, and Salinas. An overall accuracy of 98.78% was obtained in the Indian Pines dataset, and overall accuracies of 98.99% and 98.69% were obtained in the other two datasets. The results show that the proposed fusion network can obtain richer features and achieve a high classification accuracy.
The spatial and spectral information contained in the hyperspectral image (HSI) make it widely used in many fields. However, the sharp increase of HSI data brings enormous pressure to the data storage and real-time transmission. The research shows that hyperspectral compressive sensing (HCS) breaks through the bottleneck of the Nyquist sampling theorem, which can relieve the massive pressure on data storage and real-time transmission. Existing HCS methods try to design advanced compression sampling matrix or reconstruction algorithms, but cannot connect the two through a unified framework. To further improve the image reconstruction quality, a novel codec space-spectrum joint dense residual network (CDS2-DResN) is proposed. The CDS2-DResN is divided into block compression sampling part and reconstruction part. For block compression sampling, coded convolutional layer (CCL) is leveraged to compress and sample HSI. For measurements reconstruction, deconvolution layer is first leveraged to initially reconstruct HSI, and then build a space-spectrum joint network to refine the initial reconstructed HSI. Moreover, the CCL and reconstruction network are optimized via a unified framework, which can simplify the pre-processing and post-processing process of HCS. Extensive experiments have shown that CDS2-DResN has an excellent HCS reconstruction effect at measurement rates 0.25, 0.10, 0.04 and 0.01, respectively.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.