Search

Single Image Super-Resolution (SISR) for image enhancement enables the generation of high spatial resolution in Remote Sensing (RS) images without incurring additional costs. This approach offers a practical solution to obtain high-resolution RS images, addressing challenges posed by the expense of acquisition equipment and unpredictable weather conditions. To address the over-smoothing of the previous SISR models, the diffusion model has been incorporated into RS SISR to generate Super-Resolution (SR) images with enhanced textural details. In this paper, we propose a Diffusion model with Adversarial Learning Strategy (DiffALS) to refine the generative capability of the diffusion model. DiffALS integrates an additional Noise Discriminator (ND) into the training process, employing an adversarial learning strategy on the data distribution learning. This ND guides noise prediction by considering the general correspondence between the noisy image in each step, thereby enhancing the diversity of generated data and the detailed texture prediction of the diffusion model. Furthermore, considering that the diffusion model may exhibit suboptimal performance on traditional pixel-level metrics such as Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity (SSIM), we showcase the effectiveness of DiffALS through downstream semantic segmentation applications. Extensive experiments demonstrate that the proposed model achieves remarkable accuracy and notable visual enhancements. Compared to other state-of-the-art methods, our model establishes an improvement of 189 for Fréchet Inception Distance (FID) and 0.002 for Learned Perceptual Image Patch Similarity (LPIPS) in a SR dataset, namely Alsat, and achieves improvements of 0.4%, 0.3%, and 0.2% for F1 score, MIoU, and Accuracy, respectively, in a segmentation dataset, namely Vaihingen. [ABSTRACT FROM AUTHOR]

Landslide mapping via pixel-wise classification of remote sensing imagery is essential for hazard prevention and risk assessment. Deep-learning-based change detection greatly aids landslide mapping by identifying the down-slope movement of soil, rock and other materials from bitemporal images, benefiting from the feature representation capabilities of convolutional neural networks. However, these networks rely on large amounts of pixel-level annotated data to achieve their promising performance and they normally exhibit weak generalization capability on heterogeneous image data from unseen domains. To address these issues, we propose a prototype-guided domain-aware progressive representation learning (PG-DPRL) method for cross-domain landslide mapping from large-scale remote sensing images based on the multitarget domain adaptation (MTDA) technique. PG-DPRL attempts to learn a shared landslide mapping network that performs well in multiple target domains with no additional effort for sample annotation. Specifically, PG-DPRL adopts a near-to-far adaptation strategy to gradually align the representation distributions of all target domains with the source domain, considering discrepancies between them. On this basis, cross-domain prototype learning is exploited to generate reliable domain-specific pseudo-labels and aggregate representations across domains to learn a shared decision boundary. In each DPRL step, the prototype-guided adversarial learning (PGAL) algorithm is performed to achieve category-wise representation alignment and improve the discriminative capability of representations by introducing the Wasserstein distance metric and cross-domain prototype consistency (CPC) loss. Experiments on a global very-high-resolution landslide mapping (GVLM) dataset consisting of 17 heterogeneous domains from different landslide sites demonstrate the effectiveness and robustness of PG-DPRL. It considerably improves the transferability of landslide mapping networks and outperforms several state-of-the-art approaches in terms of total and average accuracy metrics among all target domains. [ABSTRACT FROM AUTHOR]

Using remote sensing techniques to monitor landslides and their resultant land cover changes is fundamentally important for risk assessment and hazard prevention. Despite enormous efforts in developing intelligent landslide mapping (LM) approaches, LM remains challenging owing to high spectral heterogeneity of very-high-resolution (VHR) images and the daunting labeling efforts. To this end, a deep learning model based on semi-supervised multi-temporal deep representation fusion network, namely SMDRF-Net, is proposed for reliable and efficient LM. In comparison with previous methods, the SMDRF-Net possesses three distinct properties. (1) Unsupervised deep representation learning at the pixel- and object-level is performed by transfer learning using the Wasserstein generative adversarial network with gradient penalty to learn discriminative deep features and retain precise outlines of landslide objects in the high-level feature space. (2) Attention-based adaptive fusion of multi-temporal and multi-level deep representations is developed to exploit the spatio-temporal dependencies of deep representations and enhance the feature representation capability of the network. (3) The network is optimized using limited samples with pseudo-labels that are automatically generated based on a comprehensive uncertainty index. Experimental results from the analysis of VHR aerial orthophotos demonstrate the reliability and robustness of the proposed approach for LM in comparison with state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Mobile edge computing (MEC) can provide computing and storage services to user equipments (UEs) by utilizing edge nodes known as the small base stations (SBS’s) deployed at the edge of the network. The short-distance transmission nature between SBS’s and UEs makes the millimeter-wave (mmWave) communication empowered with multiple-input multiple-output (MIMO) hybrid precoding techniques particularly attractive for MEC. In this work, we consider the UE-SBS association, precoding design and power allocation for MEC networks endowed with mmWave MIMO. More specifically, the user association problem is first formulated as a max-k-cut (M $k$ C) problem and then, solved by a distributed local-search algorithm. Next, the joint optimization of precoding and power allocation is cast into the difference of two convex functions (D.C.) programming framework before an iterative rank-constrained D.C. programming algorithm is developed to maximize the weighted sum-rate (WSR) of all UEs while taking into account the quality of service (QoS) requirement of each UE. Furthermore, the monotonic convergence of the proposed iterative algorithm is analytically proven. Finally, extensive computer simulation is conducted to demonstrate the effectiveness of the proposed iterative algorithm. [ABSTRACT FROM AUTHOR]

In this work, the sum-rate performance of joint opportunistic scheduling and receiver design (JOSRD) is analyzed for multiuser multiple-input-multiple output (MIMO) space-division multiple access (SDMA) downlink systems. In particular, we study linear rake receivers with selective combining, maximum ratio combining and optimal combining in which signals received from all antennas of each mobile terminal (MT) are linearly combined to improve the effective signal-to-interference-plus-noise ratios (SINRs). By exploiting limited feedback on the effective SINRs, the base station (BS) schedules simultaneous data transmission on multiple beams to the MTs with the largest effective SINRs. Using extreme value theory, the average sum-rates and their scaling laws for JOSRD are derived. In particular, it is shown that the limiting distribution of the effective signal-to-interference (SIR) is of the Frechet-type whereas that of the effective SINR converges to the Gumbel-type. Furthermore, the SIR-based sum-rate scaling laws are found to follow ε log K with 0<ε<1, which stands in contrast to the SINR-based scaling laws governed by the conventional log log K form. Both analytical and simulation results confirm that significant performance improvement can be achieved by incorporating low-complexity linear combining techniques into the design of scheduling schemes in MIMO-SDMA downlink systems. [ABSTRACT FROM AUTHOR]

Presents a letter to the editor commenting on a study regarding single intradermal tuberculin tests of milking buffaloes.

Large-scale high-resolution three-dimensional (3D) maps play a vital role in the development of smart cities. In this work, a novel deep learning-based multi-view-stereo method is proposed for reconstructing the 3D maps in large-scale urban environments by exploiting a monocular camera. Compared with other existing works, the proposed method can perform 3D depth estimation more efficiently in terms of computational complexity and graphics processing unit memory usage. As a result, the proposed method can practically perform depth estimation for each pixel before generating 3D maps for even large-scale scenes. Extensive experiments on the well-known DTU dataset and real-life data collected on our campus confirm the good performance of the proposed method. [ABSTRACT FROM AUTHOR]

Thelast decade has witnessed growing research interests in the path-planning problem for unmanned ground vehicles (UGVs) equipped with RGB-D cameras or LiDARs. However, apart from their extremely high cost, these sensors may be obscured by obstacles, which makes them impractical for many complex scenarios. Besides, most of the existing works for path planning have not considered energy efficiency for UGVs that are usually constrained by limited on-board batteries. Distinct from existing methods, this work presents a vision-based unmanned aerial vehicle (UAV)-assisted cooperative system for multiple UGVs. The proposed system harnesses the broad vision of UAV and operates in both general outdoor and global positioning system (GPS)-denied indoor environments. In sharp contrast to the conventional heuristic algorithms such as the rapidly exploring random tree (RRT) algorithm and the Dijkstra methods, the proposed energy-efficient path planning for UGVs is formulated as a non-convex optimization problem by considering the collision-aware obstacle-avoidance. More specifically, the proposed path-planning scheme contains two stages, namely the semantic segmentation that localizes UGVs and obstacles in the environment by exploiting the wide-angle camera mounted on the UAV, followed by the trajectory generation in which a disciplined convex and concave programming (DCCP) algorithm is devised for the non-convex energy-minimization problem. Extensive experiments validate the effectiveness of the UAV-UGV cooperative system and the proposed DCCP-based path-planning scheme. [ABSTRACT FROM AUTHOR]

This correspondence considers a parametric approach for multichannel adaptive signal detection in Gaussian disturbance which can be modeled as a multichannel autoregressive (AR) process and, moreover, possesses a persymmetric structure induced by a symmetric antenna geometry. By introducing the persymmetric AR (PAR) modeling for the disturbance, a persymmetric parametric adaptive matched filter (Per-PAMF) is proposed. The developed Per-PAMF extends the classical PAMF by exploiting the underlying persymmetric properties and, hence, improves the detection performance in training-limited scenarios. The performance of the proposed Per-PAMF is examined by the Monte Carlo simulations and simulation results demonstrate the effectiveness of the Per-PAMF compared with the conventional PAMF and nonparametric detectors. [ABSTRACT FROM AUTHOR]

A new methodology to measure coded image/video quality using the just-noticeable-difference (JND) idea was proposed in Lin et al. (2015). Several small JND-based image/video quality datasets were released by the Media Communications Lab at the University of Southern California in Jin et al. (2016) and Wang et al. (2016) [3]. In this work, we present an effort to build a large-scale JND-based coded video quality dataset. The dataset consists of 220 5-s sequences in four resolutions (i.e., 1920 × 1080 , 1280 × 720 , 960 × 540 and 640 × 360 ). For each of the 880 video clips, we encode it using the H.264/AVC codec with QP = 1 , … , 51 and measure the first three JND points with 30 + subjects. The dataset is called the “VideoSet”, which is an acronym for “Video Subject Evaluation Test (SET)”. This work describes the subjective test procedure, detection and removal of outlying measured data, and the properties of collected JND data. Finally, the significance and implications of the VideoSet to future video coding research and standardization efforts are pointed out. All source/coded video clips as well as measured JND data included in the VideoSet are available to the public in the IEEE DataPort (Wang et al., 2016 [4]). [ABSTRACT FROM AUTHOR]