Search

Despite significant challenges, the text-guided remote sensing image generation method shows great potential in many practical applications such as generative adversarial networks in remote sensing tasks; generated images still face challenges such as low realism, face challenges, and unclear details. Moreover, the inherent spatial complexity of remote sensing images and the limited scale of publicly available datasets make it particularly challenging to generate high-quality remote sensing images from text descriptions. To address these challenges, this paper proposes the RSVQ-Diffusion model for remote sensing image generation, achieving high-quality text-to-remote-sensing image generation applicable for target detection, simulation, and other fields. Specifically, this paper designs a spatial position encoding mechanism to integrate the spatial information of remote sensing images during model training. Additionally, the Transformer module is improved by incorporating a short-sequence local perception mechanism into the diffusion image decoder, addressing issues of unclear details and regional distortions in generated remote sensing images. Compared with the VQ-Diffusion model, our proposed model achieves significant improvements in the Fréchet Inception Distance (FID), the Inception Score (IS), and the text–image alignment (Contrastive Language-Image Pre-training, CLIP) scores. The FID score successfully decreased from 96.68 to 90.36; the CLIP score increased from 26.92 to 27.22, and the IS increased from 7.11 to 7.24. [ABSTRACT FROM AUTHOR]

A new wake-up receiver (WuRx) designed in 0.13 μm CMOS process is hybrid-integrated with a micro-electromechanical system (MEMS) RF resonator. While only consuming 166 nW of power (18.8 nW for the comparator and 147 nW for periphery), the WuRx is capable of detecting RF signals as weak as -60 dBm. In order to achieve this sensitivity, a passive voltage-boosting network comprised of a high quality factor (high-Q) piezoelectric MEMS resonator is utilized, in place of an inductor, to amplify the received voltages applied to a CMOS rectifier. The output of the rectifier is then applied to a low-power comparator used to set a logical bit that indicates when an RF signal has been detected. The trade-offs in designing the voltage boosting network are explained and an equation for the optimum number of rectifier stages is derived.

High-resolution optical images will provide planetary geology researchers with finer and more microscopic image data information. In order to maximize scientific output, it is necessary to further increase the resolution of acquired images, so image super-resolution (SR) reconstruction techniques have become the best choice. Aiming at the problems of large parameter quantity and high computational complexity in current deep learning-based image SR reconstruction methods, we propose a novel Recursive Swin Transformer Super-Resolution Network (RSTSRN) for SR applied to images. The RSTSRN improves upon the LapSRN, which we use as our backbone architecture. A Residual Swin Transformer Block (RSTB) is used for more efficient residual learning, which consists of stacked Swin Transformer Blocks (STBs) with a residual connection. Moreover, the idea of parameter sharing was introduced to reduce the number of parameters, and a multi-scale training strategy was designed to accelerate convergence speed. Experimental results show that the proposed RSTSRN achieves superior performance on 2×, 4× and 8×SR tasks to state-of-the-art methods with similar parameters. Especially on high-magnification SR tasks, the RSTSRN has great performance superiority. Compared to the LapSRN network, for 2×, 4× and 8× Mars image SR tasks, the RSTSRN network has increased PSNR values by 0.35 dB, 0.88 dB and 1.22 dB, and SSIM values by 0.0048, 0.0114 and 0.0311, respectively. [ABSTRACT FROM AUTHOR]

Vehicle detection with optical remote sensing images has become widely applied in recent years. However, the following challenges have remained unsolved during remote sensing vehicle target detection. These challenges include the dense and arbitrary angles at which vehicles are distributed and which make it difficult to detect them; the extensive model parameter (Param) that blocks real-time detection; the large differences between larger vehicles in terms of their features, which lead to a reduced detection precision; and the way in which the distribution in vehicle datasets is unbalanced and thus not conducive to training. First, this paper constructs a small dataset of vehicles, MiVehicle. This dataset includes 3000 corresponding infrared and visible image pairs, offering a more balanced distribution. In the infrared part of the dataset, the proportions of different vehicle types are as follows: cars, 48%; buses, 19%; trucks, 15%; freight, cars 10%; and vans, 8%. Second, we choose the rotated box mechanism for detection with the model and we build a new vehicle detector, ML-Det, with a novel multi-scale feature fusion triple cross-criss FPN (TCFPN), which can effectively capture the vehicle features in three different positions with an mAP improvement of 1.97%. Moreover, we propose LKC–INVO, which allows involution to couple the structure of multiple large kernel convolutions, resulting in an mAP increase of 2.86%. We also introduce a novel C2F_ContextGuided module with global context perception, which enhances the perception ability of the model in the global scope and minimizes model Params. Eventually, we propose an assemble–disperse attention module to aggregate local features so as to improve the performance. Overall, ML-Det achieved a 3.22% improvement in accuracy while keeping Params almost unchanged. In the self-built small MiVehicle dataset, we achieved 70.44% on visible images and 79.12% on infrared images with 20.1 GFLOPS, 78.8 FPS, and 7.91 M. Additionally, we trained and tested our model on the following public datasets: UAS-AOD and DOTA. ML-Det was found to be ahead of many other advanced target detection algorithms. [ABSTRACT FROM AUTHOR]

A monolithic piezoelectric MEMS-CMOS resonant transformer that can be used in ultra-low-power high-efficiency RF sensing applications is presented for the first time. The MEMS-CMOS resonant transformer is based on a 59 MHz 2-port Aluminum Nitride (AlN) Contour Mode Resonator (CMR) bonded to a 0.18 μm NMOS-based rectifier for voltage boosting and RF-to-DC conversion. The integrated device is fabricated in a foundry-based process by conductive eutectic wafer bonding. To amplify the voltage, the AlN CMR is designed to attain a large quality factor (Q=1150) and a relatively low dielectric capacitance (C0=1.51 pF) in relation to the number of rectifier stages (n=20). As a result, a ten-fold voltage gain MEMS-CMOS resonant transformer is demonstrated in this work.

The detection of vehicle targets in infrared aerial remote sensing images captured by drones presents challenges due to a significant imbalance in vehicle distribution, complex backgrounds, the large scale of vehicles, and the dense and arbitrarily oriented distribution of targets. The RYOLOv5_D model is proposed based on the YOLOv5-obb rotation model. Firstly, we reconstruct a new vehicle remote sensing dataset, BalancedVehicle, to achieve data balance. Secondly, given the challenges of complex backgrounds in infrared remote sensing images, the AAHE method is proposed to highlight infrared remote sensing vehicle targets while reducing background interference during the detection process. Moreover, in order to address the issue of detecting challenges under complex backgrounds, the CPSAB attention mechanism is proposed, which could be used together with DCNv2. GSConv is also used to reduce the model parameters while ensuring accuracy. This combination could improve the model's generalization ability and, consequently, enhance the detection accuracy for various vehicle categories. The RYOLOv5s_D model, trained on the self-built dataset BalancedVehicle, demonstrates a notable improvement in its mean average precision (mAP), increasing from 73.6% to 78.5%. Specifically, the average precision (AP) for large aspect ratio vehicles such as trucks and freight cars increases by 11.4% and 8%, respectively. The RYOLOv5m_D and RYOLOv5l_D models achieve accuracies of 82.6% and 84.3%. The Param of RYOLOv5_D is similar to that of the YOLOv5-obb, while possessing a decrease in computational complexity of 0.6, 4.5, and 12.8GFLOPS. In conclusion, the RYOLOv5_D model's superior accuracy and real-time capabilities in infrared remote sensing vehicle scenarios are validated by comparing various advanced models based on rotation boxes on the BalancedVehicle dataset. [ABSTRACT FROM AUTHOR]

Based on the continuity and momentum equations, a self-consistent simulation model is developed for describing the localized electron density enhancement caused by high-pressure H2O gas release in the ionosphere. The chemical reaction and momentum exchange process between the neutral gas and ionospheric plasma species are considered in the theoretical simulation model. The finite element method is used to solve the simulation model for H2O gas release, and the expansion and ionospheric disturbance process at the early stage of high-pressure gas release are studied. It is shown that the space expansion of the released gas is mainly dominated by the pressure difference between the H2O gas and the ionospheric plasma at the early stage of release. Then the diffusion process becomes the dominant process of the space transport of H2O molecules. An electron depletion region forms near the center of the release region due to the chemical reaction and collision process with H2O molecules. Meanwhile, an electron density enhancement region forms on both sides along the magnetic field direction due to the electron snowplow effect. With the increase in the released mass of H2O gas, the intensity and duration of the electron density enhancement increase gradually. With the release position rising, it is found that the intensity of the electron density enhancement has a peak near 380 km and the duration increases slightly with the increasing release height. [ABSTRACT FROM AUTHOR]

A new ultrawideband frequency selective surface(FSS) is proposed, which exhibits six resonances to achieve a flat passband. It consists of a three-dimensional (3-D) configuration. However, unlike many other 3-D FSSs, the proposed structure can be assembled through simple steps involving single-layer printed circuit board (PCB) fabrication only. Its unit-cell consists of a wire-loop conducting pattern, printed on a dielectric substrate. The pattern excites four resonances while two resonances are contributed by the dielectric. These six resonances are properly tuned and coupled to form an ultrawide frequency band from 7.53 to 29.45 GHz. It translates to a $-$ 3 dB bandwidth of 119 $\%$. Our design guidelines and discussions are validated through both simulation and measurement results. [ABSTRACT FROM AUTHOR]