A solution for the three-dimensional (3D) hyper-accurate localization in indoor environment for mobile equipment problem can be based on radar systems. Mobile equipment with an integrated radar system is known as a joint radar-communication (JRC) system or a joint communication and sensing (JCAS) system. The paper proposes an approach for 3D hyper-accurate localization in indoor environment without modifications of cellular network infrastructure. The simulations and experiments show the feasibility of the proposal. © 2024 IEEE.

This study presents a new back-propagation (BP) method to determine the vertical location of ionospheric irregularities using GNSS Radio Occultation (GNSS-RO) signals. GNSS-RO employs signals from GNSS satellites intercepted by Low Earth Orbit (LEO) satellites to gather data about different atmospheric layers, e.g., the ionosphere, which are crucial for weather prediction and studying ionospheric dynamics. The BP method involves computing diffractive integrals along the LEO path to identify disturbances such as sporadic E-layer clouds and equatorial plasma bubbles (EPBs). By effectively unwinding diffraction and multipath effects, the method pinpoints regions with minimal amplitude disturbance, indicating the location of ionospheric irregularities along the ray path. Beside estimates along the horizontal axis, case studies demonstrate the new method's capabilities in locating and estimating the vertical extent of these irregularities, showing its potential to enhance ionospheric modelling and forecasting. Results achieved show consistency with previous publications on the topic as well as methodologies used to locate ionospheric irregularities, allowing the presented method a better picture of the ionospheric irregularity.

Wavelength-resolution (WR) synthetic aperture radar (SAR) change detection (CD) has been used to detect concealed targets in forestry areas. However, most proposed methods are generally based on matrix or vector analyses and, therefore, do not exploit information embedded in multidimensional data. In this letter, a CD method for WR SAR image stacks based on tensor robust principal component analysis (TRPCA) is proposed. The proposed CD method used the new tensor nuclear norm induced by the definition of the tensor-tensor product to exploit temporal and spatial information contained in the image stack. To assess the performance of the proposed method, we considered SAR images obtained by the very high frequency (VHF) WR CARABAS-II SAR system. Experiments for three different stack sizes show that a significant performance gain can be achieved when large image stacks are considered. The proposed CD method performs better in terms of probability of detection (PD) and false alarm rate (FAR) than the other five CD methods in VHF WR SAR images, including one based on matrix robust principal component analysis (RPCA). In a particular setting, it achieves a PD of 99% and a FAR of 0.028 false alarms per km2. Authors

This study addresses the issue of black-grass, a herbicide-resistant weed that threatens wheat yields in Western Europe, through the use of high- resolution Unmanned Aerial Vehicles (UAVs) and synthetic data augmentation in precision agriculture. We mitigate challenges such as the need for large labeled datasets and environmental variability by employing synthetic data augmentations in training a Mask R-CNN model. Using a minimal dataset of 43 black-grass and 12 wheat field images, we achieved a 37% increase in Area Under the Curve (AUC) over the non-augmented baseline, with scaling as the most effective augmentation. The best model attained a recall of 53% at a precision of 64%, offering a promising approach for future precision agriculture applications. © NLDL 2024. All rights reserved.

This work investigates the impact of the neural networks architecture when performing fingerprint recognition. Three networks are studied; a Triplet network and two Siamese networks. They are evaluated on datasets with specified amounts of relative translation between fingerprints. The results show that the Siamese model based on contrastive loss performed best in all evaluated metrics. Moreover, the results indicate that the network with a categorical scheme performed inferior to the other models, especially in recognizing images with high confidence. The Equal Error Rate (EER) of the best model ranged between 4%−11% which was on average 6.5 percentage points lower than the categorical schemed model. When increasing the translation between images, the networks were predominantly affected once the translation reached a fourth of the image. Our work concludes that architectures designed to cluster data have an advantage when designing an authentication system based on neural networks.

This letter introduces a novel regression model structure for the inflated Rayleigh distribution, which effectively models high dynamic amplitude pixel values in synthetic aperture radar (SAR) images. The proposed model estimates the mean of inflated Rayleigh distribution signals by a structure that includes a set of regressors and a link function. The inflated Rayleigh distribution combines the Rayleigh and a degenerate distribution, assigning non-null probability specifically for observed values equal to zero. Null pixel values in amplitude SAR images can be randomly distributed within the image, especially in low-intensity areas; a model capable of incorporating these values is essential to avoid changes in image statistics. Extensive evaluations are conducted using simulated and real SAR images to validate the proposed model, specifically focusing on ground-type detection in high dynamic amplitude pixel values scenarios. The performance of the proposed inflated Rayleigh regression model is compared with traditional Gaussian-based regression models, excelling in terms of ground-type detection in a SAR image obtained from the ICEYE radar. 

This paper presents a crucial multispectral image registration and sensor calibration method for an agricultural application. The multispectral images are obtained using a special drone equipped with multiple cameras flying at low altitudes. However, the distance between lenses, the lens distortions and the low-altitude flights lead to a lack of alignment in the built-in normalized difference vegetation index (NDVI). This lack of alignment results in a very poor performance in further analysis, especially for image segmentation and target detection to distinguish crops from invasive plants. In this work, we point out the importance of reducing this misalignment. To do so, the near-infrared and red sensors are first calibrated to remove the lens distortions. Then, the corresponding keypoints are utilized to calculate the transformation matrix and to minimize the back-projection error. The registered near-infrared and red images are then used to compute NDVI. The experimental results show higher alignment and F1-score of 0.73 which is a significant improvement in the performance of a trained deep neural network using NDVI in the detection of invasive plants. This is particularly a challenging task as the invasive plants resemble the desired crops. © 2024 IEEE.

This work confronts the complex issue of cross-interference in Frequency Modulated Continuous Wave (FMCW) radars, a critical concern that has become more pronounced with the proliferation of automotive radar systems. The study intro-duces a two-dimensional autoregressive (AR) modeling technique for signal reconstruction in the time domain, tailored specifically for the textured nature of FMCW radar frames composed of fast- time (Range bin) and slow-time (Doppler bin) signals. According to the simulations conducted in this study, the proposed 2-D AR model (of order 3) exhibits superior performance compared to its 1-D counterpart (of order 5). This is evidenced by a slightly lower Mean Absolute Percentage Error (MAPE) during model training and a higher Signal-to-Interference-plus-Noise Ratio (SINR) for the reconstructed signal, suggesting that the 2-D model requires less frequent temporal sampling. The study further investigates different sampling strategies and evaluates the influence of model order on signal reconstruction. Based on these assessments, a third-order 2-D AR is recommended as a suitable trade-off model for interference mitigation of FMCW radars for the evaluated scenarios. This paper is structured as follows: Section I defines the interference problem in FM CW radars and the latest solutions to this problem are discussed. Sections II and III include the working principles of FMCW radar and theoretical backgrounds about multi-dimension auto-regressive modeling, respectively. Eventually, the mitigation techniques and numerical evaluations of the proposed approach are presented in Sections IV and V. © 2024 Warsaw University of Technology.

This paper presents a statistical analysis of intensity wavelength-resolution synthetic aperture radar (SAR) difference images. In this analysis, Anderson Darling goodness-of-fit tests are performed, considering two different statistical distributions as candidates for modeling the clutter-plus-noise, i.e., the background statistics. The results show that the Gamma distribution is a good fit for the background of the tested SAR images, especially when compared with the Exponential distribution. Based on the results of this statistical analysis, a change detection application for the detection of concealed targets is presented. The adequate selection of the background distribution allows for the evaluated change detection method to achieve a better performance in terms of probability of detection and false alarm rate, even when compared with competitive performance change detection methods in the literature. For instance, in an experimental evaluation considering a data set obtained by the Coherent All Radio Band Sensing (CARABAS) II UWB SAR system, the evaluated change detection method reached a detection probability of 0.981 for a false alarm rate of 1/km2. © 2023 by the authors.

This article proposes a method to simulate Synthetic Aperture Radar (SAR) targets for specific incidence and azimuth angles. Images synthesized by Electromagnetic Computing (EMC) are used to train a Conditional Generative Adversarial Network (cGAN). Two synthetic image chips of the same class and incidence angle, separated by two degrees in azimuth, are used as input to the cGAN. The cGAN predicts the image of the same class and incidence angle whose azimuth angle corresponds to the bisector of the two input chips. An evaluation using the SAMPLE dataset was performed to verify the quality of the image prediction. Running through a total of 100 training epochs, the cGAN converges, reaching the best Mean Squared Error (MSE) after 77 epochs. The results demonstrate that the proposed method is promising for Automatic Target Recognition (ATR) applications. © 2023 IEEE.