Search Results (207)

With the proliferation of the Internet of Things (IoT), gesture recognition has attracted attention as a core technology in human–computer interaction (HCI). In particular, mmWave frequency-modulated continuous-wave (FMCW) radar has emerged as an alternative to vision-based approaches due to its robustness to illumination changes and advantages in privacy. However, in real-world human–machine interface (HMI) environments, hand gestures are inevitably accompanied by torso- and arm-related reflections, which can also contain gesture-relevant variations. To effectively capture these variations without discarding them, we propose a preprocessing method called Adaptive Top-K Selection, which leverages vector entropy to summarize and preserve informative signals from both hand and body reflections. In addition, we present a Multi-Stream EfficientNetV2 architecture that jointly exploits temporal range and Doppler trajectories, together with radar-specific data augmentation and a training optimization strategy. In experiments on the publicly available FMCW gesture dataset released by the Karlsruhe Institute of Technology, the proposed method achieved an average accuracy of 99.5%. These results show that the proposed approach enables accurate and reliable gesture recognition even in realistic HMI environments with co-existing body reflections. Full article

Unmanned surface vehicles (USVs) rely on multi-sensor perception, such as radar, LiDAR, GPS, and vision, to ensure safe and efficient navigation in complex maritime environments. Traditional ant colony optimization (ACO) for path planning, however, suffers from premature convergence, slow adaptation, and poor smoothness in cluttered waters, while the dynamic window approach (DWA) without global guidance can become trapped in local obstacle configurations. This paper presents a sensor-oriented hybrid method that couples an improved ACO for global route planning with an enhanced DWA for local, real-time obstacle avoidance. In the global stage, the ACO state–transition rule integrates path length, obstacle clearance, and trajectory smoothness heuristics, while a cosine-annealed schedule adaptively balances exploration and exploitation. Pheromone updating combines local and global mechanisms under bounded limits, with a stagnation detector to restore diversity. In the local stage, the DWA cost function is redesigned under USV kinematics to integrate velocity adaptability, trajectory smoothness, and goal-deviation, using obstacle data that would typically originate from onboard sensors. Simulation studies, where obstacle maps emulate sensor-detected environments, show that the proposed method achieves shorter paths, faster convergence, smoother trajectories, larger safety margins, and higher success rates against dynamic obstacles compared with standalone ACO or DWA. These results demonstrate the method’s potential for sensor-based, real-time USV navigation and collision avoidance in complex maritime scenarios. Full article

Multi-modal sensor fusion has become a cornerstone of robust autonomous driving systems, enabling perception models to integrate complementary cues from cameras, LiDARs, radars, and other modalities. This survey provides a structured overview of recent advances in deep learning-based fusion methods, categorizing them by architectural paradigms (e.g., BEV-centric fusion and cross-modal attention), learning strategies, and task adaptations. We highlight two dominant architectural trends: unified BEV representation and token-level cross-modal alignment, analyzing their design trade-offs and integration challenges. Furthermore, we review a wide range of applications, from object detection and semantic segmentation to behavior prediction and planning. Despite considerable progress, real-world deployment is hindered by issues such as spatio-temporal misalignment, domain shifts, and limited interpretability. We discuss how recent developments, such as diffusion models for generative fusion, Mamba-style recurrent architectures, and large vision–language models, may unlock future directions for scalable and trustworthy perception systems. Extensive comparisons, benchmark analyses, and design insights are provided to guide future research in this rapidly evolving field. Full article

Hyperbolic reflection features from ground-penetrating radar (GPR) data have been recognized as essential indicators for detecting hidden defects in the asphalt pavement. Computer vision and deep learning algorithms have been developed to detect and enhance the hyperbolic features of hidden defects. However, migrating existing hyperbolic feature detection methods using raw GPR data results in inaccurate predictions. Pre-processing raw GPR data using straightforward image processing methods could enhance the reflection features for fast and accurate hyperbolic detection during real-time GPR measurements. This study proposed accessible and straightforward image processing methods as GPR data preprocessing steps (such as the Sobel edge detector and histogram equalization) to assist existing computer vision algorithms for reflection feature enhancement during the GPR survey. Field tests were conducted, and several image processing methods with existing standard image processing libraries were applied. The proposed regions of the identified hyperbola signal-to-noise ratio (RIHSNR) were used to quantify the enhancement performance of hyperbolic feature detectability. Applying Sobel edge detection and Otsu’s thresholding to GPR data significantly improves detection accuracy and speed: mAP@0.5 rises from 0.65 to 0.85 for Faster R-CNN and from 0.72 to 0.88 for CBAM-YOLOv8 using the proposed computer vision methods as preprocessing steps. At the same time, inference time drops to 30 ms and 25 ms, respectively. Full article

The paper presents a novel probability-informed approach to improving the accuracy of small object semantic segmentation in high-resolution imagery datasets with imbalanced classes and a limited volume of samples. Small objects imply having a small pixel footprint on the input image, for example, ships in the ocean. Informing in this context means using mathematical models to represent data in the layers of deep neural networks. Thus, the ensemble Quadtree-informed Graph Self-Attention Networks (QiGSANs) are proposed. New architectural blocks, informed by types of Markov random fields such as quadtrees, have been introduced to capture the interconnections between features in images at different spatial resolutions during the graph convolution of superpixel subregions. It has been analytically proven that quadtree-informed graph convolutional neural networks, a part of QiGSAN, tend to achieve faster loss reduction compared to convolutional architectures. This justifies the effectiveness of probability-informed modifications based on quadtrees. To empirically demonstrate the processing of real small data with imbalanced object classes using QiGSAN, two open datasets of synthetic aperture radar (SAR) imagery (up to $0.5$ m per pixel) are used: the High Resolution SAR Images Dataset (HRSID) and the SAR Ship Detection Dataset (SSDD). The results of QiGSAN are compared to those of the transformers SegFormer and LWGANet, which constitute a new state-of-the-art model for UAV (Unmanned Aerial Vehicles) and SAR image processing. They are also compared to convolutional neural networks and several ensemble implementations using other graph neural networks. QiGSAN significantly increases the $F_1$-score values by up to $63.93\%$, $48.57\%$, and $9.84\%$ compared to transformers, convolutional neural networks, and other ensemble architectures, respectively. QiGSAN outperformed the base segmentors with the mIOU (mean intersection-over-union) metric too: the highest increase was $35.79\%$. Therefore, our approach to knowledge extraction using mathematical models allows us to significantly improve modern computer vision techniques for imbalanced data. Full article

Synthetic aperture radar (SAR), with its all-weather and all-day active imaging capability, has become indispensable for geoscientific analysis and socio-economic applications. Despite advances in deep learning–based object detection, the rapid and accurate detection of small objects in SAR imagery remains a major challenge due to their extremely limited pixel representation, blurred boundaries in dense distributions, and the imbalance of positive–negative samples during training. Recently, vision–language models such as Contrastive Language-Image Pre-Training (CLIP) have attracted widespread research interest for their powerful cross-modal semantic modeling capabilities. Nevertheless, their potential to guide precise localization and detection of small objects in SAR imagery has not yet been fully exploited. To overcome these limitations, we propose the CLIP-Driven Adaptive Tiny Object Detection Diffusion Network (CDATOD-Diff). This framework introduces a CLIP image–text encoding-guided dynamic sampling strategy that leverages cross-modal semantic priors to alleviate the scarcity of effective positive samples. Furthermore, a generative diffusion-based module reformulates the sampling process through iterative denoising, enhancing contextual awareness. To address regression instability, we design a Balanced Corner–IoU (BC-IoU) loss, which decouples corner localization from scale variation and reduces sensitivity to minor positional errors, thereby stabilizing bounding box predictions. Extensive experiments conducted on multiple SAR and optical remote sensing datasets demonstrate that CDATOD-Diff achieves state-of-the-art performance, delivering significant improvements in detection robustness and localization accuracy under challenging small-object scenarios with complex backgrounds and dense distributions. Full article

Traffic accidents caused by black ice have become a serious public safety concern due to their high fatality rates and the limitations of conventional detection systems under low visibility. Millimeter-wave (mmWave) radar, capable of operating reliably in adverse weather and lighting conditions, offers a promising alternative for road surface monitoring. In this study, six representative road surface conditions—dry, wet, thin-ice, ice, snow, and sludge—were experimentally implemented on asphalt and concrete specimens using a temperature and humidity-controlled chamber. mmWave radar data were repeatedly collected to analyze the temporal variations in reflected signals. The acquired signals were transformed into range-based spectra using Range-Fast Fourier Transform (Range-FFT) and converted into statistical features and graphical representations. These features were used to train and evaluate classification models, including Extreme Gradient Boost (XGBoost), Light Gradient-Boosting Machine (LightGBM), Convolutional Neural Networks (CNN), and Vision Transformer (ViT). While machine learning models performed well under dry and wet conditions, their accuracy declined in hazardous states. Both CNN and ViT demonstrated superior performance across all conditions, with CNN showing consistent stability and ViT exhibiting competitive accuracy with enhanced global pattern-recognition capabilities. Comprehensive robustness evaluation under various noise and blur conditions revealed distinct characteristics of each model architecture. This study demonstrates the feasibility of mmWave radar for reliable road surface condition recognition and suggests potential for improvement through multimodal sensor fusion and time-series analysis. Full article

Maritime search and rescue (SAR) demands reliable sensing and communication under sea clutter. Emerging integrated sensing and communication (ISAC) technology provides new opportunities for the development and modernization of maritime radio communication, particularly in relation to search and rescue. This study investigated the dual-function capability of a phase-coded frequency modulated continuous wave (FMCW) system for search and rescue at sea, in particular for life signs detection in the presence of sea clutter. The detection capability of the FMCW system was enhanced by applying phase-modulated codes on chirps, and radar-centric communication function is supported simultaneously. Various phase-coding schemes including Barker, Frank, Zadoff-Chu (ZC), and Costas were assessed by adopting the peak sidelobe level and integrated sidelobe level of the ambiguity function of the established signals. The interplay of sea waves was represented by a compound K-distribution model. A multiple-input multiple-output (MIMO) architecture with the ZC code was adopted to detect multiple objects with a high resolution for micro-Doppler determination by taking advantage of spatial coherence with beamforming. The effectiveness of the proposed method was validated on the 4-transmit, 4-receive (4 × 4) MIMO system with ZC coded FMCW signals. Monte Carlo simulations were carried out incorporating different combinations of targets and user configurations with a wide range of signal-to-noise ratio (SNR) settings. Extensive simulations demonstrated that the mean squared error (MSE) of range estimation remained low across the evaluated SNR setting, while communication performance was comparable to that of a baseline orthogonal frequency-division multiplexing (OFDM)-based system. The high performance demonstrated by the proposed method makes it a suitable maritime search and rescue solution, in particular for vision-restricted situations. Full article

This paper presents a comprehensive survey of deep learning-based methods for 3D object detection in autonomous driving, focusing on their use of diverse sensor modalities, including monocular cameras, stereo vision, LiDAR, radar, and multi-modal fusion. To systematically organize the literature, a structured taxonomy is proposed that categorizes methods by input modality. The review also outlines the chronological evolution of these approaches, highlighting major architectural developments and paradigm shifts. Furthermore, the surveyed methods are quantitatively compared using standard evaluation metrics across benchmark datasets in autonomous driving scenarios. Overall, this work provides a detailed and modality-agnostic overview of the current landscape of deep learning approaches for 3D object detection in autonomous driving. Results of this work are available in a github open repository. Full article

Slope stability monitoring in open-pit mining remains a critical challenge for geological hazard prevention, where conventional qualitative methods often fail to address dynamic risks. This study proposes an integrated framework combining empirical modeling (slope classification, hazard assessment, and safety ratings) with multi-source real-time monitoring (synthetic aperture radar, machine vision, and Global Navigation Satellite System) to achieve quantitative stability analysis. The method establishes an initial stability baseline through mechanical modeling (Bishop/Morgenstern–Price methods, safety factors: 1.35–1.75 across five mine zones) and dynamically refines it via 3D terrain displacement tracking (0.02 m to 0.16 m average cumulative displacement, 1 h sampling). Key innovations include the following: (1) a convex hull-displacement dual-criterion algorithm for automated sensitive zone identification, reducing computational costs by ~40%; (2) Ku-band synthetic aperture radar subsurface imaging coupled with a Global Navigation Satellite System and vision for centimeter-scale 3D modeling; and (3) a closed-loop feedback mechanism between empirical and real-time data. Field validation at a 140 m high phosphate mine slope demonstrated robust performance under extreme conditions. The framework advances slope risk management by enabling proactive, data-driven decision-making while maintaining compliance with safety standards. Full article

Unmanned Aerial Vehicles (UAVs) have rapidly grown into different essential applications, including surveillance, disaster response, agriculture, and urban monitoring. However, for UAVS to steer safely and autonomously, the ability to detect obstacles and nearby aircraft remains crucial, especially under hard environmental conditions. This study comprehensively analyzes the recent landscape of obstacle and aircraft detection techniques tailored for UAVs acting in difficult scenarios such as fog, rain, smoke, low light, motion blur, and disorderly environments. It starts with a detailed discussion of key detection challenges and continues with an evaluation of different sensor types, from RGB and infrared cameras to LiDAR, radar, sonar, and event-based vision sensors. Both classical computer vision methods and deep learning-based detection techniques are examined in particular, highlighting their performance strengths and limitations under degraded sensing conditions. The paper additionally offers an overview of suitable UAV-specific datasets and the evaluation metrics generally used to evaluate detection systems. Finally, the paper examines open problems and coming research directions, emphasising the demand for lightweight, adaptive, and weather-resilient detection systems appropriate for real-time onboard processing. This study aims to guide students and engineers towards developing stronger and intelligent detection systems for next-generation UAV operations. Full article

Contactless vital sign monitoring has emerged as a transformative healthcare technology, enabling the assessment of vital signs without physical contact with the human body. This review comprehensively reviews the rapidly evolving landscape of this field, with particular emphasis on multi-modal sensing approaches and multi-task learning paradigms. We systematically categorize and analyze existing technologies based on sensing modalities (vision-based, radar-based, thermal imaging, and ambient sensing), integration strategies, and application domains. The paper examines how artificial intelligence has revolutionized this domain, transitioning from early single-modality, single-parameter approaches to sophisticated systems that combine complementary sensing technologies and simultaneously extract multiple vital sign parameters. We discuss the theoretical foundations and practical implementations of multi-modal fusion, analyzing signal-level, feature-level, decision-level, and deep learning approaches to sensor integration. Similarly, we explore multi-task learning frameworks that leverage the inherent relationships between vital sign parameters to enhance measurement accuracy and efficiency. The review also critically addresses persisting technical challenges, clinical limitations, and ethical considerations, including environmental robustness, cross-subject variability, sensor fusion complexities, and privacy concerns. Finally, we outline promising future directions, from emerging sensing technologies and advanced fusion architectures to novel application domains and privacy-preserving methodologies. This review provides a holistic perspective on contactless vital sign monitoring, serving as a reference for researchers and practitioners in this rapidly advancing field. Full article

To enhance the perception capability of radar in complex electromagnetic environments, this paper proposes an intelligent jamming recognition and parameter estimation method based on deep learning. The core idea of the method is to reformulate the jamming perception problem as an object detection task in computer vision, and we pioneer the application of oriented object detection to this problem, enabling simultaneous jamming classification and key parameter estimation. This method takes the time–frequency spectrogram of jamming signals as input. First, it employs the oriented object detection network YOLOv8-OBB (You Only Look Once Version 8–oriented bounding box) to identify three types of classic suppression jamming and five types of Interrupted Sampling Repeater Jamming (ISRJ) and outputs the positional information of the jamming in the time–frequency spectrogram. Second, for the five ISRJ types, a post-processing algorithm based on boxes fusion is designed to further extract features for secondary recognition. Finally, by integrating the detection box information and secondary recognition results, parameters of different ISRJ are estimated. In this paper, ablation experiments from the perspective of Non-Maximum Suppression (NMS) are conducted to simulate and compare the OBB method with the traditional horizontal bounding box-based detection approaches, highlighting OBB’s detection superiority in dense jamming scenarios. Experimental results show that, compared with existing jamming detection methods, the proposed method achieves higher detection probabilities under the jamming-to-noise ratio (JNR) ranging from 0 to 20 dB, with correct identification rates exceeding 98.5% for both primary and secondary recognition stages. Moreover, benefiting from the advanced YOLOv8 network, the method exhibits an absolute error of less than 1.85% in estimating six types of jamming parameters, outperforming existing methods in estimation accuracy across different JNR conditions. Full article

In the task of PolSAR image classification, effectively utilizing convolutional neural networks and vision transformer models with limited labeled data poses a critical challenge. This article proposes a novel method for PolSAR image classification that combines channel-wise convolutional local perception, detachable self-attention, and a residual feedforward network. Specifically, the proposed method comprises several key modules. In the channel-wise convolutional local perception module, channel-wise convolution operations enable accurate extraction of local features from different channels of PolSAR images. The local residual connections further enhance these extracted features, providing more discriminative information for subsequent processing. Additionally, the detachable self-attention mechanism plays a pivotal role: it facilitates effective interaction between local and global information, enabling the model to comprehensively perceive features across different scales, thereby improving classification accuracy and robustness. Subsequently, replacing the conventional feedforward network with a residual feedforward network that incorporates residual structures aids the model in better representing local features, further enhances the capability of cross-layer gradient propagation, and effectively alleviates the problem of vanishing gradients during the training of deep networks. In the final classification stage, two fully connected layers with dropout prevent overfitting, while softmax generates predictions. The proposed method was validated on the AIRSAR Flevoland, RADARSAT-2 San Francisco, and RADARSAT-2 Xi’an datasets. The experimental results demonstrate that the proposed method can attain a high level of classification performance even with a limited amount of labeled data, and the model is relatively stable. Furthermore, the proposed method has lower computational costs than comparative methods. Full article

Many radar applications rely primarily on visual classification for their evaluations. However, new research is integrating textual descriptions alongside visual input and showing that such multimodal fusion improves contextual understanding. A critical issue in this area is the effective alignment of coded text with corresponding images. To this end, our paper presents an adversarial training framework that generates descriptive text from the latent space of a visual radar classifier. Our quantitative evaluations show that this dual-task approach maintains a robust classification accuracy of 98.3% despite the inclusion of Gaussian-distributed latent spaces. Beyond these numerical validations, we conduct a qualitative study of the text output in relation to the classifier’s predictions. This analysis highlights the correlation between the generated descriptions and the assigned categories and provides insight into the classifier’s visual interpretation processes, particularly in the context of normally uninterpretable radar data. Full article