Search Results (50)

Forward scatter radar (FSR) can enhance target echo signal power by exploiting the sharp increase in radar cross-section (RCS), and has been widely studied in passive radar target detection. Traditional FSR detectors operate based on the shadowing effect that occurs when a target crosses the baseline. However, when satellite transmitters are used, the probability that a target’s trajectory intersects with the baseline in three-dimensional space approaches zero. Therefore, shadowing is difficult to occur. A moving-target detection method using weighted time-frequency (TF) entropy fusion is proposed in this paper for scenarios where targets move near the baseline. First, an echo signal model is established to show that the frequency change can be approximated as linear within a short time. Then, four TF entropy features are extracted from the received signal and linearly weighted to form the test statistic. The weights are optimized using the Nelder–Mead algorithm, with the objective of maximizing the average detection probability. Finally, the effectiveness of the proposed algorithm is verified through simulations and anechoic chamber measurements. The weighted fused TF entropy achieves a higher detection probability than any single TF entropy. Compared with the energy detector, the required signal-to-noise ratio (SNR) is reduced by about 3 dB to achieve the same detection probability at a false alarm probability of 10⁻³. Full article

In video synthetic aperture radar (Video SAR), target motion causes defocusing, making it impossible to determine the target’s real-time position using reflected echoes. However, the shadows formed by the target occluding ground reflections can accurately characterize the target’s real-time position. To address challenges such as varying shadow scales, low contrast with the moving background, and susceptibility to clutter interference, this paper proposes a shadow detection network called DSENet to enhance the detail and semantic features of shadows. First, to enhance shadow features and reduce sampling loss during backbone network feature extraction, we design a detailed information enhancement (DIE) module to achieve lossless downsampling and effectively preserve the detailed features of the shadowed target. Second, we propose a semantic spatial feature aggregation (SSFA) module to enhance global semantic space feature extraction, improve the contextual feature representation of the target’s shadow region, and provide robust semantic space prior information for the model. Finally, we designed a detailed semantic fusion (DSF) module to improve the neck network’s ability to fuse shadow details and semantic features in video SAR images, further enhancing the model’s localization performance for target shadow features and achieving accurate localization of moving targets in video SAR. Comparative and ablation experiments validate the effectiveness and superiority of the proposed method. Experimental results on the Sandia National Laboratories (SNL) public dataset demonstrate that DSENet is efficient and performs excellently, achieving a P of 92.4% and an F1 score of 83.1%. Full article

Video synthetic aperture radar (SAR) enables observation of moving targets by leveraging temporal information across successive frames. In particular, dynamic shadows in video SAR image sequences provide critical cues for detecting moving objects whose energy is smeared or Doppler-shifted. To achieve high-resolution imaging at a high frame rate for effective dynamic scene monitoring, video SAR systems typically operate at extremely high frequencies or even in the terahertz band, rather than the microwave band. However, terahertz video SAR suffers from significant signal attenuation due to atmospheric absorption. We present a deep learning framework to achieve high-frame-rate and high-resolution imaging for microwave video SAR systems. In this framework, the problem of microwave video SAR imaging is formulated as an image super-resolution reconstruction task for low-resolution yet high-frame-rate image sequences from microwave video SAR. We develop a simple yet effective image super-resolution reconstruction network that is completely built upon convolutional neural networks. The designed network takes a low-resolution image sequence and the corresponding high-resolution image with blurred shadows as input, and then produces a high-resolution image sequence where shadows are clearly visible. Furthermore, the network is trained in a self-supervised manner and thus does not require high-resolution image sequences with unblurred shadows as ground truth, which is appealing to practical applications. Processing results of real data from two different video SAR systems have shown good performance of the proposed approach with convincing generalization ability. Full article

Terahertz waves are located in the “transition zone” between millimeter waves and infrared light. Terahertz video synthetic aperture radar (THz-ViSAR) utilizes the high operating frequency, strong radar cross-section intensity, and high azimuth repetition frequency of terahertz waves to detect and track ground moving targets. The conventional methods for detecting moving targets do not take into account the imaging characteristics of moving targets in THz-ViSAR. The constant false alarm rate (CFAR) detection method is used together with other methods to detect moving targets, resulting in unsatisfactory detection performance. This article proposes a new detection method for single channel slow-moving targets in THz-ViSAR based on shadows and light spots, which extracts the features of the shadow and spot areas of the moving target, and determines the position and direction of the moving target through the identification of the shadow and spot areas. The progressiveness of this method is verified by simulation and experimental tests. Full article

Pavement maintenance programs rely on timely and accurate crack assessment to preserve roadway quality and reduce long-term rehabilitation costs. Manual inspection remains the prevailing practice, yet it is slow, subjective, and exposes crews to safety risks. Automating crack detection under real-world roadway conditions remains challenging due to inconsistent lighting, shadows, stains, and surface textures that obscure distress features. This study examines the applicability of an integrated, vehicle-mounted framework for automated pavement crack segmentation and width-based severity estimation under practical roadway operating conditions. Data were collected from a moving vehicle using a custom camera–GPS system operating under diverse conditions, capturing the variability encountered in practical surveys. The proposed approach employs a state-of-the-art segmentation model and a calibrated width estimation tool that converts pixel-level crack measurements into physical units using a position-dependent regression model. The key contribution of this work is a unified segmentation and severity evaluation pipeline supported by a novel pixel-to-inch calibration surface and validated using images acquired during normal driving operations and manual field crack measurements. By combining advanced computer vision techniques with practical field-oriented data collection, the proposed system provides a deployable solution for roadway crack assessment, enabling safer, faster, and more scalable network-level pavement monitoring. Full article

Shadow detection has become a key technology for ground-based moving target indication in video synthetic aperture radar (SAR). However, single-platform video SAR faces the issue of moving-target shadows being occluded. This paper proposes a new dynamic programming-based spatiotemporal track-before-detect (DP-ST-TBD) algorithm for moving-target shadow indication based on a distributed unmanned aerial vehicle (UAV)-borne video SAR system. First, this approach establishes a spatiotemporal cooperative shadow detection model, which extends the temporal accumulation of traditional DP-TBD to spatiotemporal accumulation by state temporal transition and spatial mapping. Second, an adaptive state transition method is proposed to address the challenge in which the fixed-state transition of traditional DP-TBD struggles with maneuvering target detection. It utilizes target’s Doppler features from heterogeneous-view range-Doppler (RD) spectra to assist in target’s shadow search within the image domain. Finally, a state shrinking–sparseness strategy is used to reduce the computational burden caused by dense states in spatiotemporal search; thus, multi-platform, multi-frame accumulation of moving-target shadows can be realized based on sparse states. The comparative experiments demonstrate that the proposed DP-ST-TBD improves shadow-detection performance through heterogeneous-view measurements while reducing the required number of frames for reliable detection compared to the conventional two-step detection method (single-platform shadow detection followed by multi-platform track fusion). Full article

Space Surveillance and Tracking (SST) plays a crucial role in ensuring space safety. To this end, accurate and numerous observational resources are needed to build and maintain a catalog of space objects. In particular, it is essential to develop optimal observation strategies to maximize both the number and the quality of detections obtained from a sensor network. This represents a key step in the assessment of the network through simulations. This work presents the integrated development of sensor tasking strategies for optical systems and a track-to-track correlation pipeline within S$\mathrm{\Xi }$NSIT, a software environment designed to simulate sensor network configurations and evaluate cataloging performance. For high-altitude low Earth orbit (HLEO) targets, which are fast-moving and widely distributed, tasking strategies emphasize systematic scans of the Earth’s shadow boundary to exploit favorable phase angles and improve observational accuracy, while medium- and geostationary-Earth orbits (MEO–GEO) rely on equatorial-plane scans. The correlation pipeline employs Two-Body Integrals, uncertainty propagation, and a ${\chi }^2$-test with the Squared Mahalanobis Distance to associate tracks and perform initial orbit determination of newly detected objects. Results indicate that the integrated approach significantly enhances detection coverage, leading to greater catalog build-up efficiency and improved SST performance. Consequently, it facilitates the cataloging of numerous uncataloged objects within a reduced timeframe. Full article

An enhanced method called FreeViBe+ for moving target segmentation is proposed in this paper, addressing limitations in the ViBe algorithm such as ghosting, shadows, and holes. To eliminate ghosts, multi-frame background modeling is introduced. Shadows are detected and removed based on their characteristics in the HSV color space, while holes are filled by merging GrabCut segmentation results with the ViBe extraction output. Furthermore, the Structure-measure is tuned to optimize image fusion, enabling improved foreground–background separation. Comprehensive experiments on the UCF101 and Weizmann datasets demonstrate the effectiveness of FreeViBe+ in comparison with Finite Difference, Gaussian Mixture Model, and ViBe methods. Ablation studies confirm the individual contributions of multi-frame modeling, shadow removal, and GrabCut refinement, while sensitivity analysis verifies the robustness of key parameters. Quantitative evaluations show that FreeViBe+ achieves superior performance in precision, recall, and F-measure compared with existing approaches. Full article

Photogrammetry-based 3D reconstruction of the shape of fast-moving objects from image sequences presents a complex yet increasingly important challenge. The 3D reconstruction of a large number of fast-moving objects may, for instance, be of high importance in the study of dynamic phenomena such as impact experiments and explosions. In this context, analyzing the 3D shape, size, and motion trajectory of the resulting fragments provides valuable insights into the underlying physical processes, including energy dissipation and material failure. High-speed cameras are typically employed to capture the motion of the resulting fragments. The high cost, the complexity of synchronizing multiple units, and lab conditions often limit the number of high-speed cameras that can be practically deployed in experimental setups. In some cases, only a single high-speed camera will be available or can be used. Challenges such as overlapping fragments, shadows, and dust often complicate tracking and degrade reconstruction quality. These challenges highlight the need for advanced 3D reconstruction techniques capable of handling incomplete, noisy, and occluded data to enable accurate analysis under such extreme conditions. In this paper, we use a combination of photogrammetry, computer vision, and artificial intelligence techniques in order to improve feature detection of moving objects and to enable more robust trajectory and 3D shape reconstruction in complex, real-world scenarios. The focus of this paper is on achieving accurate 3D shape estimation and motion tracking of dynamic objects generated by impact loading using stereo- or monoscopic high-speed cameras. Depending on the object’s rotational behavior and the number of available cameras, two methods are presented, both enabling the successful 3D reconstruction of fragment shapes and motion. Full article

Solar power generation is rapidly emerging within renewable energy due to its cost-effectiveness and ease of deployment. However, improper inspection and maintenance lead to significant damage from unnoticed solar hotspots. Even with inspections, factors like shadows, dust, and shading cause localized heat, mimicking hotspot behavior. This study emphasizes interpretability and efficiency, identifying key predictive features through feature-level and What-if Analysis. It evaluates model training and inference times to assess effectiveness in resource-limited environments, aiming to balance accuracy, generalization, and efficiency. Using Unmanned Aerial Vehicle (UAV)-acquired thermal images from five datasets, the study compares five Machine Learning (ML) models and five Deep Learning (DL) models. Explainable AI (XAI) techniques guide the analysis, with a particular focus on MPEG (Moving Picture Experts Group)-7 features for hotspot discrimination, supported by statistical validation. Medium Gaussian SVM achieved the best trade-off, with 99.3% accuracy and 18 s inference time. Feature analysis revealed blue chrominance as a strong early indicator of hotspot detection. Statistical validation across datasets confirmed the discriminative strength of MPEG-7 features. This study revisits the assumption that DL models are inherently superior, presenting an interpretable alternative for hotspot detection; highlighting the potential impact of domain mismatch. Model-level insight shows that both absolute and relative temperature variations are important in solar panel inspections. The relative decrease in “blueness” provides a crucial early indication of faults, especially in low-contrast thermal images where distinguishing normal warm areas from actual hotspot is difficult. Feature-level insight highlights how subtle changes in color composition, particularly reductions in blue components, serve as early indicators of developing anomalies. Full article

Unmanned Surface Vehicles (USVs) are commonly used as mobile docking stations for Unmanned Aerial Vehicles (UAVs) to ensure sustained operational capabilities. Conventional vision-based techniques based on horizontally-placed fiducial markers for autonomous landing are not only susceptible to interference from lighting and shadows but are also restricted by the limited Field of View (FOV) of the visual system. This study proposes a method that integrates an improved minimum snap trajectory planning algorithm with an event-triggered vision-based technique to achieve autonomous landing on a small USV. The trajectory planning algorithm ensures trajectory smoothness and controls deviations from the target flight path, enabling the UAV to approach the USV despite the visual system’s limited FOV. To avoid direct contact between the UAV and the fiducial marker while mitigating the interference from lighting and shadows on the marker, a landing platform with a vertically placed fiducial marker is designed to separate the UAV landing area from the fiducial marker detection region. Additionally, an event-triggered mechanism is used to limit excessive yaw angle adjustment of the UAV to improve its autonomous landing efficiency and stability. Experiments conducted in both terrestrial and river environments demonstrate that the UAV can successfully perform autonomous landing on a small USV in both stationary and moving scenarios. Full article

Video Synthetic Aperture Radar (ViSAR) operates by continuously monitoring regions of interest to produce sequences of SAR imagery. The detection and tracking of ground-moving targets, through the analysis of their radiation properties and temporal variations relative to the background environment, represents a significant area of focus and innovation within the SAR research community. In this study, some key challenges in ViSAR systems are addressed, including the abundance of low-confidence shadow detections, high error rates in multi-target data association, and the frequent fragmentation of tracking trajectories. A multi-target tracking algorithm for ViSAR that utilizes re-identification (ReID) features and a multi-stage data association process is proposed. The algorithm extracts high-dimensional ReID features using the Dense-Net121 network for enhanced shadow detection and calculates a cost matrix by integrating ReID feature cosine similarity with Intersection over Union similarity. A confidence-based multi-stage data association strategy is implemented to minimize missed detections and trajectory fragmentation. Kalman filtering is then employed to update trajectory states based on shadow detection. Both simulation experiments and actual data processing experiments have demonstrated that, in comparison to two traditional video multi-target tracking algorithms, DeepSORT and ByteTrack, the newly proposed algorithm exhibits superior performance in the realm of ViSAR multi-target tracking, yielding the highest MOTA and HOTA scores of 94.85% and 92.88%, respectively, on the simulated spaceborne ViSAR data, and the highest MOTA and HOTA scores of 82.94% and 69.74%, respectively, on airborne field data. Full article

Existing convolution neural network (CNN)-based video synthetic aperture radar (SAR) moving target shadow detectors are difficult to model long-range dependencies, while transformer-based ones often suffer from greater complexity. To handle these issues, this paper proposes MambaShadowDet, a novel lightweight deep learning (DL) detector based on a state space model (SSM), dedicated to high-speed and high-accuracy moving target shadow detection in video SAR images. By introducing SSM with the linear complexity into YOLOv8, MambaShadowDet effectively captures the global feature dependencies while relieving computational load. Specifically, it designs Mamba-Backbone, combining SSM and CNN to effectively extract both global contextual and local spatial information, as well as a slim path aggregation feature pyramid network (Slim-PAFPN) to enhance multi-level feature extraction and further reduce complexity. Abundant experiments on the Sandia National Laboratories (SNL) video SAR data show that MambaShadowDet achieves superior moving target shadow detection performance with a detection accuracy of 80.32% F1 score and an inference speed of 44.44 frames per second (FPS), outperforming existing models in both accuracy and speed. Full article

This paper introduces a vision-based target recognition and positioning system for UAV mobile landing scenarios, addressing challenges such as target occlusion due to shadows and the loss of the field of view. A novel image preprocessing technique is proposed, utilizing finite adaptive histogram equalization in the HSV color space, to enhance UAV recognition and the detection of markers under shadow conditions. The system incorporates a Kalman filter-based target motion state estimation method and a binocular vision-based depth camera target height estimation method to achieve precise positioning. To tackle the problem of poor controller performance affecting UAV tracking and landing accuracy, a feedforward model predictive control (MPC) algorithm is integrated into a mobile landing control method. This enables the reliable tracking of both stationary and moving targets via the UAV. Additionally, with a consideration of the complexities of real-world flight environments, a mobile tracking and landing control strategy based on airspace division is proposed, significantly enhancing the success rate and safety of UAV mobile landings. The experimental results demonstrate a 100% target recognition success rate and high positioning accuracy, with x and y-axis errors not exceeding 0.01 m in close range, the x-axis relative error not exceeding 0.05 m, and the y-axis error not exceeding 0.03 m in the medium range. In long-range situations, the relative errors for both axes do not exceed 0.05 m. Regarding tracking accuracy, both KF and EKF exhibit good following performance with small steady-state errors when the target is stationary. Under dynamic conditions, EKF outperforms KF with better estimation results and a faster tracking speed. The landing accuracy is within 0.1 m, and the proposed method successfully accomplishes the mobile energy supply mission for the vehicle-mounted UAV system. Full article

For many aquatic species, vision is important for detecting prey, predators, and conspecifics; however, the potential impacts of visual cues from offshore wind turbines have not been investigated in these crucial contexts. There is the possibility of visual cues, originating from moving wind turbine blades, propagating through the air–water interface to impact visually sensitive species. Two classes of visual cues are possible: direct motion cues originating as light reflected from moving turbine blades and indirect cues resulting from an interruption of direct sunlight causing dynamic shadowing when the sun, blade, and receptor are aligned. In both cases, the propagation of cues across the air–water interface is governed by physical principles but modulated in potentially complex ways by the aspects of the local environment that vary with time. Evidence for the extent of the exposure of aquatic organisms to the visual cues arising from moving turbine blades and for the potential response of receptor organisms is sparse. This study considers the physics involved to support the formulation and testing of robust biological hypotheses. Marine migratory salmonid species are considered as an example species because their behaviour in the marine environment is relatively well documented. This study concludes that the aquatic receptor organisms present in the uppermost layer of the sea in the vicinity of wind turbines are potentially exposed to direct motion cues originating from moving turbine blades and also, when the sun elevation angle is greater than ca. 20°, to dynamic shadowing cues. Full article