Search Results (68)

Robust object detection for autonomous driving requires perception models that remain reliable when visible imagery is degraded by darkness, glare, rain, fog, motion blur, or long-range small targets. Visible and thermal infrared cameras provide complementary evidence, yet many RGB–thermal detectors fuse modalities, mainly as aligned tensors, and may underuse relational structure in channel responses, spatial layouts, semantic scales, and modality-specific uncertainty. This paper presents TopoGraph-Fusion, a hierarchical graph-guided dual-modal object detector that formulates fusion as topology-aware reasoning rather than direct feature concatenation. The proposed framework builds a dual-stream backbone for RGB and thermal images, constructs channel-wise topology through a channel-topology graph aggregation module, derives relation-aware spatial and channel global attention from affinity graphs, and replaces fixed feature-pyramid communication with a Graph-Guided Feature-Pyramid Network. A topology-regularized detection objective further encourages stable cross-modal correspondence while suppressing noisy all-to-all connections. Experiments on M3FD, FLIR, RGBTDronePerson, and VEDAI512 cover road scenes, adverse illumination, drone–person perception, and aerial vehicle detection. Within this validation scope, the results and visual analyses indicate that topology-guided fusion improves small-object recall, cross-modal consistency, and robustness under modality imbalance. Full article

This study assesses the capabilities of UAV-based Earth observation for analyzing marginalized communities, using Roma settlements in southeastern Slovakia as a case study. Marginalized populations are often underrepresented in official spatial datasets, resulting in a limited understanding of their living conditions, infrastructure needs, and environmental risks. To address this gap, we propose a multi-scalar, UAV-based observational approach that bridges the limitations of coarse satellite imagery and logistically constrained ground surveys. High-resolution RGB and thermal imagery were acquired across three settlements with varying spatial characteristics and processed using photogrammetric workflows to generate detailed orthophotos and spatial products. The results demonstrate that UAV data with centimeter-level spatial resolution enable precise mapping of settlement morphology, infrastructure, waste distribution, and thermal inequalities. Furthermore, UAV observations enable change detection and environmental risk assessment at scales that are not achievable with conventional remote sensing. However, the study also highlights critical operational and ethical challenges, including regulatory constraints, privacy concerns, and the need for community engagement. By integrating technical evaluation with socially sensitive research practices, this work proposes a methodological framework for responsible UAV deployment in marginalized contexts. The findings underscore the potential of UAV-based observation to improve spatial visibility and support evidence-based planning while emphasizing the importance of ethical implementation. Full article

Reliable and scalable landmine detection technologies are essential for humanitarian mine action (HMA), yet standardized benchmarks for Unmanned Aerial Vehicle (UAV)-based sensing in operationally relevant environments remain limited. This study presents a comprehensive evaluation of 34 multimodal datasets acquired over a standardized seeded test site for landmine and unexploded ordnance detection. Nine sensing modalities, including RGB, thermal, multispectral, hyperspectral, LiDAR, and Synthetic Aperture Radar (SAR), are evaluated using the Anomaly, Identifiable Anomaly, Unique Identifiable Anomaly (AIU) index to establish a unified framework for quantifying detection fidelity. Results indicate that RGB imagery achieves the highest surface detection rate (94.8%), with 45.4% of targets classified as uniquely identifiable, reducing false-positive risk. For sub-surface detection, handheld electromagnetic induction (EMI) and magnetometry exceed 95% detection for ferrous items but fall below 10% for plastic ordnance. Ground-penetrating radar (GPR) is the only modality capable of detecting buried plastic targets (55.6% for cart-based systems), whereas UAV-mounted GPR remains limited (18.2%) at current operational flight heights. Based on the comparative analysis, we discuss the gaps in current detection capabilities, compare false-positive rates across modalities, and perform a cost–benefit analysis fitting contamination scenarios with the most cost-effective detection method. All datasets are publicly released, along with an interactive web-map, to support reproducible benchmarking and cross-modality comparison in UAV-enabled explosive hazard detection. Full article

Accurate geolocalization of ground targets from unmanned aerial vehicles (UAVs) is critically limited by pose estimation errors and the scarcity of active ranging sensors. To address these challenges, we propose a pipeline that integrates reference image cropping, robust cross-view matching, and geographic projection to estimate real-world coordinates using 2.5D reference maps. For evaluation, we introduce SkyPin, the first large-scale benchmark of its kind, designed to comprehensively test UAV-based localization methods. It comprises UAV imagery from eight diverse environments, featuring both visible and thermal infrared modalities under a wide range of conditions, including variations in weather, time of day, flight altitude, and camera perspective. All ground targets are annotated with centimeter-accuracy Real-Time Kinematic (RTK) coordinates. We establish a comprehensive benchmark by evaluating a series of feature matching methods combined with different projection strategies, allowing systematic comparison of algorithm performance. Representative results show that RoMa combined with PnP-based raytracing achieves the best overall performance, reaching a median 2D error of 0.87 m and Recall@5m values of 0.94 and 0.98 on RGB and thermal infrared UAV-map settings, respectively. Further analysis reveals that performance degrades in challenging mountainous scenes and under large viewing-angle variations, highlighting terrain relief and UAV perspective changes as remaining critical challenges for robust target geo-localization. The full dataset and implementation code will be made publicly available to facilitate future research in UAV-based geolocalization. Full article

Lithium-ion batteries experience structural degradation during operation and storage, which can negatively impact performance, safety, and service life. Early identification of these degradation-induced structural changes is important for battery health assessment and reliability monitoring. This study proposes a deep learning-based framework for classifying the structural condition of 18650 lithium-ion batteries using X-ray micro-computed tomography (µCT) images. The proposed approach combines centroid-based core cropping, image normalization, three-slice stacking, and transfer learning using a fine-tuned InceptionResNet-V2 architecture. Three adjacent µCT slices are stacked into an RGB-like representation to preserve local three-dimensional structural information while maintaining compatibility with a two-dimensional convolutional neural network. The original classification head of InceptionResNet-V2 was replaced with a custom classification block consisting of dropout layers, fully connected layers, and a SoftMax classifier optimized for battery condition recognition. The framework was evaluated using four battery structural conditions: pristine, cycle-aged, calendar-aged, and thermally cycled cells. Experimental results demonstrated an overall classification accuracy of 96.62%, with a precision of 95.62%, sensitivity of 96.94%, specificity of 98.92%, and F1-score of 96.20%. Comparative analysis with previously reported battery imaging studies demonstrated that the proposed framework achieves competitive performance while addressing the challenging task of structural condition classification from µCT imagery. The results demonstrate the potential of combining advanced X-ray imaging and transfer learning for automated lithium-ion battery structural health assessment and degradation monitoring. Full article

Waterbody extraction is of great significance for water resource investigation and monitoring. In addition to RGB bands, most common satellite images have a near-infrared (NIR) band. By combining these RGB-NIR bands, certain water, vegetation, and shadow indices can be calculated. The near-infrared band and these indices are very similar to the X modality in RGB+X data (common examples include RGB-D and RGB-Thermal). However, at present, no studies have thoroughly examined multimodal feature fusion from the RGB+X perspective in order to extract waterbodies with high precision. As a result, existing algorithms do not fully utilize satellite image information and have limited generalization ability. To overcome this limitation, we propose a dual-complexity backbone for waterbody extraction from the perspective of RGB+X data semantic segmentation. Its complex Transformer branch is used to extract RGB modality features, while its simple CNN branch is used to extract X modality features. This network structure can effectively capture multimodal, global, and local features in remote sensing images. It can also fully leverage the fact that the scale of RGB image datasets in computer vision is significantly larger than that of remote sensing waterbody extraction datasets. If a large pretrained model is used in the RGB branch, it is unnecessary to freeze the weights. Instead, both branches can be trained jointly, allowing the RGB branch to better adapt to the remote sensing waterbody extraction task without raising concerns that fine-tuning might undermine the pretrained model’s strong representation capability. We also propose two X modality configurations with strong generalization performance. To fully fuse multimodal features, we design a hybrid fusion module combining a CNN and a cross-attention mechanism. To integrate the multi-scale features, we employ a multi-scale Transformer structure in the RGB branch and design a multi-scale decoder. Our algorithm achieves state-of-the-art performance on the GID-5 dataset and competitive performance on the S1S2-Water dataset. Furthermore, it significantly outperforms existing methods in cross-dataset zero-shot transfer between the two datasets, with IoU/F1-score gains of 26.08%/27.33% on GID-5 and 38.74%/31.37% on S1S2-Water over previous SOTA methods. Our processing paradigm of modeling RGB-NIR remote sensing images as RGB+X data shows potential for generalization to other multi-modal remote sensing tasks. The dual-complexity backbone we design also has potential to be extended to other tasks that transfer large pretrained RGB models to remote sensing imagery with RGB-NIR four bands or even more spectral bands. We have open-sourced the code and trained models used in this research. Full article

Vineyards are affected by pathogens globally. Some of the most damaging pathogens are Uncinula necator, Plasmopara viticola, and thrips, which affect the plant entirely and threaten the health and productivity of vineyards. To control the emergence and spread of pathogens, early detection is essential. Studies to date focus on visual or molecular detection of pathogens but are limited in terms of scalability, labor intensity, need for equipment and expertise. To tackle these limitations, we propose the early detection of grapevine virus infections using Convolutional Neural Networks on both RGB and thermal infrared imagery captured via a smartphone and an FLIR sensor. To do so, we employ a four-step workflow where we first acquire nearly 500 images detecting symptoms of pathogens, which we then crop in smaller tiles. Then, we use the ArcGIS Train Deep Learning Model tool trained with Single Shot Detector and RetinaNet frameworks to detect image areas showing pathogen presence. Finally, we calculate the IoU score to compare precisions between different tile sizes and frameworks. The results demonstrate that pathogen detection using these models is highly effective, with most images having a IoU score above 0.7. Moreover, 30% of images score a precision of 1.0. The consequences of these findings highlight the importance of early detection of pathogens to better understand their spread and effects on vineyards, which finally contribute to proposing effective management measures. Full article

Accurate registration of UAV-derived thermal infrared orthophotos and RGB orthophotos is essential for multi-sensor geospatial analysis, but it remains challenging because thermal imagery generally has lower spatial resolution, weaker texture, and less distinct structural information than RGB imagery. This study comparatively evaluated five histogram equalization methods—histogram equalization (HE), contrast-limited adaptive histogram equalization (CLAHE), brightness-preserving bi-histogram equalization (BBHE), dualistic sub-image histogram equalization (DSIHE), and minimum mean brightness error bi-histogram equalization (MMBEBHE)—for improving AKAZE-based registration of land surface temperature (LST) orthophotos to reference RGB orthophotos. High-accuracy RGB orthophotos generated using GNSS-surveyed ground control points were used as the geometric reference. Thermal data were acquired twice at each of two study sites with contrasting surface characteristics and processed into LST orthophotos. Each histogram equalization method was applied to the LST orthophotos, after which keypoints and descriptors were extracted using AKAZE, tentative correspondences were established, outliers were removed using RANSAC, and an affine transformation was estimated from the inlier correspondences. Here, an inlier denotes a tentative match that remained geometrically consistent after RANSAC-based outlier rejection. The estimated transformation was then applied to the source LST raster to preserve radiometric values in the final corrected product. Performance was assessed using the number of detected keypoints, tentative matches, RANSAC-verified inliers, matching efficiency, reproducibility, and exploratory statistical analysis. Among the five methods, BBHE consistently produced the highest number of inliers and the best matching efficiency at both study sites, while also showing the lowest variability between repeated acquisitions. These results indicate that brightness-preserving histogram equalization is particularly effective for thermal–RGB orthophoto registration and can improve the reliability of UAV-derived thermal mapping products for geomatics applications. Full article

Unmanned aerial vehicle (UAV)-mounted thermal infrared (TIR) sensors occupy a useful middle ground between sparse in situ measurements, occasional aircraft-based campaigns, and coarse satellite products, enabling centimeter-scale thermal mapping under field conditions. Yet converting UAV thermal imagery into quantitative temperature products remains challenging because uncooled microbolometers are radiometrically drift-prone, thermal scenes often provide weak geometric texture, and surface temperature retrieval depends on scene-specific emissivity and atmospheric assumptions. This review focuses on quantitative UAV–TIR mapping rather than on the full range of drone thermal applications. It synthesizes the technical decisions that most strongly affect the reliability, comparability, and physical interpretability of UAV-derived temperature products, from radiometric data integrity and field calibration to RGB–TIR integration, physical correction, uncertainty propagation, and validation. We clarify the literature synthesis approach, compare field-deployable calibration and drift mitigation strategies, discuss application-specific uncertainty priorities, and derive a practical reporting checklist for reproducible studies. The review emphasizes how radiometric, geometric, and physical correction choices interact, and uses comparative tables to summarize recurring trade-offs, reporting gaps, and remaining research needs. Its aim is to clarify why UAV–TIR temperature products can differ across studies and which methodological details are needed for meaningful interpretation and comparison. Full article

Unmanned aerial vehicles (UAVs) have become indispensable tools in precision agriculture and plant phenotyping, enabling the rapid, non-destructive assessment of crop traits across space and time. Equipped with RGB, multispectral, thermal, and other sensors, UAVs provide detailed information on canopy structure, physiology, and stress responses that can guide management decisions and accelerate breeding programs. Despite these advances, the downstream processing of UAV imagery remains technically demanding. Converting orthomosaics into standardized, biologically meaningful data often requires a combination of photogrammetry, geospatial analysis, and custom scripting, which can limit reproducibility and accessibility across research groups. We present drone2report, an open-source python-based software that processes orthomosaics from UAV flights to generate vegetation indices, summary statistics, derived subimages, and text (html) reports, supporting both research and applied crop breeding needs. Alongside the basic structure and functioning of drone2report, we also present five case studies that illustrate practical applications common in UAV-/drone-phenotyping of plants: (i) thresholding to remove background noise and highlight regions of interest; (ii) monitoring plant phenotypes over time; (iii) extracting information on plant height to detect events like lodging or the falling over of spikes; (iv) integrating multiple sensors (cameras) to construct and optimize new synthetic indices; (v) integrate a trained deep learning network to implement a classification task. These examples demonstrate the tool’s ability to automate analysis, integrate heterogeneous data and models, and support reproducible computation of agronomically relevant traits. drone2report streamlines orthorectified UAV-image processing for precision agriculture by linking orthomosaics to standardized, plot-level outputs. Its modular, configuration-driven design allows transparent workflows, easy customization, and integration of multiple sensors within a unified analytical framework. By facilitating reproducible, multi-modal image analysis, drone2report lowers technical barriers to UAV-based phenotyping and opens the way to robust, data-driven crop monitoring and breeding applications. Full article

Foreign Object Debris (FOD) poses critical risks to aircraft during takeoff and landing, resulting in billions of dollars in losses annually due to infrastructure damage and flight delays. Advancements in automated inspection technologies have enabled the use of Unmanned Aerial Systems (UAS) combined with Artificial Intelligence (AI) for rapid FOD identification. While prior research has extensively evaluated optical sensors such as RGB imaging and radar, limited work has investigated the potential of thermal imaging for improved FOD visibility under challenging environmental conditions. This study proposes DualFOD, a dual-modality detection framework that integrates a supervised YOLO12-based RGB detector with an unsupervised thermal anomaly extraction pipeline for identifying debris on runway surfaces. A decision-level fusion algorithm combines detections from both branches using spatial proximity matching to produce a unified FOD inventory. The RGB branch achieves a precision of 0.954 and mAP@0.5 of 0.890 on the held-out test set. Cross-site validation at the Cobb County Sport Aviation Complex demonstrates that thermal detection recovers debris missed by RGB at higher altitudes, with the fused output consistently outperforming either single-modality branch. This research contributes toward scalable autonomous FOD monitoring that enhances operational safety in aviation environments. Full article

Drone-mounted ground-penetrating radar (GPR) systems offer new opportunities for integrating subsurface characterization into remote sensing workflows. However, the interaction between flight parameters, surface conditions, and vegetation characteristics remains poorly understood. This study investigates the impact of flight altitude, surface topography, crop presence, and canopy water content on the stability and interpretability of GPR signals collected using a drone. Field experiments were conducted under controlled conditions using agricultural plots with variable canopy cover and soil moisture regimes. Radargrams were processed to evaluate signal amplitude, reflection continuity, and attenuation patterns in relation to terrain slope and vegetation structure derived from co-registered RGB drone imagery. The results reveal that lower flight altitudes and smoother surfaces yield higher signal coherence and greater subsurface penetration, while increased canopy water content and biomass reduce signal strength and clarity. Integrating drone-based GPR observations with surface spectral and thermal data improved discrimination between soil and vegetation-induced signal distortions. The findings highlight the potential of drone–GPR systems as a complementary layer in a multi-sensor remote sensing framework for precision agriculture, environmental monitoring, and 3D soil mapping. Full article

Hyperspectral imaging in the long-wave infrared (LWIR) range enables identification of chemical compositions and material properties, but reconstructing 3D models from gimballed pushbroom sensors remains challenging because their unique acquisition geometry is incompatible with conventional photogrammetric software designed for frame cameras. This study presents a workflow for creating explorable 3D models from multi-angle LWIR hyperspectral imagery by co-registering hyperspectral line-scan data with simultaneously acquired RGB frame camera imagery using deep learning-based image matching. The co-registered images are processed in commercial photogrammetric software (Agisoft Metashape), and a texture-to-image mapping algorithm preserves correspondences between 3D model coordinates and original hyperspectral pixels across multiple viewing angles. Quantitative evaluation against reference data demonstrates that co-registration reduces geometric error approaching the accuracy of models built from high-resolution RGB imagery. The resulting models enable the retrieval of 8–50 spectral signatures per surface point, captured from different viewing geometries. This approach facilitates interactive exploration of angular variations in thermal infrared spectra, supporting material identification for non-Lambertian surfaces where single-angle observations may be insufficient for reliable classification. Full article

In oriented object detection from drone imagery, many existing RGB-infrared (RGB-IR) fusion methods derive modality weights from input statistics alone, without regard for downstream detection objectives. We present SGFNet, a Semantic-Guided Fusion Network that feeds detection-level semantics back into the fusion stage through learned importance masks. SGFNet comprises three modules: (1) a Frequency-aware Disentanglement Module (FDM) that separates high-frequency textures from low-frequency thermal structures through Laplacian and Gaussian filtering; (2) a Semantic-Guided Module (SGM) that generates P5-level semantic masks to steer fusion toward detection-critical regions; and (3) an Adaptive Geometric Convolution (AGC) whose rotation-aware sampling matches receptive fields to arbitrarily oriented objects. On the DroneVehicle benchmark (28,439 RGB-IR pairs, five vehicle categories), SGFNet achieves 82.0% mAP@0.5, surpassing the runner-up DMM by 3.2 percentage points while lowering mean angular error from 7.4° to 6.2° (−16%). Ablation analysis attributes the largest single-module gain (+1.7 pp) to the semantic feedback path. Full article

Non-contact monitoring in precision livestock farming (PLF) needs reliable individual identification and face-anchored analytics to link animals with longitudinal health and behavior signals in variable barns. Evidence is fragmented across pipeline modules and deployment readiness is difficult to assess because robustness and operational KPIs are inconsistently reported. We map research evolution and synthesize deployment-oriented evidence and design principles. A two-stage review was conducted: CiteSpace bibliometric mapping of Web of Science Core Collection records (2005–2025; pre-2005 relevant records were sporadic), followed by a scoping synthesis of peer-reviewed empirical studies (2022–2025) searched mainly in ScienceDirect and supplemented by Web of Science, Scopus, IEEE Xplore, and CNKI. We included studies using livestock facial imagery (RGB and/or thermal/IR) for identity functions or face-coupled ROI analytics with quantitative cohort evaluation. Following QRD screening, 24 studies were retained. We consolidate deployment factors and reporting gaps and propose “Digital Individuals” as persistent identity anchors for multimodal longitudinal records and closed-loop decision support. Full article