Search Results (109)

Roof damage caused by hurricanes and other storms needs to be rapidly identified and repaired to help communities recover from catastrophic events and support the well-being of residents. Traditional, ground-based inspections are time-consuming but have recently been expedited via manual interpretation of remote sensing imagery. To potentially accelerate the process, automated methods involving artificial intelligence (i.e., deep learning) can be applied. Here, we present an end-to-end workflow for training and evaluating deep learning image segmentation models that detect and delineate two classes of post-storm roof damage: roof decking and roof holes. Mask2Former models were trained using 2500 roof decking and 2500 roof hole samples from drone RGB orthomosaics (0.02–0.08 m ground sample distance [GSD]) captured in Sint Maarten and Dominica following Hurricanes Irma and Maria in 2017. The trained models were evaluated using 1440 reference samples from 10 test images, including eight drone orthomosaics (0.03–0.08 m GSD) acquired outside of the training areas in Sint Maarten and Dominica, one drone orthomosaic (0.05 m GSD) from the Bahamas, and one orthomosaic (0.15 m GSD) captured in the US Virgin Islands with a crewed aircraft and different sensor. Accuracies increased with a single-class modeling approach (instead of training one dual-class model) and expansion of the training datasets with 500 roof decking and 500 roof hole samples from external areas in the Bahamas and US Virgin Islands. The best-performing models reached overall F1 scores of 0.88 (roof decking) and 0.80 (roof hole). In this study, we provide: our end-to-end deep learning workflow; a detailed accuracy assessment organized by modeling approach, damage class, and test location; discussion of implications, limitations, and future research; and access to all data, tools, and trained models. Full article

In the field of drone-to-drone detection tasks, the issue of fusing temporal information with infrared and visible light data for detection has been rarely studied. This paper presents the first temporal misaligned rgb-thermal dataset for drone-to-drone target detection, named TMRGBT-D2D. The dataset covers various lighting conditions (i.e., high-light scenes captured during the day, medium-light and low-light scenes captured at night, with night scenes accounting for 38.8% of all data), different scenes (sky, forests, buildings, construction sites, playgrounds, roads, etc.), different seasons, and different locations, consisting of a total of 42,624 images organized into sequential frames extracted from 19 RGB-T video pairs. Each frame in the dataset has been meticulously annotated, with a total of 94,323 annotations. Except for drones that cannot be identified under extreme conditions, infrared and visible light annotations are one-to-one corresponding. This dataset presents various challenges, including small object detection (the average size of objects in visible light images is approximately 0.02% of the image area), motion blur caused by fast movement, and detection issues arising from imaging differences between different modalities. To our knowledge, this is the first temporal misaligned rgb-thermal dataset for drone-to-drone target detection, providing convenience for research into rgb-thermal image fusion and the development of drone target detection. Full article

The integration of unmanned aerial vehicles (UAVs) and deep learning (DL) has significantly advanced crop disease detection by enabling scalable, high-resolution, and near real-time monitoring within precision agriculture. This systematic review analyzes peer-reviewed literature indexed in the Web of Science Core Collection as articles or proceeding papers through 2024. The main selection criterion was combining “unmanned aerial vehicle*” OR “UAV” OR “drone” with “deep learning”, “agriculture” and “leaf disease” OR “crop disease”. Results show a marked surge in publications after 2019, with China, the United States, and India leading research contributions. Multirotor UAVs equipped with RGB sensors are predominantly used due to their affordability and spatial resolution, while hyperspectral imaging is gaining traction for its enhanced spectral diagnostic capability. Convolutional neural networks (CNNs), along with emerging transformer-based and hybrid models, demonstrate high detection performance, often achieving F1-scores above 95%. However, critical challenges persist, including limited annotated datasets for rare diseases, high computational costs of hyperspectral data processing, and the absence of standardized evaluation frameworks. Addressing these issues will require the development of lightweight DL architectures optimized for edge computing, improved multimodal data fusion techniques, and the creation of publicly available, annotated benchmark datasets. Advancements in these areas are vital for translating current research into practical, scalable solutions that support sustainable and data-driven agricultural practices worldwide. Full article

Marine mammals serve as indicator species for environmental and human health. However, they are increasingly exposed to pressure from human activities and climate change. The white-beaked dolphin (Lagenorhynchus albirostris) (WBD) is among the species negatively affected by these conditions. To support conservation and management efforts, a deeper understanding of their behavior and movement patterns is essential. One approach is drone-based monitoring combined with artificial intelligence (AI), allowing efficient data collection and large-scale analysis. This study aims to: (1) investigate the use of drone imagery and AI to monitor and analyze marine mammal behavior, and (2) test the application of machine learning (ML) to identify behavioral patterns. Data were collected in Skjálfandi Bay, Iceland, between 2021 and 2023. Three behavioral types were identified: Traveling, Milling, and Respiration. The AI_RGB model showed high performance on Traveling behavior (precision 92.3%, recall 96.9%), while the AI_gray model achieved higher precision (97.3%) but much lower recall (9.5%). The model struggled to classify Respiration accurately (recall 1%, F1-score 2%). A key challenge was misidentification of WBDs due to visual overlap with birds, waves, and reflections, resulting in high false positive rates. Multimodal AI systems may help reduce such errors in future research. Full article

Synthetic data has become an increasingly important tool for semantic segmentation, where collecting large-scale annotated datasets is often costly and impractical. Prior work has leveraged computer graphics and game engines to generate training data, but many pipelines remain limited to single modalities and constrained environments or require substantial manual setup. To address these limitations, we present a fully automated pipeline built within Unreal Engine 5 (UE5) that procedurally generates diverse, labeled environments and collects multimodal visual data for semantic segmentation tasks. Our system integrates UE5’s biome-based procedural generation framework with a spline-following drone actor capable of capturing both RGB and depth imagery, alongside pixel-perfect semantic segmentation labels. As a proof of concept, we generated a dataset consisting of 1169 samples across two visual modalities and seven semantic classes. The pipeline supports scalable expansion and rapid environment variation, enabling high-throughput synthetic data generation with minimal human intervention. To validate our approach, we trained benchmark computer vision segmentation models on the synthetic dataset and demonstrated their ability to learn meaningful semantic representations. This work highlights the potential of game-engine-based data generation to accelerate research in multimodal perception and provide reproducible, scalable benchmarks for future segmentation models. Full article

Drones have rapidly emerged as transformative tools in landscape research, enabling high-resolution spatial data acquisition, real-time environmental monitoring, and advanced modelling that surpass the limitations of traditional methodologies. This scoping review systematically explores and synthesises the technological applications of drones within the context of landscape studies, addressing a significant gap in the integration of Uncrewed Aerial Systems (UASs) into environmental and spatial planning disciplines. The study investigates the typologies of drone platforms—including fixed-wing, rotary-wing, and hybrid systems—alongside a detailed examination of sensor technologies such as RGB, LiDAR, multispectral, and hyperspectral imaging. Following the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines, a comprehensive literature search was conducted across Scopus, Web of Science, and Google Scholar, utilising predefined inclusion and exclusion criteria. The findings reveal that drone technologies are predominantly applied in mapping and modelling, vegetation and biodiversity analysis, water resource management, urban planning, cultural heritage documentation, and sustainable tourism development. Notably, vegetation analysis and water management have shown a remarkable surge in application over the past five years, highlighting global shifts towards sustainability-focused landscape interventions. These applications are critically evaluated in terms of spatial efficiency, operational flexibility, and interdisciplinary relevance. This review concludes that integrating drones with Geographic Information Systems (GISs), artificial intelligence (AI), and remote sensing frameworks substantially enhances analytical capacity, supports climate-resilient landscape planning, and offers novel pathways for multi-scalar environmental research and practice. Full article

Monitoring crop damage caused by wildlife remains a significant challenge in agricultural management, particularly in the case of large-scale monocultures such as maize. The given study presents a semi-automated process for detecting wildlife-induced damage using RGB imagery acquired from unmanned aerial vehicles (UAVs). The method is designed for non-specialist users and is fully integrated within the QGIS platform. The proposed approach involves calculating three vegetation indices—Excess Green (ExG), Green Leaf Index (GLI), and Modified Green-Red Vegetation Index (MGRVI)—based on a standardized orthomosaic generated from RGB images collected via UAV. Subsequently, an unsupervised k-means clustering algorithm was applied to divide the field into five vegetation vigor classes. Within each class, 25% of the pixels with the lowest average index values were preliminarily classified as damaged. A dedicated QGIS plugin enables drone data analysts (Drone Data Analysts—DDAs) to adjust index thresholds, based on visual interpretation, interactively. The method was validated on a 50-hectare maize field, where 7 hectares of damage (15% of the area) were identified. The results indicate a high level of agreement between the automated and manual classifications, with an overall accuracy of 81%. The highest concentration of damage occurred in the “moderate” and “low” vigor zones. Final products included vigor classification maps, binary damage masks, and summary reports in HTML and DOCX formats with visualizations and statistical data. The results confirm the effectiveness and scalability of the proposed RGB-based procedure for crop damage assessment. The method offers a repeatable, cost-effective, and field-operable alternative to multispectral or AI-based approaches, making it suitable for integration with precision agriculture practices and wildlife population management. Full article

Developing accurate activity data on tree biomass using remote sensing tools such as LiDAR and drone-mounted sensors is essential for improving carbon accounting in the agricultural sector. However, direct biomass measurements of perennial fruit trees remain limited, especially for validating remote sensing estimates. This study evaluates the potential of terrestrial laser scanning (TLS) and drone-mounted RGB sensors (Drone_RGB) for estimating biomass in two major perennial crops in South Korea: apple (‘Fuji’/M.9) and citrus (‘Miyagawa-wase’). Trees of different ages were destructively sampled for biomass measurement, while volume, height, and crown area data were collected via TLS and Drone_RGB. Regression analyses were performed, and the model accuracy was assessed using R², RMSE, and bias. The TLS-derived volume showed strong predictive power for biomass (R² = 0.704 for apple, 0.865 for citrus), while the crown area obtained using both sensors showed poor fit (R² ≤ 0.7). Aboveground biomass was reasonably estimated (R² = 0.725–0.865), but belowground biomass showed very low predictability (R² < 0.02). Although limited in scale, this study provides empirical evidence to support the development of remote sensing-based biomass estimation methods and may contribute to improving national greenhouse gas inventories by refining emission/removal factors for perennial fruit crops. Full article

Abies nebrodensis L. is a critically endangered conifer endemic to Sicily (Italy). Its residual population is confined to the Madonie mountain range under challenging climatological conditions. Despite the good adaptation shown by the relict population to the environmental conditions occurring in its habitat, Abies nebrodensis is subject to a series of threats, including climate change. Effective conservation strategies require reliable and versatile methods for monitoring its health status. Combining high-resolution remote sensing data with reanalysis of climatological datasets, this study aimed to identify correlations between vegetation indices (NDVI, GreenDVI, and EVI) and key climatological variables (temperature and precipitation) using advanced machine learning techniques. High-resolution RGB (Red, Green, Blue) and IrRG (infrared, Red, Green) maps were used to delineate tree crowns and extract statistics related to the selected vegetation indices. The results of phytosanitary inspections and multispectral analyses showed that the microclimatic conditions at the site level influence both the impact of crown disorders and tree physiology in terms of water content and photosynthetic activity. Hence, the correlation between the phytosanitary inspection results and vegetation indices suggests that multispectral techniques with drones can provide reliable indications of the health status of Abies nebrodensis trees. The findings of this study provide significant insights into the influence of environmental stress on Abies nebrodensis and offer a basis for developing new monitoring procedures that could assist in managing conservation measures. Full article

Timely and accurate identification of plant diseases is critical to mitigating crop losses and enhancing yield in precision agriculture. This paper proposes AgriFusionNet, a lightweight and efficient deep learning model designed to diagnose plant diseases using multimodal data sources. The framework integrates RGB and multispectral drone imagery with IoT-based environmental sensor data (e.g., temperature, humidity, soil moisture), recorded over six months across multiple agricultural zones. Built on the EfficientNetV2-B4 backbone, AgriFusionNet incorporates Fused-MBConv blocks and Swish activation to improve gradient flow, capture fine-grained disease patterns, and reduce inference latency. The model was evaluated using a comprehensive dataset composed of real-world and benchmarked samples, showing superior performance with 94.3% classification accuracy, 28.5 ms inference time, and a 30% reduction in model parameters compared to state-of-the-art models such as Vision Transformers and InceptionV4. Extensive comparisons with both traditional machine learning and advanced deep learning methods underscore its robustness, generalization, and suitability for deployment on edge devices. Ablation studies and confusion matrix analyses further confirm its diagnostic precision, even in visually ambiguous cases. The proposed framework offers a scalable, practical solution for real-time crop health monitoring, contributing toward smart and sustainable agricultural ecosystems. Full article

Low-altitude unmanned aerial vehicle (UAV) vision is critically hindered by the Sim-to-Real Gap, where models trained exclusively on simulation data degrade under real-world variations in lighting, texture, and weather. To address this problem, we propose RA3T (Region-Aligned 3D Transformer), a novel self-supervised framework that enables robust Sim-to-Real adaptation. Specifically, we first develop a dual-branch strategy for self-supervised feature learning, integrating Masked Autoencoders and contrastive learning. This approach extracts domain-invariant representations from unlabeled simulated imagery to enhance robustness against occlusion while reducing annotation dependency. Leveraging these learned features, we then introduce a 3D Transformer fusion module that unifies multi-view RGB and LiDAR point clouds through cross-modal attention. By explicitly modeling spatial layouts and height differentials, this component significantly improves recognition of small and occluded targets in complex low-altitude environments. To address persistent fine-grained domain shifts, we finally design region-level adversarial calibration that deploys local discriminators on partitioned feature maps. This mechanism directly aligns texture, shadow, and illumination discrepancies which challenge conventional global alignment methods. Extensive experiments on UAV benchmarks VisDrone and DOTA demonstrate the effectiveness of RA3T. The framework achieves +5.1% mAP on VisDrone and +7.4% mAP on DOTA over the 2D adversarial baseline, particularly on small objects and sparse occlusions, while maintaining real-time performance of 17 FPS at 1024 × 1024 resolution on an RTX 4080 GPU. Visual analysis confirms that the synergistic integration of 3D geometric encoding and local adversarial alignment effectively mitigates domain gaps caused by uneven illumination and perspective variations, establishing an efficient pathway for simulation-to-reality UAV perception. Full article

Farmers face increasing pressure to maintain vital populations of the critically endangered field hamster (Cricetus cricetus) while managing crop damage caused by field mice. This challenge is linked to the UN Sustainable Development Goals (SDGs) 2 and 15, addressing food security and biodiversity. Consequently, the reliable detection of hamster activity in agricultural fields is essential. While remote sensing offers potential for wildlife monitoring, commonly used RGB imagery has limitations in detecting small burrow entrances in vegetated areas. This study investigates the potential of drone-based Light Detection and Ranging (LiDAR) data for identifying field hamster burrow entrances in agricultural landscapes. A geostatistical method was developed to detect local elevation minima as indicators of burrow openings. The analysis used four datasets captured at varying flight altitudes and spatial resolutions. The method successfully detected up to 20 out of 23 known burrow entrances and achieved an F1-score of 0.83 for the best-performing dataset. Detection was most accurate at flight altitudes of 30 m or lower, with performance decreasing at higher altitudes due to reduced point density. These findings demonstrate the potential of UAV-based LiDAR to support non-invasive species monitoring and habitat management in agricultural systems, contributing to sustainable conservation practices in line with the SDGs. Full article

Camera-centric perception has matured into a cornerstone of modern autonomy, from self-driving cars and factory cobots to underwater and planetary exploration. This review synthesizes more than a decade of progress in vision-based robotic navigation through an engineering lens, charting the full pipeline from sensing to deployment. We first examine the expanding sensor palette—monocular and multi-camera rigs, stereo and RGB-D devices, LiDAR–camera hybrids, event cameras, and infrared systems—highlighting the complementary operating envelopes and the rise of learning-based depth inference. The advances in visual localization and mapping are then analyzed, contrasting sparse and dense SLAM approaches, as well as monocular, stereo, and visual–inertial formulations. Additional topics include loop closure, semantic mapping, and LiDAR–visual–inertial fusion, which enables drift-free operation in dynamic environments. Building on these foundations, we review the navigation and control strategies, spanning classical planning, reinforcement and imitation learning, hybrid topological–metric memories, and emerging visual language guidance. Application case studies—autonomous driving, industrial manipulation, autonomous underwater vehicles, planetary rovers, aerial drones, and humanoids—demonstrate how tailored sensor suites and algorithms meet domain-specific constraints. Finally, the future research trajectories are distilled: generative AI for synthetic training data and scene completion; high-density 3D perception with solid-state LiDAR and neural implicit representations; event-based vision for ultra-fast control; and human-centric autonomy in next-generation robots. By providing a unified taxonomy, a comparative analysis, and engineering guidelines, this review aims to inform researchers and practitioners designing robust, scalable, vision-driven robotic systems. Full article

This paper proposes a cluster-based flight path construction method for automated drone-assisted pear pollination systems in orchard environments. The approach uses RGB-D (Red-Green-Blue-Depth) sensing through an observation drone equipped with RGB and depth cameras to detect blooming pear flowers. Flower detection is performed using a YOLO (You Only Look Once)-based object detection algorithm, and three-dimensional flower positions are estimated by integrating depth information with the drone’s positional and orientation data in the east-north-up coordinate system. To enhance pollination efficiency, the method applies the OPTICS (Ordering Points To Identify the Clustering Structure) algorithm to group detected flowers based on spatial proximity that correspond to branch-level distributions. The cluster centroids then construct a collision-free flight path, with offset vectors ensuring safe navigation and appropriate nozzle orientation for effective pollen spraying. Field experiments conducted using RTK-GNSS-based flight control confirmed the accuracy and stability of generated flight trajectories. The drone hovered in front of each flower cluster and performed uniform spraying along the planned path. The method achieved a fruit set rate of 62.1%, exceeding natural pollination at 53.6% and compared to the 61.9% of manual pollination. These results demonstrate the effectiveness and practicability of the method for real-world deployment in pear orchards. Full article

Object detection is essential for precision agriculture applications like automated plant counting, but the minimum dataset requirements for effective model deployment remain poorly understood for arable crop seedling detection on orthomosaics. This study investigated how much annotated data is required to achieve standard counting accuracy (R² = 0.85) for maize seedlings across different object detection approaches. We systematically evaluated traditional deep learning models requiring many training examples (YOLOv5, YOLOv8, YOLO11, RT-DETR), newer approaches requiring few examples (CD-ViTO), and methods requiring zero labeled examples (OWLv2) using drone-captured orthomosaic RGB imagery. We also implemented a handcrafted computer graphics algorithm as baseline. Models were tested with varying training sources (in-domain vs. out-of-distribution data), training dataset sizes (10–150 images), and annotation quality levels (10–100%). Our results demonstrate that no model trained on out-of-distribution data achieved acceptable performance, regardless of dataset size. In contrast, models trained on in-domain data reached the benchmark with as few as 60–130 annotated images, depending on architecture. Transformer-based models (RT-DETR) required significantly fewer samples (60) than CNN-based models (110–130), though they showed different tolerances to annotation quality reduction. Models maintained acceptable performance with only 65–90% of original annotation quality. Despite recent advances, neither few-shot nor zero-shot approaches met minimum performance requirements for precision agriculture deployment. These findings provide practical guidance for developing maize seedling detection systems, demonstrating that successful deployment requires in-domain training data, with minimum dataset requirements varying by model architecture. Full article