Search Results (98)

The accurate monitoring of waterbird abundance and their habitat preferences is essential for effective ecological management and conservation planning in aquatic ecosystems. This study explores the efficacy of unmanned aerial vehicle (UAV)-based high-resolution orthomosaics for waterbird monitoring and mapping along the Lieve Canal, Belgium. We systematically classified habitats into residential, industrial, riparian tree, and herbaceous vegetation zones, examining their influence on the spatial distribution of three focal waterbird species: Eurasian coot (Fulica atra), common moorhen (Gallinula chloropus), and wild duck (Anas platyrhynchos). Herbaceous vegetation zones consistently supported the highest waterbird densities, attributed to abundant nesting substrates and minimal human disturbance. UAV-based waterbird counts correlated strongly with ground-based surveys (R² = 0.668), though species-specific detectability varied significantly due to morphological visibility and ecological behaviors. Detection accuracy was highest for coots, intermediate for ducks, and lowest for moorhens, highlighting the crucial role of image resolution ground sampling distance (GSD) in aerial monitoring. Operational challenges, including image occlusion and habitat complexity, underline the need for tailored survey protocols and advanced sensing techniques. Our findings demonstrate that UAV imagery provides a reliable and scalable method for monitoring waterbird habitats, offering critical insights for biodiversity conservation and sustainable management practices in aquatic landscapes. Full article

Structural cracks can critically undermine infrastructure integrity, driving the need for precise, scalable inspection methods beyond conventional visual or 2D image-based approaches. This study presents an automated system integrating photogrammetric 3D reconstruction with deep learning to quantify crack dimensions in a spatial context. Multiple images are processed via Agisoft Metashape to generate high-fidelity 3D meshes. Then, a subset of images are automatically selected based on camera orientation and distance, and a deep learning algorithm is applied to detect cracks in 2D images. The detected crack edges are projected onto a 3D mesh, enabling width measurements grounded in the structure’s true geometry rather than perspective-distorted 2D approximations. This methodology addresses the key limitations of traditional methods (parallax, occlusion, and surface curvature errors) and shows how these limitations can be mitigated by spatially anchoring measurements to the 3D model. Laboratory validation confirms the system’s robustness, with controlled tests highlighting the importance of near-orthogonal camera angles and ground sample distance (GSD) thresholds to ensure crack detectability. By synthesizing photogrammetry and a convolutional neural network (CNN), the framework eliminates subjectivity in inspections, enhances safety by reducing manual intervention, and provides engineers with dimensionally accurate data for maintenance decisions. Full article

Extraction of dense 3D geographic information from ultra-high-resolution unmanned aerial vehicle (UAV) imagery unlocks a great number of mapping and monitoring applications. This is facilitated by a step called dense image matching, which tries to find pixels corresponding to the same object within overlapping images captured by the UAV from different locations. Recent developments in deep learning utilize deep convolutional networks to perform this dense pixel correspondence task. A common theme in these developments is to train the network in a supervised setting using available dense 3D reference datasets. However, in this work we propose a novel unsupervised dense point cloud extraction routine for UAV imagery, called UnDER. We propose a novel disparity-shifting procedure to enable the use of a stereo matching network pretrained on an entirely different typology of image data in the disparity-estimation step of UnDER. Unlike previously proposed disparity-shifting techniques for forming cost volumes, the goal of our procedure was to address the domain shift between the images that the network was pretrained on and the UAV images, by using prior information from the UAV image acquisition. We also developed a procedure for occlusion masking based on disparity consistency checking that uses the disparity image space rather than the object space proposed in a standard 3D reconstruction routine for UAV data. Our benchmarking results demonstrated significant improvements in quantitative performance, reducing the mean cloud-to-cloud distance by approximately 1.8 times the ground sampling distance (GSD) compared to other methods. Full article

Coastal litter is a severe environmental issue impacting marine ecosystems and coastal communities in Thailand, with plastic pollution posing one of the most urgent challenges. Every month, millions of tons of plastic waste enter the ocean, where items such as bottles, cans, and other plastics can take hundreds of years to degrade, threatening marine life through ingestion, entanglement, and habitat destruction. To address this issue, we deploy drones equipped with high-resolution cameras and sensors to capture detailed coastal imagery for assessing litter distribution. This study presents the development of an AI-driven coastal litter detection system using edge computing and 5G communication networks. The AI edge server utilizes YOLOv8 and a recurrent neural network (RNN) to enable the drone to detect and classify various types of litter, such as bottles, cans, and plastics, in real-time. High-speed 5G communication supports seamless data transmission, allowing efficient monitoring. We evaluated drone performance under optimal flying heights above ground of 5 m, 7 m, and 10 m, analyzing accuracy, precision, recall, and F1-score. Results indicate that the system achieves optimal detection at an altitude of 5 m with a ground sampling distance (GSD) of 0.98 cm/pixel, yielding an F1-score of 98% for cans, 96% for plastics, and 95% for bottles. This approach facilitates real-time monitoring of coastal areas, contributing to marine ecosystem conservation and environmental sustainability. Full article

Silvicultural operations such as planting, pruning, and thinning are vital for the forest value chain, requiring efficient monitoring to prevent value loss. While effective, traditional field plots are time-consuming, costly, spatially limited, and rely on assumptions that they adequately represent a wider area. Alternatively, unmanned aerial vehicles (UAVs) can cover large areas while keeping operators safe from hazards including steep terrain. Despite their utility, optimal flight parameters to ensure flight efficiency and data quality remain under-researched. This study evaluated the impact of forward and side overlap and flight altitude on the quality of two- and three-dimensional spatial data products from UAV photogrammetry (UAV-SfM) for assessing stand density in a recently thinned Pinus radiata D. Don plantation. A contemporaneously acquired UAV laser scanner (ULS) point cloud provided reference data. The results indicate that the optimal UAV-SfM flight parameters are 90% forward and 85% side overlap at a 120 m altitude. Flights at an 80 m altitude offered marginal resolution improvement (2.2 cm compared to 3.2 cm ground sample distance/GSD) but took longer and were more error-prone. Individual tree detection (ITD) for stand density assessment was then applied to both UAV-SfM and ULS canopy height models (CHMs). Manual cleaning of the detected ULS tree peaks provided ground truth for both methods. UAV-SfM had a lower recall (0.85 vs. 0.94) but a higher precision (0.97 vs. 0.95) compared to ULS. Overall, the F-score indicated no significant difference between a prosumer-grade photogrammetric UAV and an industrial-grade ULS for stand density assessments, demonstrating the efficacy of affordable, off-the-shelf UAV technology for forest managers. Furthermore, in addressing the knowledge gap regarding optimal UAV flight parameters for conducting operational forestry assessments, this study provides valuable insights into the importance of side overlap for orthomosaic quality in forest environments. Full article

Jimson weed (Datura stramonium L.) is a toxic weed that is occasionally found in fields with common bean (Phaseolus vulgaris L.) for the processing industry. Common bean growers are required to manually remove toxic weeds. If toxic weed plants remain, the standing crop will be rejected. Hence, the implementation of an automatic weed detection system aiding the farmers is badly needed. The overall goal of this study was to investigate if D. stramonium can be located in common bean fields using an unmanned aerial vehicle (UAV)-based ten-band multispectral camera. Therefore four objectives were defined: (I) assessing the spectral discriminative capacity between common bean and D. stramonium by the development and application of logistic regression models; (II) examining the influence of ground sampling distance (GSD) on model performance; and improving model generalization by (III) incorporating the use of vegetation indices and cumulative distribution function (CDF) matching and by (IV) combining spectral data from multiple common bean fields with the use of leave-one-group-out cross-validation (LOGO CV). Logistic regression models were created using data from fields at four different locations in Belgium. Based on the results, it was concluded that common bean and D. stramonium are separable based on multispectral information. A model trained and tested on the data of one location obtained a validation true positive rate and true negative rate of 99% and 95%, respectively. In this study, where D. stramonium had a mean plant size of 0.038 m² ($\sigma$ = 0.020), a GSD of 2.1 cm was found to be appropriate. However, the results proved to be location dependent as the model was not able to reliably distinguish D. stramonium in two other datasets. Finally, the use of a LOGO CV obtained the best results. Although small D. stramonium plants were still systematically overlooked and classified as common bean, the model was capable of detecting large D. stramonium plants on three of the four fields. This study emphasizes the variability in reflectance data among different common bean fields and the importance of an independent dataset to test model generalization. Full article

Civil infrastructure systems cover large land areas and need frequent inspections to maintain their public service capabilities. Conventional approaches of manual surveys or vehicle-based automated surveys to assess infrastructure conditions are often labor-intensive and time-consuming. For this reason, it is worthwhile to explore more cost-effective methods for monitoring and maintaining these infrastructures. Fortunately, recent advancements in satellite systems and image processing algorithms have opened up new possibilities. Numerous satellite systems have been employed to monitor infrastructure conditions and identify damages. Due to the improvement in the ground sample distance (GSD), the level of detail that can be captured has significantly increased. Taking advantage of these technological advancements, this research evaluated pavement conditions using deep learning models for analyzing satellite images. We gathered over 3000 satellite images of pavement sections, together with pavement evaluation ratings from the TxDOT’s PMIS database. The results of our study show an accuracy rate exceeding 90%. This research paves the way for a rapid and cost-effective approach for evaluating the pavement network in the future. Full article

Low-altitude aerial photogrammetry can be an alternative source of forest inventory data and a practical tool for rapid forest attribute updates. The availability of low-cost unmanned aerial systems (UASs) and continuous technological advances in terms of their flight duration and automation capabilities makes these solutions interesting tools for supporting various forest management needs. However, any practical application requires a priori empirical validation and optimization steps, especially if it is to be used under different forest conditions. This study investigates the influence of the main flight parameters, i.e., ground sampling distance and photo overlap, on the performance of individual tree detection (ITD) stand-level forest inventories, based on photogrammetric data obtained from budget unmanned aerial systems. The investigated sites represented the most common forest conditions in the Polish lowlands. The results showed no direct influence of the investigated factors on growing stock volume predictions within the analyzed range, i.e., overlap from 80 × 80 to 90 × 90% and GSD from 2 to 6 cm. However, we found that the tree detection ratio had an influence on estimation errors, which ranged from 0.6 to 15.3%. The estimates were generally coherent across repeated flights and were not susceptible to the weather conditions encountered. The study demonstrates the suitability of the ITD method for small-area forest inventories using photogrammetric UAV data, as well as its potential optimization for larger-scale surveys. Full article

For the purpose of achieving long-range, high-resolution, and ultra-wide-swath airborne earth imaging at extremely low-light levels (0.01 Lux), a low-light imaging system built on multi-detector optical butting was researched. Having decomposed the system’s specifications and verified its low-light imaging capability, we proposed to employ an optical system with a large relative aperture and low distortion and achieve imaging through the field-of-view (FOV) butting facilitated by eight 1080P high-sensitivity scientific complementary metal-oxide semiconductor (SCMOS) detectors. This paper elaborates on the design concept of the mechanical configuration of the imaging system; studies the calculation method of the structural parameters of the reflection prism; provides mathematical expressions for geometric parameters, such as the length and width of the splicing prism; and designs in detail the splicing structure of six reflection prisms for eight-channel beam splitting. Based on the design and computational results, a high-resolution, wide-swath imaging system for an ambient illuminance of 0.01 Lux was developed. Exhibiting a ground sampling distance (GSD) of 0.5 m (at a flight height of 5 km), this low-light imaging system keeps the FOV overlap ratio between adjacent detectors below 3% and boasts an effective image resolution of 4222 × 3782. The results from flight testing revealed that the proposed imaging system is capable of generating wide-swath, high-contrast resolution imagery under airborne and low-light conditions. As such, the way the system is prepared can serve as a reference point for the development of airborne low-light imaging devices. Full article

With the popularity of solar energy in the electricity market, demand rises for data such as precise locations of solar panels for efficient energy planning and management. However, these data are not easily accessible; information such as precise locations sometimes does not exist. Furthermore, existing datasets for training semantic segmentation models of photovoltaic (PV) installations are limited, and their annotation is time-consuming and labor-intensive. Therefore, for additional remote sensing (RS) data creation, the pix2pix generative adversarial network (GAN) is used, enriching the original resampled training data of varying ground sampling distances (GSDs) without compromising their integrity. Experiments with the DeepLabV3 model, ResNet-50 backbone, and pix2pix GAN architecture were conducted to discover the advantage of using GAN-based data augmentations for a more accurate RS imagery segmentation model. The result is a fine-tuned solar panel semantic segmentation model, trained using transfer learning and an optimal amount—60% of GAN-generated RS imagery for additional training data. The findings demonstrate the benefits of using GAN-generated images as additional training data, addressing the issue of limited datasets, and increasing IoU and F1 metrics by 2% and 1.46%, respectively, compared with classic augmentations. Full article

Corn (Zea mays L.) is the most abundant food/feed crop, making accurate yield estimation a critical data point for monitoring global food production. Sensors with varying spatial/spectral configurations have been used to develop corn yield models from intra-field (0.1 m ground sample distance (GSD)) to regional scales (>250 m GSD). Understanding the spatial and spectral dependencies of these models is imperative to result interpretation, scaling, and deploying models. We leveraged high spatial resolution hyperspectral data collected with an unmanned aerial system mounted sensor (272 spectral bands from 0.4–1 μm at 0.063 m GSD) to estimate silage yield. We subjected our imagery to three band selection algorithms to quantitatively assess spectral reflectance features applicability to yield estimation. We then derived 11 spectral configurations, which were spatially resampled to multiple GSDs, and applied to a support vector regression (SVR) yield estimation model. Results indicate that accuracy degrades above 4 m GSD across all configurations, and a seven-band multispectral sensor which samples the red edge and multiple near-infrared bands resulted in higher accuracy in 90% of regression trials. These results bode well for our quest toward a definitive sensor definition for global corn yield modeling, with only temporal dependencies requiring additional investigation. Full article

Improving urban mobility, especially pedestrian mobility, is a current challenge in virtually every city worldwide. To calculate the least-cost paths and safer, more efficient routes, it is necessary to understand the geometry of streets and their various elements accurately. In this study, we propose a semi-automatic methodology to assess the capacity of urban spaces to enable adequate pedestrian mobility. We employ various data sources, but primarily point clouds obtained through a mobile laser scanner (MLS), which provide a wealth of highly detailed information about the geometry of street elements. Our method allows us to characterize preferred pedestrian-traffic zones by segmenting crosswalks, delineating sidewalks, and identifying obstacles and impediments to walking in urban routes. Subsequently, we generate different displacement cost surfaces and identify the least-cost origin–destination paths. All these factors enable a detailed pedestrian mobility analysis, yielding results on a raster with a ground sampling distance (GSD) of 10 cm/pix. The method is validated through its application in a case study analyzing pedestrian mobility around an educational center in a purely urban area of A Coruña (Galicia, Spain). The segmentation model successfully identified all pedestrian crossings in the study area without false positives. Additionally, obstacle segmentation effectively identified urban elements and parked vehicles, providing crucial information to generate precise friction surfaces reflecting real environmental conditions. Furthermore, the generation of cumulative displacement cost surfaces allowed for identifying optimal routes for pedestrian movement, considering the presence of obstacles and the availability of traversable spaces. These surfaces provided a detailed representation of pedestrian mobility, highlighting significant variations in travel times, especially in areas with high obstacle density, where differences of up to 15% were observed. These results underscore the importance of considering obstacles’ existence and location when planning pedestrian routes, which can significantly influence travel times and route selection. We consider the capability to generate accurate cumulative cost surfaces to be a significant advantage, as it enables urban planners and local authorities to make informed decisions regarding the improvement of pedestrian infrastructure. Full article

Arnica montana L. is a medicinal plant with significant conservation importance. It is crucial to monitor this species, ensuring its sustainable harvesting and management. The aim of this study is to develop a practical system that can effectively detect A. montana inflorescences utilizing unmanned aerial vehicles (UAVs) with RGB sensors (red–green–blue, visible light) to improve the monitoring of A. montana habitats during the harvest season. From a methodological point of view, a model was developed based on a convolutional neural network (CNN) ResNet101 architecture. The trained model offers quantitative and qualitative assessments of A. montana inflorescences detected in semi-natural grasslands using low-resolution imagery, with a correctable error rate. The developed prototype is applicable in monitoring a larger area in a short time by flying at a higher altitude, implicitly capturing lower-resolution images. Despite the challenges posed by shadow effects, fluctuating ground sampling distance (GSD), and overlapping vegetation, this approach revealed encouraging outcomes, particularly when the GSD value was less than 0.45 cm. This research highlights the importance of low-resolution image clarity, on the training data by the phenophase, and of the need for training across different photoperiods to enhance model flexibility. This innovative approach provides guidelines for mission planning in support of reaching sustainable management goals. The robustness of the model can be attributed to the fact that it has been trained with real-world imagery of semi-natural grassland, making it practical for fieldwork with accessible portable devices. This study confirms the potential of ResNet CNN models to transfer learning to new plant communities, contributing to the broader effort of using high-resolution RGB sensors, UAVs, and machine-learning technologies for sustainable management and biodiversity conservation. Full article

In the last decade, many aerial photographic archives have started to be digitized for multiple purposes, including digital preservation and geoprocessing. This paper analyzes the effects of professional photogrammetric versus consumer-grade scanners on the processing of analog historical aerial photographs. An image block over Warsaw is considered, featuring 38 photographs acquired in 1986 (Wild RC10, Normal Aviogon II lens, 23 × 23 cm format) with a ground sampling distance (GSD) of 4 cm. Aerial triangulation (AT) and dense image matching (DIM) procedures are considered, analyzing how scanning modalities are important in the massive digitization of analog images for georeferencing and 3D product generation. The achieved results show how consumer-grade scanners, unlike more expensive photogrammetric scanners, do not possess adequate recording quality to ensure high accuracy and geometric precision for geoprocessing purposes. However, consumer-grade scanners can be used for time and cost-efficient applications where a partial loss of data quality is not critical. Full article

Understanding the demographic structure is vital for wildlife research and conservation. For crocodylians, accurately estimating total length and demographic class usually necessitates close observation or capture, often of partially immersed individuals, leading to potential imprecision and risk. Drone technology offers a bias-free, safer alternative for classification. We evaluated the effectiveness of drone photos combined with head length allometric relationships to estimate total length, and propose a standardized method for drone-based crocodylian demographic classification. We evaluated error sources related to drone flight parameters using standardized targets. An allometric framework correlating head to total length for 17 crocodylian species was developed, incorporating confidence intervals to account for imprecision sources (e.g., allometric accuracy, head inclination, observer bias, terrain variability). This method was applied to wild crocodylians through drone photography. Target measurements from drone imagery, across various resolutions and sizes, were consistent with their actual dimensions. Terrain effects were less impactful than Ground-Sample Distance (GSD) errors from photogrammetric software. The allometric framework predicted lengths within ≃11–18% accuracy across species, with natural allometric variation among individuals explaining much of this range. Compared to traditional methods that can be subjective and risky, our drone-based approach is objective, efficient, fast, cheap, non-invasive, and safe. Nonetheless, further refinements are needed to extend survey times and better include smaller size classes. Full article