Search Results (216)

Effective semantic segmentation of Airborne Laser Scanning (ALS) point clouds is a crucial field of study and influences subsequent point cloud application tasks. Transformer networks have made significant progress in 2D/3D computer vision tasks, exhibiting superior performance. We propose a multilevel geometric feature embedding transformer network (MGFE-T), which aims to fully utilize the three-dimensional structural information carried by point clouds and enhance transformer performance in ALS point cloud semantic segmentation. In the encoding stage, compute the geometric features surrounding tee sampling points at each layer and embed them into the transformer workflow. To ensure that the receptive field of the self-attention mechanism and the geometric computation domain can maintain a consistent scale at each layer, we propose a fixed-radius dilated KNN (FR-DKNN) search method to address the limitation of traditional KNN search methods in considering domain radius. In the decoding stage, we aggregate prediction deviations at each level into a unified loss value, enabling multilevel supervision to improve the network’s feature learning ability at different levels. The MGFE-T network can predict the class label of each point in an end-to-end manner. Experiments were conducted on three widely used benchmark datasets. The results indicate that the MGFE-T network achieves superior OA and mF1 scores on the LASDU and DFC2019 datasets and performs well on the ISPRS dataset with imbalanced classes. Full article

Canopy volume is a crucial biological parameter for assessing tree growth, accurately estimating forest Above-Ground Biomass (AGB), and evaluating ecosystem stability. Airborne Laser Scanning (ALS) and Terrestrial Laser Scanning (TLS) are advanced precision mapping technologies that capture highly accurate point clouds for forest digitization studies. Despite advances in calculating canopy volume, challenges remain in accurately extracting the canopy and removing gaps. This study proposes a canopy volume extraction method based on an improved PointNeXt model, fusing ALS and TLS point cloud data. In this work, improved PointNeXt is first utilized to extract the canopy, enhancing extraction accuracy and mitigating under-segmentation and over-segmentation issues. To effectively calculate canopy volume, the canopy is divided into multiple levels, each projected into the xOy plane. Then, an improved Mean Shift algorithm, combined with KdTree, is employed to remove gaps and obtain parts of the real canopy. Subsequently, a convex hull algorithm is utilized to calculate the area of each part, and the sum of the areas of all parts multiplied by their heights yields the canopy volume. The proposed method’s performance is tested on a dataset comprising poplar, willow, and cherry trees. As a result, the improved PointNeXt model achieves a mean intersection over union (mIoU) of 98.19% on the test set, outperforming the original PointNeXt by 1%. Regarding canopy volume, the algorithm’s Root Mean Square Error (RMSE) is 0.18 m³, and a high correlation is observed between predicted canopy volumes, with an R-Square (R²) value of 0.92. Therefore, the proposed method effectively and efficiently acquires canopy volume, providing a stable and accurate technical reference for forest biomass statistics. Full article

Extracting moso bamboo parameters from single-source point cloud data has limitations. In this article, a new approach for extracting moso bamboo parameters using airborne laser scanning (ALS) and terrestrial laser scanning (TLS) point cloud data is proposed. Using the field-surveyed coordinates of plot corner points and the Iterative Closest Point (ICP) algorithm, the ALS and TLS point clouds were aligned. Considering the difference in point distribution of ALS, TLS, and the merged point cloud, individual bamboo plants were segmented from the ALS point cloud using the point cloud segmentation (PCS) algorithm, and individual bamboo plants were segmented from the TLS and the merged point cloud using the comparative shortest-path (CSP) method. The cylinder fitting method was used to estimate the diameter at breast height (DBH) of the segmented bamboo plants. The accuracy was calculated by comparing the bamboo parameter values extracted by the above methods with reference data in three sample plots. The comparison results showed that by using the merged data, the detection rate of moso bamboo plants could reach up to 97.30%; the R² of the estimated bamboo height was increased to above 0.96, and the root mean square error (RMSE) decreased from 1.14 m at most to a range of 0.35–0.48 m, while the R² of the DBH fit was increased to a range of 0.97–0.99, and the RMSE decreased from 0.004 m at most to a range of 0.001–0.003 m. The accuracy of moso bamboo parameter extraction was significantly improved by using the merged point cloud data. Full article

Light Detection and Ranging systems serve as robust tools for creating three-dimensional representations of the Earth’s surface. These representations are known as point clouds. Point cloud scene segmentation is essential in a range of applications aimed at understanding the environment, such as infrastructure planning and monitoring. However, automating this process can result in notable challenges due to variable point density across scenes, ambiguous object shapes, and substantial class imbalances. Consequently, manual intervention remains prevalent in point classification, allowing researchers to address these complexities. In this work, we study the elements contributing to the automatic semantic segmentation process with deep learning, conducting empirical evaluations on a self-captured dataset by a hybrid airborne laser scanning sensor combined with two nadir cameras in RGB and near-infrared over a 247 km² terrain characterized by hilly topography, urban areas, and dense forest cover. Our findings emphasize the importance of employing appropriate training and inference strategies to achieve accurate classification of data points across all categories. The proposed methodology not only facilitates the segmentation of varying size point clouds but also yields a significant performance improvement compared to preceding methodologies, achieving a mIoU of 94.24% on our self-captured dataset. Full article

This work is inscribed into a more comprehensive project related to the architectural requalification and restoration of Frinco Castle, one of the most significant fortified medieval structures in the Monferrato area (province of Asti, Italy), that experienced a structural collapse. In particular, this manuscript focuses on data fusion of multi-sensor acquisitions of metric surveys for 3D documenting this structural-risky building. The structural collapse made the entire south front fragile. The metric survey was performed by using terrestrial and aerial sensors to reach every area of the building. Topographically oriented Terrestrial Laser Scans (TLS) data were collected for the exterior and interior of the building, along with the DJI Zenmuse L1 Airborne Laser Scans (ALS) and Zenmuse P1 Photogrammetric Point Cloud (APC). First, the internal alignment in the TLS data set was verified, followed by the intra-technique alignments, choosing TLS as the reference data set. The point clouds from each sensor were analyzed by computing voxel-based point density and roughness, then segmented, aligned, and fused. 3D acquisitions and segmentation processes were fundamental for having a complete and structured dataset of almost every outdoor and indoor area of the castle. The collected metrics data was the starting point for the modeling phase to prepare 2D and 3D outputs fundamental for the restoration process. Full article

The quantification of tree-related microhabitats (TreMs) and multi-taxon biodiversity is pivotal to the implementation of forest conservation policies, which are crucial under the current climate change scenarios. We assessed the capacity of Airborne Laser Scanning (ALS) data to quantify biodiversity indices related to both forest beetle and bird communities and TreMs, calculating the species richness and types of saproxylic and epixylic TreMs using the Shannon index. As biodiversity predictors, 240 ALS-derived metrics were calculated: 214 were point-cloud based, 14 were pixel-level from the canopy height model, and 12 were RGB spectral statistics. We used the random forests algorithm to predict species richness and the Shannon diversity index, using the field plot measures as dependent variables and the ALS-derived metrics as predictors for each taxon and TreMs type. The final models were used to produce wall-to-wall maps of biodiversity indices. The Shannon index produced the best performance for each group considered, with a mean difference of −6.7%. Likewise, the highest R² was for the Shannon index (0.17, against 0.14 for richness). Our results confirm the importance of ALS data in assessing forest biodiversity indicators that are relevant for monitoring forest habitats. The proposed method supports the quantification and monitoring of the measures needed to implement better forest stands and multi-taxon biodiversity conservation. Full article

Timely acquisition of forest structure is crucial for understanding the dynamics of ecosystem functions. Despite the fact that the combination of different quantitative structure models (QSMs) and point cloud sources (ALS and DAP) has shown great potential to characterize tree structure, few studies have addressed their pros and cons in alpine temperate deciduous forests. In this study, different point clouds from UAV-mounted LiDAR and DAP under leaf-off conditions were first processed into individual tree point clouds, and then explicit 3D tree models of the forest were reconstructed using the TreeQSM and AdQSM methods. Structural metrics obtained from the two QSMs were evaluated based on terrestrial LiDAR (TLS)-based surveys. The results showed that ALS-based predictions of forest structure outperformed DAP-based predictions at both plot and tree levels. TreeQSM performed with comparable accuracy to AdQSM for estimating tree height, regardless of ALS (plot level: 0.93 vs. 0.94; tree level: 0.92 vs. 0.92) and DAP (plot level: 0.86 vs. 0.86; tree level: 0.89 vs. 0.90) point clouds. These results provide a robust and efficient workflow that takes advantage of UAV monitoring for estimating forest structural metrics and suggest the effectiveness of LiDAR in temperate deciduous forests. Full article

The effective development of digital twins of real-world objects requires sophisticated data collection techniques and algorithms for the automated modeling of individual objects. In City Information Modeling (CIM) systems, individual buildings can be modeled automatically at the second Level of Detail or LOD2. Similarly, for Tree Information Modeling (TIM) and building Forest Digital Twins (FDT), automated solutions for the 3D modeling of individual trees at different levels of detail are required. The existing algorithms support the automated modeling of trees by generating models of the canopy and the lower part of the trunk. Our argument for this work is that the structure of tree trunk and branches is as important as canopy shape. As such, the aim of the research is to develop an algorithm for automatically modeling tree trunks based on data from point clouds obtained through laser scanning. Aiming to generate 3D models of tree trunks, the suggested approach starts with extracting the trunk point cloud, which is then segmented into single stems. Subsets of point clouds, representing individual branches, are measured using Airborne Laser Scanning (ALS) and Terrestrial Laser Scanning (TLS). Trunks and branches are generated by fitting cylinders to the layered subsets of the point cloud. The individual stems are modeled by a structure of slices. The accuracy of the model is calculated by determining the fitness of cylinders to the point cloud. Despite the huge variation in trunk geometric forms, the proposed modeling approach can gain an accuracy of better than 4 cm in the constructed tree trunk models. As the developed tree models are represented in a matrix format, the solution enables automatic comparisons of tree elements over time, which is necessary for monitoring changes in forest stands. Due to the existence of large variations in tree trunk geometry, the performance of the proposed modeling approach deserves further investigation on its generality to other types of trees in multiple areas. Full article

In this work, we investigate the effect of dissolved gas concentration on cavitation inception and cavitation development in a transparent sharp-edged orifice, similar to that previously analyzed by Nurick in the context of liquid injectors. The working liquid is water, and carbon dioxide is employed as a non-condensable dissolved gas. Cavitation inception points are determined for different dissolved gas concentration levels by measuring wall-static pressures just downstream of the orifice contraction and visually observing the onset of a localized (vapor) bubble cloud formation and collapse. Cavitation onset correlates with a plateau in wall-static pressure measurements as a function of a cavitation number. An increase in the amount of dissolved carbon dioxide is found to increase the cavitation number at which the onset of cavitation occurs. The transition from cloud cavitation to extended-sheet or full cavitation along the entire orifice length occurs suddenly and is shifted to higher cavitation numbers with increasing dissolved gas content. Volume flow rate measurements are performed to determine the change in the discharge coefficient with the cavitation number and dissolved gas content for the investigated cases. CFD analyses are carried out based on the cavitation model by Zwart et al. and the model by Yang et al. to account for non-condensable gases. Discharge coefficients obtained from the numerical simulations are in good agreement with experimental values, although they are slightly higher in the cavitating case. The earlier onset of fluid cavitation (i.e., cavitation inception at higher cavitation numbers) with increasing dissolved carbon dioxide content is not predicted using the employed numerical model. Full article

Deep Neural Network (DNN)-based point cloud semantic segmentation has presented significant breakthrough using large-scale labeled aerial laser point cloud datasets. However, annotating such large-scaled point clouds is time-consuming. Self-Supervised Learning (SSL) is a promising approach to this problem by pre-training a DNN model utilizing unlabeled samples followed by a fine-tuned downstream task involving very limited labels. The traditional contrastive learning for point clouds selects the hardest negative samples by solely relying on the distance between the embedded features derived from the learning process, potentially evolving some negative samples from the same classes to reduce the contrastive learning effectiveness. This work proposes a hard-negative sample-aware self-supervised contrastive learning algorithm to pre-train the model for semantic segmentation. We designed a k-means clustering-based Absolute Positive And Negative samples (AbsPAN) strategy to filter the possible false-negative samples. Experiments on two typical ALS benchmark datasets demonstrate that the proposed method is more appealing than supervised training schemes without pre-training. Especially when the labels are severely inadequate (10% of the ISPRS training set), the results obtained by the proposed HAVANA method still exceed 94% of the supervised paradigm performance with full training set. Full article

The alpine environment with a high degree of nature protection is characterized by complete non-intervention. The processes and phenomena occurring in it are exclusively of a natural origin. Related geohazards are threatening the safety of people’s movement. They arise as a result of a combination of meteorological, hydrological, and geological–morphological factors permanently operating in the country. Therefore, the prevention of fatal events is limited to monitoring and predicting changes in selected objects where we expect change. Changes in the shape and dimension, or the object’s deformation, can be documented using geodetic and photogrammetric measurements. Our research focuses on monitoring a rock talus cone in High Tatras, Slovakia, at an altitude of 1700 m above sea level (ASL), created mainly due to erosion and seasonal torrential rains. To monitor changes in selected objects, we used mass non-contact methods of terrestrial laser scanning (TLS), UAS photogrammetry based on the principle of structure-from-motion–multi-view stereo (SfM–MVS), and airborne laser scanning (ALS). From the selective measurement methods, spatial measurement by a total station (TS) and height measurement based on the principle of precise leveling were used in the monitoring deformation network on a stand-alone boulder. The research results so far analyze and evaluate the possibilities, limits, effectiveness, and accuracy of the measurement and data processing methods used. As a result, we propose a complex methodology for monitoring similar phenomena in alpine environments. Full article

Airborne Laser Scanning (ALS) point cloud classification in ground and non-ground points can be accurately performed using various algorithms, which rely on a range of information, including signal analysis, intensity, amplitude, echo width, and return number, often focusing on the last return. With its high point density and the vast majority of points (approximately 99%) measured with the first return, filtering LiDAR-UAS data proves to be a more challenging task when compared to ALS point clouds. Various algorithms have been proposed in the scientific literature to differentiate ground points from non-ground points. Each of these algorithms has advantages and disadvantages, depending on the specific terrain characteristics. The aim of this research is to obtain an enhanced Digital Terrain Model (DTM) based on LiDAR-UAS data and to qualitatively and quantitatively compare three filtering approaches, i.e., hierarchical robust, volume-based, and cloth simulation, on a complex terrain study area. For this purpose, two flights over a residential area of about 7.2 ha were taken at 60 m and 100 m, with a DJI Matrice 300 RTK UAS, equipped with a Geosun GS-130X LiDAR sensor. The vertical and horizontal accuracy of the LiDAR-UAS point cloud, obtained via PPK trajectory processing, was tested using Check Points (ChPs) and manually extracted features. A combined approach for ground point classification is proposed, using the results from a hierarchic robust filter and applying an 80% slope condition for the volume-based filtering result. The proposed method has the advantage of representing with accuracy man-made structures and sudden slope changes, improving the overall accuracy of the DTMs by 40% with respect to the hierarchical robust filtering algorithm in the case of a 60 m flight height and by 28% in the case of a 100 m flight height when validated against 985 ChPs. Full article

During the leaching process of ion-adsorbed rare earth ores, large amounts of non-rare earth impurities such as aluminum and iron will be generated. This study selected glutamic acid as a complex agent to selectively calculate aluminum ions; then, added non-ionic surfactants and extract and separate aluminum ions from a rare earth solution using the cloud point extraction method. The effects of solution pH, reaction temperature, equilibration time, amount of glutamic acid, reaction time, and amount of Triton X-114 on aluminum extraction were investigated. The results showed that with a M_glu:M_Al ratio of 3:1, a solution pH of 4.5, a constant temperature of 40 °C, and the addition of 10 mL Triton X-114 after 10 min of reaction time, the single extraction efficiency of aluminum ions reached 78.01%, and the extraction efficiency of rare earths was only 5.09% after 10 min of equilibration time. The reaction equation of glutamic acid with aluminum ions was determined, and the lowest extraction concentration of aluminum ions in the glutamic acid complexation extraction solution was found to be c_Al = 0.045 ± 0.003 g/L, with a separation coefficient of β(Al/RE) = 66.15. This result indicated that the aluminum ions in the mixed solution could be effectively separated from the rare earth ions when using glutamic acid as a complexing agent in combination with the turbidity point extraction method. Full article

Nonrigid registration presents a significant challenge in the domain of point cloud processing. The general objective is to model complex nonrigid deformations between two or more overlapping point clouds. Applications are diverse and span multiple research fields, including registration of topographic data, scene flow estimation, and dynamic shape reconstruction. To provide context, the first part of the paper gives a general introduction to the topic of point cloud registration, including a categorization of existing methods. Then, a general mathematical formulation for the point cloud registration problem is introduced, which is then extended to address also nonrigid registration methods. A detailed discussion and categorization of existing approaches to nonrigid registration follows. In the second part of the paper, we propose a new method that uses piecewise tricubic polynomials for modeling nonrigid deformations. Our method offers several advantages over existing methods. These advantages include easy control of flexibility through a small number of intuitive tuning parameters, a closed-form optimization solution, and an efficient transformation of huge point clouds. We demonstrate our method through multiple examples that cover a broad range of applications, with a focus on remote sensing applications—namely, the registration of airborne laser scanning (ALS), mobile laser scanning (MLS), and terrestrial laser scanning (TLS) point clouds. The implementation of our algorithms is open source and can be found our public repository. Full article

As important geospatial data, point cloud collected from an aerial laser scanner (ALS) provides three-dimensional (3D) information for the study of the distribution of typical urban land cover, which is critical in the construction of a “digital city”. However, existing point cloud classification methods usually use a single machine learning classifier that experiences uncertainty in making decisions for fuzzy samples in confusing areas. This limits the improvement of classification accuracy. To take full advantage of different classifiers and reduce uncertainty, we propose a classification method based on possibility theory and multi-classifier fusion. Firstly, the feature importance measure was performed by the XGBoost algorithm to construct a feature space, and two commonly used support vector machines (SVMs) were the chosen base classifiers. Then, classification results from the two base classifiers were quantitatively evaluated to define the confusing areas in classification. Finally, the confidence degree of each classifier for different categories was calculated by the confusion matrix and normalized to obtain the weights. Then, we synthesize different classifiers based on possibility theory to achieve more accurate classification in the confusion areas. DALES datasets were utilized to assess the proposed method. The results reveal that the proposed method can significantly improve classification accuracy in confusing areas. Full article