Most airborne and terrestrial laser scanning systems additionally record the received signal intensity for each measurement. Multiple studies show the potential of this intensity value for a great ...variety of applications (e.g. strip adjustment, forestry, glaciology), but also state problems if using the original recorded values. Three main factors, a) spherical loss, b) topographic and c) atmospheric effects, influence the backscatter of the emitted laser power, which leads to a noticeably heterogeneous representation of the received power. This paper describes two different methods for correcting the laser scanning intensity data for these known influences resulting in a value proportional to the reflectance of the scanned surface. The first approach – data-driven correction – uses predefined homogeneous areas to empirically estimate the best parameters (least-squares adjustment) for a given global correction function accounting for all range-dependent influences. The second approach – model-driven correction – corrects each intensity independently based on the physical principle of radar systems. The evaluation of both methods, based on homogeneous reflecting areas acquired at different heights in different missions, indicates a clear reduction of intensity variation, to 1/3.5 of the original variation, and offsets between flight strips to 1/10. The presented correction methods establish a great potential for laser scanning intensity to be used for surface classification and multi-temporal analyses.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK
Three dimensional city models are necessary for supporting numerous management applications. For the determination of city models for visualization purposes, several standardized workflows do exist. ...They are either based on photogrammetry or on LiDAR or on a combination of both data acquisition techniques. However, the automated determination of reliable and highly accurate city models is still a challenging task, requiring a workflow comprising several processing steps. The most relevant are building detection, building outline generation, building modeling, and finally, building quality analysis. Commercial software tools for building modeling require, generally, a high degree of human interaction and most automated approaches described in literature stress the steps of such a workflow individually. In this article, we propose a comprehensive approach for automated determination of 3D city models from airborne acquired point cloud data. It is based on the assumption that individual buildings can be modeled properly by a composition of a set of planar faces. Hence, it is based on a reliable 3D segmentation algorithm, detecting planar faces in a point cloud. This segmentation is of crucial importance for the outline detection and for the modeling approach. We describe the theoretical background, the segmentation algorithm, the outline detection, and the modeling approach, and we present and discuss several actual projects.
This paper suggests a new approach for change detection (CD) in 3D point clouds. It combines classification and CD in one step using machine learning. The point cloud data of both epochs are merged ...for computing features of four types: features describing the point distribution, a feature relating to relative terrain elevation, features specific for the multi-target capability of laser scanning, and features combining the point clouds of both epochs to identify the change. All these features are merged in the points and then training samples are acquired to create the model for supervised classification, which is then applied to the whole study area. The final results reach an overall accuracy of over 90% for both epochs of eight classes: lost tree, new tree, lost building, new building, changed ground, unchanged building, unchanged tree, and unchanged ground.
Airborne LiDAR Bathymetry (ALB) has been rapidly evolving in recent years and now allows fluvial topography to be mapped in high resolution (>20 points/m2) and height accuracy (<10 cm) for both the ...aquatic and the riparian area. This article presents methods for enhanced modeling and monitoring of instream meso- and microhabitats based on multitemporal data acquisition. This is demonstrated for a near natural reach of the Pielach River, with data acquired from April 2013 to October 2014, covering two flood events. In comparison with topographic laser scanning, ALB requires a number of specific processing steps. We present, firstly, a novel approach for modeling the water surface in the case of sparse water surface echoes and, secondly, a strategy for improved filtering and modeling of the Digital Terrain Model of the Watercourse (DTM-W). Based on the multitemporal DTM-W we discuss the massive changes of the fluvial topography exhibiting deposition/erosion of 103 m3 caused by the 30-years flood event in May 2014. Furthermore, for the first time, such a high-resolution data source is used for monitoring of hydro-morphological units (mesohabitat scale) including the consequences for the target fish species nase (Chondrostoma nasus, microhabitat scale). The flood events caused a spatial displacement of the hydro-morphological units but did not effect their overall frequency distribution, which is considered an important habitat feature as it documents resilience against disturbances.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
In this article, we propose a method for instance segmentation of individual grains from a terrestrial laser scanning point cloud representing a mountain river bed. The method was designed as a ...classification followed by a segmentation approach. The binary classification into either points representing river bed or grains is performed using the random forest algorithm. The point cloud is classified based only on geometrical features calculated for a local, spherical neighborhood. A multisize neighborhood approach was used together with the feature selection method that is based on correlation analysis. The final classification was performed using a set of features calculated for the neighborhood size of 5, 15, and 20 cm. The achieved classification results have the overall accuracy of 85-95%, depending on the test site. The segmentation is performed using the density-based spatial clustering of applications with noise algorithm in order to cluster the point cloud based on Euclidean distances between points. The performed experiments showed that the proposed method enables us to correctly delineate 67-88% of grains, depending on the test site. However, the resulting point cloud based completeness expressed as Jaccard index is similar for each of the test sites and is approximately 88%. Moreover, the proposed method proved that it is robust to the shadowing effect.
The success achieved by deep learning techniques in image labeling has triggered a growing interest in applying deep learning for three-dimensional point cloud classification. To provide better ...insights into different deep learning architectures and their applications to ALS point cloud classification, this article presents a comprehensive comparison among three state-of-the-art deep learning networks: PointNet++, SparseCNN, and KPConv, on two different ALS datasets. The performances of these three deep learning networks are compared w.r.t. classification accuracy, computation time, generalization ability as well as the sensitivity to the choices of hyper-parameters. Overall, we observed that PointNet++, SparseCNN, and KPConv all outperform Random Forest on the classification results. Moreover, SparseCNN leads to a slightly better classification result compared to PointNet++ and KPConv, while requiring less computation time and memory. At the same time, it shows a better ability to generalize and is less impacted by the different choices of hyper-parameters.
The last two decades have witnessed increasing awareness of the potential of terrestrial laser scanning (TLS) in forest applications in both public and commercial sectors, along with tremendous ...research efforts and progress. It is time to inspect the achievements of and the remaining barriers to TLS-based forest investigations, so further research and application are clearly orientated in operational uses of TLS. In such context, the international TLS benchmarking project was launched in 2014 by the European Spatial Data Research Organization and coordinated by the Finnish Geospatial Research Institute. The main objectives of this benchmarking study are to evaluate the potential of applying TLS in characterizing forests, to clarify the strengths and the weaknesses of TLS as a measure of forest digitization, and to reveal the capability of recent algorithms for tree-attribute extraction. The project is designed to benchmark the TLS algorithms by processing identical TLS datasets for a standardized set of forest attribute criteria and by evaluating the results through a common procedure respecting reliable references. Benchmarking results reflect large variances in estimating accuracies, which were unveiled through the 18 compared algorithms and through the evaluation framework, i.e., forest complexity categories, TLS data acquisition approaches, tree attributes and evaluation procedures. The evaluation framework includes three new criteria proposed in this benchmarking and the algorithm performances are investigated through combining two or more criteria (e.g., the accuracy of the individual tree attributes are inspected in conjunction with plot-level completeness) in order to reveal algorithms’ overall performance. The results also reveal some best available forest attribute estimates at this time, which clarify the status quo of TLS-based forest investigations. Some results are well expected, while some are new, e.g., the variances of estimating accuracies between single-/multi-scan, the principle of the algorithm designs and the possibility of a computer outperforming human operation. With single-scan data, i.e., one hemispherical scan per plot, most of the recent algorithms are capable of achieving stem detection with approximately 75% completeness and 90% correctness in the easy forest stands (easy plots: 600 stems/ha, 20 cm mean DBH). The detection rate decreases when the stem density increases and the average DBH decreases, i.e., 60% completeness with 90% correctness (medium plots: 1000 stem/ha, 15 cm mean DBH) and 30% completeness with 90% correctness (difficult plots: 2000 stems/ha, 10 cm mean DBH). The application of the multi-scan approach, i.e., five scans per plot at the center and four quadrant angles, is more effective in complex stands, increasing the completeness to approximately 90% for medium plots and to approximately 70% for difficult plots, with almost 100% correctness. The results of this benchmarking also show that the TLS-based approaches can provide the estimates of the DBH and the stem curve at a 1–2 cm accuracy that are close to what is required in practical applications, e.g., national forest inventories (NFIs). In terms of algorithm development, a high level of automation is a commonly shared standard, but a bottleneck occurs at stem detection and tree height estimation, especially in multilayer and dense forest stands. The greatest challenge is that even with the multi-scan approach, it is still hard to completely and accurately record stems of all trees in a plot due to the occlusion effects of the trees and bushes in forests. Future development must address the redundant yet incomplete point clouds of forest sample plots and recognize trees more accurately and efficiently. It is worth noting that TLS currently provides the best quality terrestrial point clouds in comparison with all other technologies, meaning that all the benchmarks labeled in this paper can also serve as a reference for other terrestrial point clouds sources.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK
High-resolution stereo and multi-view imagery are used for digital surface model (DSM) derivation over large areas for numerous applications in topography, cartography, geomorphology, and 3D surface ...modelling. Dense image matching is a key component in 3D reconstruction and mapping, although the 3D reconstruction process encounters difficulties for water surfaces, areas with no texture or with a repetitive pattern appearance in the images, and for very small objects. This study investigates the capabilities and limitations of space-borne very high resolution imagery, specifically Pléiades (0.70 m) and WorldView-3 (0.31 m) imagery, with respect to the automatic point cloud reconstruction of small isolated objects. For this purpose, single buildings, vehicles, and trees were analyzed. The main focus is to quantify their detectability in the photogrammetrically-derived DSMs by estimating their heights as a function of object type and size. The estimated height was investigated with respect to the following parameters: building length and width, vehicle length and width, and tree crown diameter. Manually measured object heights from the oriented images were used as a reference. We demonstrate that the DSM-based estimated height of a single object strongly depends on its size, and we quantify this effect. Starting from very small objects, which are not elevated against their surroundings, and ending with large objects, we obtained a gradual increase of the relative heights. For small vehicles, buildings, and trees (lengths <7 pixels, crown diameters <4 pixels), the Pléiades-derived DSM showed less than 20% or none of the actual object's height. For large vehicles, buildings, and trees (lengths >14 pixels, crown diameters >7 pixels), the estimated heights were higher than 60% of the real values. In the case of the WorldView-3 derived DSM, the estimated height of small vehicles, buildings, and trees (lengths <16 pixels, crown diameters <8 pixels) was less than 50% of their actual height, whereas larger objects (lengths >33 pixels, crown diameters >16 pixels) were reconstructed at more than 90% in height.
Recent advances in 3D laser scanner technology have provided a large amount of accurate geo-information as point clouds. The methods of machine vision and photogrammetry are used in various ...applications such as medicine, environmental studies, and cultural heritage. Aerial laser scanners (ALS), terrestrial laser scanners (TLS), mobile mapping laser scanners (MLS), and photogrammetric cameras via image matching are the most important tools for producing point clouds. In most applications, the process of point cloud registration is considered to be a fundamental issue. Due to the high volume of initial point cloud data, 3D keypoint detection has been introduced as an important step in the registration of point clouds. In this step, the initial volume of point clouds is converted into a set of candidate points with high information content. Many methods for 3D keypoint detection have been proposed in machine vision, and most of them were based on thresholding the saliency of points, but less attention had been paid to the spatial distribution and number of extracted points. This poses a challenge in the registration process when dealing with point clouds with a homogeneous structure. As keypoints are selected in areas of structural complexity, it leads to an unbalanced distribution of keypoints and a lower registration quality. This research presents an automated approach for 3D keypoint detection to control the quality, spatial distribution, and the number of keypoints. The proposed method generates a quality criterion by combining 3D local shape features, 3D local self-similarity, and the histogram of normal orientation and provides a competency index. In addition, the Octree structure is applied to control the spatial distribution of the detected 3D keypoints. The proposed method was evaluated for the keypoint-based coarse registration of aerial laser scanner and terrestrial laser scanner data, having both cluttered and homogeneous regions. The obtained results demonstrate the proper performance of the proposed method in the registration of these types of data, and in comparison to the standard algorithms, the registration error was diminished by up to 56%.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
In this study, eight airborne laser scanning (ALS)-based single tree detection methods are benchmarked and investigated. The methods were applied to a unique dataset originating from different ...regions of the Alpine Space covering different study areas, forest types, and structures. This is the first benchmark ever performed for different forests within the Alps. The evaluation of the detection results was carried out in a reproducible way by automatically matching them to precise in situ forest inventory data using a restricted nearest neighbor detection approach. Quantitative statistical parameters such as percentages of correctly matched trees and omission and commission errors are presented. The proposed automated matching procedure presented herein shows an overall accuracy of 97%. Method based analysis, investigations per forest type, and an overall benchmark performance are presented. The best matching rate was obtained for single-layered coniferous forests. Dominated trees were challenging for all methods. The overall performance shows a matching rate of 47%, which is comparable to results of other benchmarks performed in the past. The study provides new insight regarding the potential and limits of tree detection with ALS and underlines some key aspects regarding the choice of method when performing single tree detection for the various forest types encountered in alpine regions.