Search

At the present time, many publicly available point cloud datasets exist, which are mainly focused on autonomous driving. The objective of this study is to develop a new large-scale mobile 3D LiDAR point cloud dataset for outdoor scene semantic segmentation tasks, which has a classification scheme suitable for geospatial applications. Our dataset (Saint Petersburg 3D) contains both real-world (34 million points) and synthetic (34 million points) subsets that were acquired using real and virtual sensors with the same characteristics. An original classification scheme is proposed that contains a set of 10 universal object categories into which any scene represented by dense outdoor mobile LiDAR point clouds can be divided. The evaluation procedure for semantic segmentation of point clouds for geospatial applications is described. An experiment with the Kernel Point Fully Convolution Neural Network model trained on the proposed dataset was carried out. We obtained an overall 92.56% mIoU, which demonstrates the high efficiency of using deep learning models for point cloud semantic segmentation for geospatial applications in accordance with the proposed classification scheme.

Glavni cilj magistrske naloge je bila raziskava obdelave in združevanja oblakov točk mobilnega (MLS) in aerolaserskega skeniranja (ALS). Z združevanjem oblakov MLS in ALS dobimo večje število informacij o skeniranem okolju in se izognemo določenim pomanjkljivostim vsakega od sistemov. Združen oblak točk pokriva celotno skenirano površje razen atrijev, ki jih z nobenim od sistemov ne moremo doseči. Najprej smo raziskali različne možnosti registracije oblakov točk MLS v programu Terrasolid in na testnem območju na osnovi odstopanj na kontrolnih točkah določili najboljši postopek. Oblaku točk MLS smo nato dodali oblak točk ALS in dobili združen oblak točk. Za avtomatsko modeliranje stavb iz združenega oblaka točk MLS in ALS na trgu nismo našli ustreznega programa, zato smo v programu Terrasolid na avtomatski način izdelali modele stavb le iz oblaka točk ALS. Nato smo na primeru izbrane kompleksnejše stavbe iz združenega oblaka točk ročno izdelali njen model, ki smo ga z vidika natančnosti in podrobnosti primerjali z avtomatsko izdelanim modelom. Na koncu v obliki razprave povzamemo težave pri zajemu in obdelavi podatkov, združevanju oblakov točk MLS in ALS ter modeliranju stavb. The main goal of the master's thesis was to research the processing and merging of point clouds from mobile (MLS) and airborne laser scanning (ALS). By merging MLS and ALS point clouds, we obtain more information about the scanned environment and avoid certain limitations of each system. The merged point cloud covers the entire scanned surface except for atriums, which cannot be reached by either of the systems. Initially, we explored various options for registration of MLS point clouds in the Terrasolid software and determined the best process based on deviations at control points in a test area. We then added ALS point clouds to the MLS point cloud to obtain the merged point cloud. We did not find an appropriate program for automatic building modeling from the merged MLS and ALS point cloud on the market, so we used Terrasolid to automatically create building models only from the ALS point cloud. We manually created the model of a selected complex building from the merged point cloud and compared its accuracy and detail with the automatically created model. Finally, in the form of a discussion, we summarized the problems with data acquisition and processing, merging MLS and ALS point clouds, and building modeling.

Funding Information: We gratefully acknowledge the Henry Ford Foundation for the grant “Towards Automatic Mapping of Road Environment for Civil and Other Engineering Applications Using Autonomous Big Data”, the Academy of Finland, who supported this research through several grants, including “Forest-Human-Machine Interplay—Building Resilience, Redefining Value Networks and Enabling Meaningful Experiences (337656)”, “Feasibility of Inside-Canopy UAV Laser Scanning for Automated Tree Quality Surveying” (334002), “Autonomous Driving on Snow-Covered Terrain” (318437), and “Lidar-based energy efficient ICT solutions” (319011), and the Ministry of Agriculture and Forestry for the research grant “Future forest information system at individual tree level” (VN/3482/2021). Publisher Copyright: © 2023 by the authors. The continuous flow of autonomous vehicle-based data could revolutionize current map updating procedures and allow completely new types of mapping applications. Therefore, in this article, we demonstrate the feasibility of using perception data of autonomous vehicles to replace traditionally conducted mobile mapping surveys with a case study focusing on updating a register of roadside city trees. In our experiment, we drove along a 1.3-km-long road in Helsinki to collect laser scanner data using our autonomous car platform ARVO, which is based on a Ford Mondeo hybrid passenger vehicle equipped with a Velodyne VLS-128 Alpha Prime scanner and other high-grade sensors for autonomous perception. For comparison, laser scanner data from the same region were also collected with a specially-planned high-grade mobile mapping laser scanning system. Based on our results, the diameter at breast height, one of the key parameters of city tree registers, could be estimated with a lower root-mean-square error from the perception data of the autonomous car than from the specially-planned mobile laser scanning survey, provided that time-based filtering was included in the post-processing of the autonomous perception data to mitigate distortions in the obtained point cloud. Therefore, appropriately performed post-processing of the autonomous perception data can be regarded as a viable option for keeping maps updated in road environments. However, point cloud-processing algorithms may need to be adapted for the post-processing of autonomous perception data due to the differences in the sensors and their arrangements compared to designated mobile mapping systems. We also emphasize that time-based filtering may be required in the post-processing of autonomous perception data due to point cloud distortions around objects seen at multiple times. This highlights the importance of saving the time stamp for each data point in the autonomous perception data or saving the temporal order of the data points.

The use of drones to explore indoor spaces has gained attention and popularity for disaster management and indoor navigation applications. In this paper we present the operations and mapping techniques of two drones that are different in terms of size, the sensors deployed, and the positioning and mapping techniques used. The first drone is a low-cost commercial quadcopter microdrone, a Crazyflie, while the second drone is a relatively expensive research quadcopter macrodrone, called MAX. We investigated their feasibility in mapping areas where satellite positioning is not available, such as indoor spaces. We compared the point clouds obtained by a multi-ranger deck, a multi-layer LIDAR scanner and a stereo camera, and assessed each against ground truth obtained with a terrestrial laser scanner. Results showed that both drones are capable of mapping relatively cluttered indoor environments and can provide point clouds that are sufficient for a quick exploration. Furthermore, the LIDAR scanner-based system can handle a relatively large office environment with an accumulated drift less than 0.02% (1 cm) on the Z-axis and 0.77% (50 cm) on the X and Y axes over a length trajectory of about 65 m. Despite the limited features of the sensor configuration of the Crazyflie, its performance is promising for mapping indoor spaces, given the relatively low deviation from the ground truth: cloud-to-cloud distances measured were generally less than 20 cm.

Convergence and rockmass failure are significant hazards to personnel and physical assets in underground tunnels, caverns, and mines. Mobile Laser Scanning Systems (MLS) can deliver large volumes of point cloud data at a high frequency and on a large scale. However, current change detection approaches do not deliver sufficient sensitivity and precision for real-time performance on large-scale datasets. We present a novel, octree-based computational framework for intra-voxel statistical inference change detection and deformation analysis. Our approach exploits high-density MLS data to test for statistical significance for appearing objects caused by rockfall and for low-magnitude deformations, such as convergence. In field tests, our method detects rock falls with side lengths as small as 0.03 m and convergence as low as 0.01 m, or 0.5% wall-to-wall strain. When compared against a state-of-the-art multi-scale model-to-model cloud comparison (M3C2)-based method, ours is less sensitive to noisy data and parameter selection while also requiring fewer parameters. Most notably, our method is the only one tested that can perform real-time change detection on large-scale datasets on a single processor thread. Our method achieves a computational improvement of 50 times over single-threaded M3C2 while maintaining a performance scalability that is four times greater with dataset size. Our framework shows significant potential to enable accurate real-time geotechnical monitoring of large-scale underground spaces.

The use of mobile laser scanning to survey forest ecosystems is a promising, scalable technology to describe the 3D structure of forests at a high resolution. We use a structurally complex, mixed-species Mediterranean forest to test the performance of a mobile Handheld Laser Scanning (HLS) system to estimate tree attributes within a forest patch in central Spain. We describe the different stages of the HLS approach: field position, ground data collection, scanning path design, point cloud processing, alignment between detected trees and measured reference trees, and finally, the assessment of main tree structural attributes diameter at breast height (DBH) and tree height considering species and tree size as control factors. We surveyed 418 reference trees to account for omission and commission error rates over a 1 ha plot divided into 16 sections and scanned using two different scanning paths. The HLS-based approach reached a high of 88 and 92% tree detection rate for the best combination of scanning path and point cloud processing modes for the HLS system. The root mean squared errors for DBH estimates varied between species: errors for Pinus pinaster were below 2 cm for Scan 02. Quercus pyrenaica, and Alnus glutinosa showed higher error rates. We observed good agreement between ALS and HLS estimates for tree height, highlighting differences to field measurements. Despite the complexity of the mixed forest area surveyed, our results show that HLS is highly efficient at detecting tree locations, estimating DBH, and supporting tree height measurements as confirmed with airborne laser data used for validation. This study is one of the first HLS-based studies conducted in the Mediterranean mixed forest region, where variability in tree allometries and spacing and the presence of natural regeneration pose challenges for the HLS approach. HLS is a feasible, time-efficient, scalable technology for tree mapping in mixed forests with potential to support forest monitoring programmes such as national forest inventories lacking three-dimensional, remote sensing data to support field measurements.

[EN] The detection of deformations on man-made structures such as bridges and dams are an essential task in engineering geodesy. The classical method uncovering deformations is based on geodetic networks using measurements from total stations or GNSS receivers. Another new approach is the determination of deformations based on terrestrial laser scans leading to large-scale deformation results by point cloud comparisons. In the field of geodetic engineering, mobile laser scanning systems are increasingly used for high-resolution point cloud generation in short measurement times, which leads to the idea to use these for deformation analysis. A crucial part of this measurement strategy is the estimation of the trajectory (position and orientation) of the scanner, which allows a consistent registration of the single scan lines in a global coordinate system (georeferencing). The largest limitation to the accuracy of the resulting point cloud is the accuracy of the estimated trajectory. In most applications, the estimation of position and orientation are based on the fusion of GNSS (Global Navigation Satellite System) and IMU (Inertial Measurement Unit) measurements. Systematic errors, as they often appear in GNSS measurements, are directly transferred to the georeferenced point cloud and therefor limit the potential for deformation analysis. With this paper we address the questions, if the trajectory estimation can be improved by the integration of known landmarks into the trajectory estimation procedure. Using a point cloud generated with an initial GNSS/IMU based trajectory, landmark targets can be observed in the point cloud and integrated into an updated estimate, using a factor graph-based approach. For the evaluation of a potential accuracy increase due to landmark observations, we performed measurements, comparing GNSS/IMU based results with the ones where landmarks are additionally integrated. The experiments show, that the accuracy increases especially in the heading angle, which is reflected in lower residuals to observed reference coordinates, but also in the trajectory covariances of the estimation results., Funding: This work was funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany’s Excellence Strategy–EXC 2070–390732324.

The Mobile Laser Scanning (MLS) data inevitably includes dynamic objects because there are always other vehicles (e.g., other cars, motorbikes, bikes, etc.) moving in the area near the MLS data collection vehicle on the road. These dynamic objects need to be removed in advance for many point cloud applications. This paper designs an efficient and memory-friendly data frame aware optimized Octomap-based dynamic object detection and removal method for MLS data. Firstly, the input MLS data is split into multiple data frames based on the timestamp. Each data frame is inserted into a separate Octomap with part of its neighbouring data frames. A statistics-based method is applied to each data frame to find the passable voxel cell space (free space) in Octomap and all points in the free space are extracted as free points. Second, the region of interest (ROI) related to the dynamic object is delineated to retain free points related to dynamic objects. Then the free-point rate and the multi-return rate are calculated to further remove noise and vegetation points from free points. Finally, the fixed radius search is used to extract dynamic objects from the filtered free points. The proposed method is tested in four case sites in Delft, the Netherlands. Results show that 84.98% of dynamic objects are detected and extracted correctly. The proposed method is 18.27% more efficient on average than the original Octomap method, can be further accelerated by parallel computing, and only needs 39.40% of the maximum memory consumption.

A mobile laser scanning (MLS) system equipped with a lidar, inertial navigation system and satellite positioning can be used to reconstruct georeferenced point-based models of the surveyed environments. Ideal reconstruction requires accurate trajectories that are challenging to obtain in forests. Satellite signals are heavily degraded under the forest canopy, while lidar-based positioning is often inefficient due to the forest’s unstructured and complex nature. Most forestry-related solutions compute or improve the trajectory in post-processing, focusing on accuracy rather than the possibility of real-time operation. On the other hand, real-time solutions exist, but they are primarily tested and evaluated in urban environments, and the forest’s effect on them is less known. In this study, high-quality, real-time point-based forest model generation was considered by applying techniques from the field of robotics. Forest data were collected with an MLS system mounted 1) on a stick carried by a person and 2) mounted on a forest harvester while performing thinning operations. The system’s trajectory was computed using lidar-inertial-based smoothing and mapping algorithms with real-time limitations. In addition, satellite measurements were either fused into the smoothing algorithm contributing to the trajectory estimation or were used to georeference the trajectory in a post-processing manner. Collecting reliable reference trajectories is difficult in forests. Therefore, this study mainly contains qualitative and relative evaluation. The results indicate that real-time and onboard processing is feasible for forest data with adequate accuracy. State-of-the-art edge and planar feature-based lidar odometry was the most accurate but could not fully maintain real-time operation. On the other hand, the normal distributions transform-based odometry can maintain fast and constant computation with slightly lower accuracy. Fusing the satellite positioning for the mapping reduced the internal integrity of the reconstructed point cloud models, and it is suggested to use it for post-processed georeferencing instead. Ett mobilt laserskanningssystem (MLS) utrustat med ett lidar, tröghetsnavigeringssystem och satellitpositionering kan användas för att rekonstruera georefererade punktbaserade modeller av de undersökta miljöerna. Idealisk återuppbyggnad kräver exakta banor som är utmanande att uppnå i skogar. Satellitsignaler är kraftigt försämrade under skogens tak, medan lidarbaserad positionering ofta är ineffektiv på grund av skogens ostrukturerade och komplexa natur. De flesta skogsbruksrelaterade lösningar beräknar eller förbättrar banan i efterbearbetning, med fokus på noggrannhet snarare än möjligheten till drift i realtid. Å andra sidan finns realtidslösningar, men de är främst testade och utvärderade i stadsmiljöer och skogens påverkan på dem är mindre känd. I denna studie övervägdes högkvalitativ, punktbaserad skogsmodellgenerering i realtid genom att tillämpa tekniker från robotteknikområdet. Skogsdata samlades in med ett MLS-system monterat 1) på en pinne som bärs av en person och 2) monterad på en skogsskördare under gallringsoperationer. Systemets bana beräknades med hjälp av lidar-tröghetsbaserade utjämnings- och kartläggningsalgoritmer med realtidsbegränsningar. Dessutom fuserades satellitmätningar antingen in i utjämningsalgoritmen som bidrog till banuppskattningen eller användes för att georeferera banan på ett efterbearbetningssätt. Att samla pålitliga referensbanor är svårt i skogar. Därför innehåller denna studie främst kvalitativ och relativ utvärdering. Resultaten indikerar att bearbetning i realtid och ombord är möjlig för skogsdata med tillräcklig noggrannhet. Toppmodern kant- och planfunktionsbaserad lidarodometri var den mest exakta men kunde inte helt upprätthålla realtidsdrift. Å andra sidan kan normalfördelningstransformationsbaserad odometri upprätthålla snabb och konstant beräkning med något lägre noggrannhet. Att sammansmälta satellitpositioneringen för kartläggningen minskade den interna integriteten hos de rekonstruerade punktmolnmodellerna, och det föreslås att man istället använder den för efterbehandlad georeferens.

Gardens play a key role in the definition of the cultural landscape since they reflect the culture, identity, and history of a people. They also contribute to the ecological balance of the city. Despite the fact that gardens have an historic and social value, they are not protected as much as the rest of the existing heritage, such as architecture and archaeological sites. While methods of built-heritage mapping and monitoring are increasing and constantly improving to reduce built-heritage loss and the severe impact of natural disasters, the documentation and survey techniques for gardens are often antiquated. In addition, inventories are typically made by non-updated/updateable reports, and they are rarely in digital format or in 3D. This paper presents the results of a comprehensive study on the latest technology for laser scanning in gardens. We compared static terrestrial laser scanning and mobile laser scanning point clouds generated by the Focus 3D S120 and the Leica BLK2GO, respectively, to evaluate their quality for documentation, estimate tree attributes, and terrain morphology. The evaluation is based on visual observation, C2C comparisons, and terrain information extraction capabilities, i.e., M3C2 comparisons for topography, DTM generation, and contour lines. Both methods produced useful outcomes for the scope of the research within their limitations. Terrestrial laser scanning is still the method that offers accurate point clouds with a higher point density and less noise. However, the more recent mobile laser scanning is able to survey in less time, significantly reducing the costs for site activities, data post-production, and registration. Both methods have their own restrictions that are amplified by site features, mainly the lack of plans for the geometric alignment of scans and the simultaneous location and mapping (SLAM) process. We offer a critical description of the issues related to the functionality of the two sensors, such as the operative range limit, light dependency, scanning time, point cloud completeness and size, and noise level.

To reduce the cost of manually annotating training data for supervised classifiers, we propose an automated approach to extract training data of urban objects in six classes: buildings, fences, man-made poles, vegetation, vehicles, and low objects. In this study, two segmentation algorithms are firstly implemented to generate meaningful objects from the non-ground point cloud. Then, we generated valid strict rules to label partial RANSAC (Random Sample Consensus) planes and meaningful objects as training data. The strict rules are built upon the semantic knowledge formed by the features of geometric, eigenvalue, RANSAC plane, multidimensional slice, and relative location. The accuracy of strict rule-based (SRB) training data is higher than 98.5 % for buildings, man-made poles, vegetation, and vehicles. The accuracy of low objects and fences reaches 97.10 % and 94.99 %, respectively. Finally, we compared the performance of the KPConv and PointNET++ networks trained by SRB and manually labeled training data to evaluate the effectiveness of our training data. The KPConv overall accuracy using manually labeled and (SRB) training data are 91.5 % and 86.8 % in the Paris dataset, 95.6 % and 92.0 % in the Freiburg dataset, respectively. The experiments demonstrate that automatically labeled training data can achieve similar accuracy compared to manual labels when coupled with two deep learning networks. Therefore, SRB training data extraction can effectively deal with the problem of training data scarcity and provide significant advancements in urban point cloud classification, where manual labeling of training data remains a crucial challenge.

Tree species characterise biodiversity, health, economic potential, and resilience of an ecosystem, for example. Tree species classification based on remote sensing data, however, is known to be a challenging task. In this paper, we study for the first time the feasibility of tree species classification using high-density point clouds collected with an airborne close-range multispectral laser scanning system – a technique that has previously proved to be capable of providing stem curve and volume accurately and rapidly for standing trees. To this end, we carried out laser scanning measurements from a helicopter on 53 forest sample plots, each with a size of 32 m × 32 m. The plots covered approximately 5500 trees in total, including Scots pine (Pinus sylvestris L.), Norway spruce (Picea abies (L.) H.Karst.), and deciduous trees such as Downy birch (Betula pubescens Ehrh.) and Silverbirch (Betula pendula Roth). The multispectral laser scanning system consisted of integrated Riegl VUX-1HA, miniVUX-3UAV, and VQ-840-G scanners (Riegl GmbH, Austria) operating at wavelengths of 1550 nm, 905 nm, and 532 nm, respectively. A new approach, layer-by-layer segmentation, was developed for individual tree detection and segmentation from the dense point cloud data. After individual tree segmentation, 249 features were computed for tree species classification, which was tested with approximately 3000 trees. The features described the point cloud geometry as well as single-channel and multi-channel reflectance metrics. Both feature selection and the tree species classification were conducted using the random forest method. Using the layer-by-layer segmentation algorithm, trees in the dominant and co-dominant categories were found with detection rates of 89.5% and 77.9%, respectively, whereas suppressed trees were detected with a success rate of 15.2%–42.3%, clearly improving upon the standard watershed segmentation. The overall accuracy of the tree species classification was 73.1% when using geometric features from the 1550 nm scanner data and 86.6% when combining the geometric features with reflectance information of the 1550 nm data. The use of multispectral reflectance and geometric features improved the overall classification accuracy up to 90.8%. Classification accuracies were as high as 92.7% and 93.7% for dominant and co-dominant trees, respectively.

Quantifying off-fault deformation in the near field remains a challenge for earthquake monitoring using geodetic observations. We propose an automated change detection strategy using geometric primitives generated using a deep neural network, random sample consensus and least squares adjustment. Using mobile laser scanning point clouds of vineyards acquired after the magnitude 6.0 2014 South Napa earthquake, our results reveal centimeter-level horizontal ground deformation over three kilometers along a segment of the West Napa Fault. A fault trace is detected from rows of vineyards modeled as planar primitives from the accumulated coseismic response, and the postseismic surface displacement field is revealed by tracking displacements of vineyard posts modeled as cylindrical primitives. Interpreted from the detected changes, we summarized distributions of deformation versus off-fault distances and found evidence of off-fault deformation. The proposed framework using geometric primitives is shown to be accurate and practical for detection of near-field off-fault deformation.

The classification and extraction of street tree geometry information in road scenes is crucial in urban forest biomass statistics and road safety. To address the problem of 3D fine extraction of street trees in complex road scenes, this paper designs and investigates a method for extracting street tree geometry and forest parameters from vehicle-mounted LiDAR point clouds in road scenes based on a Gaussian distributed regional growth algorithm and Voronoi range constraints. Firstly, a large number of non-tree and other noise points, such as ground points, buildings, shrubs and vehicle points, are filtered by applying multi-geometric features; then, the main trunk of the street tree is extracted based on the vertical linear features of the tree and the region growth algorithm based on Gaussian distribution; secondly, a Voronoi polygon constraint is established to segment the single tree canopy region with the main trunk center of mass; finally, based on the extracted locations of the street trees and their 3D points, the tree growth parameters of individual trees are obtained for informative management and biomass estimation by combining geometric statistical methods. In this paper, the experimental data from vehicle-borne LiDAR point clouds of different typical areas were selected to verify that the proposed Gaussian-distributed regional growth algorithm can achieve fine classification and extraction of tree growth parameters for different types of roadside trees, with accuracy, recall and F1 values reaching 96.34%, 97.22% and 96.45%, respectively. This research method can be used for the extraction of 3D fine classification of street trees in complex road environments, which in turn can provide support for the safety management of traffic facilities and forest biomass estimation in urban environments.

Currently, the street tree resource survey using Mobile laser scanning (MLS) represents a hot spot around the world. Refined trunk extraction is an essential step for 3D reconstruction of street trees. However, due to scanning errors and the effects of occlusion by various types of features in the urban environment, street tree point cloud data processing has the problem of excessive noise. For the noise points that are difficult to remove using statistical methods in close proximity to the tree trunk, we propose an adaptive trunk extraction and denoising method for street trees based on an improved iForest (Isolation Forest) algorithm. Firstly, to extract the individual tree trunk points, the trunk and the crown are distinguished from the individual tree point cloud through point cloud slicing. Next, the iForest algorithm is improved by conducting automatic calculation of the contamination and further used to denoise the tree trunk point cloud. Finally, the method is validated with five datasets of different scenes. The results indicate that our method is robust and effective in extracting and denoising tree trunks. Compared with the traditional Statistical Outlier Removal (SOR) filter and Radius filter denoising methods, the denoising accuracy of the proposed method can be improved by approximately 30% for noise points close to tree trunks. Compared to iForest, the proposed method automatically calculates the contamination, improving the automation of the algorithm. Our method can provide more precise trunk point clouds for 3D reconstruction of street trees.

A mobile laser scanning (MLS) system can acquire railway scene information quickly and provide a data foundation for regular railway inspections. The location of the catenary support device in an electrified railway system has a direct impact on the regular operation of the power supply system. However, multi-type support device data accounts for a tiny proportion of the whole railway scene, resulting in its poor characteristic expression in the scene. Therefore, using traditional point cloud filtering or point cloud segmentation methods alone makes it difficult to achieve an effective segmentation and extraction of the support device. As a result, this paper proposes an automatic extraction algorithm for complex railway support devices based on MLS point clouds. First, the algorithm obtains hierarchies of the pillar point clouds and the support device point clouds in the railway scene through high stratification and then realizes the noise that was point-cloud-filtered in the scene. Then, the center point of the pillar device is retrieved from the pillar corridor by a neighborhood search, and then the locating and initial extracting of the support device are realized based on the relatively stable spatial topological relationship between the pillar and the support device. Finally, a post-processing optimization method integrating the pillar filter and the voxelized projection filter is designed to achieve the accurate and efficient extraction of the support device based on the feature differences between the support device and other devices in the initial extraction results. Furthermore, in the experimental part, we evaluate the treatment effect of the algorithm in six types of support devices, three types of support device distribution scenes, and two types of railway units. The experimental results show that the average extraction IoU of the multi-type support device, support device distribution scenes, and railway unit were 97.20%, 94.29%, and 96.11%, respectively. In general, the proposed algorithm can achieve the accurate and efficient extraction of various support devices in different scenes, and the influence of the algorithm parameters on the extraction accuracy and efficiency is elaborated in the discussion section.

Norway spruce (Picea abies (L.) H.Karst) trees planted with high stem densities produce finely branched, solid logs but are vulnerable to extreme weather events, e.g., storms. Over the last decades spruce stands have been planted at lower stand densities, resulting in wider crowns, lower crown bases, and higher stand stability, but this might decrease the quality of coniferous timber due to an increased growing rate and wider annual rings. Therefore, in this case study we investigated the influence of different silvicultural treatments and stand densities on tree morphology and wood properties of 100 spruce trees up to sawn timber as the final product. Tree morphology was assessed using mobile laser scanning. Ring width analysis, wood density measurements, and the four-point bending strength test on visually graded boards were conducted to gain information on wood properties and product quality. In stands thinned from below, higher wood densities were observed due to smaller annual rings compared to stands that were thinned from above at equal annual ring widths. In addition, crown asymmetry and the height-to-diameter ratio were identified as proxies for wood density. Lastly, visually assessed quality differences between the forest stands were discerned on the examined boards.

The traditional railway survey adopts a manual observation method, such as a total station measuring system. This method has high precision, but the amount of data is small, and the measurement efficiency is low. Manual measurement cannot meet the requirements of dynamic continuous high-precision holographic measurement during railway outages. Mobile laser scanning is a mobile mapping system based mainly on a laser scanner, inertial measurement unit (IMU) and panoramic camera. Mobile laser scanning has the advantages of high efficiency, high precision and automation. However, integrating inertial navigation data and mobile laser scanning data to obtain real 3D information about railways has always been an urgent problem to be solved. Therefore, a point cloud reconstruction method is proposed based on trajectory filtering for a mobile laser scanning system. This paper corrects the odometer data by identifying railway feature points through deep learning and uses Rauch–Tung–Striebel (RTS) filtering to optimize the trajectory results. Combined with the railway experimental track data, the maximum difference in the east and north coordinate direction can be controlled within 7 cm, and the average elevation error is 2.39 cm. This paper applies a multi-sensor integrated mobile detection system to railway detection. It is of great significance to the healthy development of the intelligent railway system.

Urban trees are vital elements of outdoor scenes via mobile laser scanning (MLS), accurate individual trees detection from disordered, discrete, and high-density MLS is an important basis for the subsequent analysis of city management and planning. However, trees cannot be easily extracted because of the occlusion with other objects in urban scenes. In this work, we propose a coarse-to-fine individual trees detection method from MLS point cloud data (PCD) based on treetop points extraction and radius expansion. Firstly, an improved semantic segmentation deep network based on PointNet is applied to segment tree points from the scanned urban scene, which combining spatial features and dimensional features. Next, through calculating the local maximum, the candidate treetop points are located. In addition, the optimized treetop points are extracted after the tree point projection plane was filtered to locate the candidate treetop points, and a distance rule is used to eliminate the pseudo treetop points then the optimized treetop points are obtained. Finally, after the initial clustering of treetop points and vertical layering of tree points, a top-down layer-by-layer segmentation based on radius expansion to realize the complete individual extraction of trees. The effectiveness of the proposed method is tested and evaluated on five street scenes in point clouds from Oakland outdoor MLS dataset. Furthermore, the proposed method is compared with two existing individual trees segmentation methods. Overall, the precision, recall, and F-score of instance segmentation are 98.33%, 98.33%, and 98.33%, respectively. The results indicate that our method can extract individual trees effectively and robustly in different complex environments.

3D building modeling is becoming an important support in civil engineering, architecture and cultural heritage applications. Despite static laser scanning can be considered as the state-of-the-art in such kind of applications, mobile mapping techniques can be considered as a suitable alternative to quickly gather geospatial information. Outdoor mobile mapping can be considered as a mature technique, which takes into advantage of the Global Navigation Satellite System (GNSS)-laser scanning information fusion. Instead, indoor mobile mapping is typically more challenging: the unavailability of GNSS makes the mapping system rely either just on the inertial navigation system, or on some control points. A drift in the navigation solution, and consequently in the 3D reconstruction, is typically visible after a while in the former case, whereas the use of other surveying instruments is required in the latter.This work aims at exploiting geometric characteristics of the buildings, such as symmetries and regularities, to reduce the drift effect in indoor mobile mapping, in particular when dealing with affordable systems. The proposed approach is based on the segmentation of the point clouds acquired with a time of flight camera (ToF), detecting in particular vertical planar surfaces. It is well known that aligning planar surfaces can be a viable way for reducing the drift in this kind of applications. Nevertheless, this paper aims also at investigating the use of geometric symmetries to such aim.The proposed approach is tested on a case study, a building of the University of Padova, whose reconstruction was produced by an ad hoc affordable mobile mapping system, integrating low cost inertial sensors, RGB and ToF camera.

Hand-held mobile laser scanning (HMLS) can quickly and effectively obtain tree point cloud data, which has great potential to conduct forest resource survey at the plot or stand scale. To improve t...

Applicability of SLAM (simultaneous localization and mapping) technology for mine surveys and subsequent 3D modelling of post-extracted surfaces is assessed. The resulting surface geometry is valid...

Background and Aims In addition to terrestrial laser scanning (TLS), mobile laser scanning (MLS) is increasingly arousing interest as a technique which provides valuable 3-D data for various applications in forest research. Using mobile platforms, the 3-D recording of large forest areas is carried out within a short space of time. Vegetation structure is described by millions of 3-D points which show an accuracy in the millimetre range and offer a powerful basis for automated vegetation modelling. The successful extraction of single trees from the point cloud is essential for further evaluations and modelling at the individual-tree level, such as volume determination, quantitative structure modelling or local neighbourhood analyses. However, high-precision automated tree segmentation is challenging, and has so far mostly been performed using elaborate interactive segmentation methods. Methods Here, we present a novel segmentation algorithm to automatically segment trees in MLS point clouds, applying distance adaptivity as a function of trajectory. In addition, tree parameters are determined simultaneously. In our validation study, we used a total of 825 trees from ten sample plots to compare the data of trees segmented from MLS data with manual inventory parameters and parameters derived from semi-automatic TLS segmentation. Key Results The tree detection rate reached 96 % on average for trees with distances up to 45 m from the trajectory. Trees were almost completely segmented up to a distance of about 30 m from the MLS trajectory. The accuracy of tree parameters was similar for MLS-segmented and TLS-segmented trees. Conclusions Besides plot characteristics, the detection rate of trees in MLS data strongly depends on the distance to the travelled track. The algorithm presented here facilitates the acquisition of important tree parameters from MLS data, as an area-wide automated derivation can be accomplished in a very short time.

Traditional precise engineering surveys adopt manual static, discrete observation, which cannot meet the dynamic, continuous, high-precision and holographic fine measurements required for large-scale infrastructure construction, operation and maintenance, where mobile laser scanning technology is becoming popular. However, in environments without GNSS signals, it is difficult to use mobile laser scanning technology to obtain 3D data. We fused a scanner with an inertial navigation system, odometer and inclinometer to establish and track mobile laser measurement systems. The control point constraints and Rauch-Tung-Striebel filter smoothing were fused, and a 3D point cloud generation method based on multi-sensor fusion was proposed. We verified the method based on the experimental data; the average deviation of positioning errors in the horizontal and elevation directions were 0.04 m and 0.037 m, respectively. Compared with the stop-and-go mode of the Amberg GRP series trolley, this method greatly improved scanning efficiency; compared with the method of generating a point cloud in an absolute coordinate system based on tunnel design data conversion, this method improved data accuracy. It effectively avoided the deformation of the tunnel, the sharp increase of errors and more accurately and quickly processed the tunnel point cloud data. This method provided better data support for subsequent tunnel analysis such as 3D display, as-built surveying and disease system management of rail transit tunnels.

The 3D semantic segmentation of a LiDAR point cloud is essential for various complex infrastructure analyses such as roadway monitoring, digital twin, or even smart city development. Different geometric and radiometric descriptors or diverse combinations of point descriptors can extract objects from LiDAR data through classification. However, the irregular structure of the point cloud is a typical descriptor learning problem—how to consider each point and its surroundings in an appropriate structure for descriptor extraction? In recent years, convolutional neural networks (CNNs) have received much attention for automatic segmentation and classification. Previous studies demonstrated deep learning models’ high potential and robust performance for classifying complicated point clouds and permutation invariance. Nevertheless, such algorithms still extract descriptors from independent points without investigating the deep descriptor relationship between the center point and its neighbors. This paper proposes a robust and efficient CNN-based framework named D-Net for automatically classifying a mobile laser scanning (MLS) point cloud in urban areas. Initially, the point cloud is converted into a regular voxelized structure during a preprocessing step. This helps to overcome the challenge of irregularity and inhomogeneity. A density value is assigned to each voxel that describes the point distribution within the voxel’s location. Then, by training the designed CNN classifier, each point will receive the label of its corresponding voxel. The performance of the proposed D-Net method was tested using a point cloud dataset in an urban area. Our results demonstrated a relatively high level of performance with an overall accuracy (OA) of about 98% and precision, recall, and F1 scores of over 92%.

Light Detection and Ranging (LiDAR) technology is playing a major role in different applications. Indeed, the possibility of exploiting either 3D geometric features and radiometric information makes LiDAR suitable for a wide range of practical domains. LiDAR proved also being quite flexible in terms of platforms where it can be implemented for the acquisition, spanning from airborne sensors up to car-based and hand-held instruments. Due to the rapid expansion of research concerning LiDAR intensity, the ISPRS WG III/5 launched in 2017 an initiative aimed at providing free access to LiDAR data acquired by modern multispectral ALS sensors as well as MLS data. The two datasets, MLS Data Set 1 – (“Sun Prairie”), and Multispectral LiDAR Data Set 2 – (“Tobermory”), were provided by Teledyne Optech Company (Canada) and were made freely available to researchers upon request. This paper is presenting the first results of this initiative in terms of applications, application domains and topics tackled by applicants. The relevance of this data set is also evaluated through a bibliometric analysis considering both Scopus and Web of Science indexed databases to analyse the main directions where the scientific research, the technical development and the application interest is moving to.

Traffic signs are one of the most relevant road assets for driving, as the safety of drivers depends to a great extent on their correct location. In this paper two methods are compared for the segmentation of the sign and the pole supporting it. Both methods are based on the morphological opening to identify the sign points, the first one directly employs the mathematical morphology directly applied to point clouds and the second one through point cloud rasterization into images. The comparison was conducted on twenty real traffic signs acquired with Mobile Laser Scanning obtaining point clouds from environments with signposts, traffic lights and lampposts. The results showed a correct segmentation of the signs, obtaining a F-score of 0.81 by the point-based method and a 0.75 by 2D image method. In particular, the point-based mathematical morphology proved to be more accurate in the segmentation of traffic sings installed on traffic lights and lampposts, avoiding over detection shown by the 2D image method.

Routine pavement inspection is crucial to keep roads safe and reduce traffic accidents. However, traditional practices in pavement inspection are labour-intensive and time-consuming. Mobile laser scanning (MLS) has proven a rapid way for collecting a large number of highly dense point clouds covering roadway surfaces. Handling a huge amount of unstructured point clouds is still a very challenging task. In this paper, we propose an effective approach for pavement crack detection using MLS point clouds. Road surface points are first converted into intensity images to improve processing efficiency. Then, a Capsule Neural Network (CapsNet) is developed to classify the road points for pavement crack detection. Quantitative evaluation results showed that our method achieved the recall, precision, and F1-score of 95.3%, 81.1%, and 88.2% in the testing scene, respectively, which demonstrated the proposed CapsNet framework can accurately and robustly detect pavement cracks in complex urban road environments.

Objective: To compare the possibilities of using mobile laser scanning (MLS) and aerial photography (AFS) from an unmanned aircraft system (UAS) and to make a survey from an integrated road laboratory when performing diagnostics of highways. Methods: For the analysis, a section of the regional road in the Kursk region was selected, on which the survey was carried out using considered methods. The main characteristics were identified when performing the diagnostics, their values were obtained on the basis of data from the integrated road laboratory, aerial photography with UAS, as well as ILS, and the accuracy of the results obtained, the compliance of the data with the requirements of regulatory documents were assessed. Results: Based on the work performed, the following conclusions were made: the determination of identified diagnostic parameters by the methods of ILS and APS with UAS is correct and aerial photography with UAS at the cost of equipment, the cost of shooting is the most profitable when drawing up topographic road plans. It is noted that in terms of accuracy, the APS method meets the requirements for plans at a scale of 1:500, MLS – 1:1000. Practical importance: Not all indicators required for diagnostics can be obtained with APS with ALS and MLS, since they require specialized equipment and direct interaction with the road surface, however, the range of application of the selected methods can be significantly expanded. Adhesion coefficient is measured using an integrated mobile road laboratory, so it is not advisable to abandon it. It was noted that the equipment of the laboratory, depending on the cost, may be different

The main stage of the mobile laser scanning data processing results, affecting the total accuracy of creating the final product, is the relative adjustment of trajectories and point clouds obtained during the re-passage of the survey system over the same area. The MLS data adjustment is performed based on the search for tie points in the overlapping areas of the driveways. Corresponding points can be added both interactively and automatically found using various algorithms and techniques. The accuracy of the adjustment depends on the reliability of the tie point identification, their number and the algorithm for searching local corrections to the position of the laser points. The study of the adjustment results depending on these factors is performed. It is shown how the selected adjustment algorithm and its parameters affect the final accuracy.

The use of drones to explore indoor spaces has gained attention and popularity for disaster management and indoor navigation applications. In this paper we present the operations and mapping techniques of two drones that are different in terms of size, the sensors deployed, and the positioning and mapping techniques used. The first drone is a low-cost commercial quadcopter microdrone, a Crazyflie, while the second drone is a relatively expensive research quadcopter macrodrone, called MAX. We investigated their feasibility in mapping areas where satellite positioning is not available, such as indoor spaces. We compared the point clouds obtained by a multi-ranger deck, a multi-layer LIDAR scanner and a stereo camera, and assessed each against ground truth obtained with a terrestrial laser scanner. Results showed that both drones are capable of mapping relatively cluttered indoor environments and can provide point clouds that are sufficient for a quick exploration. Furthermore, the LIDAR scanner-based system can handle a relatively large office environment with an accumulated drift less than 0.02% (1 cm) on the Z-axis and 0.77% (50 cm) on the X and Y axes over a length trajectory of about 65 m. Despite the limited features of the sensor configuration of the Crazyflie, its performance is promising for mapping indoor spaces, given the relatively low deviation from the ground truth: cloud-to-cloud distances measured were generally less than 20 cm.

In times of steadily increasing traffic loads and extreme weather phenomena, the safe maintenance of infrastructure poses a difficult challenge to operators, especially when a vast number ...

Roof bolts such as rock bolts and cable bolts provide structural support in underground mines. Frequent assessment of these support structures is critical to maintain roof stability and minimise safety risks in underground environments. This study proposes a robust workflow to classify roof bolts in 3D point cloud data and to generate maps of roof bolt density and spacing. The workflow was evaluated for identifying roof bolts in an underground coal mine with suboptimal lighting and global navigation satellite system (GNSS) signals not available. The approach is based on supervised classification using the multi-scale Canupo classifier coupled with a random sample consensus (RANSAC) shape detection algorithm to provide robust roof bolt identification. The issue of sparseness in point cloud data has been addressed through upsampling by using a moving least squares method. The accuracy of roof bolt identification was measured by correct identification of roof bolts (true positives), unidentified roof bolts (false negatives), and falsely identified roof bolts (false positives) using correctness, completeness, and quality metrics. The proposed workflow achieved correct identification of 89.27% of the roof bolts present in the test area. However, considering the false positives and false negatives, the overall quality metric was reduced to 78.54%.

The application of mobile laser scanning and aerial photography from unmanned aerial vehicles for shooting highways is considered. The aim of the research was to compare the results of shooting using mobile laser scanning systems and aerial photography from an unmanned aerial vehicle to de-termine the preferred option for shooting a highway. The experimental part of the research was carried out using the following equipment: scanning was performed using the Topcon IP - S2 Compact sys-tem, aerial photography was carried out from the GEOSCAN 201 unmanned aerial vehicle. Based on the comparative tests performed on the section of the A - 121 "Sortavala" highway, a comparative analysis of the data obtained for various indicators was carried out: the speed of the shooting stages, the cost of a set of equipment, the cost of shooting, and the accuracy of the results was evaluated. Practical recommendations for the application of these methods are given, their advantages and disad-vantages are indicated.

Adjustment is a main step in the preliminary processing of mobile laser scanning (MLS) data. As a result of this step, a point cloud is generated in a certain coordinate system. The modern software, provided with the corresponding surveying system, is capable of performing in automatic mode most stages of MLS data adjustment obtained for territories with different quantity of buildings. With a suf-ficient number of vertically arranged planar objects, such as building walls, the algorithms embedded in the software provide a high accuracy of relative adjustment, which consists in calculating and ap-plying corrections for trajectories obtained with re-scanning the same area. Absolute adjustment can also be carried out automatically, subject to the rules for placing control points in order to automatically detect them. This kind of adjustment involves transforming a point cloud with using control point coordinates measured with more accurate surveying methods. The accuracy of automatic relative adjustment can be significantly reduced with the almost complete absence of vertical flat objects. In this case, it is necessary to develop additional adjustment techniques capable of using not only flat objects of a large area, but also vertical objects, such as road signs and poles. Comprehensive technique of MLS data adjustment, which can use information on the position of road signs and poles for territories with an insufficient number of vertical flat objects is proposed. The accuracy estimation of both the relative and absolute MLS data adjustment according to the proposed technique was carried out. The choice of the required control point density for territories with different quantity of buildings is explained.

This paper, by critically reviewing different years (from 2010 to 2020) of research activities performed with Mobile Laser Scanning system, aims to review existing systems and how they are exploited in multifaceted domains. To such extent, the work defines five field domains where Mobile Laser Scanning have been used: Built and urban environment, Cultural heritage and Archaeology, Underground environment, Environmental monitoring, Forestry and Agriculture. Besides, this paper sheds the light on the pros and cons for each domain field, providing useful guidelines for those researchers involved in three-dimensional data collection with innovative systems. To achieve these purposes, research papers, were analysed, mainly considering geosciences related journals. The comparison among them revealed that, despite the incredible potential of Mobile Mapping System, the human intervention is still mandatory, and post-processing actions are needed to achieve the desired results, regardless the domain field. Moreover, our study provides insight into the technical and methodological limitations that raise a general scepticism on Mobile Mapping System for three-dimensional surveying, highlighting that in most of cases supplementary data are required to make the final result trustworthy. Such obstacles, hampering Mobile Laser Scanning diffusion, point towards unexplored areas for further investigations, serving as useful guidelines for future research directions.

The tree diameter at breast height (DBH) is one of the most important variables for monitoring the forest ecology. Mobile laser scanning (MLS), which has been widely applied in the forestry field, makes DBH measurement fast and convenient. However, there are many shrubs and deadwood in the neutral forest environment and the point clouds quality from MLS are easily affected by the environment which results in low single tree segmentation and DBH estimation accuracy. To improve the accuracy in a complex forest environment and low point cloud quality, we propose a relative density segmentation method for the single tree segmentation and DBH estimation method based on multi-height diameters for the DBH estimation. The relative density segmentation method calculates the relative density according to the ratio of density in two different scales, and segments the tree trunks by the higher relative density of trunk point clouds compared with their surroundings points. In the natural forest plot, the precision and recall of the proposed segmentation method reached 0.966 and 0.946, respectively; In the urban forest plot, the precision and recall reached 1 and 0.966, respectively. The proposed DBH estimation method was used to estimate the DBH of trees using multi-height diameters. The multi-height diameters combined with the outlier detection algorithm were able to improve the accuracy and robustness when the trunk point clouds have large noise. For the DBH estimation results, the mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean square error (RMSE) were 2.5 cm, 11.54%, and 3.17 cm, respectively, in the natural forest plot and 1.65 cm, 6.31%, and 1.97 cm, respectively, in the urban forest plot. The good experiment results indicate that the proposed method can achieve accurate and robust DBH extraction and provide fundamental data for supervision and sustainable development of forest resources.

The result of laser scanning is an array of laser points. The generation of a single point cloud in a given coordinate system is carried out during the registration process at the stage of preliminary field data processing. At this stage it is also often necessary to filter the data. Laser points with an erroneous position are eliminated during the data filleting. The number of erroneous laser points is determined by the of the laser scanner characteristics, surveyed area peculiarities and weather conditions. The devel-opment of methods and algorithms for filtering laser scanning data is carried out based on the analysis of the laser point spatial position and a certain set of additional characteristics, such as intensity value, echo signal, color value. The technique of mobile laser scanning data filtering for the territory of the road passing among the forest and close to individual industrial facilities and building. The main goal of the proposed filtration technique is to obtain data for automatic generation of an accurate digital terrain model. The filtration technique was developed for data acquired under the least favorable con-ditions – in wet weather. Accuracy estimation of generating digital terrain model based on filtered data was carried out.

The automatic extraction of individual tree from mobile laser scanning (MLS) scenes has important applications in tree growth monitoring, tree parameter calculation and tree modeling. However, trees often grow in rows and tree crowns overlap with varying shapes, and there is also incompleteness caused by occlusion, which makes individual tree extraction a challenging problem. In this paper, we propose a trunk-constrained and tree structure analysis method to extract trees from scanned urban scenes. Firstly, multi-feature enhancement is performed via PointNet to segment the tree points from raw urban scene point clouds. Next, the candidate local tree trunk clusters are obtained by clustering based on the intercepted local tree trunk layer, and the real local tree trunk is obtained by removing noise data. Then, the trunk is located and extracted by combining circle fitting and region growing, so as to obtain the center of the tree crown. Further, the points near the tree’s crown (core points) are segmented through distance difference, and the tree crown boundary (boundary points) is distinguished by analyzing the density and centroid deflection angle. Therefore, the core and boundary points are deleted to obtain the remaining points (intermediate points). Finally, the core, intermediate and boundary points, as well as the tree trunks, are combined to extract individual tree. The performance of the proposed method was evaluated on the Pairs-Lille-3D dataset, which is a benchmark for point cloud classification, and data were produced using a mobile laser system (MLS) applied to two different cities in France (Paris and Lille). Overall, the precision, recall, and F1-score of instance segmentation were 90.00%, 98.22%, and 99.08%, respectively. The experimental results demonstrate that our method can effectively extract trees with multiple rows of occlusion and improve the accuracy of tree extraction.

This presentation was given by Benjamin Wild at the 3D-ARCH 2022 conference in Mantova, Italy. The presentation won the best paper award., The INDIGO graffiti project is funded by the Heritage Science Austria programme of the Austrian Academy of Sciences (��AW)

Graffiti is a short-lived form of heritage balancing between tangible and intangible, offensive and pleasant. Graffiti makes people laugh, wonder, angry, think. These conflicting traits are all present along Vienna's Donaukanal (Eng. Danube Canal), a recreational hotspot – located in the city's heart – famous for its endless display of graffiti. The graffiti-focused heritage science project INDIGO aims to build the basis to systematically document, monitor, and analyse circa 13 km of Donaukanal graffiti in the next decade. The first part of this paper details INDIGO's goals and overarching methodological framework, simultaneously placing it into the broader landscape of graffiti research. The second part of the text concentrates on INDIGO's graffiti documentation activities. Given the project's aim to create a spatially, spectrally, and temporally accurate record of all possible mark-makings attached in (il)legal ways to the public urban surfaces of the Donaukanal, it seems appropriate to provide insights on the photographic plus image-based modelling activities that form the foundation of INDIGO's graffiti recording strategy. The text ends with some envisioned strategies to streamline image acquisition and process the anticipated hundreds of thousands of images.

The sudden deterioration of the condition of linear infrastructure networks makes road management a complex task. Knowledge of the surface condition of the pavement is a requirement in order to estimate the causes of instabilities, select the appropriate action and identify all those sections that require urgent intervention. The mobile laser scanning (MLS) technique allows for a fast and safe diagnosis, thus making it possible to plan an early intervention program quickly and cost-effectively. This paper describes a methodology implemented with a twofold purpose: (i) the optimal definition, during the design phase, of the input parameters of the MLS survey (velocity of the vehicle and acquisition rate), defined through the study of the relationship between these parameters and the density of the scanned points and, therefore, with the resolution that allows the analysis of a certain type of pavement distress; (ii) the creation of a Digital Elevation Model with a curved abscissa (DEMc), specific for the analysis of road pavements. The field surveys made and the procedure developed allowed the velocity of the MLS to be associated with the resolution of the DEMc, and thus its capability to highlight distresses at different levels of severity. The creation of the road model is semiautomatic; the height value of each single node of the grid is estimated through spatial interpolation algorithms. Starting from experimental data, a few charts were created that relate the density of the point cloud to the variation of the acquisition rate, together with the minimum resolution. Depending on the type of distress analyzed, it is possible to infer the values to be respected of the parameters. In this way, it should be possible to draw up a few guidelines about MLS surveys addressing linear infrastructures focused on the optimization of the survey design, so as to identify strategies that can maximize benefits with the same available budget.

Vehicle-related ground occlusion is a common problem in MLS data. This study aims to design a detection and reconstruction method of static vehicle-related ground occlusion for MLS data. Ground extraction and vehicle segmentation are performed on the input point cloud data in advance. Then an α-shape boundary based on the prior vehicle geometry is designed to split non-ground empty area and ground occlusions. The occlusion is detected and matched with its corresponding vehicle using the relative position between them. This relative position relation and the height difference are used to detect the curb direction as the local road direction. Finally, the occlusions are reconstructed using two different methods: (1) a cell-based linear interpolation and (2) a point-based mathematical morphology. The methodology is tested by original scanned data and multi-temporal evaluation data captured from a residential area in Delft, the Netherlands with vehicle-mounted LiDAR sensors. The result shows that all occlusions cause by vehicles are successfully detected and the curb (road) direction is correctly extracted in most of the occluded areas. Both reconstructed results can visually integrate the original scanned data and recover the curb structure. The reconstruction errors of the linear interpolation method are 0.045 m in the z-axis direction and 0.051 m in total and the reconstruction errors of mathematical morphology are 0.048 m in the z-axis direction and 0.052 m in total.

Тема выпускной квалификационной работы: «Исследование и разработка крупномасштабного набора Ð´Ð°Ð½Ð½Ñ‹Ñ Ð´Ð»Ñ семантической сегментации Ñ‚Ñ€ÐµÑ Ð¼ÐµÑ€Ð½Ñ‹Ñ Ð¾Ð±Ð»Ð°ÐºÐ¾Ð² точек мобильного лазерного сканирования». Данная работа посвящена изучению наборов Ð´Ð°Ð½Ð½Ñ‹Ñ Ð´Ð»Ñ семантической сегментации Ñ‚Ñ€ÐµÑ Ð¼ÐµÑ€Ð½Ñ‹Ñ Ð¾Ð±Ð»Ð°ÐºÐ¾Ð² точек мобильного лазерного сканирования. В Ñ Ð¾Ð´Ðµ работы были изучены методы семантической сегментации облаков точек и проведен анализ Ð¸ÑÐ¿Ð¾Ð»ÑŒÐ·ÑƒÐµÐ¼Ñ‹Ñ Ð½Ð°Ð±Ð¾Ñ€Ð¾Ð² Ð´Ð°Ð½Ð½Ñ‹Ñ Ñ последующим структурированием Ð¿Ð¾Ð»ÑƒÑ‡ÐµÐ½Ð½Ñ‹Ñ Ð´Ð°Ð½Ð½Ñ‹Ñ Ð¸ выявлением на основе этого ÑÑƒÑ‰ÐµÑÑ‚Ð²ÑƒÑŽÑ‰Ð¸Ñ Ð¿Ñ€Ð¾Ð±Ð»ÐµÐ¼, Ñ‚Ñ€ÐµÐ±ÑƒÑŽÑ‰Ð¸Ñ Ð´Ð»Ñ своего решения определение требований к наборам Ð´Ð°Ð½Ð½Ñ‹Ñ . На базе этого был разработан новый набор Ð´Ð°Ð½Ð½Ñ‹Ñ , который решает некоторые из Ð¾Ð±Ð½Ð°Ñ€ÑƒÐ¶ÐµÐ½Ð½Ñ‹Ñ Ð½ÐµÐ´Ð¾ÑÑ‚Ð°Ñ‚ÐºÐ¾Ð² Ñ€Ð°ÑÑÐ¼Ð¾Ñ‚Ñ€ÐµÐ½Ð½Ñ‹Ñ Ð½Ð°Ð±Ð¾Ñ€Ð¾Ð², с учетом Ð²ÑÐµÑ Ð¾ÑÐ½Ð¾Ð²Ð½Ñ‹Ñ Ð½Ð°Ð¿Ñ€Ð°Ð²Ð»ÐµÐ½Ð¸Ð¹ развития в Ð¾Ð±Ð»Ð°ÑÑ‚ÑÑ Ð¸Ð·ÑƒÑ‡ÐµÐ½Ð¸Ñ, разработки и использования облаков точек, а также ÑÐ²ÑÐ·Ð°Ð½Ð½Ñ‹Ñ Ñ ними методов. Разработанный набор Ð´Ð°Ð½Ð½Ñ‹Ñ ÑƒÐ´Ð¾Ð²Ð»ÐµÑ‚Ð²Ð¾Ñ€ÑÐµÑ‚ всем предъявленным требованиям., The subject of the graduate qualification work is «Research and development of a large-scale data set for semantic segmentation of three-dimensional point clouds of mobile laser scanning». This work is devoted to the study of data sets for semantic segmentation of three-dimensional point clouds of mobile laser scanning. In the course of the work, the methods of semantic segmentation of point clouds were studied and the analysis of the data sets used was carried out, followed by structuring the data obtained and identifying existing problems based on this, requiring the definition of requirements for data sets for their solution.Based on this, a new data set was developed that solves some of the identified shortcomings of the considered sets, considering all the main directions of development in the fields of studying, developing and using point clouds, as well as related methods.The developed data set meets all the requirements.

Mobile Laser Scanning (MLS) is a technique characterized by high data acquisition efficiency and level of detail. However, a lot of information contained in the LiDAR point cloud is only implicitly available. Therefore, in order to create a digital topographic map from a large quantity of MLS survey data, it is necessary to define a methodology that requires a combination of various software tools. In general, the applied methodology mainly depends on the final product specifications (data model, accuracy, level of detail, etc.). This paper describes the standard methodology of creating a detailed digital topographic map using data collected by MLS, which proved to be two times faster than the conventional methods (total station or GNSS survey).

Norway spruce (Picea abies (L.) H.Karst) trees planted with high stem densities produce finely branched, solid logs but are vulnerable to extreme weather events, e.g., storms. Over the last decades spruce stands have been planted at lower stand densities, resulting in wider crowns, lower crown bases, and higher stand stability, but this might decrease the quality of coniferous timber due to an increased growing rate and wider annual rings. Therefore, in this case study we investigated the influence of different silvicultural treatments and stand densities on tree morphology and wood properties of 100 spruce trees up to sawn timber as the final product. Tree morphology was assessed using mobile laser scanning. Ring width analysis, wood density measurements, and the four-point bending strength test on visually graded boards were conducted to gain information on wood properties and product quality. In stands thinned from below, higher wood densities were observed due to smaller annual rings compared to stands that were thinned from above at equal annual ring widths. In addition, crown asymmetry and the height-to-diameter ratio were identified as proxies for wood density. Lastly, visually assessed quality differences between the forest stands were discerned on the examined boards.

Today, high-quality reference tree measurements, including the position, diameter, height and volume, are cumbersome and slow to carry out, but highly needed for forest inventories based on airborne laser scanning. Mobile laser scanning technologies hold the promise for collecting reference data for forest inventories with an extremely high efficiency. Perhaps, the most efficient approach for reference data collection would be to mount a high-resolution laser scanning system on board an airborne vehicle flying at a low altitude above the forest canopy since this would allow recording reference samples of individual trees with the speed of flight. To demonstrate the potential of this technology, we mounted an in-house developed HeliALS-DW laser scanning system on board a helicopter and collected point cloud data in a boreal forest on three test sites containing a total of 1469 trees. The obtained point clouds incorporated sufficiently many high-quality stem hits for estimating the stem curves and stem volumes of individual trees since the point clouds had a relatively high point density of 2200–3800 echoes/m2, and the scanner had been tilted by 15° from the nadir to increase the possibility of recording stem hits. To automatically estimate the diameters at breast height (DBH) and stem curves of individual trees, we used algorithms designed to tolerate moderate drifts in the trajectory of the laser scanner. Furthermore, the stem volumes of individual trees were computed by using the estimated stem curves and tree heights without any allometric models. Using the proposed methods, we were able to estimate the stem curves with a root-mean-square error (RMSE) of 1.7–2.6 cm (6–9%) while detecting 42–71% of the trees. The RMSE of stem volume estimates was 0.1–0.15 m3 (12–21%). We also showed that the tree detection rate could be improved up to 87–96% for trees with a DBH exceeding 20 cm if slightly larger average errors for the stem attributes were allowed. Our results pave the way for using high-resolution airborne laser scanning for field reference data collection by conducting direct measurements of tree stems with a high efficiency.

Cycling lane centerlines (CLC) play an important role in the evaluation of safety-related conditions and guiding systems for cyclists along road corridors. The unavailability of design files or undocumented changes in the road infrastructures after improvements has created great difficulty in delineating CLC on existing roads. In this study, mobile laser scanning (MLS) data are introduced into this domain and a four-step semi-automated framework is proposed for generating CLC on roads with roadside barriers (RB). First, MLS data are restructured into the aligned scan-pattern grid using the mapping trajectory data. Second, a rasterization-based clustering approach is applied to segment the off-ground objects from the reorganized MLS data. Third, the RB amongst the segmented objects are identified using a sequential application of the k-Means clustering method and the proposed unidirectional growing method. Finally, the moving average technique and natural cubic spline are applied to generate CLC from the critical positions alongside the identified RB. Testing on three road sections with different types of RB demonstrated that the developed framework can successfully generate CLC from MLS data in the presence of considerable noises. The results also show that the proposed procedure shows better accuracy performance on processing roads with wide RB than a road with narrow RB.

In recent years, the importance of indoor mapping increased in a wide range of applications, such as facility management and mapping hazardous sites. The essential technique behind indoor mapping is simultaneous localization and mapping (SLAM) because SLAM offers suitable positioning estimates in environments where satellite positioning is not available. State-of-the-art indoor mobile mapping systems employ Visual-based SLAM or LiDAR-based SLAM. However, Visual-based SLAM is sensitive to textureless environments and, similarly, LiDAR-based SLAM is sensitive to a number of pose configurations where the geometry of laser observations is not strong enough to reliably estimate the six-degree-of-freedom (6DOF) pose of the system. In this paper, we present different strategies that utilize the benefits of the inertial measurement unit (IMU) in the pose estimation and support LiDAR-based SLAM in overcoming these problems. The proposed strategies have been implemented and tested using different datasets and our experimental results demonstrate that the proposed methods do indeed overcome these problems. We conclude that IMU observations increase the robustness of SLAM, which is expected, but also that the best reconstruction accuracy is obtained not with a blind use of all observations but by filtering the measurements with a proposed reliability measure. To this end, our results show promising improvements in reconstruction accuracy.

Change detection is an important tool for processing multiple epochs of mobile LiDAR data in an efficient manner, since it allows to cope with an otherwise time-consuming operation by focusing on regions of interest. State-of-the-art approaches usually either do not handle the case of incomplete observations or are computationally expensive. We present a novel method based on a combination of point clouds and voxels that is able to handle said case, thereby being computationally less expensive than comparable approaches. Furthermore, our method is able to identify special classes of changes such as partially moved, fully moved and deformed objects in addition to the appeared and disappeared objects recognized by conventional approaches. The performance of our method is evaluated using the publicly available TUM City Campus datasets, showing an overall accuracy of 88 %.