Dense 3D Point Clouds Research Articles

Enhancing environmental modeling and 3D point cloud construction for unmanned vehicles using laser SLAM and stereo vision with Convolutional Neural Networks

Abstract. This research presents an innovative SLAM algorithm that integrates Convolutional Neural Networks (CNNs) with LIDAR and stereo vision to significantly enhance the accuracy of environmental modeling and the construction of dense 3D point cloud maps in complex and dynamic surroundings. By processing pre-recorded video data and employing advanced image segmentation techniques, this study achieves a deep fusion of visual and geometric data, resulting in highly detailed and precise 3D representations of the environment. The experimental results demonstrate that this approach effectively detects and excludes dynamic objects, thereby significantly improving the overall quality, robustness, and reliability of the constructed maps. This work represents a substantial advancement in SLAM technology, particularly in its capability to model and capture intricate environmental details under varying conditions, making it a powerful tool for precise environmental mapping.

Immersive remote telerobotics: foveated unicasting and remote visualization for intuitive interaction

Abstract Precise and efficient performance in remote robotic teleoperation relies on intuitive interaction. This requires both accurate control actions and complete perception (vision, haptic, and other sensory feedback) of the remote environment. Especially in immersive remote teleoperation, the complete perception of remote environments in 3D allows operators to gain improved situational awareness. Color and Depth (RGB-D) cameras capture remote environments as dense 3D point clouds for real-time visualization. However, providing enough situational awareness needs fast, high-quality data transmission from acquisition to virtual reality rendering. Unfortunately, dense point-cloud data can suffer from network delays and limits, impacting the teleoperator’s situational awareness. Understanding how the human eye works can help mitigate these challenges. This paper introduces a solution by implementing foveation, mimicking the human eye’s focus by smartly sampling and rendering dense point clouds for an intuitive remote teleoperation interface. This provides high resolution in the user’s central field, which gradually reduces toward the edges. However, this systematic visualization approach in the peripheral vision may benefit or risk losing information and burdening the user’s cognitive load. This work investigates these advantages and drawbacks through an experimental study and describes the overall system, with its software, hardware, and communication framework. This will show significant enhancements in both latency and throughput, surpassing 60% and 40% improvements in both aspects when compared with state-of-the-art research works. A user study reveals that the framework has minimal impact on the user’s visual quality of experience while helping to reduce the error rate significantly. Further, a 50% reduction in task execution time highlights the benefits of the proposed framework in immersive remote telerobotics applications.

Improving Aerial Targeting Precision: A Study on Point Cloud Semantic Segmentation with Advanced Deep Learning Algorithms

The integration of technological advancements has significantly impacted artificial intelligence (AI), enhancing the reliability of AI model outputs. This progress has led to the widespread utilization of AI across various sectors, including automotive, robotics, healthcare, space exploration, and defense. Today, air defense operations predominantly rely on laser designation. This process is entirely dependent on the capability and experience of human operators. Considering that UAV systems can have flight durations exceeding 24 h, this process is highly prone to errors due to the human factor. Therefore, the aim of this study is to automate the laser designation process using advanced deep learning algorithms on 3D point clouds obtained from different sources, thereby eliminating operator-related errors. As different data sources, dense 3D point clouds produced with photogrammetric methods containing color information, and point clouds produced with LiDAR systems were identified. The photogrammetric point cloud data were generated from images captured by the Akinci UAV’s multi-axis gimbal camera system within the scope of this study. For the point cloud data obtained from the LiDAR system, the DublinCity LiDAR dataset was used for testing purposes. The segmentation of point cloud data utilized the PointNet++ and RandLA-Net algorithms. Distinct differences were observed between the evaluated algorithms. The RandLA-Net algorithm, relying solely on geometric features, achieved an approximate accuracy of 94%, while integrating color features significantly improved its performance, raising its accuracy to nearly 97%. Similarly, the PointNet++ algorithm, relying solely on geometric features, achieved an accuracy of approximately 94%. Notably, the model developed as a unique contribution in this study involved enriching the PointNet++ algorithm by incorporating color attributes, leading to significant improvements with an approximate accuracy of 96%. The obtained results demonstrate a notable improvement in the PointNet++ algorithm with the proposed approach. Furthermore, it was demonstrated that the methodology proposed in this study can be effectively applied directly to data generated from different sources in aerial scanning systems.

Blind Quality Assessment of Dense 3D Point Clouds with Structure Guided Resampling

Objective quality assessment of three-dimensional (3D) point clouds is essential for the development of immersive multimedia systems in real-world applications. Despite the success of perceptual quality evaluation for 2D images and videos, blind/no-reference metrics are still scarce for 3D point clouds with large-scale irregularly distributed 3D points. Therefore, in this article, we propose an objective point cloud quality index with Structure Guided Resampling (SGR) to automatically evaluate the perceptually visual quality of dense 3D point clouds. The proposed SGR is a general-purpose blind quality assessment method without the assistance of any reference information. Specifically, considering that the human visual system is highly sensitive to structure information, we first exploit the unique normal vectors of point clouds to execute regional pre-processing that consists of keypoint resampling and local region construction. Then, we extract three groups of quality-related features, including (1) geometry density features, (2) color naturalness features, and (3) angular consistency features. Both the cognitive peculiarities of the human brain and naturalness regularity are involved in the designed quality-aware features that can capture the most vital aspects of distorted 3D point clouds. Extensive experiments on several publicly available subjective point cloud quality databases validate that our proposed SGR can compete with state-of-the-art full-reference, reduced-reference, and no-reference quality assessment algorithms.

Using Passive Multi-Modal Sensor Data for Thermal Simulation of Urban Surfaces

Abstract. This paper showcases an integrated workflow hinged on passive airborne multi-modal sensor data for the simulation of the thermal behavior of built-up areas with a focus on urban heat islands. The geometry of the underlying parametrized model, or digital twin, is derived from high-resolution nadir and oblique RGB, near-infrared and thermal infrared imagery. The captured bitmaps get photogrammetrically processed into comprehensive surface models, terrain, dense 3D point clouds and true-ortho mosaics. Building geometries are reconstructed from the projected point sets with procedures presupposing outlining, analysis of roof and fac¸ade details, triangulation, and texturing mapping. For thermal simulation, the composition of the ground is determined using supervised machine learning based on a modified multi-modal DeepLab v3+ architecture. Vegetation is retrieved as individual trees and larger tree regions to be added to the meshed terrain. Building materials are assigned from the available visual, infrared and surface planarity information as well as publicly available references. With actual weather data, surface temperatures can be calculated for any period of time by evaluating conductive, convective, radiative and emissive energy fluxes for triangular layers congruent to the faces of the modeled scene. Results on a sample dataset of the Moabit district in Berlin, Germany, showed the ability of the simulator to output surface temperatures of relatively large datasets efficiently. Compared to the thermal infrared images, several insufficiencies in terms of data and model caused occasional deviations between measured and simulated temperatures. For some of these shortcomings, improvement suggestions within future work are presented.

Automated Derivation of Vine Objects and Ecosystem Structures Using UAS-Based Data Acquisition, 3D Point Cloud Analysis, and OBIA

This study delves into the analysis of a vineyard in Carinthia, Austria, focusing on the automated derivation of ecosystem structures of individual vine parameters, including vine heights, leaf area index (LAI), leaf surface area (LSA), and the geographic positioning of single plants. For the derivation of these parameters, intricate segmentation processes and nuanced UAS-based data acquisition techniques are necessary. The detection of single vines was based on 3D point cloud data, generated at a phenological stage in which the plants were in the absence of foliage. The mean distance from derived vine locations to reference measurements taken with a GNSS device was 10.7 cm, with a root mean square error (RMSE) of 1.07. Vine height derivation from a normalized digital surface model (nDSM) using photogrammetric data showcased a strong correlation (R2 = 0.83) with real-world measurements. Vines underwent automated classification through an object-based image analysis (OBIA) framework. This process enabled the computation of ecosystem structures at the individual plant level post-segmentation. Consequently, it delivered comprehensive canopy characteristics rapidly, surpassing the speed of manual measurements. With the use of uncrewed aerial systems (UAS) equipped with optical sensors, dense 3D point clouds were computed for the derivation of canopy-related ecosystem structures of vines. While LAI and LSA computations await validation, they underscore the technical feasibility of obtaining precise geometric and morphological datasets from UAS-collected data paired with 3D point cloud analysis and object-based image analysis.

USING MACHINE LEARNING TECHNIQUES TO FILTER VEGETATION IN COLORIZED SFM POINT CLOUDS OF SOIL SURFACES

Abstract. Various soil erosion processes can be quantified using digital elevation models (DEMs) of difference. In this study, cameras were used to capture images of bare soil during artificial rainfall simulations. The photos were then used to generate dense 3D point clouds with millimeter resolution using Structure-from-Motion and Multiview-Stereo (SfM+MVS) techniques. However, the point clouds also captured some vegetation, such as agricultural plants, grass, and weeds, present at the soil surface. It had to be removed to accurately measure soil erosion processes. The removal can be done manually and is hence time-consuming. In this study, several methods have been tested and compared to perform (semi-)automatic vegetation filtering from point clouds of soil surfaces. First, the point clouds were labelled into vegetation and ground data to establish a basis set for the subsequent experiments. Then, three branches of algorithms were tested. The first branch considers knowledge-based thresholding. Thereby, unique features were considered, e.g., point color, height, and roughness within a specified neighborhood. For instance, a threshold was set in the color space to separate green vegetation from brown soil considering the green band. The second branch used a machine learning (ML) algorithm to classify each point as vegetation or ground by automatically finding thresholds. Thereby, again features such as point color were used. In addition, multi-scale features were computed for each point to characterize it in the context of its neighborhood. The calculated features were used afterwards with the random forest (RF). The third branch considered an end-to-end learning approach and thus avoiding the necessity to define features. The deep learning-based architecture PointNet++ was used. For the classification, an adapted model for soil surfaces and vegetation was trained. The performance of the different methods was compared, and an assessment of each method was provided. Overall, the study aims to find a (semi-)automatic method to remove vegetation from time series of soil surface point clouds to achieve an accurate measurement of soil surface changes and thus eventually erosion processes while minimizing manual effort and time consumption.

Interactive 3D Annotation of Objects in Moving Videos from Sparse Multi-view Frames

Segmenting and determining the 3D bounding boxes of objects of interest in RGB videos is an important task for a variety of applications such as augmented reality, navigation, and robotics. Supervised machine learning techniques are commonly used for this, but they need training datasets: sets of images with associated 3D bounding boxes manually defined by human annotators using a labelling tool. However, precisely placing 3D bounding boxes can be difficult using conventional 3D manipulation tools on a 2D interface. To alleviate that burden, we propose a novel technique with which 3D bounding boxes can be created by simply drawing 2D bounding rectangles on multiple frames of a video sequence showing the object from different angles. The method uses reconstructed dense 3D point clouds from the video and computes tightly fitting 3D bounding boxes of desired objects selected by back-projecting the 2D rectangles. We show concrete application scenarios of our interface, including training dataset creation and editing 3D spaces and videos. An evaluation comparing our technique with a conventional 3D annotation tool shows that our method results in higher accuracy. We also confirm that the bounding boxes created with our interface have a lower variance, likely yielding more consistent labels and datasets.

Automatic reconstruction and modeling of dormant jujube trees using three-view image constraints for intelligent pruning applications

Automatic reconstruction and modeling of dormant jujube trees provide a basis and prerequisite for intelligent pruning applications in large-scale, dwarf, and high-density planting orchards. For accurate 3D reconstruction of the trunk and pruning branches, this study presents a method based on a multi-view image sequence of dormant jujube trees. It involves four main steps. First, we determine the way of image acquisition, equipment parameters and posture, and reconstruction accuracy by investigating and analyzing their planting mode to meet the requirements of robot intelligent pruning operation. Second, performing image matching in images of dormant jujube trees is challenging due to few local feature regions, weak continuity, and difference in individual morphological structures. We provide a bilateral image-matching method based on the three-view geometry constraint. Third, this study optimizes a camera self-calibration algorithm based on image EXIF tags by broadening its applicability to improve reconstruction efficiency. It does not rely on the particular geometric constraints in the specific scenes. Finally, a dense 3D point cloud of a tree is built automatically with this improved SfM reconstruction strategy and combined with the PMVS algorithm. Both qualitative and quantitative evaluations are performed on generating 3D models of eight dormant jujube trees and their number of branches, average plant height, and crown are used as indicators. The results show that our method identifies the number of pruning branches with an accuracy of 92% and provides a performance of 95% for measuring the diameter of the plant height and canopy. The results provide visual research basis and technical support for the intelligent pruning of jujube trees.

Research on Multi-Sensor Simultaneous Localization and Mapping Technology for Complex Environment of Construction Machinery

Simultaneous localization and mapping (SLAM), as a key task of unmanned vehicles for construction machinery, is of great significance for later path planning and control. Construction tasks in the engineering field are mostly carried out in bridges, tunnels, open fields, etc. The prominent features of these environments are high scene similarity, few geometric features, and large-scale repetitive texture information, which is prone to sensor detection degradation. This leads to positioning drift and map building failure. The traditional method of motion estimation and 3D reconstruction uses a single sensor, which lacks enough information, has poor adaptability to the environment, and cannot guarantee good positioning accuracy and robustness in complex environments. Currently, the strategy of multi-sensor fusion is proven to be an effective solution and is widely studied. This paper proposes a SLAM framework that integrates LiDAR, IMU, and camera. It tightly couples the texture information observed by camera, the geometric information scanned by LiDAR, and the measured value of IMU, allowing visual-inertial odometry (VIO) and LiDAR-inertial odometry (LIO) common implementation. The LIO subsystem extracts point cloud features and matches them with the global map. The obtained pose estimation can be used for the initialization of the VIO subsystem. The VIO system uses direct method to minimize the photometric error and IMU measurement error between images to estimate the pose of the robot and the geometric structure of the scene. The two subsystems assist each other to perform pose estimation, and can operate normally even when any subsystem fails. A factor graph is used to combine all constraints to achieve global pose optimization. Keyframe and sliding window strategies are used to ensure real-time performance. Through real-vehicle testing, the system can perform incremental and real-time state estimation and reconstruct a dense 3D point cloud map, which can effectively solve the problems of positioning drift and mapping failure in the lack of geometric features or challenging construction environments.

Point clouds segmentation of rapeseed siliques based on sparse-dense point clouds mapping.

In this study, we propose a high-throughput and low-cost automatic detection method based on deep learning to replace the inefficient manual counting of rapeseed siliques. First, a video is captured with a smartphone around the rapeseed plants in the silique stage. Feature point detection and matching based on SIFT operators are applied to the extracted video frames, and sparse point clouds are recovered using epipolar geometry and triangulation principles. The depth map is obtained by calculating the disparity of the matched images, and the dense point cloud is fused. The plant model of the whole rapeseed plant in the silique stage is reconstructed based on the structure-from-motion (SfM) algorithm, and the background is removed by using the passthrough filter. The downsampled 3D point cloud data is processed by the DGCNN network, and the point cloud is divided into two categories: sparse rapeseed canopy siliques and rapeseed stems. The sparse canopy siliques are then segmented from the original whole rapeseed siliques point cloud using the sparse-dense point cloud mapping method, which can effectively save running time and improve efficiency. Finally, Euclidean clustering segmentation is performed on the rapeseed canopy siliques, and the RANSAC algorithm is used to perform line segmentation on the connected siliques after clustering, obtaining the three-dimensional spatial position of each silique and counting the number of siliques. The proposed method was applied to identify 1457 siliques from 12 rapeseed plants, and the experimental results showed a recognition accuracy greater than 97.80%. The proposed method achieved good results in rapeseed silique recognition and provided a useful example for the application of deep learning networks in dense 3D point cloud segmentation.

DIGITAL REPLICAS OF BRITISH MUSEUM ARTEFACTS

Abstract. The digitisation of museum exhibits has played an essential role in geomatics research for generating digital replicas, as it offers the chance to address rather challenging issues. The use of different sensors, ranging from active to passive, and also structured light scanners or hybrid solutions, the various destinations and purposes of the final results combined with the extreme variety of possible objects have made it a field of investigation highly inquired in the literature.The present study aims to analyse and discuss a digitalisation workflow applied to four Sumerian civilisation masterpieces preserved in the British Museum. The dense and accurate 3D point clouds derived from a specimen of Articulated Arm Coordinate Measuring Machines in collaboration with Faro technologies have twofold roles: ground truth and geometric reference of the final digital replicas. Digital photogrammetry is employed to enrich the models with the relevant radiometric component. The significant contribution results, exploiting co-registration strategies, offer careful guidance of a photogrammetric protocol created in a highly controlled environment combined with skilful expedients and devices. The proposed approach enables the acquisition of high-quality and radiometrically balanced images and improves the possibility of automating the masking procedure before the photogrammetric processing.

Analysis of Lidar Actuator System Influence on the Quality of Dense 3D Point Cloud Obtained with SLAM

Mobile mapping technologies, based on techniques such as simultaneous localization and mapping (SLAM) and surface-from-motion (SfM), are being vigorously developed both in the scientific community and in industry. They are crucial concepts for automated 3D surveying and autonomous vehicles. For various applications, rotating multiline scanners, manufactured, for example, by Velodyne and Ouster, are utilized as the main sensor of the mapping hardware system. However, their principle of operation has a substantial drawback, as their scanning pattern creates natural gaps between the scanning lines. In some models, the vertical lidar field of view can also be severely limited. To overcome these issues, more sensors could be employed, which would significantly increase the cost of the mapping system. Instead, some investigators have added a tilting or rotating motor to the lidar. Although the effectiveness of such a solution is usually clearly visible, its impact on the quality of the acquired 3D data has not yet been investigated. This paper presents an adjustable mapping system, which allows for switching between a stable, tilting or fully rotating lidar position. A simple experiment in a building corridor was performed, simulating the conditions of a mobile robot passing through a narrow tunnel: a common setting for applications, such as mining surveying or industrial facility inspection. A SLAM algorithm is utilized to create a coherent 3D point cloud of the mapped corridor for three settings of the sensor movement. The extent of improvement in the 3D data quality when using the tilting and rotating lidar, compared to keeping a stable position, is quantified. Different metrics are proposed to account for different aspects of the 3D data quality, such as completeness, density and geometry coherence. The ability of SLAM algorithms to faithfully represent selected objects appearing in the mapped scene is also examined. The results show that the fully rotating solution is optimal in terms of most of the metrics analyzed. However, the improvement observed from a horizontally mounted sensor to a tilting sensor was the most significant.

Reduced-Reference Quality Assessment of Point Clouds via Content-Oriented Saliency Projection

Many dense 3D point clouds have been exploited to represent visual objects instead of traditional images or videos. To evaluate the perceptual quality of various point clouds, in this letter, we propose a novel and efficient Reduced-Reference quality metric for point clouds, which is based on Content-oriented sAliency Projection (RR-CAP). Specifically, we make the first attempt to simplify reference and distorted point clouds into projected saliency maps with a downsampling operation. Through this process, we tackle the issue of transmitting large-volume original point clouds to user-ends for quality assessment. Then, motivated by the characteristics of the human visual system (HVS), the objective quality scores of distorted point clouds are produced by combining content-oriented similarity and statistical correlation measurements. Finally, extensive experiments are conducted on SJTU-PCQA and WPC databases. The experimental results demonstrate that our proposed algorithm outperforms existing reduced-reference and no-reference quality metrics, and significantly reduces the performance gap between state-of-the-art full-reference quality assessment methods. In addition, we show the performance variation of each proposed technical component by ablation tests.

Semi-Global Matching Assisted Absolute Phase Unwrapping.

Measuring speed is a critical factor to reduce motion artifacts for dynamic scene capture. Phase-shifting methods have the advantage of providing high-accuracy and dense 3D point clouds, but the phase unwrapping process affects the measurement speed. This paper presents an absolute phase unwrapping method capable of using only three speckle-embedded phase-shifted patterns for high-speed three-dimensional (3D) shape measurement on a single-camera, single-projector structured light system. The proposed method obtains the wrapped phase of the object from the speckle-embedded three-step phase-shifted patterns. Next, it utilizes the Semi-Global Matching (SGM) algorithm to establish the coarse correspondence between the image of the object with the embedded speckle pattern and the pre-obtained image of a flat surface with the same embedded speckle pattern. Then, a computational framework uses the coarse correspondence information to determine the fringe order pixel by pixel. The experimental results demonstrated that the proposed method can achieve high-speed and high-quality 3D measurements of complex scenes.

Automatic Recognition and Digital Documentation of Cultural Heritage Hemispherical Domes using Images

Recent advancements in optical metrology have enabled continuous documentation of dense 3-dimensional (3D) point clouds of construction projects, including cultural heritage preservation projects. These point clouds must then be further processed to generate semantic digital models, which is integral to the lifecycle management of heritage sites. For large-scale and continuous digital documentation, processing of dense 3D point clouds is computationally cumbersome, and consequentially requires additional hardware for data management and analysis, increasing the time, cost, and complexity of the project. Fast and reliable solutions for generating the geometric digital models is, hence, eminently desirable. This article presents an original approach to generate reliable semantic digital models of heritage hemispherical domes using only two images. New closed formulations were derived to establish the relationships between a sphere and its projected ellipse onto an image. These formulations were then utilised to create new methods for: (i) selecting the best pair of images from an image network; (ii) detecting ellipses corresponding to projection of spheres in images; (iii) matching of the detected ellipses between images; and (iv) generating the sphere's geometric digital models. The effectiveness of the proposed method was evaluated under both laboratory and real-world datasets. Laboratory experiments revealed that the proposed process using the best pair of images provided results as accurate as that achieved using eight randomly selected images, while improving computation time by a factor of 50. The results of the two real-world datasets showed that the digital model of a hemispherical dome was generated with 6.2 mm accuracy, while improving the total computation time of current best practice by a factor of 7. Real-world experimentation also showed that the proposed method can provide metric-scale definition for photogrammetric point clouds with 3 mm accuracy using spherical targets. The results suggest that the proposed method was successful in automatically generating fast and accurate geometric digital models of hemispherical domes.

A Probabilistic Approach for Stereo 3D Point Cloud Reconstruction from Airborne Single-Channel Multi-Aspect SAR Image Sequences

We investigate the problem of obtaining dense 3D reconstruction from airborne multi-aspect synthetic aperture radar (SAR) image sequences. Dense 3D reconstructions of multi-view SAR images are vulnerable to anisotropic scatters. To address this issue, we propose a probabilistic 3D reconstruction method based on jointly estimating the pixel’s height and degree of anisotropy. Specifically, we propose a mixture distribution model for the stereo-matching results, where the degree of anisotropy is modeled as an underlying error source. Then, a Bayesian filtering method is proposed for dense 3D point cloud generation. For real-time applications, redundancy in multi-aspect observations is further exploited in a probabilistic manner to accelerate the stereo-reconstruction process. To verify the effectiveness and reliability of the proposed method, 3D point cloud generation is tested on Ku-band drone SAR data for a domestic airport area.

Wasserstein distributional harvesting for highly dense 3D point clouds

In this paper, we present a novel 3D point cloud harvesting method, which can harvest 3D points from an estimated surface distribution in an unsupervised manner (i.e., an input is a prior distribution). Our method outputs the surface distribution of a 3D object and samples 3D points from the distribution based on the proposed progressive random sampling strategy. The progressive sampling regards a prior distribution itself as a network input and uses a progressively increasing number of latent variables for training, which can diversify the coordinates of 3D points with fast convergence. Subsequently, our stochastic instance normalization transforms the implicit distribution into other distributions, which enables diverse shapes of 3D objects. Experimental results show that our method is competitive with other state-of-the-art methods. Our method can harvest an arbitrary number of 3D points, wherein the 3D object is represented in detail with highly dense 3D points or a part of it is described with partial sampling.

Iterative BTreeNet: Unsupervised learning for large and dense 3D point cloud registration

3D point cloud registration is a computational process that aligns two 3D point clouds through transformation. i.e. finding matching translation and rotation. Existing state-of-the-art learning-based methods require ground-truth transformation as supervision and often perform poorly in dealing with partial point clouds and large scenes that are not trained, resulting in poor generalization for neural networks.In this paper, we propose a novel unsupervised deep learning network - Binary Tree Network (BTreeNet) that consists of a novel forward propagation, which learns features for the rotation separately from the translation and avoids the interference between the estimations of rotation and translation in one single matrix. We then propose an Iterative Binary Tree Network (IBTreeNet) to continuously improve the registration accuracy for large and dense 3D point clouds. The Chamfer Distance and the Earth Mover’s Distance are adopted as the loss function for unsupervised learning. We show that BTreeNet and IBTreeNet outperform state-of-the-art learning-based and traditional methods on partial and noisy point clouds without training them in such scenarios. Most importantly, the proposed methods exhibit remarkable generalization and robustness to unseen large and dense scenes that are never trained.

Change detection for indoor construction progress monitoring based on BIM, point clouds and uncertainties

Automatic construction progress documentation and metric evaluation of execution work in confined building interiors requires particularly reliable geometric evaluation and interpretation of statistically uncertain as-built point clouds. This paper presents a method for high-resolution change detection based on dense 3D point clouds from terrestrial laser scanning (TLS) and the discretization of space by voxels. In order to evaluate the metric accuracy of a BIM according to the Level of Accuracy (LOA) specification, the effects of laser range measurements on the occupancy of space are modeled with belief functions and evaluated using Dempster and Shafer's theory of evidence. The application is demonstrated on the point cloud data of multi temporal scanning campaigns of real indoor reconstructions. The results show that TLS point clouds are suitable to verify a given BIM up to LOA 40 if special attention is paid to the scanning geometry during the acquisition. The proposed method can be used to document construction progress, verify and even update the LOA status of a given BIM, confirming valid and BIM-compliant as-built models for further planning.