Reconstruction Of Surface Models Research Articles

DSM Reconstruction from Uncalibrated Multi-View Satellite Stereo Images by RPC Estimation and Integration

In this paper, we propose a 3D Digital Surface Model (DSM) reconstruction method from uncalibrated Multi-view Satellite Stereo (MVSS) images, where Rational Polynomial Coefficient (RPC) sensor parameters are not available. While recent investigations have introduced several techniques to reconstruct high-precision and high-density DSMs from MVSS images, they inherently depend on the use of geo-corrected RPC sensor parameters. However, RPC parameters from satellite sensors are subject to being erroneous due to inaccurate sensor data. In addition, due to the increasing data availability from the internet, uncalibrated satellite images can be easily obtained without RPC parameters. This study proposes a novel method to reconstruct a 3D DSM from uncalibrated MVSS images by estimating and integrating RPC parameters. To do this, we first employ a structure from motion (SfM) and 3D homography-based geo-referencing method to reconstruct an initial DSM. Second, we sample 3D points from the initial DSM as references and reproject them to the 2D image space to determine 3D–2D correspondences. Using the correspondences, we directly calculate all RPC parameters. To overcome the memory shortage problem while running the large size of satellite images, we also propose an RPC integration method. Image space is partitioned to multiple tiles, and RPC estimation is performed independently in each tile. Then, all tiles’ RPCs are integrated into the final RPC to represent the geometry of the whole image space. Finally, the integrated RPC is used to run a true MVSS pipeline to obtain the 3D DSM. The experimental results show that the proposed method can achieve 1.455 m Mean Absolute Error (MAE) in the height map reconstruction from multi-view satellite benchmark datasets. We also show that the proposed method can be used to reconstruct a geo-referenced 3D DSM from uncalibrated and freely available Google Earth imagery.

Reconstruction method of high-precision longwall mining floor curved surface model driven by data points fitting of equipment

Abstract High-precision coal seam model is the basis of intelligent mining. The longwall mining face floor model, which can provide data sources for the correction of the dynamic coal seam model, is difficult to measurement directly. To address this issue, this paper proposes a high-precision coal seam surface model reconstruction and correction method based on a large number of operating data points. Firstly, the coupling model of equipment and floor is obtained based on the coupling model of plane and surface. Subsequently, the plane data points of the equipment are corrected based on the coupling model of equipment and floor to obtain the floor reconstruction points. The Catmull–Clark surface subdivision method is then used to subdivide the plane formed by the equipment data points to obtain surface subdivision points. The floor model reconstructed using surface data points is validated and corrected using the physics engine in the Unity 3d platform. Finally, the verification of the reconstruction point selection method, the coupling principle between the equipment and the floor model, the reconstruction accuracy of the base plate and the correction principle were carried out based on the equipment and floor model in the laboratory. The experimental results show the feasibility of the floor reconstruction, verification and correction method, which can provide a new idea for the reconstruction of the floor of the longwall mining face and the correction of the dynamic coal seam.

A fully automatic fiducial detection and correspondence establishing method for online C-arm calibration.

Online C-arm calibration with a mobile fiducial cage plays an essential role in various image-guided interventions. However, it is challenging to develop a fully automatic approach, which requires not only an accurate detection of fiducial projections but also a robust 2D-3D correspondence establishment. We propose a novel approach for online C-arm calibration with a mobile fiducial cage. Specifically, a novel mobile calibration cage embedded with 16 fiducials is designed, where the fiducials are arranged to form 4 line patterns with different cross-ratios. Then, an auto-context-based detection network (ADNet) is proposed to perform an accurate and robust detection of 2D projections of those fiducials in acquired C-arm images. Subsequently, we present a cross-ratio consistency-based 2D-3D correspondence establishing method to automatically match the detected 2D fiducial projections with those 3D fiducials, allowing for an accurate online C-arm calibration. We designed and conducted comprehensive experiments to evaluate the proposed approach. For automatic detection of 2D fiducial projections, the proposed ADNet achieved a mean point-to-point distance of pixels. Additionally, the proposed C-arm calibration approach achieved a mean re-projection error of pixels and a mean point-to-line distance of mm. When the proposed C-arm calibration approach was applied to downstream tasks involving landmark and surface model reconstruction, sub-millimeter accuracy was achieved. In summary, we developed a novel approach for online C-arm calibration. Both qualitative and quantitative results of comprehensive experiments demonstrated the accuracy and robustness of the proposed approach. Our approach holds potentials for various image-guided interventions.

Surgical Navigation in the Anterior Skull Base Using 3-Dimensional Endoscopy and Surface Reconstruction

Image guidance is an important adjunct for endoscopic sinus and skull base surgery. However, current systems require bulky external tracking equipment, and their use can interrupt efficient surgical workflow. To evaluate a trackerless surgical navigation system using 3-dimensional (3D) endoscopy and simultaneous localization and mapping (SLAM) algorithms in the anterior skull base. This interventional deceased donor cohort study and retrospective clinical case study was conducted at a tertiary academic medical center with human deceased donor specimens and a patient with anterior skull base pathology. Participants underwent endoscopic endonasal transsphenoidal dissection and surface model reconstruction from stereoscopic video with registration to volumetric models segmented from computed tomography (CT) and magnetic resonance imaging. To assess the fidelity of surface model reconstruction and accuracy of surgical navigation and surface-CT model coregistration, 3 metrics were calculated: reconstruction error, registration error, and localization error. In deceased donor models (n = 9), high-fidelity surface models of the posterior wall of the sphenoid sinus were reconstructed from stereoscopic video and coregistered to corresponding volumetric CT models. The mean (SD; range) reconstruction, registration, and localization errors were 0.60 (0.24; 0.36-0.93), 1.11 (0.49; 0.71-1.56) and 1.01 (0.17; 0.78-1.25) mm, respectively. In a clinical case study of a patient who underwent a 3D endoscopic endonasal transsphenoidal resection of a tubercular meningioma, a high-fidelity surface model of the posterior wall of the sphenoid was reconstructed from intraoperative stereoscopic video and coregistered to a volumetric preoperative fused CT magnetic resonance imaging model with a root-mean-square error of 1.38 mm. The results of this study suggest that SLAM algorithm-based endoscopic endonasal surgery navigation is a novel, accurate, and trackerless approach to surgical navigation that uses 3D endoscopy and SLAM-based algorithms in lieu of conventional optical or electromagnetic tracking. While multiple challenges remain before clinical readiness, a SLAM algorithm-based endoscopic endonasal surgery navigation system has the potential to improve surgical efficiency, economy of motion, and safety.

LatentPCN: latent space-constrained point cloud network for reconstruction of 3D patient-specific bone surface models from calibrated biplanar X-ray images.

Accurate three-dimensional (3D) models play crucial roles in computer assisted planning and interventions. MR or CT images are frequently used to derive 3D models but have the disadvantages that they are expensive or involving ionizing radiation (e.g., CT acquisition). An alternative method based on calibrated 2D biplanar X-ray images is highly desired. A point cloud network, referred as LatentPCN, is developed for reconstruction of 3D surface models from calibrated biplanar X-ray images. LatentPCN consists of three components: an encoder, a predictor, and a decoder. During training, a latent space is learned to represent shape features. After training, LatentPCN maps sparse silhouettes generated from 2D images to a latent representation, which is taken as the input to the decoder to derive a 3D bone surface model. Additionally, LatentPCN allows for estimation of a patient-specific reconstruction uncertainty. We designed and conducted comprehensive experiments on datasets of 25 simulated cases and 10 cadaveric cases to evaluate the performance of LatentLCN. On these two datasets, the mean reconstruction errors achieved by LatentLCN were 0.83mm and 0.92mm, respectively. A correlation between large reconstruction errors and high uncertainty in the reconstruction results was observed. LatentPCN can reconstruct patient-specific 3D surface models from calibrated 2D biplanar X-ray images with high accuracy and uncertainty estimation. The sub-millimeter reconstruction accuracy on cadaveric cases demonstrates its potential for surgical navigation applications.

Protective Coating Interfaces for Perovskite Solar Cell Materials: A First-Principles Study.

The protection of halide perovskites is important for the performance and stability of emergent perovskite-based optoelectronic technologies. In this work, we investigate the potential inorganic protective coating materials ZnO, SrZrO3, and ZrO2 for the CsPbI3 perovskite. The optimal interface registries are identified with Bayesian optimization. We then use semilocal density functional theory (DFT) to determine the atomic structure at the interfaces of each coating material with the clean CsI-terminated surface and three reconstructed surface models with added PbI2 and CsI complexes. For the final structures, we explore the level alignment at the interface with hybrid DFT calculations. Our analysis of the level alignment at the coating–substrate interfaces reveals no detrimental mid-gap states but rather substrate-dependent valence and conduction band offsets. While ZnO and SrZrO3 act as insulators on CsPbI3, ZrO2 might be suitable as an electron transport layer with the right interface engineering.

RTSfM: Real-Time Structure From Motion for Mosaicing and DSM Mapping of Sequential Aerial Images With Low Overlap

Inspired by simultaneous localization and mapping (SLAM) style workflow, this article presented an online sequential structure from motion (SfM) solution for high-frequency video and large baseline high-resolution aerial images with high efficiency and novel precision. First, as traditional SLAM systems are not good in processing low overlap images, based on our novel hierarchical feature matching paradigm with multihomography and BoW, we proposed a robust tracking method where the relative pose and its scale are estimated separately followed by a joint optimization by considering both perspective-n-point (PnP) and epipolar constraints. Second, to further optimize the camera poses for the sparse map and dense pointcloud reconstruction, we provided a graph-based optimization with reprojection and GPS constraints, which make the camera trajectory and map georeferenced. We also incrementally generated the dense point cloud in real time from keyframes after local mapping optimization. Finally, we use a publicly available aerial image dataset with sequences of different environments, to evaluate the effectiveness of the proposed method, meanwhile, the robust performance of our solution is demonstrated with applications of high-quality aerial images mosaic and digital surface model (DSM) reconstruction in real time. Compared with the state-of-the-art SLAM and traditional SfM methods, the presented system can output large-scale high-quality ortho-mosaic and DSM in real time with the low computational cost.

Semantic Joint Monocular Remote Sensing Image Digital Surface Model Reconstruction Based on Feature Multiplexing and Inpainting

Digital surface model (DSM) presents height information of the Earth’s surface and plays an important role in many remote sensing (RS) applications. Since the conventional acquisition of DSM is laborious and expensive, DSM reconstruction from monocular RS images has attracted extensive research in recent years, which is an ill-posed problem and thus rather challenging. Related works have achieved great accomplishments in this regard; however, they still face some limitations in training robustness, accuracy, and efficiency. To address the issues, a semantic joint monocular RS image DSM regression framework is proposed in this article, whose salient points include that: 1) semantic segmentation is integrated into the DSM regression task so that a shared backbone can extract complementary features from each objective to improve the performance of the individual task. Meanwhile, based on the consistency of the two training objectives, a two-stage joint loss function is introduced to improve the convergence and robustness of model training; 2) an encoding–decoding backbone is designed based on feature multiplexing, which simultaneously achieves multiscale feature fusion and information decoupling, thereby greatly reducing model parameters and improving efficiency while ensuring feature extraction effect; and 3) an iterative upsampling approach is introduced to transform the full-scale spatial features into large receptive-field and locally discriminative dynamic kernels, which are used to inpaint coarse-grained features while decoding, thus enhancing regression accuracy. Finally, experiments demonstrate the effectiveness of the proposal. It is easy to train and achieves superior or comparable accuracy compared with state-of-the-art related works while improving the efficiency by a large margin.

Assessing Surface Texture Features of Asphalt Pavement Based on Three-Dimensional Laser Scanning Technology

Pavement surface texture features are one of key factors affecting the skid resistance of pavement. In this study, a set of stable and reliable texture measurement equipment was firstly assembled by using the linear laser ranging sensor, control system and data acquisition system. Secondly, the equipment was calibrated, and the superposition error of sensor and control system was tested by making a standard gauge block. Thirdly, four different kinds of asphalt mixture were designed, and their surface texture features were obtained by leveraging a three-dimensional laser scanner. Therefore, the surface texture features were characterized as one-dimensional profile features and three-dimensional surface features. At the end of this study, a multi-scale texture feature characterization method was proposed. Results demonstrate that the measurement accuracy of the laser scanning system in the x-axis direction can be controlled ranging from −0.01 mm to 0.01 mm, the resolution in the XY plane is 0.05 mm, and the reconstructed surface model of surface texture features can achieve a good visualization effect. They also show that the root mean square deviation of surface profiles of different asphalt pavements fluctuates greatly, which is mainly affected by the nominal particle size of asphalt mixture and the proportion of coarse aggregate, and the non-uniformity of pavement texture distribution makes it difficult to characterize the roughness of asphalt pavement effectively by a single pavement surface profile. This study proposed a texture section method to describe the 3D distribution of road surface texture at different depths. The macrotexture of the road surface gradually changes from sparse to dense starting from the shallow layer. The actual asphalt pavement texture can be characterized by a simplified combination model of “cone + sphere + column”. By calculating the surface area distribution of macro and microtextures of different asphalt pavements, it was concluded that the surface area of asphalt pavement under micro scale is about 1.8–2.2 times of the cutting area, and the surface area of macrotexture is about 1.4 times of the cutting area. Moreover, this study proposed texture distribution density to characterize the roughness of asphalt pavement texture at different scales. The SMA index can represent the macroscopic structure level of different asphalt pavements to a certain extent, and the SMI index can well represent the friction level of different asphalt pavements.

A novel geometry image to accurately represent a surface by preserving mesh topology

Geometry images parameterise a mesh with a square domain and store the information in a single chart. A one-to-one correspondence between the 2D plane and the 3D model is convenient for processing 3D models. However, the parameterised vertices are not all located at the intersection of the gridlines the existing geometry images. Thus, errors are unavoidable when a 3D mesh is reconstructed from the chart. In this paper, we propose parameterise surface onto a novel geometry image that preserves the constraint of topological neighbourhood information at integer coordinate points on a 2D grid and ensures that the shape of the reconstructed 3D mesh does not change from supplemented image data. We find a collection of edges that opens the mesh into simply connected surface with a single boundary. The point distribution with approximate blue noise spectral characteristics is computed by capacity-constrained delaunay triangulation without retriangulation. We move the vertices to the constrained mesh intersection, adjust the degenerate triangles on a regular grid, and fill the blank part by performing a local affine transformation between each triangle in the mesh and image. Unlike other geometry images, the proposed method results in no error in the reconstructed surface model when floating-point data are stored in the image. High reconstruction accuracy is achieved when the xyz positions are in a 16-bit data format in each image channel because only rounding errors exist in the topology-preserving geometry images, there are no sampling errors. This method performs one-to-one mapping between the 3D surface mesh and the points in the 2D image, while foldovers do not appear in the 2D triangular mesh, maintaining the topological structure. This also shows the potential of using a 2D image processing algorithm to process 3D models.

Surface reconstruction of tetragonal methylammonium lead triiodide

We present a detailed first-principles analysis of the (001) surface of methylammonium lead triiodide (MAPbI3). With density functional theory, we investigate the atomic and electronic structure of the tetragonal (I4cm) phase of MAPbI3. We analyzed surface models with MAI-termination (MAI-T) and PbI2-termination (PbI2-T). For both terminations, we studied the clean surface and a series of surface reconstructions. We find that the clean MAI-T model is more stable than its counterpart, PbI2-T. For the MAI-T, reconstructions with added or removed units of nonpolar MAI and PbI2 are most stable. The corresponding band structures reveal surface states originating from the conduction band. Despite the presence of such additional surface states, our stable reconstructed surface models do not introduce new states within the bandgap.

Extraction of the discontinuity orientation from a digital surface model

The traditional field contact measurement for obtaining parameters of the rock mass discontinuity is of low efficiency and big workload, and the accuracy of the results are affected by human factors. In this paper a method is presented to automatically recognize the discontinuity based on the 3D digital surface model of rock mass obtained with the digital photogrammetry and SFM algorithm. The steps of rock mass DSM reconstruction include collecting rock mass images, matching image features based on the SIFT algorithm, reconstructing sparse point cloud, encrypting point cloud, and reconstructing the rock mass surface model. The main flow of the discontinuity recognition method include smoothing the DSM of rock mass, changing the searching radius and the angle threshold to split model plane, searching the discontinuity based on the regional growth principle, and fitting the discontinuity based on random sampling consistency to get the orientation. The method is applied to the underground experimental roadway in the Beishan area of Gansu, and the reconstruction of 3D digital surface model of roadway and the orientation acquisition of discontinuities are realized. The discontinuities are also mapped on the roadway model by groups. A comparison the results with those of the manual field measurement method and the existing discontinuity recognition software shows that the method proposed in this paper is of good accuracy and can provide a certain reference for engineering applications.

Watertight 2-manifold 3D bone surface model reconstruction from CT images based on visual hyper-spherical mapping.

This paper proposes a general algorithm to reconstruct watertight 2-manifold 3D bone surface model from CT images based on visual hyper-spherical mapping. The reconstruction algorithm includes three main steps: two-step thresholding, initial watertight surface reconstruction and shape optimization. Firstly, volume sampling points of the target bone with given narrower threshold range are extracted by thresholding with combination of 3D morphology operation. Secondly, visible points near the bone's outer surface are extracted from its corresponding volume sampling points by hyper-spherical projection mapping method. Thirdly, implicit surface reconstruction algorithm is employed on the extracted visible surface points to obtain an initial watertight 3D bone surface model which is used as the deformation model in the following accurate bone surface model generation stage. Finally, the initial surface model is deformed according to the segmentation data with wider threshold range under given constraints in order to achieve an accurate watertight 3D bone surface model. Experiment and comparison results show that the proposed algorithm can reconstruct watertight 3D bone surface model from CT images, and local details of the bone surface can be restored accurately for the cases used in this paper.

Research on Slope Model Reconstruction Based on Mobile Terminal Monocular Vision

In this paper, a method of slope surface model reconstruction based on smart phone is proposed for the problems of point layout limitation, expensive measuring equipment and easy operation of monitoring personnel. By explaining the principle and steps of the SfM-MVS algorithm, the slope surface model is reconstructed based on the slope image taken by smart phone. In this paper, the principle of partial reconstruction is described, which involves the principle of polar geometry and projection error, and the corresponding description of motion recovery structure algorithm and dense reconstruction algorithm steps. The concrete steps of slope 3D reconstruction are as follows: first, the mobile phone camera is calibrated by Zhang Zhengyou camera and the slope image is enhanced for subsequent processing. Finally, the SfM-MVS algorithm is used for sparse reconstruction and dense reconstruction to obtain point cloud data, and the slope surface model is reconstructed by triangulation and texture mapping. The slope surface model obtained by smartphone image lays the foundation of slope shape change monitoring and coordinate calculation, and has the characteristics of perfect slope overall information. The model reconstruction based on mobile terminal image acquisition can reduce the equipment cost of slope monitoring and the maneuverability of monitoring personnel, and has certain application value.

Structure-from-Motion-Derived Digital Surface Models from Historical Aerial Photographs: A New 3D Application for Coastal Dune Monitoring

Recent advances in structure-from-motion (SfM) techniques have proliferated the use of unmanned aerial vehicles (UAVs) in the monitoring of coastal landform changes, particularly when applied in the reconstruction of 3D surface models from historical aerial photographs. Here, we explore a number of depth map filtering and point cloud cleaning methods using the commercial software Agisoft Metashape Pro to determine the optimal methodology to build reliable digital surface models (DSMs). Twelve different aerial photography-derived DSMs are validated and compared against light detection and ranging (LiDAR)- and UAV-derived DSMs of a vegetated coastal dune system that has undergone several decades of coastline retreat. The different studied methods showed an average vertical error (root mean square error, RMSE) of approximately 1 m, with the best method resulting in an error value of 0.93 m. In our case, the best method resulted from the removal of confidence values in the range of 0–3 from the dense point cloud (DPC), with no filter applied to the depth maps. Differences among the methods examined were associated with the reconstruction of the dune slipface. The application of the modern SfM methodology to the analysis of historical aerial (vertical) photography is a novel (and reliable) new approach that can be used to better quantify coastal dune volume changes. DSMs derived from suitable historical aerial photographs, therefore, represent dependable sources of 3D data that can be used to better analyse long-term geomorphic changes in coastal dune areas that have undergone retreat.

A new Construction Method of Vehicle Digital Camouflage Spraying Model

Digital camouflage plays an important role in improving the combat performance of vehicles. The reconstruction of the spraying model of the automobile surface can improve the automation level of the digital camouflage painting operation. The surface digital camouflage spraying model construction method is a processing flow that incorporates a variety of technical methods, including surface point cloud data collection technology, point cloud synthesis and segmentation method, surface model reconstruction method and spray pattern fusion technology. Four linear laser sensors are used to scan the vehicle surface to obtain the local point cloud data of the vehicle. The vehicle CAD model and the painting pattern figures are analysed. And the region growing segmentation method is used to subdivide the scanned point cloud data. For the point cloud after partitioning, the point set of the digital camouflage pattern is directly searched by using the constructed discrete metric. Then each point cloud is merged with the 2D camouflage pattern to obtain the digital camouflage spraying model of the vehicle surface.

Distribution of bone thickness in the human mandibular ramus \u2013 a CBCT-based study

BackgroundThe bone thickness of the human mandibular ramus is an important parameter in mandibular surgeries. The aim of this study was to systematically measure the bicortical bone thickness, the ramus dimensions and the position of the lingula. The measurements were tested on significant correlations to the patients’ parameters.MethodsBased on CBCT scans 150 rami were reconstructed as 3D polygon surfaces. An anatomical grid was adapted to the ramus surface to mark the bone thickness measurement points and to achieve comparability between the measurements on different mandibles. The bone thickness, ramus height, ramus width and the gonion angle were measured. A cluster analysis was performed with these parameters to identify clinically relevant groups with anatomical similarities.ResultsThe median distribution of the bone thickness was calculated and visualized in a pseudo-colour map. The mean ramus height was 44.78 mm, the mean width was 31.31 mm and the mean gonion angle was 124.8°. The average distance from the lingula to the dorsal tangent was 53% of the total width and its distance to the caudal tangent was 65% of the total height. Significant correlations between the bone thickness and the ramus proportions could be identified. Age and sex had no significant influence on the mean bone thickness. The measured rami could be divided into two groups by cluster analysis.ConclusionThe dimensions of the human mandibular ramus can be determined from 3D reconstructed surface models from CBCT scans. Measurements could be made comparable by applying an anatomically oriented grid. A cluster analysis allowed the differentiation of two groups with different bone thickness distributions and geometries, which can be used for the optimization of osteosynthesis systems and their precision of adaptation to different ramus morphologies.

Rock surface modeling as a tool to assess the morphology of inland notches, Mount Carmel, Israel

Inland notches are elongated C-shape indentations carved into hard, dense carbonate rocks of the Mediterranean climate zone. In recent years these unique features became of particular interest as geoindicators of denudation and slope erosion processes. The study goals are to learn the processes acting upon the notches cavity by (1) examining the micromorphology of the backwall, (2) identifying and classifying zones of erosion, (3) learning the surface flow pattern and, (4) proposing an erosion mechanism induced by exfoliation. To this end, a machine learning algorithm was designed, using the microstructure, texture, streamlines formation and potential focal flow. The workflow uses data from terrestrial laser scanning, applies high-resolution textural and curvature analyses and trains an artificial neural network to the different segments of the notch. The reconstructed surface model shows division into three distinct belts within the cavity surface: (1) The spalled belt [SB]; (2) The transition zone belt [TZ] and (3) The deposition belt [DB]. Each belt owes its distinct microtopography, implying on different geomorphic processes. The newly developed methodology improves the recognition of streamline networks along the cavity backwall, which mimic alluvial networks. The organization of the reconstructed micro channels is similar to drainage basin systems, where, first order channels developed upstream converge into larger ones and diverge as distributaries as the gradient decreases, depositing tufa along the notches base.

Automatic 3-D Reconstruction of Indoor Environment With Mobile Laser Scanning Point Clouds

Three-dimensional (3-D) modeling of indoor environment plays an important role in various applications such as indoor navigation, Building Information Modeling (BIM), interactive visualization, etc. While automated reconstruction of 3-D models from point clouds is receiving more and more attention. Indoor modeling remains a challenging task in terms of dealing with the complexity of indoor environment, the level of automation and restrictions of input data. To address these issues, an automatic indoor reconstruction method that quickly and effectively reconstructs indoor environment of multi-floors and multi-rooms using both point clouds and trajectories from mobile laser scanning (MLS) is proposed. The proposed automatic method of parametric structure modeling comprises three steps. First, structural elements, such as doors, windows, walls, floors, and ceilings, are extracted based on the geometric and semantic features of point clouds. Then, the point clouds are automatically segmented into adjoining rooms through a combination of visibility analysis and physical constraints of the structural elements, which ensures the integrity of the room-space partitions and yields priors for the definition of point cloud label for reconstructed model. Finally, 3-D models of individual rooms are constructed by solving an energy optimization function via multi-label graph cuts. Three benchmark datasets collected by two handheld laser scanning (HLS) and a backpack laser scanning (BLS) system were used to evaluate the proposed method. Experiments demonstrate that the recall and precision of reconstructed surface models obtained by the proposed method are mostly larger than 60%, and the average F1-score of the model is close to 5 cm.

Three-Dimensional Reconstruction of Structural Surface Model of Heritage Bridges Using UAV-Based Photogrammetric Point Clouds

Three-dimensional (3D) digital technology is essential to the maintenance and monitoring of cultural heritage sites. In the field of bridge engineering, 3D models generated from point clouds of existing bridges is drawing increasing attention. Currently, the widespread use of the unmanned aerial vehicle (UAV) provides a practical solution for generating 3D point clouds as well as models, which can drastically reduce the manual effort and cost involved. In this study, we present a semi-automated framework for generating structural surface models of heritage bridges. To be specific, we propose to tackle this challenge via a novel top-down method for segmenting main bridge components, combined with rule-based classification, to produce labeled 3D models from UAV photogrammetric point clouds. The point clouds of the heritage bridge are generated from the captured UAV images through the structure-from-motion workflow. A segmentation method is developed based on the supervoxel structure and global graph optimization, which can effectively separate bridge components based on geometric features. Then, recognition by the use of a classification tree and bridge geometry is utilized to recognize different structural elements from the obtained segments. Finally, surface modeling is conducted to generate surface models of the recognized elements. Experiments using two bridges in China demonstrate the potential of the presented structural model reconstruction method using UAV photogrammetry and point cloud processing in 3D digital documentation of heritage bridges. By using given markers, the reconstruction error of point clouds can be as small as 0.4%. Moreover, the precision and recall of segmentation results using testing date are better than 0.8, and a recognition accuracy better than 0.8 is achieved.