- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2018 Eighth International Conference on Image Processing Theory, Tools and Applications (IPTA) - Xi'an, China (2018.11.7-2018.11.10)] 2018 Eighth International Conference on Image Processing Theory, Tools and Applications (IPTA) - Classification of LiDAR Point Cloud based on Multiscale Features and PointNet
摘要： Aiming at classifying the feature of LiDAR point cloud data in complex scenario, this paper proposed a deep neural network model based on multi-scale features and PointNet. The method improves the local feature of PointNet and realize automatic classification of LiDAR point cloud under the complex scene. Firstly, this paper adds multi-scale network on the basis of PointNet network to extract the local features of points. And then these local features of different scales are composed into a multi-dimensional feature through the fully connected layer, and combined with the global features extracted by PointNet, the scores of each point class are returned to complete the point cloud classification. The deep neural network model proposed in this paper is verified using the Semantic3D dataset and the Vaihingen dataset provided by ISPRS. The experimental results show that the proposed algorithm achieves higher classification accuracy compared with other neural networks used for point cloud classification.
关键词： Classification of point cloud,multi-scale features,PointNet,LiDAR
更新于2025-09-19 17:15:36
-
Comparing sUAS Photogrammetrically-Derived Point Clouds with GNSS Measurements and Terrestrial Laser Scanning for Topographic Mapping
摘要： Interest in small unmanned aircraft systems (sUAS) for topographic mapping has significantly grown in recent years, driven in part by technological advancements that have made it possible to survey small- to medium-sized areas quickly and at low cost using sUAS aerial photography and digital photogrammetry. Although this approach can produce dense point clouds of topographic measurements, they have not been tested extensively to provide insights on accuracy levels for topographic mapping. This case study examines the accuracy of a sUAS-derived point cloud of a parking lot located at the Citizens Bank Arena (CBA) in Ontario, California, by comparing it to ground control points (GCPs) measured using global navigation satellite system (GNSS) data corrected with real-time kinematic (RTK) and to data from a terrestrial laser scanning (TLS) survey. We intentionally chose a flat surface due to the prevalence of flat scenes in sUAS mapping and the challenges they pose for accurately deriving vertical measurements. When the GNSS-RTK survey was compared to the sUAS point cloud, the residuals were found to be on average 18 mm and ?20 mm for the horizontal and vertical components. Furthermore, when the sUAS point cloud was compared to the TLS point cloud, the average difference observed in the vertical component was 2 mm with a standard deviation of 31 mm. These results indicate that sUAS imagery can produce point clouds comparable to traditional topographic mapping methods and support other studies showing that sUAS photogrammetry provides a cost-effective, safe, efficient, and accurate solution for topographic mapping.
关键词： terrestrial laser scanning (TLS),small unmanned aircraft system (sUAS),point cloud,accuracy,global navigation satellite system (GNSS),photogrammetry
更新于2025-09-19 17:13:59
-
Displacement Study of a Large-Scale Freeform Timber Plate Structure Using a Total Station and a Terrestrial Laser Scanner
摘要： Recent advances in timber construction have led to the realization of complex timber plate structures assembled with wood-wood connections. Although advanced numerical modelling tools have been developed to perform their structural analysis, limited experimental tests have been carried out on large-scale structures. However, experimental investigations remain necessary to better understand their mechanical behaviour and assess the numerical models developed. In this paper, static loading tests performed on timber plate shells of about 25 m span are reported. Displacements were measured at 16 target positions on the structure using a total station and on its entire bottom surface using a terrestrial laser scanner. Both methods were compared to each other and to a finite element model in which the semi-rigidity of the connections was represented by springs. Total station measurements provided more consistent results than point clouds, which nonetheless allowed the visualization of displacement fields. Results predicted by the model were found to be in good agreement with the measurements compared to a rigid model. The semi-rigid behaviour of the connections was therefore proven to be crucial to precisely predict the behaviour of the structure. Furthermore, large variations were observed between as-built and designed geometries due to the accumulation of fabrication and construction tolerances.
关键词： terrestrial laser scanning,total station,finite element spring model,point cloud registration,timber plate structures
更新于2025-09-19 17:13:59
-
[IEEE 2020 IEEE 33rd International Conference on Micro Electro Mechanical Systems (MEMS) - Vancouver, BC, Canada (2020.1.18-2020.1.22)] 2020 IEEE 33rd International Conference on Micro Electro Mechanical Systems (MEMS) - 3D Laser Nanoprinting
摘要： Digital phantoms are vital for various biomedical researches. Traditional phantoms include theoretical models and voxel models reconstructed from medical images. It has been demonstrated that the homogeneous phantom filled with uniform tissue is accurate enough for wearable antenna design, body-centric channel modeling, etc. Therefore, it is interesting and necessary to investigate the novel approach of generating digital phantoms using an optical noncontact measurement system. In this letter, the point cloud data are first obtained; then, they are simplified via principal component analysis; finally, by applying surface reconstruction and mesh simplification techniques, a digital Chinese phantom is established. To verify the usability of the phantom, numerical calculation is performed to check E-fields at different positions on the body. Results sufficiently prove the feasibility of the train of thought presented in this letter.
关键词： noncontact measurement system,point cloud data,Digital phantom,numerical calculation,surface reconstruction,principal component analysis (PCA)
更新于2025-09-19 17:13:59
-
Combined Use of Terrestrial Laser Scanning and UAV Photogrammetry in Mapping Alpine Terrain
摘要： Airborne and terrestrial laser scanning and close-range photogrammetry are frequently used for very high-resolution mapping of land surface. These techniques require a good strategy of mapping to provide full visibility of all areas otherwise the resulting data will contain areas with no data (data shadows). Especially, deglaciated rugged alpine terrain with abundant large boulders, vertical rock faces and polished roche-moutones surfaces complicated by poor accessibility for terrestrial mapping are still a challenge. In this paper, we present a novel methodological approach based on a combined use of terrestrial laser scanning (TLS) and close-range photogrammetry from an unmanned aerial vehicle (UAV) for generating a high-resolution point cloud and digital elevation model (DEM) of a complex alpine terrain. The approach is demonstrated using a small study area in the upper part of a deglaciated valley in the Tatry Mountains, Slovakia. The more accurate TLS point cloud was supplemented by the UAV point cloud in areas with insu?cient TLS data coverage. The accuracy of the iterative closest point adjustment of the UAV and TLS point clouds was in the order of several centimeters but standard deviation of the mutual orientation of TLS scans was in the order of millimeters. The generated high-resolution DEM was compared to SRTM DEM, TanDEM-X and national DMR3 DEM products con?rming an excellent applicability in a wide range of geomorphologic applications.
关键词： terrestrial laser scanning,digital modelling,point cloud,UAV photogrammetry,alpine terrain
更新于2025-09-19 17:13:59
-
Research on Fast Calculation Method of Complex Soil Yard Excavation Volume Based on 3D Laser Scanning
摘要： The measurement of earthwork excavation in hydropower project construction is an important control process in engineering construction. The traditional measurement and calculation process is not only inefficient, but also easy to cause errors. In this paper, the 3D laser scanner is applied to continuously measure the excavation process of the soil material yard and the efficient processing method of registration, compression and extraction process of excavation point cloud data is established respectively. At the same time, two fast calculation methods of excavation volume based on point cloud data are established. The practical application proves the data processing method established in this paper can shorten the data processing time by more than 80%, and ensure the accuracy of the data, and can control the calculation error of the excavation volume within 1%.
关键词： 3D laser scanning,point cloud data,volume calculation,earthwork excavation,hydropower project
更新于2025-09-19 17:13:59
-
Review of mobile laser scanning target‐free registration methods for urban areas using improved error metrics
摘要： Registration is one of the most important tasks in mobile laser scanning (MLS) point cloud processing. This paper ?rstly reviews existing target-free matching techniques as well as methods to evaluate the quality of the registration. Next, a new error metric is introduced that takes into account the residuals of check planes as well as their orientation. Experiments using real datasets in combination with reference data were performed to evaluate the suitability of these metrics. The proposed error metric proved to be more suitable for evaluating the quality of point cloud registration than state-of-the-art equivalents. The results also indicate that least squares plane ?tting is the best technique for MLS point cloud registration.
关键词： point cloud matching,target-free registration,matching quality,error metric,mobile laser scanning
更新于2025-09-19 17:13:59
-
[IEEE 2019 18th International Conference on Optical Communications and Networks (ICOCN) - Huangshan, China (2019.8.5-2019.8.8)] 2019 18th International Conference on Optical Communications and Networks (ICOCN) - A Fast Point Cloud Segmentation Algorithm Based on Region Growth
摘要： Point cloud segmentation is a key prerequisite for object classification recognition. We propose a fast region growing algorithm by using the neighborhood search, filter sampling, Euclidean clustering and region growth. Segmentation experiment on point cloud data in indoor environment demonstrated that segmentation accuracy and efficiency were improved by the proposed algorithm.
关键词： regional growth,Euclidean clustering,point cloud segmentation
更新于2025-09-16 10:30:52
-
Automated Method for Detection of Missing Road Point Regions in Mobile Laser Scanning Data
摘要： The paper proposes a method supported by MATLAB for detection and measurement of missing point regions (MPR) which may cause severe road information loss in mobile laser scanning (MLS) point clouds. First, the scan-angle thresholds are used to segment the road area for MPR detection. Second, the segmented part is mapped onto a binary image with a pixel size of ε through rasterization. Then, MPR featuring connected 1-pixels are identi?ed and measured via image processing techniques. Finally, the parameters regarding MPR in the image space are reparametrized in relation to the vehicle path recorded in MLS data for a better understanding of MPR properties on the geodetic plane. Tests on two MLS datasets show that the output of the proposed approach can e?ectively detect and assess MPR in the dataset. The ε parameter exerts a substantial in?uence on the performance of the method, and it is recommended that its value should be optimized for accurate MPR detections.
关键词： occlusion,image processing,missing points,point cloud,mobile laser scanning
更新于2025-09-16 10:30:52
-
[IEEE 2019 Chinese Control And Decision Conference (CCDC) - Nanchang, China (2019.6.3-2019.6.5)] 2019 Chinese Control And Decision Conference (CCDC) - The Weld Extraction Algorithm for Robotic Arc Welding Based on 3D Laser Sensor
摘要： A weld extraction algorithm combining 2D image and 3D point cloud data is proposed in this paper, based on 3D laser sensor and a six-DOF industrial robot. Firstly, 3D point cloud data and 2D depth image can be obtained through the 3D laser sensor. Secondly, the weld feature points can be extracted while the weld can be accurately positioned, using 2D image processing method. Thirdly, the 3D weld information can be extracted by 2D weld mapping to 3D space through certain rules. Finally, the feasibility of the proposed algorithm is verified by experiments. The results strongly prove that the algorithm can be used to obtain the 3D weld information of type 1 weld in the bicycle frame, which completely meets the needs of industrial production.
关键词： 2D image processing,3D point cloud,Bicycle frame,Weld extraction
更新于2025-09-16 10:30:52