• IEMEK Journal of Embedded Systems and Applications
• /
• v.16 no.5
• /
• pp.215-223
• /
• 2021

3D data can be categorized into two parts : Euclidean data and non-Euclidean data. In general, 3D data exists in the form of non-Euclidean data. Due to irregularities in non-Euclidean data such as mesh and point cloud, early 3D deep learning studies transformed these data into regular forms of Euclidean data to utilize them. This approach, however, cannot use memory efficiently and causes loses of essential information on objects. Thus, various approaches that can directly apply deep learning architecture to non-Euclidean 3D data have emerged. In this survey, we introduce various deep learning methods for mesh and point cloud data. After analyzing the operating principles of these methods designed for irregular data, we compare the performance of existing methods for shape classification and segmentation tasks.

• Journal of the Society of Naval Architects of Korea
• /
• v.59 no.4
• /
• pp.235-242
• /
• 2022

As ship condition inspection technology has been developed, research on collecting, analyzing, and diagnosing condition information has become active. In ships, related research has been conducted, such as analyzing, detecting, and classifying major hull failures such as cracks and corrosion using 2D and 3D data information. However, for geometric deformation such as indents and bulges, 2D data has limitations in detection, so 3D data is needed to utilize spatial feature information. In this study, we aim to detect hull structural deformation positions. It builds a specimen based on actual hull structure deformation and acquires a point cloud from a model scanned with a 3D scanner. In the obtained point cloud, deformation(outliers) is found with a combination of RANSAC algorithms that find the best matching model in the Octree data structure and dataset.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_1
• /
• pp.1349-1365
• /
• 2020

In recent years, in the fields of smart cities and digital twins, research on model generation is increasing due to the advantage of acquiring actual 3D coordinates by using point clouds. In addition, there is an increasing demand for a solid model that can easily modify the shape and texture of the building. In this paper, we propose a method to create a clustered solid building model based on point cloud data. The proposed method consists of five steps. Accordingly, in this paper, we propose a method to create a clustered solid building model based on point cloud data. The proposed method consists of five steps. In the first step, the ground points were removed through the planarity analysis of the point cloud. In the second step, building area was extracted from the ground removed point cloud. In the third step, detailed structural area of the buildings was extracted. In the fourth step, the shape of 3D building models with 3D coordinate information added to the extracted area was created. In the last step, a 3D building solid model was created by giving texture to the building model shape. In order to verify the proposed method, we experimented using point clouds extracted from unmanned aerial vehicle images using commercial software. As a result, 3D building shapes with a position error of about 1m compared to the point cloud was created for all buildings with a certain height or higher. In addition, it was confirmed that 3D models on which texturing was performed having a resolution of less than twice the resolution of the original image was generated.

• Journal of the Korea Computer Graphics Society
• /
• v.13 no.4
• /
• pp.21-27
• /
• 2007

The 3D Delaunay triangulation is the most widely used method for the mesh creation via the triangulation of a 3D point cloud. However, the method involves a heavy computational cost and, hence, in many interactive applications, it is not appropriate for surface triangulation. In this paper, we propose an efficient triangulation method to create a surface mesh from a 3D point cloud. We divide a set of object points into multiple subsets and apply the 2D Delaunay triangulation to each subset. A given 3D point cloud is cut into slices with respect to the OBB(Oriented Bounding Box) of the point set. The 2D Delaunay triangulation is applied to each subset producing a partial triangulation. The sum of the partial triangulations constitutes the global mesh. As a postprocessing process, we eliminate false edges introduced in the split steps of the triangulation and improve the results. The proposed method can be effectively applied to various image-based modeling applications.

• Journal of Broadcast Engineering
• /
• v.26 no.3
• /
• pp.258-268
• /
• 2021

Point cloud content is immersive content that represents real-world objects with three-dimensional (3D) points. In the process of acquiring point cloud data or encoding and decoding point cloud data, the resolution of point cloud content could be degraded. In this paper, we propose a method of progressively enhancing the resolution of sequential point cloud contents through inter-frame registration. To register a point cloud, the iterative closest point (ICP) algorithm is commonly used. Existing ICP algorithms can transform rigid bodies, but there is a disadvantage that transformation is not possible for non-rigid bodies having motion vectors in different directions locally, such as point cloud content. We overcome the limitations of the existing ICP-based method by registering regions with motion vectors in different directions locally between the point cloud content of the current frame and the previous frame. In this manner, the resolution of the point cloud content with geometric movement is enhanced through the process of registering points between frames. We provide four different point cloud content that has been enhanced with our method in the experiment.

• Journal of the Korean Society for Precision Engineering
• /
• v.24 no.5
• /
• pp.127-134
• /
• 2007

Presented in the paper is an algorithm to generate a section curve by slicing a point cloud including tens of thousands of points. Although, there have been previous research results on the slicing problem, they are quite sensitive on the density variations of the point cloud, as well as on the local noise in the point cloud. To relive the difficulties, three technological requirements are identified; 1) dominant point sampling, 2) avoiding local vibration, and 3) robustness on the density changes. To satisfy these requirements, we propose a new slicing algorithm which is based on a node-sphere diagram. The algorithm has been implemented and tested with various examples.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.12
• /
• pp.505-518
• /
• 2023

3D point cloud semantic segmentation is a computer vision task that involves dividing the point cloud into different objects and regions by predicting the class label of each point. Existing 3D semantic segmentation models have some limitations in performing sufficient fusion of multi-modal features while ensuring both characteristics of 2D visual features extracted from RGB images and 3D geometric features extracted from point cloud. Therefore, in this paper, we propose MMCA-Net, a novel 3D semantic segmentation model using 2D-3D multi-modal features. The proposed model effectively fuses two heterogeneous 2D visual features and 3D geometric features by using an intermediate fusion strategy and a multi-modal cross attention-based fusion operation. Also, the proposed model extracts context-rich 3D geometric features from input point cloud consisting of irregularly distributed points by adopting PTv2 as 3D geometric encoder. In this paper, we conducted both quantitative and qualitative experiments with the benchmark dataset, ScanNetv2 in order to analyze the performance of the proposed model. In terms of the metric mIoU, the proposed model showed a 9.2% performance improvement over the PTv2 model using only 3D geometric features, and a 12.12% performance improvement over the MVPNet model using 2D-3D multi-modal features. As a result, we proved the effectiveness and usefulness of the proposed model.

• Cartoon and Animation Studies
• /
• s.48
• /
• pp.199-215
• /
• 2017

Recently, a drone is used for the general purpose application although the drone was builtfor the military purpose. A drone is actively used for the creation of contents, and an image acquisition. In this paper, we develop a 3D library module platform using 3D mesh model data, which is generated by a drone image and its point cloud. First, a lot of 2D image data are taken by a drone, and a point cloud data is generated from 2D drone images. A 3D mesh data is acquired from point cloud data. Then, we develop a service library platform using a transformed 3D data for multi-purpose uses. Our platform with 3D data can minimize the cost and time of contents creation for special effects during the production of a movie, drama, or documentary. Our platform can contribute the creation of experts for the digital contents production in the field of a realistic media, a special image, and exhibitions.

• Journal of the Society of Naval Architects of Korea
• /
• v.58 no.5
• /
• pp.303-313
• /
• 2021

Recently, quality control of the Liquefied Natural Gas Carrier (LNGC) cargo hold and block-erection interference areas using 3D scanners have been performed, focusing on large shipyards and the international association of classification societies. In this study, as a part of the research on LNGC cargo hold quality management advancement, a study on deep-learning-based scaffolding system 3D point cloud object detection and post-processing were conducted using a LNGC cargo hold 3D point cloud. The scaffolding system point cloud object detection is based on the PointNet deep learning architecture that detects objects using point clouds, achieving 70% prediction accuracy. In addition, the possibility of improving the accuracy of object detection through parameter adjustment is confirmed, and the standard of Intersection over Union (IoU), an index for determining whether the object is the same, is achieved. To avoid the manual post-processing work, the object detection architecture allows automatic task performance and can achieve stable prediction accuracy through supplementation and improvement of learning data. In the future, an improved study will be conducted on not only the flat surface of the LNGC cargo hold but also complex systems such as curved surfaces, and the results are expected to be applicable in process progress automation rate monitoring and ship quality control.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.30 no.8 s.251
• /
• pp.906-915
• /
• 2006

This study concerns an advanced 3D surface reconstruction method that the vertices of surface model can be completely matched to the unstructured point cloud measured from arbitrary complex shapes. The concept of bounding voxel model is introduced to generate the mesh model well-representing the geometrical and topological characteristics of point cloud. In the reconstruction processes, the application of various methodologies such as shrink-wrapping, mesh simplification, local subdivision surface fitting, insertion of is isolated points, mesh optimization and so on, are required. Especially, the effectiveness, rapidity and reliability of the proposed surface reconstruction method are demonstrated by the simulation results for the geometrically and topologically complex shapes like dragon and human mouth.