• Tunnel and Underground Space
• /
• v.25 no.1
• /
• pp.97-106
• /
• 2015

We must precisely investigate the mechanical characters of rock to design rock slope safely and efficiently. But the method of clinometer has some disadvantages. So, we need a new measurement that can replace the method of clinometer. In this study, we analyze the reliability of joint orientation measurements in rock slope using the 3D laser scanner and program Split-FX that is a point cloud data analysis software. We could acquire the 495 pieces joint data through the automatic extraction of features. And we confirmed that there were some errors occurred with ${\pm}4^{\circ}$ of dip and ${\pm}5^{\circ}$ of dip direction. Generally, the method of clinometer has ${\pm}5^{\circ}$ and ${\pm}10^{\circ}$ error ranges of the joint orientation(dip/dip direction) that are the results of the advance research. Therefore, we analyzed the method of 3D laser scanner, and it is found to be efficient, reliable. This method is expected to mend the disadvantages of Clinometer method.

• 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.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.6
• /
• pp.874-880
• /
• 2018

3D modeling is extensively used in the field of architecture, machinery and contents production such as movies. Modeling is a time-consuming task. In order to compensate for these drawbacks, attempts have recently been made to reduce the production period by applying 3D scanning technology. 3D scanning for small objects can be done directly with laser or optics, but large buildings and sculptures require expensive equipment, which makes it difficult to acquire data directly. In this study, 3D modeling data for a large object is acquired using photometry with using drones to acquire the image data. The maintenance method for uniform spacing between the sculpture and the drone, the measurement method for the flight line were presented. In addition, we presented a production environment that can utilize the obtained 3D point cloud data for animation and a rendered animation result to find ways to make it in various environments.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.11a
• /
• pp.219-222
• /
• 2008

3차원 인체 스캐너로부터 얻어진 인체형상데이터는 여러 인체에 대한 3차원 평균 모델을 만들어 내는 등의 통계적 분석이나 자세 변경을 위해 필요한 내부 골격 구조와 골격과 피부조직 사이의 관계 등을 계산해 내기 어렵다. 또, 이러한 통계적 분석을 위해서는 각 모델 간의 상응 관계가 확립되어야 하지만 스캐너로부터 얻어진 인체 형상 데이터들은 측정 환경이나 대상에 따라 각각이 서로 상이한 기하학적 구조로 이루어져 있다. 본 논문에서는 템플릿 모델을 3차원 인체데이터에 맞도록 변형함으로써 다수의 인체 형상에 대하여 토폴로지를 일치시키도록 한다. 3차원 인체 데이터에 대해 템플릿 모델이 가장 근사한 형상이 되도록 하는 변형을 자동으로 찾아내기 위해서 표면 위에 정의된 특징점들을 사용한다. 또한, 기존에 찾아둔 특징점군 및 변형정보 데이터가 충분히 많다면 새로운 변형을 계산하는 데 유용하게 사용될 수 있음을 보인다. 이렇게 상응 관계가 확립된 모델들은 삼차원 벡터 공간의 점들의 집합으로 표현 및 통계적 분석이 가능하게 된다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.3
• /
• pp.16-22
• /
• 2019

Off-line programming and robot calibration through simulation are essential when setting up a robot in a robot automation production line. In this study, we developed a new robot calibration method to match the CAD data of the production line with the measurement data on the site using 3D scanner. The proposed method calibrates the robot using 3D point cloud data through Iterative Closest Point algorithm. Registration is performed in three steps. First, vertices connected by three planes are extracted from CAD data as feature points for registration. Three planes are reconstructed from the scan point data located around the extracted feature points to generate corresponding feature points. Finally, the transformation matrix is calculated by minimizing the distance between the feature points extracted through the ICP algorithm. As a result of applying the software to the automobile welding robot installation, the proposed method can calibrate the required accuracy to within 1.5mm and effectively shorten the set-up time, which took 5 hours per robot unit, to within 40 minutes. By using the developed system, it is possible to shorten the OLP working time of the car body assembly line, shorten the precision teaching time of the robot, improve the quality of the produced product and minimize the defect rate.

• Journal of Broadcast Engineering
• /
• v.28 no.3
• /
• pp.329-332
• /
• 2023

3D Object Detection using deep neural network has been developed a lot for obstacle detection in autonomous vehicles because it can recognize not only the class of target object but also the distance from the object. But in the case of 3D Object Detection models, the detection performance for distant objects is lower than that for nearby objects, which is a critical issue for autonomous vehicles. In this paper, we introduce a technique that increases the performance of 3D object detection models, particularly in recognizing distant objects, by generating virtual 3D vehicle data and adding it to the dataset used for model training. We used a spherical point tracing method that leverages the characteristics of 3D LiDAR sensor data to create virtual vehicles that closely resemble real ones, and we demonstrated the validity of the virtual data by using it to improve recognition performance for objects at all distances in model training.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.1
• /
• pp.8-15
• /
• 2011

In this paper, we propose a new structure modeling algorithm from 3D cloud points of terrestrial LADAR data. Terrestrial LIDAR data have various obstacles which make it difficult to apply conventional algorithms designed for air-borne LIDAR data. In the proposed algorithm, the field data are separated into several clusters by adopting the structure extraction method which uses color information and Hough transform. And cluster based Delaunay triangulation technique is sequentially applied to model the artificial structure. Each cluster has its own priority and it makes possible to determine whether a cluster needs to be considered not. The proposed algorithm not only minimizes the effects of noise data but also interactively controls the level of modeling by using cluster-based approach.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.26 no.2
• /
• pp.113-128
• /
• 2024

Items of road tunnel PISD (Precise Inspection for Safety and Diagnosis) were reviewed and analyzed using newly enhanced MMS (Mobile Mapping System) technology. Possible items with MMS can be visual inspection, survey and non-destructive test, structural analysis, and maintenance plan. The resolution of 3D point cloud decreased when the vehicle speed of MMS is too fast while the calibration error increased when it is too slow. The speed measurement of 50 km/h is determined to be effective in this study. Although image resolution by MMS has a limit to evaluating the width of crack with high precision, it can be used as data to identify the status of facilities in the tunnel and determine whether they meet disaster prevention management code of tunnel. 3D point cloud with MMS can be applicable for matching of cross-section and also possible for the variation of longitudinal survey, which can intuitively check vehicle clearance throughout the road tunnel. Compared with the measurement of current PISD, number of test and location of survey is randomly sampled, the continuous measurement with MMS for environment condition can be effective and meaningful for precise estimation in various analysis.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.06a
• /
• pp.5-8
• /
• 2016

키 프레임 추출 기법은 2차원 비오 영상을 3차원으로 재구성하기 위해 꼭 필요한 프레임을 선택하는 방법이다. 본 논문에서는 비디오에서 빠르게 프레임을 검사하며 최적의 키 프레임을 선택하는 기법을 제안한다. 제안하는 기법은 3차원 재구성을 위한 전처리 과정에 초점을 둔 것으로 프레임 간 대응점 비율 검사를 통해 프레임의 도약 강도를 결정하고 기하 모델 추정이 원활한 프레임을 선택한다. 이로부터 3차원 복원 후처리 과정을 통해 최종적인 3차원 점군(point cloud) 데이터를 획득한다. 실험을 통해 다른 기법과 성능을 비교했을 때, 제안하는 기법이 복원 소요 시간도 적게 들고 보다 밀집된 3차원 데이터를 얻을 수 있었다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.6
• /
• pp.535-544
• /
• 2018

Autonomous driving can be limited by only using sensors if the sensor is blocked by sudden changes in surrounding environments or large features such as heavy vehicles. In order to overcome the limitations, the precise road-map has been used additionally. This study was conducted to segment and classify road objects using 3D point cloud data acquired by terrestrial mobile mapping system provided by National Geographic Information Institute. For this study, the original 3D point cloud data were pre-processed and a filtering technique was selected to separate the ground and non-ground points. In addition, the road objects corresponding to the lanes, the street lights, the safety fences were initially segmented, and then the objects were classified using the support vector machine which is a kind of machine learning. For the training data for supervised classification, only the geometric elements and the height information using the eigenvalues extracted from the road objects were used. The overall accuracy of the classification results was 87% and the kappa coefficient was 0.795. It is expected that classification accuracy will be increased if various classification items are added not only geometric elements for classifying road objects in the future.