• 방송공학회논문지
• /
• 제24권4호
• /
• pp.660-669
• /
• 2019

최근 3차원 스캐닝 장비 및 다차원 어레이 카메라의 발달로 AR(Augmented Reality)/VR(Virtual Reality), 자율 주행과 같은 응용분야에서 3차원 데이터를 다루는 기술에 관한 연구가 지속해서 이루어지고 있다. 특히, AR/VR 분야에서는 3차원 영상을 포인트 데이터로 표현하는 콘텐츠가 등장하였으나, 이는 기존의 2차원 영상보다 많은 양의 데이터가 필요하다. 따라서 3차원 포인트 클라우드 콘텐츠를 사용자에게 서비스하기 위해서는 고효율의 부호화/복호화와 저장 및 전송과 같은 다양한 기술 개발이 요구된다. 본 논문에서는 MPEG-I(MPEG-Immersive) V-PCC(Video based Point Cloud Compression) 그룹에서 제안한 V-PCC 부호화기를 통해 생성된 V-PCC 비트스트림을 MPEG-DASH(Dynamic Adaptive Streaming over HTTP) 표준에서 정의한 세그먼트로 구성하는 방안을 제안한다. 또한, 사용자에게 3차원 좌표계 정보를 제공하기 위해 시그널링 메시지에 깊이 정보 파라미터를 추가로 정의한다. 그리고 본 논문에서 제안된 기술을 검증하기 위한 검증 플랫폼을 설계하고, 제안한 기술의 알고리듬 측면에서 확인한다.

• 한국측량학회지
• /
• 제22권2호
• /
• pp.179-186
• /
• 2004

본 연구는 산업 사진측량을 이용하여 자동차의 외형을 정밀 측정하고, 사고 등의 원인으로 변형이 발생하였을 때 변형량을 측정하는 방법에 관한 것이다. 자동차의 외형을 정밀 측정하기 위하여 점군데이터를 취득할 수 있는 프로젝션 타겟을 사용함으로써 보다 곡면에 대한 정밀한 측정이 가능하도록 하였으며, 대상물 촬영 및 좌표해석을 통하여 타겟의 3차원 좌표를 취득하였다. 취득된 점군데이터는 불규칙 삼각망으로 표면을 형성하여 3차원 모델링을 하였다. 또한, 변형 발생부위를 정밀 측정함으로써 교통사고 분석 등에 효율적이고 정밀한 데이터를 제공할 수 있을 것이다.

• 대한조선학회논문집
• /
• 제58권5호
• /
• 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.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.1250-1251
• /
• 2022

Measuring management is an important part of preventing the collapse of retaining walls in advance by evaluating their stability with a variety of measuring instruments. The current work of measuring management requires considerable human and material resources since measurement companies need to install measuring instruments at various places on the retaining wall and visit the construction site to collect measurement data and evaluate the stability of the retaining wall. It was investigated that the applicability of the current work of measuring management is poor at small and medium-sized urban construction sites(excavation depth<10m) where measuring management is not essential. Therefore, the purpose of this study is to develop a laser sensor-based hardware to support the wall displacement measurements and their control software applicable to small and medium-sized urban construction sites. The 2D lidar sensor, which is more economical than a 3D laser scanner, is applied as element technology. Additionally, the hardware is mounted on the corner strut of the retaining wall, and it collects point cloud data of the retaining wall by rotating the 2D lidar sensor 360° through a servo motor. Point cloud data collected from the hardware can be transmitted through Wi-Fi to a displacement analysis device (notebook). The hardware control software is designed to control the 2D lidar sensor and servo motor in the displacement analysis device by remote access. The process of analyzing the displacement of a retaining wall using the developed hardware and software is as follows: the construction site manager uses the displacement analysis device to 1)collect the initial point cloud data, and after a certain period 2)comparative point cloud data is collected, and 3)the distance between the initial point and comparison point cloud data is calculated in order. As a result of performing an indoor experiment, the analyses show that a displacement of approximately 15 mm can be identified. In the future, the integrated system of the hardware designed here, and the displacement analysis software to be developed can be applied to small and medium-sized urban construction sites through several field experiments. Therefore, effective management of the displacement of the retaining wall is possible in comparison with the current measuring management work in terms of ease of installation, dismantlement, displacement measurement, and economic feasibility.

• 한국정보통신학회논문지
• /
• 제18권10호
• /
• pp.2443-2450
• /
• 2014

깊이 영상을 이용한 동작 인식 시스템에서는 효율적인 알고리즘 적용을 위하여 깊이 영상을 3차원 점군 데이터로 구성되는 실제 공간으로 변환하여 알고리즘을 적용한 후 투영공간으로 변환하여 출력한다. 하지만 변환 과정 중 반올림 오차와 적용되는 알고리즘에 의한 데이터 손실이 발생하게 된다. 본 논문에서는 3차원 점군 데이터에서 깊이 영상으로의 변환 시 반올림 오차와 영상의 크기 변화에 따른 데이터 손실이 발생하지 않는 효율적인 방법과 이를 하드웨어로 구현 하는 방법을 제안 하였다. 최종적으로 제안된 알고리즘은 OpenCV와 Window 프로그램을 사용하여 소프트웨어적으로 알고리즘을 검증하였고, Kinect를 사용하여 실시간으로 성능을 테스트하였다. 또한, Verilog-HDL을 사용하여 하드웨어 시스템을 설계하고, Xilinx Zynq-7000 FPGA 보드에 탑재하여 검증하였다.

• Ecology and Resilient Infrastructure
• /
• 제8권4호
• /
• pp.204-211
• /
• 2021

본 연구에서는 3차원 지상 라이다 스캐너를 통해 수집되는 포인트 클라우드를 활용하여 식생의 정보를 수집하였으며, 수집된 데이터를 기반으로 객체를 재구현하여 물리적 형상을 분석하였다. 이를 위해 원시 데이터의 필터링 단계별 최적의 데이터를 구축하였으며, 구축된 데이터를 활용하여 실제 부피와 Alpha Shape 및 Voxel 기법을 활용한 부피 산정 결과를 산정한 후 각각 비교하였다. 분석 결과, Alpha Shape를 적용하여 부피를 산정한 경우 데이터 필터링과 관계없이 실제 부피보다 과다 산정되는 것으로 나타났다. 또한 Voxel 기법을 활용할 경우 8차 필터링 후 실제 부피와 가장 유사한 것으로 나타났으며, 이후 필터링이 진행될수록 실제 부피에 비해 과소 산정되는 것을 알 수 있었다. 따라서 포인트 클라우드를 활용하여 객체를 재구현 할 경우, 대상이 되는 객체의 복잡한 형상으로 인한 내부 공극을 고려해야 하며, 필터링 과정에서 최적의 데이터 구축을 위한 필터링 과정에 반드시 주의할 필요가 있다.

• 농업과학연구
• /
• 제49권3호
• /
• pp.483-493
• /
• 2022

It is important to improve the efficiency of plant breeding and crop yield to fulfill increasing food demands. In plant phenotyping studies, the capability to correlate morphological traits such as plant height, stem diameter, leaf length, leaf width, leaf angle and size of panicle of the plants has an important role. However, manual phenotyping of plants is prone to human errors and is labor intensive and time-consuming. Hence, it is important to develop techniques that measure plant phenotypic traits accurately and rapidly. The aim of this study was to determine the feasibility of point cloud data based on a 3D light detection and ranging (LiDAR) system for plant phenotyping. The obtained results were then verified through manually acquired data from the sorghum samples. This study measured the plant height, plant crown diameter and the panicle height and diameter. The R² of each trait was 0.83, 0.94, 0.90, and 0.90, and the root mean square error (RMSE) was 6.8 cm, 1.82 cm, 5.7 mm, and 7.8 mm, respectively. The results showed good correlation between the point cloud data and manually acquired data for plant phenotyping. The results indicate that the 3D LiDAR system has potential to measure the phenotypes of sorghum in a rapid and accurate way.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2023년도 봄 학술논문 발표대회
• /
• pp.345-346
• /
• 2023

As the shape and size of detectable objects diversifying recognition and segmentation algorithms have been developed to acquire accurate shape information. Although a high density of data captured by the repetition of scanning improves the accuracy of algorithms the high dense data decreases the efficiency due to its large size. This paper proposes standardization algorithms using the feature of structural members on indoor point cloud data to improve the process. First of all we determine the reduction rate of the density based on the features of the target objects then the data reduction algorithm compresses the data based on the reduction rate. Second the data arrangement algorithm rotates the data until the normal vector of data is aligned along the coordinate axis to allow the following algorithms to operate properly. Final the data arrangement algorithm separates the rotated data into their leaning axis. This allows reverse engineering of indoor point clouds to obtain the efficiency and accuracy of refinement processes.

• 한국컴퓨터정보학회논문지
• /
• 제23권1호
• /
• pp.123-129
• /
• 2018

The purpose of this paper is to investigate the influence of utilitarian, hedonic and social motivations on continuance intention to use cloud services. To do this, this study built a research model and examined how ease of use, usefulness, enjoyment, social influence affect the continuance usage intention of cloud services. The survey method was used for this paper, and data from a total of 82 university students were used for the analysis. And structural equation model was used to analyze the data. The results of this empirical study is summarized as followings. First, enjoyment has a direct effect on the continuance usage intention of cloud services. Second, social influence has a direct effect on the continuance usage intention. Further, it will provide meaning suggestion point of the importance of not only utilitarian motivation but also hedonic and social motivations in establishing the use policy of cloud services.

• 로봇학회논문지
• /
• 제11권3호
• /
• pp.115-126
• /
• 2016

This paper suggests the method of the spherical signature description of 3D point clouds taken from the laser range scanner on the ground vehicle. Based on the spherical signature description of each point, the extractor of significant environmental features is learned by the Deep Belief Nets for the urban structure classification. Arbitrary point among the 3D point cloud can represents its signature in its sky surface by using several neighborhood points. The unit spherical surface centered on that point can be considered to accumulate the evidence of each angular tessellation. According to a kind of point area such as wall, ground, tree, car, and so on, the results of spherical signature description look so different each other. These data can be applied into the Deep Belief Nets, which is one of the Deep Neural Networks, for learning the environmental feature extractor. With this learned feature extractor, 3D points can be classified due to its urban structures well. Experimental results prove that the proposed method based on the spherical signature description and the Deep Belief Nets is suitable for the mobile robots in terms of the classification accuracy.