• ETRI Journal
• /
• 제45권5호
• /
• pp.836-846
• /
• 2023

Mobile robots are used in modern life; however, object recognition is still insufficient to realize robot navigation in crowded environments. Mobile robots must rapidly and accurately recognize the movements and shapes of pedestrians to navigate safely in pedestrian-rich spaces. This study proposes real-time, accurate, three-dimensional (3D) multi-pedestrian detection and tracking using a 3D light detection and ranging (LiDAR) point cloud in crowded environments. The pedestrian detection quickly segments a sparse 3D point cloud into individual pedestrians using a lightweight convolutional autoencoder and connected-component algorithm. The multi-pedestrian tracking identifies the same pedestrians considering motion and appearance cues in continuing frames. In addition, it estimates pedestrians' dynamic movements with various patterns by adaptively mixing heterogeneous motion models. We evaluate the computational speed and accuracy of each module using the KITTI dataset. We demonstrate that our integrated system, which rapidly and accurately recognizes pedestrian movement and appearance using a sparse 3D LiDAR, is applicable for robot navigation in crowded spaces.

• 한국CDE학회논문집
• /
• 제21권3호
• /
• pp.341-352
• /
• 2016

Manual 3D pipeline modeling from LiDAR scanned point cloud data is laborious and time-consuming process. This paper presents a method to extract the pipe, elbow and branch information which is essential to the automatic modeling of the pipeline connection. The pipe geometry is estimated from the point cloud data through the Hough transform and the elbow position is calculated by the medial axis intersection for assembling the nearest pair of pipes. The branch is also created for a pair of pipe segments by estimating the virtual points on one pipe segment and checking for any feasible intersection with the other pipe's endpoint within the pre-defined range of distance. As a result of the automatic modeling, a complete 3D pipeline model is generated by connecting the extracted information of pipes, elbows and branches.

• 한국BIM학회 논문집
• /
• 제9권2호
• /
• pp.21-28
• /
• 2019

Recently, many scan projects are gradually increasing for maintenance, construction. The scan data contains useful data, which can be generated in the target application from the facility, space. However, modeling the scan data required for the application requires a lot of cost. In example, the converting 3D point cloud obtained from scan data into 3D object is a time-consuming task, and the modeling task is still very manual. This research proposes Scan-to-Geometry Mapping Rule Definition (S2G-MD) which maps point cloud data to geometry for irregular building plane objects. The S2G-MD considers user use case variability. The method to define rules for mapping scan to geometry is proposed. This research supports the reverse engineering semi-automatic process for the building planar geometry from the user perspective.

• 한국BIM학회 논문집
• /
• 제10권4호
• /
• pp.32-39
• /
• 2020

In recent years, the construction industry is getting bigger and more complex, so it is becoming difficult to acquire point cloud data for construction equipments and workers. Point cloud data is measured using a drone and MMS(Mobile Mapping System), and the collected point cloud data is used to create a 3D digital map. In particular, the construction site is located at outdoors and there are many irregular terrains, making it difficult to collect point cloud data. For these reasons, adopting a noise reduction algorithm suitable for the characteristics of the construction industry can affect the improvement of the analysis accuracy of digital maps. This is related to various environments and variables of the construction site. Therefore, this study reviewed and analyzed the existing research and techniques on the noise reduction algorithm. And based on the results of literature review, performance evaluation of major noise reduction algorithms was conducted for digital maps of construction sites. As a result of the performance evaluation in this study, the voxel grid algorithm showed relatively less execution time than the statistical outlier removal algorithm. In addition, analysis results in slope, space, and earth walls of the construction site digital map showed that the voxel grid algorithm was relatively superior to the statistical outlier removal algorithm and that the noise removal performance of voxel grid algorithm was superior and the object preservation ability was also superior. In the future, based on the results reviewed through the performance evaluation of the noise reduction algorithm of this study, we will develop a noise reduction algorithm for 3D point cloud data that reflects the characteristics of the construction site.

• Journal of Computational Design and Engineering
• /
• 제1권3호
• /
• pp.202-212
• /
• 2014

To survive in the current shipbuilding industry, it is of vital importance for shipyards to have the ship components' accuracy evaluated efficiently during most of the manufacturing steps. Evaluating components' accuracy by comparing each component's point cloud data scanned by laser scanners and the ship's design data formatted in CAD cannot be processed efficiently when (1) extract components from point cloud data include irregular obstacles endogenously, or when (2) registration of the two data sets have no clear direction setting. This paper presents reformative point cloud data processing methods to solve these problems. K-d tree construction of the point cloud data fastens a neighbor searching of each point. Region growing method performed on the neighbor points of the seed point extracts the continuous part of the component, while curved surface fitting and B-spline curved line fitting at the edge of the continuous part recognize the neighbor domains of the same component divided by obstacles' shadows. The ICP (Iterative Closest Point) algorithm conducts a registration of the two sets of data after the proper registration's direction is decided by principal component analysis. By experiments conducted at the shipyard, 200 curved shell plates are extracted from the scanned point cloud data, and registrations are conducted between them and the designed CAD data using the proposed methods for an accuracy evaluation. Results show that the methods proposed in this paper support the accuracy evaluation targeted point cloud data processing efficiently in practice.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2024년도 춘계학술발표대회
• /
• pp.482-483
• /
• 2024

Real-time Point Cloud Ground Segmentation은 자율주행에서 판단 및 객체 탐지/추적 등 다양한 분야에 도움을 준다. 이에 따라, Real-time Point Cloud Ground Segmentation을 했으며, 센서로는 라이다, 알고리즘으로는 TRAVEL논문을 인용했다. 또한 Real-time Point Cloud Ground Segmentation뿐 만 아니라 이동가능지형 판단(Traversability)을 하였다. 그리고 최종적으로, 위와 같은 알고리즘들을 회사 로봇(Scout Mini Robot)에 접목시켰으며 그 과정에서 TRAVEL 알고리즘내에 내제된 파라미터 값들을 최적화시키는 과정이 필요하였다. 그래서 3가지의 방법을 통해 파라미터 값을 선정한 후, 결과값을 비교 분석하였다. 연구 결과, Rellis-3D와 베이지안 최적화를 사용한 베이지안 파라미터가 최적의 파라미터임을 확인할 수 있었다.

• 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.

• 사물인터넷융복합논문지
• /
• 제9권6호
• /
• pp.11-16
• /
• 2023

물체나 공간을 디지털화하는 기술인 3D 복원은 주로 포인트 클라우드 데이터를 활용한다. 본 논문은 강화학습을 활용하여 주어진 환경에서 포인트 클라우드의 획득을 목표로 한다. 이를 위해 시뮬레이션 환경은 유니티를 이용하여 구성하고, 강화학습은 유니티 패키지인 ML-Agents를 활용한다. 포인트 클라우드 획득 과정은 먼저 목표를 설정하고, 목표 주변을 순회할 수 있는 경로를 계산한다. 순회 경로는 일정 비율로 분할하여 각 스텝마다 보상한다. 이때 에이전트의 경로 이탈을 방지하기 위해 보상을 증가시킨다. 에이전트가 순회하는 동안 목표를 응시할 때마다 보상을 부여하여 각 순회 스텝에서 포인트 클라우드의 획득 시점을 학습하도록 한다. 실험결과, 순회 경로가 가변적이지만 상대적으로 정확한 포인트 클라우드를 획득할 수 있었다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제14권3호
• /
• pp.276-284
• /
• 2022

In this paper, we implemented cloud rendering using WebRTC for high-quality AR and VR services. Cloud rendering is an applied technology of cloud computing. It efficiently handles the rendering of large volumes of 3D content. The conventional VR and AR service is a method of downloading 3D content. The download time is delayed as the 3D content capacity increases. Cloud rendering is a streaming method according to the user's point of view. Therefore, stable service is possible regardless of the 3D content capacity. In this paper, we implemented cloud rendering using WebRTC and analyzed its performance. We compared latency of 100MB, 300MB, and 500MB 3D AR content in 100Mbps and 300Mbps internet environments. As a result of the analysis, cloud rendering showed stable latency regardless of data volume. On the other hand, the conventional method showed an increase in latency as the data volume increased. The results of this paper quantitatively evaluate the stability of cloud rendering. This is expected to contribute to high-quality VR and AR services

• 한국군사과학기술학회지
• /
• 제23권6호
• /
• pp.542-553
• /
• 2020

Virtual world and simulation need large scale map rendering. However, rendering too many vertices is a computationally complex and time-consuming process. Some game development companies have developed 3D LOD objects for high-speed rendering based on distance between camera and 3D object. Terrain physics simulation researchers need a way to recognize the original object shape from 3D LOD objects. In this paper, we proposed simply automatic LOD framework using point cloud data (PCD). This PCD was created using a 6-direct orthographic ray. Various experiments are performed to validate the effectiveness of the proposed method. We hope the proposed automatic LOD generation framework can play an important role in game development and terrain physic simulation.