http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
A New Kmeans Clustering Algorithm for Point Cloud
Kun Zhang,Weihong Bi,Xiaoming Zhang,Xinghu Fu,Li Zhu,Kunpeng Zhou 보안공학연구지원센터 2015 International Journal of Hybrid Information Techno Vol.8 No.9
With development of 3D scanner, it becomes more convenient to access point data. However, for processing the large-scale point cloud, it raised a new challenge for computer graphics. This paper places an emphasis on the point data own characteristics, and then the point data have been divided into certain point sets by clustering algorithm, that is will be divided into different clusters. In order to suit for the point data organization or space division, the clustering algorithm would be improved. This paper provided a new Kmeans algorithm with density constraints. Before processing the point cloud by Kmeans algorithm with density constraints, the density of the point cloud have been defined in this paper, the density of the point cloud can be used for quantification of the convergence. Finally, the Kmeans algorithm with density constraints is verified by the experiment results. Our experiment showed that the improved Kmeans can reduce the processing time, especially, As the increase of the value of K, that is number of cluster, the calculating time of the clustering algorithm can be decreased greatly. In addition, with the increases of the the scale of data size, the stability of the improved Kmeans algorithm has been verified.
Palette-based Color Attribute Compression for Point Cloud Data
( Li Cui ),( Euee S. Jang ) 한국인터넷정보학회 2019 KSII Transactions on Internet and Information Syst Vol.13 No.6
Point cloud is widely used in 3D applications due to the recent advancement of 3D data acquisition technology. Polygonal mesh-based compression has been dominant since it can replace many points sharing a surface with a set of vertices with mesh structure. Recent point cloud-based applications demand more point-based interactivity, which makes point cloud compression (PCC) becomes more attractive than 3D mesh compression. Interestingly, an exploration activity has been started to explore the feasibility of PCC standard in MPEG. In this paper, a new color attribute compression method is presented for point cloud data. The proposed method utilizes the spatial redundancy among color attribute data to construct a color palette. The color palette is constructed by using K-means clustering method and each color data in point cloud is represented by the index of its similar color in palette. To further improve the compression efficiency, the spatial redundancy between the indices of neighboring colors is also removed by marking them using a flag bit. Experimental results show that the proposed method achieves a better improvement of RD performance compared with that of the MPEG PCC reference software.
이경근(Kyung-Keun Lee),정경훈(Kyeong-Hoon Jung),김기두(Ki-Doo Kim) 大韓電子工學會 2011 電子工學會論文誌-SP (Signal processing) Vol.48 No.1
본 논문에서는 지상라이다에서 획득한 3차원 점군데이터로부터 구조물을 모델링하는 알고리듬을 제안한다. 지상라이다 점군데이터는 항공라이다의 경우와 달리 목표 구조물의 크기와 비슷한 다양한 장애물이 존재하고 데이터의 밀도, 거리 등의 특성이 다르기 때문에 항공라이다에서 사용된 기존의 알고리듬을 그대로 적용하기가 곤란하다. 제안한 방법에서는 색상정보와 호프변환을 이용하여 구조물을 추출하는 기법<SUP>[7]</SUP>을 기반으로 주어진 필드데이터를 여러 개의 클러스터로 구분한다. 클러스터링된데이터의 우선순위에 따라서 Delaunay triangulation 기법을 차례대로 적용하여 모델링을 수행한다. 제안한 방법은 클러스터단위로 모델링을 진행하므로 잡음에 의한 영향을 최소화할 수 있으며 사용자가 원하는 개수만큼의 클러스터를 선택함으로써 모델링의 수준을 대화식으로 조정할 수 있다는 장점이 있다. 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<SUP>[7]</SUP>. 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.
Supervoxel-based Staircase Detection from Range Data
Oh, Ki-Won,Choi, Kang-Sun The Institute of Electronics and Information Engin 2015 IEIE Transactions on Smart Processing & Computing Vol.4 No.6
In this paper, we propose a supervoxel clustering-based staircase extraction algorithm to obtain poses and dimensions of staircases from a point cloud. In order to effectively reduce the candidate points and accelerate supervoxel clustering, large planes in the scene, such as walls, floors, and ceilings, are eliminated while scanning the environment. Next, staircase candidates with small planes are initially estimated using supervoxel clustering. Then, parameter values for the staircases are refined, and higher staircases that remain undetected due to occlusion are predicted and generated virtually. Experimental results show that staircases are detected accurately and predicted successfully.
라이다와 RTK-GPS 센서 융합을 통한 효율적인 포인트 클라우드 제거 및 차량 주행 경로 상의 장애물 위치 추정
홍순원(Sunwon Hong),한형진(Hyungjin Han),김학일(Hakil Kim) 한국자동차공학회 2020 한국자동차공학회 학술대회 및 전시회 Vol.2020 No.11
Obstacle detection remains one of the most important task for the advancement of fully autonomous driving. This paper proposes an efficient object detection algorithm based on the LiDAR sensor. LiDAR point cloud data provides an accurate three-dimensional coordinate of the surrounding environment with a wide FOV, however pose computational challenges due to the expansive data size and environmental noise. To circumvent such challenges a multistage filtering process was used. First, unessential data such as ground plane points were removed. The remaining points were then used to make object clusters which were presented as obstacles to the autonomous vehicle. Furthermore, processing time was greatly reduced using variable cropping and the optimization of the LiDAR resolution. The following algorithm was tested using real world data and resulted in a 10㎳ processing time when executing Euclidean clustering.
Object Detection and Localization on Map using Multiple Camera and Lidar Point Cloud
Pansipansi, Leonardo John,Minseok Jang,Yonsik Lee 한국정보통신학회 2021 한국정보통신학회 종합학술대회 논문집 Vol.25 No.2
In this paper, it leads the approach of fusing multiple RGB cameras for visual objects recognition based on deep learning with convolution neural network and 3D Light Detection and Ranging (LiDAR) to observe the environment and match into a 3D world in estimating the distance and position in a form of point cloud map. The goal of perception in multiple cameras are to extract the crucial static and dynamic objects around the autonomous vehicle, especially the blind spot which assists the AV to navigate according to the goal. Numerous cameras with object detection might tend slow-going the computer process in real-time. The computer vision convolution neural network algorithm to use for eradicating this problem use must suitable also to the capacity of the hardware. The localization of classified detected objects comes from the bases of a 3D point cloud environment. But first, the LiDAR point cloud data undergo parsing, and the used algorithm is based on the 3D Euclidean clustering method which gives an accurate on localizing the objects. We evaluated the method using our dataset that comes from VLP-16 and multiple cameras and the results show the completion of the method and multi-sensor fusion strategy.
라이다 데이터의 수상 객체 분류를 위한 복셀 필터링 기반의 향상된 유클리디언 클러스터링
전현준(Hyeonjun Jeon),이세진(Sejin Lee) 대한기계학회 2023 대한기계학회 춘추학술대회 Vol.2023 No.11
The increasing use of LiDAR platforms has led to a variety of related research; however, most of this research has been conducted in terrestrial environments. This study focuses on the unique maritime environment, emphasizing research on clustering within the LiDAR data preprocessing phase. When dealing with Point Cloud information collected through LiDAR, proper preprocessing is crucial due to the substantial data volume. Clustering is frequently employed, especially in segmentation tasks, but traditional clustering methods often suffer from slow processing speeds, making real-time applications challenging. To address this issue, this research proposes the application of voxel filtering to enhance the speed and accuracy of existing clustering techniques and aims to validate this approach.