• 한국정밀공학회지
• /
• 제17권10호
• /
• pp.119-124
• /
• 2000

One of the main problems in 3D shape measuring systems that use the triangulation of line-shaped laser light is precise center line detection of line-shaped laser stripe. The intensity of a line-shaped laser light stripe on the CCD image varies following to the reflection angles, colors and shapes of objects. In this paper, a new center line detection algorithm to compensate the local intensity variation on a line-shaped laser light stripe is proposed. The 3-D surface shape measuring system using the proposed center line detection algorithm can measure 3-D surface shape with enhanced measurement resolution by using the dynamic shape reconstruction with adaptive pattern clustering of the line-shaped laser light. This proposed 3-D shape measuring system can be easily applied to practical situations of measuring 3-D surface by virtue of high speed measurement and compact hardware compositions.

• 센서학회지
• /
• 제23권6호
• /
• pp.377-382
• /
• 2014

Detecting and segmenting diffuse targets in laser ranging data is a critical problem for tactical reconnaissance. In this study, we propose a new method that facilitates the characterization of diffuse irregularly shaped objects using "spin images," i.e., local 2D histograms of laser returns oriented in 3D space, and a clustering process. The proposed "cluster-based spin imaging" method resolves the problem of using standard spin images for diffuse targets and it eliminates much of the computational complexity that characterizes the production of conventional spin images. The direct processing of pre-segmented laser points, including internal points that penetrate through a diffuse object's topmost surfaces, avoids some of the requirements of the approach used at present for spin image generation, while it also greatly reduces the high computational time overheads incurred by searches to find correlated images. We employed 3D airborne range data over forested terrain to demonstrate the effectiveness of this method in discriminating the different geometric structures of individual tree clusters. Our experiments showed that cluster-based spin images have the potential to separate classes in terms of different ages and portions of tree crowns.

• 한국정밀공학회지
• /
• 제22권5호
• /
• pp.113-120
• /
• 2005

Because of the turbulent markets and the increasing demand on product quality, the application of new technology to practice is increasingly important. In case of automotive industries, they take interest in laser welding to solve these problems because laser welding has many advantages such as good accessibility, welding quality, fast welding speed and so on. To apply this technology to welding of car body, the data of laser welding are collected through lots of the experiment according to the material, geometry and layer number of welding points. Based on the experiment results and the information of product, i.e. the car side panel, the clustering of stitches for laser welding was carried out and the optimal equipments are selected through the comparison between the requirements of welding and the potential of equipments. Using these results, laser welding cell for the car side panel are configured with the concept of the digital manufacturing, which ensures maximum planning security with visualization and simulation. Finally, the optimal laser welding cell is chosen by the evaluation of alternative cells with assessment criteria.

• 한국기계가공학회지
• /
• 제21권7호
• /
• pp.91-97
• /
• 2022

Pipes transport and supply fuel in various categories; however, corrosion occurs because of the external environment, impurities are mixed in the fuel, and substances leak to the outside, which can lead to serious accidents. Therefore, in this study, inspection equipment using a laser scanner was manufactured to classify conditions according to the degree of corrosion of the outer wall of the pipe, and the corrosion height and maximum value of the pipe were obtained from the surface information. Using the k-means method, it was classified into four states, and the standard of the average height and maximum height of corrosion for each state was derived.

• 제어로봇시스템학회논문지
• /
• 제18권12호
• /
• pp.1115-1121
• /
• 2012

This paper proposes a method to extract accurate plane of an object in unstructured environment for a humanoid robot by using a laser scanner. By panning and tilting 2D laser scanner installed on the head of a humanoid robot, 3D depth map of unstructured environment is generated. After generating the 3D depth map around a robot, the proposed plane extraction method is applied to the 3D depth map. By using the hierarchical clustering method, points on the same plane are extracted from the point cloud in the 3D depth map. After segmenting the plane from the point cloud, dimensions of the planes are calculated. The accuracy of the extracted plane is evaluated with experimental results, which show the effectiveness of the proposed method to extract planes around a humanoid robot in unstructured environment.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권1호
• /
• pp.131-147
• /
• 2020

RFID (Radio Frequency Identification) identifies a specific object by radio signals. As the tag provides a unique ID for the purpose of identification, RFID technology effectively solves the ambiguity and occlusion problem that challenges the laser or camera-based approach. This paper proposes an approach to track a moving object based on the integration of RFID and laser ranging information using a particle filter. To be precise, we split laser scan points into different clusters which contain the potential moving objects and calculate the radial velocity of each cluster. The velocity information is compared with the radial velocity estimated from RFID phase difference. In order to achieve the positioning of the moving object, we select a number of K best matching clusters to update the weights of the particle filter. To further improve the positioning accuracy, we incorporate RFID signal strength information into the particle filter using a pre-trained sensor model. The proposed approach is tested on a SCITOS service robot under different types of tags and various human velocities. The results show that fusion of signal strength and laser ranging information has significantly increased the positioning accuracy when compared to radial velocity matching-based or signal strength-based approaches. The proposed approach provides a solution for human machine interaction and object tracking, which has potential applications in many fields for example supermarkets, libraries, shopping malls, and exhibitions.

• 한국자동차공학회논문집
• /
• 제7권5호
• /
• pp.258-267
• /
• 1999

An intelligent safety vehicle(ISV) should have an ability to predict the possibility of an accident and help a driver avoid the accident in advance. The basic function of the ISV is to alert the driver by warning when the collision is to occur. For this purpose, the ISV has to function efficiently in sensing the environmental context. While image processing provides lane information, laser radar senses road obstacles including vehicles. By applying a simple clustering algorithm to radar signals, it is possible to obtain the vehicle information. Consequently, we can identify the existence of the vehicle of interest on my lane. The reliability of the sensing algorithm is evaluated by running on the highway with a test vehicle.

• 자원리싸이클링
• /
• 제26권2호
• /
• pp.46-55
• /
• 2017

본 연구에서는 레이저유도붕괴분광(Laser Induced Breakdown Spectroscopy, LIBS)을 이용하여 방사형 기저함수 신경회로망(Radial Basis Function Neural Networks, RBFNNs) 분류기 설계방법론을 개발하고 실제 폐소형가전제품의 플라스틱 분류 시스템에 적용하였다. ABS, PP, PS와 같은 검정색 플라스틱을 구별하기 위해, 지능형 알고리즘 중 하나인 방사형 기저함수 신경회로망 분류기를 설계하였다. 획득한 입력변수는 주성분 분석법(Principal Component Analysis, PCA)을 이용하여 축소시켰으며, 군집화기법 중 하나인 K-means 클러스터링 방법을 이용해 여러 그룹으로 분할하였다. 전체 데이터는 학습 데이터와 테스트 데이터를 4:1의 비율로 나누었으며, 제안된 분류기의 성능 및 신뢰도를 평가하기 위하여 5-FCV(5-Fold Cross Validation) 기법을 사용하였다. 입력변수와 클러스터의 개수가 각각 5개인 경우, 제안된 분류기의 분류 성능은 96.78%로 나타났다. 또한, 제안된 분류기는 다른 분류기들과 비교하였을 경우 분류 성능의 관점에서 우수성을 보여주었다.

• 한국측량학회지
• /
• 제33권2호
• /
• pp.111-122
• /
• 2015

본 연구에서는 모바일 레이저 스캐닝 데이터로부터 철도 선로탐지 및 선로모델 추출을 위한 방법을 제시하였다. 제안된 방법은 크게 세 단계로 구성된다. 첫째, 레이저 포인트로부터 잠재적인 철도 선로지역을 탐지하고, 초기 철도 선로궤적 방향을 추정한다. 둘째, 철도 선로에 관한 선 지식을 이용하여 첫번째 스트립에서 초기 선로위치를 결정한다. 여기서, 스트립은 국부 탐색공간을 나타내며 철도 선로궤적에 수직인 방향으로 정의된다. 마지막으로, 초기 선로위치에서 GMM-EM기반 분류방법을 통해 선로 포인트들을 탐지한 후 초기 선로 모델을 생성하고 스트립을 데이터 처리 기본단위로 하여 tracking by detection관점에서 연속적으로 선로모델을 생성하였다. 제안된 방법의 주요 특징은 다음과 같다. 첫째, 이전 스트립에서 생성된 선로 모델을 가이드 라인으로 다음 스트립에 전파되어 국부 탐색영역을 예측하여 선로 포인트를 탐지하는 하는데 있어서 처리 복잡성을 줄일 수 있었다. 둘째, 선로 포인트 탐지와 선로 모델링을 동시에 진행 함으로써 데이터 처리 시간을 최소화 할 수 있었다. 개발된 알고리즘은 C++ 프로그램 언어로 구현되었고 도시지역에서 MMS 측량을 통해 취득된 LiDAR 데이터(경부선 일부 구간)를 이용하여 성능 테스트를 진행하였다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2002년도 춘계학술대회 논문집
• /
• pp.487-490
• /
• 2002

AGV is very useful equipment to transfer containers in automated container terminal. AGV must have Obstacle Detection System (ODS) fur port automation. ODS needs the function to classify some specified object from background in acquired data. And it must be able to track classified moving objects. Finally, ODS could determine its next action for safe deriving whether it should do emergency stop or speed down, or it should change its deriving lane. For these functions, ODS can have many different kinds of algorithm. In this paper, we present one of them under developing.