• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2002년도 춘계학술대회 논문집
• /
• pp.462-465
• /
• 2002

This paper deals with the problem of synthesis of stable and optimal grasps with unknown objects by 3-finger hand. Previous robot grasp research has analyzed mainly with either unknown objects 2D by vision sensor or unknown objects, cylindrical or hexahedral objects, 3D. Extending the previous work, in this paper we propose an algorithm to analyze grasp of unknown objects 3D by vision sensor. This is archived by two steps. The first step is to make a 3D geometrical model of unknown objects by stereo matching which is a kind of 3D computer vision technique. The second step is to find the optimal grasping points. In this step, we choose the 3-finger hand because it has the characteristic of multi-finger hand and is easy to modeling. To find the optimal grasping points, genetic algorithm is used and objective function minimizing admissible farce of finger tip applied to the object is formulated. The algorithm is verified by computer simulation by which an optimal grasping points of known objects with different angles are checked.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제12권1호
• /
• pp.56-65
• /
• 2006

최근 서비스 로봇에 대한 연구가 여러분야에서 활발해지며, 노인 보조와 같은 실내 서비스를 위한 연구가 많이 이루어지고 있다. 이 때 로봇이 효과적이고 정확한 서비스를 하기 위해서 물체와 상황을 적절하게 인식하는 것은 중요하다. 전통적인 물체 인식 방법은 미리 정의된 기하학적 모델에 기반하였으나 이런 접근 방법은 대상 물체가 다른 물체에 가려져 보이지 않는 상황 둥 불확실성을 포함하는 실내환경에서는 한계가 있다 본 논문에서는 로봇의 효과적인 물체 탐색을 위해 대상이 되는 물체의 존재 가능성을 추론하기 위한 베이지안 네트워크 모델을 제안한다. 이를 위해 활동별로 물체간의 관계를 모델링하여 고정되어 있지 않은 환경에 보다 유연하게 적용될 수 있게 하였다. 전체적인 구조는 공통-원인 구조를 물체간의 관계를 나타내는 단위로 사용하여 이를 결합해가며 구성되는데 이러한 방법은 베이지안 네트워크 설계를 효과적이게 한다. 제안하는 베이지안 네트워크 모델을 검증하기 위해 두 개의 베이지안 네트워크의 성능을 실험을 통해 검사하였는데 각각 $86.5\%$와 $89.6\%$의 정확도를 보였다.

• 전기학회논문지
• /
• 제67권4호
• /
• pp.578-585
• /
• 2018

In this paper, we propose a classification and theft detection system for human and livestock for various moving objects in a barn. To do this, first, we extract the moving objects using the GMM method. Second, the noise generated when extracting the moving object is removed, and the moving object is recognized through the labeling method. And we propose a method to classify human and livestock using model formation and color for the unique form of the detected moving object. In addition, we propose a method of tracking and overlapping the classified moving objects using Kalman filter. Through this overlap determination method, an event notifying a dangerous situation is generated and a theft determination system is constructed. Finally, we demonstrate the feasibility and applicability of the proposed system through several experiments.

• 한국통계학회:학술대회논문집
• /
• 한국통계학회 2003년도 추계 학술발표회 논문집
• /
• pp.9-14
• /
• 2003

A Bayesian model-based clustering method is proposed for clustering objects on the basis of dissimilarites. This combines two basic ideas. The first is that tile objects have latent positions in a Euclidean space, and that the observed dissimilarities are measurements of the Euclidean distances with error. The second idea is that the latent positions are generated from a mixture of multivariate normal distributions, each one corresponding to a cluster. We estimate the resulting model in a Bayesian way using Markov chain Monte Carlo. The method carries out multidimensional scaling and model-based clustering simultaneously, and yields good object configurations and good clustering results with reasonable measures of clustering uncertainties. In the examples we studied, the clustering results based on low-dimensional configurations were almost as good as those based on high-dimensional ones. Thus tile method can be used as a tool for dimension reduction when clustering high-dimensional objects, which may be useful especially for visual inspection of clusters. We also propose a Bayesian criterion for choosing the dimension of the object configuration and the number of clusters simultaneously. This is easy to compute and works reasonably well in simulations and real examples.

• 로봇학회논문지
• /
• 제3권1호
• /
• pp.42-51
• /
• 2008

Robots need to understand as much as possible about their environmental situation and react appropriately to any event that provokes changes in their behavior. In this paper, we pay attention to topological relations between spatial objects and propose a model of robotic cognition that represents and infers temporal relations. Specifically, the proposed model extracts specified features of the cooccurrence matrix represents from disparity images of the stereo vision system. More importantly, a habituation model is used to infer intrinsic spatial relations between objects. A preliminary experimental investigation is carried out to verify the validity of the proposed method under real test condition.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제27권8호
• /
• pp.795-803
• /
• 2000

본 논문에서는 다중 사용자를 지원하는 분산 소프트웨어 개발 환경에서 동시성을 향상시킬수 있는 공유 데이타 분할 모델을 제안한다. 제안된 모델에서는 공유 데이타에 해당하는 목표 소프트웨어 시스템을 프로젝트 역할을 기반으로 분할한 후, 분산 환경의 각 클라이언트에 분산시키고 이를 다시 뷰(view) 객체와 코어(core) 객체로 분할하여 저장한다. 여러 클라이언트가 참여하는 협동 작업에서는 뷰객체만을 각 클라이언트에 복사(replicate)하여 빠른 응답 시간을 보장하도록 하고, 코어 객체는 하나의 클라이언트에만 저장한 한 후 역할 단위의 잠금(locking) 기법을 이용하여 불일치 문제가 발생하지 않도록 하였다. 실험 결과, 제안된 모델은 기존 도구들에서 사용하는 클래스 단위의 잠금 기법보다 12${\sim}$18%의 성능 향상을 보였고, 클라이언트의 수가 증가하더라도 응답 시간이 급격히 증가하지 않아 확장성(scalability) 이 뛰어난 특징을 보였다.

• 경영과학
• /
• 제25권1호
• /
• pp.139-147
• /
• 2008

Conjoint Analysis is marketers' favorite methodology for finding out how buyers make trade-offs among competing products and suppliers. Thousands of applications of conjoint analysis have been carried out over the past three decades. The conjoint analysis has been so popular as a management decision tool due to the availability of a choice simulator. A conjoint simulator enables managers to perform 'what if' question accompanying the output of a conjoint study. Traditionally the First Choice Model (FCM) has been widely used as a choice simulator. The FCM is simple to do, easy to understand. In the FCM, the probability of an alternative is zero until its value is greater than others in the set. Once its value exceeds that threshold, however, it receives 100%. The LOGIT simulation model, which is also called as "Share of Preference", has been used commonly as an alternative of the FCM. In the model part worth utilities aren't required to be positive. Besides, it doesn't require part worth utilities computed under LOGIT model. The simulator can be used based on regression, monotone regression, linear programming, and so on. However, it is not free from the Independent from Irrelevant Alternatives (IIA) problem. This paper proposes the EBA (Elimination-By-Aspects) model as a useful conjoint-like method. One advantage of the EBA model is that it models choice in terms of the actual psychological processes that might be taking place. According to EBA, when choosing from choice objects, a person chooses one of the aspects that are effective for the objects and eliminates all objects which do not have this aspect. This process continues until only one alternative remains.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제4권4호
• /
• pp.618-632
• /
• 2010

This paper presents a novel approach to control the augmented reality (AR) objects robustly in a marker-less AR system by fingertip tracking and hand pattern recognition. It is known that one of the promising ways to develop a marker-less AR system is using human's body such as hand or face for replacing traditional fiducial markers. This paper introduces a real-time method to manipulate the overlaid virtual objects dynamically in a marker-less AR system using both hands with a single camera. The left bare hand is considered as a virtual marker in the marker-less AR system and the right hand is used as a hand mouse. To build the marker-less system, we utilize a skin-color model for hand shape detection and curvature-based fingertip detection from an input video image. Using the detected fingertips the camera pose are estimated to overlay virtual objects on the hand coordinate system. In order to manipulate the virtual objects rendered on the marker-less AR system dynamically, a vision-based hand control interface, which exploits the fingertip tracking for the movement of the objects and pattern matching for the hand command initiation, is developed. From the experiments, we can prove that the proposed and developed system can control the objects dynamically in a convenient fashion.

• 한국게임학회 논문지
• /
• 제1권1호
• /
• pp.55-60
• /
• 2001

With rapid development of graphic hardware, researches on Virtual Reality and 3D Games have received more attention than before. For more realistic 3D graphic scene, objects were to be presented with lots of polygons and the number of objects shown in a scene was remarkably increased. Therefore, for effective visualization of large polygon models like this, view-frustum culling method, that visualizes only objects shown in the screen, has been widely used. In general, the bounding boxes that include objects are generated firstly, and the boxes are intersected with view-frustum to check whether object is in the visible area or not. Recently, an algorithm that can check in-out test of objects using OpenGL's selection mode, which is originally used to select the objects in the screen, is suggested. This algorithm is fast because it can use hardware acceleration. In this study, by implementing and applying this algorithm to large polygon models, we showed the efficiency of OpenGL assisted View-Frustum Culling algorithm. If this algorithm is applied to 3D games that have to process more complicated characters and landscapes, performance improvement can be expected.

• 전기학회논문지
• /
• 제65권3호
• /
• pp.477-486
• /
• 2016

This paper presents the area classification, identification, and tracking for multiple moving objects with the similar colors. To do this, first, we use the GMM(Gaussian Mixture Model)-based background modeling method to detect the moving objects. Second, we propose the use of the binary and morphology of image in order to eliminate the shadow and noise in case of detection of the moving object. Third, we recognize ROI(region of interest) of the moving object through labeling method. And, we propose the area classification method to remove the background from the detected moving objects and the novel method for identifying the classified moving area. Also, we propose the method for tracking the identified moving object using Kalman filter. To the end, we propose the effective tracking method when detecting the multiple objects with the similar colors. Finally, we demonstrate the feasibility and applicability of the proposed algorithms through some experiments.