• 제어로봇시스템학회논문지
• /
• 제22권10호
• /
• pp.839-846
• /
• 2016

Bin picking is a task of picking a small object from a bin. For accurate bin picking, the 3D pose information, position, and orientation of a small object is required because the object is mixed with other objects of the same type in the bin. Using this 3D pose information, a robotic gripper can pick an object using exact distance and orientation measurements. In this paper, we propose a 3D vision technique for accurate measurement of 3D position and orientation of small objects, on which a paper label is stuck to the surface. We use a maximally stable extremal regions (MSERs) algorithm to detect the label areas in a left bin image acquired from a stereo camera. In each label area, image features are detected and their correlation with a right image is determined by a stereo vision technique. Then, the 3D position and orientation of the objects are measured accurately using a transformation from the camera coordinate system to the new label coordinate system. For stable measurement during a bin picking task, the pose information is filtered by averaging at fixed time intervals. Our experimental results indicate that the proposed technique yields pose accuracy between 0.4~0.5mm in positional measurements and $0.2-0.6^{\circ}$ in angle measurements.

• 대한기계학회논문집A
• /
• 제23권11호
• /
• pp.1929-1939
• /
• 1999

This paper presents a neural network approach, which was named PRONET, to 3D object recognition and pose calculation. 3D objects are represented using a set of centroidal profile patterns that describe the boundary of the 2D views taken from evenly distributed view points. PRONET consists of the training stage and the execution stage. In the training stage, a three-layer feed-forward neural network is trained with the centroidal profile patterns using an error back-propagation method. In the execution stage, by matching a centroidal profile pattern of the given image with the best fitting centroidal profile pattern using the neural network, the identity and approximate orientation of the real object, such as a workpiece in arbitrary pose, are obtained. In the matching procedure, line-to-line correspondence between image features and 3D CAD features are also obtained. An iterative model posing method then calculates the more exact pose of the object based on initial orientation and correspondence.

• 전자공학회논문지B
• /
• 제28B권7호
• /
• pp.578-589
• /
• 1991

In this paper, there is proposed a novel concept of Incremintal Circle Transform which can describe the boundary contour of a two-dimensional object without object without occlusions. And a pattern recognition algorithm to determine the posture of an object is developed with the aid of line integral and similarity transform. Also, It is confirmed via experiments that the algorithm can find the posture of an object in a very fast manner independent of the starting point for boundary coding and the position of the object.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2006년도 춘계 종합학술대회 논문집
• /
• pp.50-53
• /
• 2006

본 논문은 적외선 컴퓨터 비전으로 책상형 스크린상에 사용자 조작 물체의 위치와 각도를 실시간으로 추적할 수 있는 시스템을 제안한다. 제안하는 시스템은 기존 컴퓨터 비전 시스템의 약점인 주변 조명의 영향을 거의 받지 않는다. 위치뿐만 아니라 각도와 버튼 클릭 상태도 실시간으로 얻어낸다. 이 시스템을 활용하여 컬러랩 박스를 제작하였다.

• 게임&엔터테인먼트 논문지
• /
• 제2권2호
• /
• pp.70-74
• /
• 2006

본 논문은 적외선 컴퓨터 비전으로 책상형 스크린상에 사용자 조작 물체의 위치와 각도를 실시간으로 추적할 수 있는 시스템을 제안한다. 제안하는 시스템은 기존 컴퓨터 비전 시스템의 약점인 주변 조명의 영향을 거의 받지 않는다. 위치뿐만 아니라 각도와 버튼 클릭 상태도 실시간으로 얻어낸다. 이 시스템을 활용하여 컬러랩 박스를 제작하였다.

• 한국정밀공학회지
• /
• 제12권12호
• /
• pp.38-44
• /
• 1995

This paper presents a method to measure the position and orientation of a Cylindrical Object(unknown the eiameter and length) lying on a floor, using a camera. The two extreme cross section of the cylinder will be viewed as distorted ellipese or circular are, while its limb edge will be shown as two straight lines. The diameter of the cylinder is determined from the geometric properties of the two straight lines, which in turn provides information regarding the length of the cylinder. From the 3-dimensional measurement, the 3D coordinates of the center points of the two extreme cross sections are determined to give the position and orientation of the cylinder. This method is used for automated pick-and-place operations of cylinder, such as sheet coils, or drums in warehouses.

• 인지과학
• /
• 제27권3호
• /
• pp.355-376
• /
• 2016

이차원 표면에 난 구멍은 이를 둘러싼 물체에 의해 경계 지워진 빈 배경임에도 불구하고, 구멍의 모양은 다른 물체만큼 쉽게 지각된다. 즉, 구멍은 전경-배경 조직화의 깊이-형태 간 연결 관계(depth-shape coupling)를 예외적으로 위반하여, 깊이 상으로는 배경임에도 불구하고 형태를 갖는 준-전경적(quasi-figural) 사례처럼 보인다. 구멍의 준-전경적 속성을 지지하는 연구들은 구멍과 물체의 재인율이 유사하다는 기억 과제 결과에 주로 의존하고 있으므로, 구멍 모양의 기억이 지각적 처리에 기반하고 있는지는 불분명하다. 본 연구는 재인 과제보다 즉각적인 지각 처리를 반영하는 변화탐지 과제를 이용하여, 구멍을 경계 짓는 물체의 안쪽 윤곽선이 시각 작업기억에 어떻게 표상되는지 알아보았다. 이를 위해, 물체 내부에 다른 물체가 중첩된 접합 물체 조건과 구멍이 있는 물체 조건에서 안쪽 윤곽선과 바깥 영역의 색에 대한 변화탐지 수행을 비교하였다. 시각 작업기억의 선행 연구들은 형태나 방향과 같은 물체의 윤곽선 속성(boundary feature)이 표면 속성(surface feature)과 함께 통합되어 하나의 물체로 저장됨을 시사한다. 만일 구멍의 경계선이 구멍을 둘러싼 물체에 지각적으로 할당된다면, 이 경계선과 물체의 표면색이 통합적으로 부호화되는 물체 중심적 처리 이득으로 인해, 구멍 자극 조건에서 접합 자극 조건보다 높은 변화 탐지 수행이 예측되었다. 두 실험의 결과, 구멍 자극 조건의 변화 탐지 수행은 접합 자극 조건과 다르지 않았다. 이는 물체 내부의 윤곽선(구멍의 경계선) 속성이 물체의 표면 속성과 통합적으로 부호화되지 않으며, 구멍을 둘러싼 물체와 독립적으로 처리됨을 시사한다.

• 한국멀티미디어학회논문지
• /
• 제6권4호
• /
• pp.698-706
• /
• 2003

The primary goal of surface approximation is to reduce the degree of deviation of the simplified surface from the original surface. However it is difficult to define the metric that can measure the amount of deviation quantitatively. Many of the existing studies analogize it by using the change of the scalar quantity before and after simplification. This approach makes a lot of sense in the point that the local surfaces with small scalar are relatively less important since they make a low impact on the adjacent areas and thus can be removed from the current surface. However using scalar value alone there can exist many cases that cannot compute the degree of geometric importance of local surface. Especially the perceptual geometric features providing important clues to understand an object, in our observation, are generally constructed with small scalar value. This means that the distinguishing features can be removed in the earlier stage of the simplification process. In this paper, to resolve this problem, we present various factors and their combination as the metric for calculating the deviation error by introducing the orientation of local surfaces. Experimental results indicate that the surface orientation has an important influence on measuring deviation error and the proposed combined error metric works well retaining the relatively high curvature regions on the object's surface constructed with various and complex curvatures.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1993년도 한국자동제어학술회의논문집(국제학술편); Seoul National University, Seoul; 20-22 Oct. 1993
• /
• pp.271-276
• /
• 1993

Here in the present paper. A methodology for understanding scenes which includes moving objects in it, in the framework of notion of concepts. First by conceptualizing, understanding an object which is an element of a scene will be described. Then how to know the direction to which that object is heading will be discussed. Further, the methodology proposed, for understanding conceptually the motion of an object will be described utilizing the above knowledge of direction.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1990년도 한국자동제어학술회의논문집(국제학술편); KOEX, Seoul; 26-27 Oct. 1990
• /
• pp.917-922
• /
• 1990

Pattern classification is an essential step in automatic robotic assembly which joins together finite number of seperated industrial parts. In this paper, a fast and systematic algorithm for classifying occlusion-free objects is proposed, using the notion of incremental circle transform which describes the boundary contour of an object as a parametric vector function of incremental elements. With similarity transform and line integral, normalized determinant curve of an object classifies each object, independent of position, orientation, scaling of an object and cyclic shift of the stating point for the boundary description.