• 정보처리학회논문지B
• /
• 제12B권3호
• /
• pp.301-312
• /
• 2005

이동물체 추적은 카메라와 물체사이의 이동관계에 따라 카메라는 고정되어 있고 물체가 이동하는 경우, 물체는 고정되어 있고 카메라가 움직이는 경우와 물체가 이동하고 카메라도 움직이는 경우로 분류된다. 이동 물체를 추적하는 기존의 방법으로는 차영상 기반의 방법과 광류(Optical Flow)를 이용한 방법이 있다. 광류를 이용한 방법은 카메라와 물체 중에서 하나가 고정되어 있는 경우에 주로 쓰인다. 이 방법은 이전 프레임에서 구한 물체가 다음 프레임의 한 위치에 있을 때 시공간 벡터를 이용하여 물체의 이동을 인식하고 추적한다. 그러나 이 방법은 계산 량이 많아 처리속도가 느리기 때문에, DVR(Digital Video Recorder)과 같이 실시간 처리가 필요한 보안 시스템에서는 사용할 수 없다. 차영상을 이용한 방법은 카메라는 고정되어 있고 물체가 이동하는 경우에 적용 가능하며 배경영상과 차영상을 이용하여 물체를 추적한다. 이 방법은 계산 량이 적어 처리속도가 빠르기 때문에, 실시간 처리가 필요한 보안 시스템에 적합하다. 하지만, 카메라가 움직일 경우에는 배경영상을 구하기가 어려우므로 물체 검출을 할 수 없는 단점이 있다. 본 논문에서 설계, 구현한 PTZ(Pan-Tilt-zoom) 제어에 의한 차영상 기반의 이동물체 추적 시스템은 카메라와 물체가 모두 이동하는 상황에서 사용할 수 있다. 이 이동물체 추적 시스템은 차영상 기반방식의 장점을 이용, 실시간 처리가 가능하기 때문에 DVR과 같은 실시간 처리가 필요한 보안 시스템 구축을 용이하게 해 줄 것이다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 Proceedings of the Korea Automatic Control Conference, 11th (KACC); Pohang, Korea; 24-26 Oct. 1996
• /
• pp.145-148
• /
• 1996

In moving object tracking based on the visual sensory feedback, a prerequisite is to determine which feature or which object is to be tracked and then the feature or the object identification precedes the tracking. In this paper, we focus on the object identification not image feature identification. The target identification is realized by finding out corresponding line segments to the hypothesized model segments of the target. The key idea is the combination of the Mahalanobis distance with the geometrica relationship between model segments and extracted line segments. We demonstrate the robustness and feasibility of the proposed target identification algorithm by a moving vehicle identification and tracking in the video traffic surveillance system over images of a road scene.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.768-771
• /
• 1997

Geometric probing addresses the problem of determining geometric aspects of a structure from the mathematics and results of a physical measuring device such as a probe. This paper presents a new algorithm to recognize the shape of an unknown object by using a robot hand with a force and torque sensor. The new algorithm is called S.E.P.(Shape Exploration Procedure) which finds the global shape of an unknown object. The proposed method is composed of three major parts, finding contact informations such as contact point, calculation of shape information such as curvature, and expression of global shape from these informations. Comparing with the conventional approaches, the advantages of the proposed method are explained and verified by conducting experiments with a 3-dof SCARA robot.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.2033-2036
• /
• 2004

A novel approach to estimate the real time moving trajectory of an object is proposed in this paper. The object position is obtained from the image data of a CCD camera, while a state estimator predicts the linear and angular velocities of the moving object. To overcome the uncertainties and noises residing in the input data, a Kalman filter and neural networks are utilized. Since the Kalman filter needs to approximate a non-linear system into a linear model to estimate the states, there always exist errors as well as uncertainties again. To resolve this problem, the neural networks are adopted in this approach, which have high adaptability with the memory of the input-output relationship. Kohonen Network(Self-Organized Map) is selected to learn the motion trajectory since it is spatially oriented. The superiority of the proposed algorithm is demonstrated through the real experiments.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.2731-2736
• /
• 2003

In highly informative, perception-rich environments that we call Omniscient Spaces, robots interact with physical objects which in turn afford robots the information showing how the objects should be manipulated. Object manipulation is commonly believed one of the most basic tasks in robot applications. However, no approaches including visual servoing seem satisfactory in unstructured environments such as our everyday life. Thus, in Omniscient Spaces, the features of the environments embed themselves in every entity, allowing robots to easily identify and manipulate unknown objects. To achieve this end, we propose a new paradigm of the interaction through Radio Frequency Identification (RFID). The aim of this paper is to learn about RFID and investigate how it works in object manipulation. Specifically, as an innovative trial for autonomous, real-time manipulation, a likely mobile robot equipped with an RFID system is developed. Details on the experiments are described together with some preliminary results.

• 대한임베디드공학회논문지
• /
• 제3권2호
• /
• pp.119-125
• /
• 2008

This paper presents the polygon-based Q-leaning and Cascade Support Vector Machine algorithm for object search with multiple robots. We organized an experimental environment with ten mobile robots, twenty five obstacles, and an object, and then we sent the robots to a hallway, where some obstacles were lying about, to search for a hidden object. In experiment, we used four different control methods: a random search, a fusion model with Distance-based action making (DBAM) and Area-based action making (ABAM) process to determine the next action of the robots, and hexagon-based Q-learning and dodecagon-based Q-learning and Cascade SVM to enhance the fusion model with DBAM and ABAM process.

• 대한산업공학회지
• /
• 제23권4호
• /
• pp.669-686
• /
• 1997

In this research, an object-oriented Petri net model for representing a flexible process plan is proposed, which is hierarchically multi-faceted for supporting planning, scheduling, and shop floor control functions. The multi-faceted process plan model consists of the following: a) an object model which represents on object-oriented data model, b) a static model which represents a process flow model with process alternatives, and c) a dynamic model which represents a process activity model with resources alternatives, of a flexible process plan. Petri nets allow the static and the dynamic process plan models to be represented in a unified formalism with an ease of model transformation. The multi-faceted process plan model suggested in this paper, is illustrated with a prismatic port in comprehensive detail.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 제37회 하계학술대회 논문집 D
• /
• pp.1929-1930
• /
• 2006

Human like robot arm posture for grasping by considering the shape of the target object is quite a challenge in the field of robotics. In this paper, an optimized grasp posture with respect to the shape of the object considering the wrist joint angle and elbow elevation angle, in order to verify that the grasp posture is human like has been proposed. Given a target object, the candidates for grasp are computed by the method described in this paper. For each candidate, the closed loop inverse kinematics has been solved for the corresponding hand position and orientation. From the obtained joint angles through inverse kinematics, the elbow elevation angle has been computed and compared with the elbow elevation angle obtained through human movement data by the characteristic equation. After considering all the candidates, the hand position and orientation with minimum wrist joint and difference in elbow elevation angles has been utilized as the optimized grasp posture. Simulation results are presented.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.2010-2014
• /
• 2005

Object detection and parameter estimation in point cloud data is a relevant subject to robotics, reverse engineering, computer vision, and sport mechanics. In this paper a software is presented for fully-automatic object detection and parameter estimation in unordered, incomplete and error-contaminated point cloud with a large number of data points. The software consists of three algorithmic modules each for object identification, point segmentation, and model fitting. The newly developed algorithms for orthogonal distance fitting (ODF) play a fundamental role in each of the three modules. The ODF algorithms estimate the model parameters by minimizing the square sum of the shortest distances between the model feature and the measurement points. Curvature analysis of the local quadric surfaces fitted to small patches of point cloud provides the necessary seed information for automatic model selection, point segmentation, and model fitting. The performance of the software on a variety of point cloud data will be demonstrated live.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.1524-1529
• /
• 2005

Particle filter is a kind of conditional density propagation model. Its similar characteristics to both selection and mutation operator of evolutionary strategy (ES) due to its Bayesian inference rule structure, shows better performance than any other tracking algorithms. When a new object is entering the region of interest, particle filter sets which have been swarming around the existing objects have to move and track the new one instantaneously. Moreover, there is another problem that it could not track multiple objects well if they were moving away from each other after having been overlapped. To resolve reinitialization problem, we use competitive-AVQ algorithm of neural network. And we regard interfarme difference (IFD) of background images as potential field and give priority to the particles according to this IFD to track multiple objects independently. In this paper, we showed that the possibility of real-time object tracking as intelligent interfaces by simulating the deformable contour particle filters.