• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2003년도 춘계학술대회 논문집
• /
• pp.1055-1058
• /
• 2003

The robustness and reliability of vision algorithms is the key issue in robotic research and industrial applications. In this paper robust real time visual tracking in complex scene is considered. A common approach to increase robustness of a tracking system is the use of different model (CAD model etc.) known a priori. Also fusion or multiple features facilitates robust detection and tracking of objects in scenes of realistic complexity. Voting-based fusion of cues is adapted. In voting. a very simple or no model is used for fusion. The approach for this algorithm is tested in a 3D Cartesian robot which tracks a toy vehicle moving along 3D rail, and the Kalman filter is used to estimate the motion parameters. namely the system state vector of moving object with unknown dynamics. Experimental results show that fusion of cues and motion estimation in a tracking system has a robust performance.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1992년도 추계학술대회 논문집
• /
• pp.215-219
• /
• 1992

This paper presents a motion coordination of two robot manipulators coordinating an object. To coordinate the object, a force/position control scheme in a mode of leaer/follower is devised. The dynamics of the object are incorporated into the dynamics of the leader arm, which yields a reduced order model of two arm system. In order to regulate interaction forces between two arm, the dynamics of the follower arm are expressed as force dynamic equations such that a novel direct forces between two arms and two different type of bounded input disturbances, boundedness and asymptotic stability results based on a proposed Lyapunov function are shown. Also, a sufficient condition for a stability robustness is derived based on the Lyapunov approach.

• 한국공작기계학회논문집
• /
• 제17권1호
• /
• pp.106-112
• /
• 2008

In this paper, It does the profile measurement of the cam of diesel engine SOHC of the actual object. It uses the measurement of run-out method. This method is that the surface of the object is measured by the sensor when the object rotate, and calculated and displayed by the computer the signal which acquired by sensor. When we acquire the signals, we have two error because of motion and contacting between cam and probe. In this paper, we compensate the motion error while simply liner equation. And we have a solution that we change the figure of probe when we have a contacting error. We compared the data measuring on developed automatic cam profile measuring system with the data measured on CMM.

• 설비공학논문집
• /
• 제17권2호
• /
• pp.110-116
• /
• 2005

This paper deals with interaction between two bubbles or particles and flow around them, visualized by a moving object flow image analyzer(MOFIA) consisting of a three-dimensional (3D) moving object image analyzer(MOIA) and two-dimensional particle image velocimetry(PIV). The experiments were carried out for rising bubbles or particles of various densities, sizes, and/or shapes in stagnant water in a vertical pipe. In the MOFIA employed, 3D-MOIA was used to measure particles or bubbles motion and PIV was used to measure fluid flow, The experimental results showed that the interaction was characterized by the shape, size and density of two particles or bubbles.

• 전기학회논문지
• /
• 제63권6호
• /
• pp.810-812
• /
• 2014

In this paper, a hagwon-bus boarding danger warning system based on computer vision is proposed to protect children from an accident causing injuries or death. Three zones are defined and different algorithms are applied to detect moving objects. In zone 1, a block-based entropy value is calculated using the absolute difference image generated by the absolute differential estimation between background image and incoming video frame. In zone 2, an effective and robust motion object tracking algorithm is performed based on the particle filter. Experimental results demonstrate the efficient and effectively of the algorithm for moving object inspection in each zone.

• 스마트미디어저널
• /
• 제5권1호
• /
• pp.78-87
• /
• 2016

The major problems of recent object tracking methods are related to the inefficient detection of moving objects due to occlusions, noisy background and inconsistent body motion. This paper presents a robust method for the detection and tracking of a moving in infrared animal videos. The tracking system is based on adaptive optical flow generation, Gaussian mixture and Kalman filtering. The adaptive Gaussian model of optical flow (GMOF) is used to extract foreground and noises are removed based on the object motion. Kalman filter enables the prediction of the object position in the presence of partial occlusions, and changes the size of the animal detected automatically along the image sequence. The presented method is evaluated in various environments of unstable background because of winds, and illuminations changes. The results show that our approach is more robust to background noises and performs better than previous methods.

• 한국멀티미디어학회논문지
• /
• 제10권1호
• /
• pp.139-146
• /
• 2007

Wireless Sensor network를 이용하여 객체를 추적하는 방법에 대해 많은 연구가 진행되어 왔다. 본 연구는 객체 추적에 사용되는 방법에 따라 에너지의 양과 추적의 정확도 사이에 존재하는 상관관계를 관찰하고, 움직임 예측 방법에서 에너지 소비량을 최소화할 수 있음을 확인하였다. 추적에 사용되는 에너지는 센서노드가 객체를 감지하기 위해 소모하는 것이며, 추적의 정확도는 객체의 실제위치와 감지에 의해 계산된 위치의 차이이다. 몇 가지 추적방법과 파라미터의 조절에 따라 추적의 정확도와 소비되는 에너지의 양에 차이가 있고, 움직임 예측 알고리즘을 사용할 때 가장 좋은 에너지 효율을 얻을 수 있었다. 또한 가속도를 고려한 움직임 예측 알고리즘의 개선을 통해 더 나은 정확도와 에너지 효율을 기록하였다. 시뮬레이션 결과 움직임 예측 알고리즘에서 목표의 미래위치에 따라 노드를 활성화시키는 범위는 예측 알고리즘이 정확할 경우 센서 노드의 감지범위 정도로 제한하는 것이 유리함을 알 수 있었다.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2011년도 춘계학술대회 논문집
• /
• pp.1161-1166
• /
• 2011

A camera is mounted vertically downwards viewing the people heads from the top. This configuration is successful in people counting technique especially when only a few isolated people pass through a counting region in a non-crowded situation. Thus, this paper describes object counting which detects and count moving people using mixture of gaussian and motion vector. This method is intended to estimates the number of people in outdoor environment. This method use single gaussian background modeling which is more robust an noise and has adaptiveness. The experimental results that is based on mixture of gaussian and motion vector is also helpful to design intelligent surveillance.

• 산업기술연구
• /
• 제21권B호
• /
• pp.91-98
• /
• 2001

In this paper, center detection and motion analysis of a moving object are studied. Kohonen's self-organizing neural network models are used for the moving objects tracking and time delay neural networks are used for dynamic characteristic analysis. Instead of objects brightness, neuron projections by Kohonen Networks are used. The motion of target objects can be analyzed by using the differential neuron image between the two projections. The differential neuron image which is made by two consecutive neuron projections is used for center detection and moving objects tracking. The two differential neuron images which are made by three consecutive neuron projections are used for the moving trajectory estimation. It is possible to distinguish 8 directions of a moving trajectory with two frames and 16 directions with three frames.

• 아동학회지
• /
• 제28권4호
• /
• pp.245-264
• /
• 2007

This study analyzed physical knowledge displayed in the utterances of 10 Korean children 23 - 76 months of age. Utterances were blocked into four-month time periods, except the first two months and classified into 5 categories including properties of physical objects and materials, friction, buoyancy, gravity, and the motion of physical objects. All five types of physical expressions were found in the data of the earliest period the percent age of the properties and motion was higher than the percent of friction, buoyancy, and gravity. Data suggested two transitional points of change in physical knowledge : 2-year-old's descriptions were based only on perceptually salient physical features 3- to 4-year-olds described only end-state results while children older than 4 included systematic causality.