• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1996년도 춘계학술대회 논문집
• /
• pp.254-258
• /
• 1996

In this paper, we proposed realtime visual tracking system of moving object for 2D target using extended Kalman Filter Algorithm. A targeting marker are recongnized in each image frame and positions of targer object in each frame from a CCD camera while te targeting marker is attached to the tip of the SCARA robot hand. After the detection of a target coming into any position of the field-of-view, the target is tracked and always made to be located at the center of target window. Then, we can track the moving object which moved in inter-frames. The experimental results show the effectiveness of the Kalman filter algorithm for realtime tracking and estimated state value of filter, predicting the position of moving object to minimize an image processing area, and by reducing the effect by quantization noise of image

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2003년도 춘계학술대회 논문집
• /
• pp.915-919
• /
• 2003

This paper presents a fuzzy-motion-control based tracking algorithm of mobile robots, which uses the geometrical information derived from the active stereo-vision system mounted on the mobile robot. The active stereo-vision system consists of two color cameras that rotates in two angular dimensions. With the stereo-vision system, the center position and depth information of the target object can be calculated. The proposed fuzzy motion controller is used to calculate the tracking velocity and angular position of the mobile robot, which makes the mobile robot keep following the object with a constant distance and orientation.

• International Journal of Control, Automation, and Systems
• /
• 제4권3호
• /
• pp.308-317
• /
• 2006

To control the tip position of a flexible-link manipulator, a neural network (NN) controller is proposed in this paper. The dynamics error used to construct NN controller is derived based on output redefinition approach. Without the filtered tracking error, the proposed NN controller can still guarantee the closed-loop system uniformly asymptotically stable as well as NN weights bounded. Furthermore, the tracking error of desired trajectory can converge to zero with the proposed controller. For comparison an NN controller with filtered tracking error is also designed for the flexible-link manipulator. Finally, simulation studies are carried out to verify the theoretic results.

• 제어로봇시스템학회논문지
• /
• 제12권11호
• /
• pp.1061-1064
• /
• 2006

In this study, the performance of the tracking control of a pneumatic servo motor driven position control system using sliding mode is investigated. It is usually quite difficult to obtain precise tracking control of a pneumatic servo motor driven position control system because of the nonlinear deadband and stick-slip friction of the proportional valve. Therefore, a continuous sliding mode controller with velocity feedforward gain is proposed. Experimental results show that the tracking accurracy can be remarkably improved by adding a proper velocity feedforward term to continuous sliding mode controller.

• 한국태양에너지학회 논문집
• /
• 제29권1호
• /
• pp.38-43
• /
• 2009

In this paper. a prototype of a mobile Sun tracking system is proposed. The proposed system uses 2-axis tilt sensor and 3-axis magnetic sensor to measure the orientation and the posture of the system according to the horizontal system of coordinates, which are used to compensate the slope effects. Then through astronomical calculation using the time and position information obtained by GPS sensor the azimuth and altitude of the Sun from that location is calculated. The position of the Sun is converted to that of the mobile Sun tracking system coordinates and used to control A-axis and C-axis of the system.

• 디지털산업정보학회논문지
• /
• 제17권4호
• /
• pp.85-94
• /
• 2021

The LPR system's trigger sensor makes problem occasionally due to the heave weight of vehicle or the obsolescence equipment. If we replace the hardware sensor to the deep-learning based software sensor in order to generate the trigger signal, LPR system maintenance would be a lot easier. In this paper we proposed the deep-learning sliding window based object detection and tracking algorithm for the LPR system's trigger signal generation. The gate passing vehicle's license plate recognition results are combined into the normal tracking algorithm to catch the position of the vehicle on the trigger line. The experimental results show that the deep learning sliding window based trigger signal generating performance was 100% for the gate passing vehicles including the 5.5% trigger signal position errors due to the minimum bounding box location errors in the vehicle detection process.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1998년도 제13차 학술회의논문집
• /
• pp.8-13
• /
• 1998

A tracking controller is presented for RLFJ(rigid link flexible joint) robot manipulators with only position measurements. The controller is developed based on the integrator backstepping design method and on the two observers: the first is simple linear form observer for the filtered link velocity errors and the other for the actuator velocities. The proposed controller achieves exponential tracking of link positions and velocities while keeping all internal signals bounded. It also guarantees exponential convergence of the estimated signals to their actual ones. Finally, simulation results are included to demonstrate the tracking performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권4호
• /
• pp.834-848
• /
• 2013

To effectively use these functions many kinds of human-phone interface are used such as touch, voice, and gesture. However, the most important touch interface cannot be used in case of hand disabled person or busy both hands. Although eye tracking is a superb human-computer interface method, it has not been applied to smartphones because of the small screen size, the frequently changing geometric position between the user's face and phone screen, and the low resolution of the frontal cameras. In this paper, a new eye tracking method is proposed to act as a smartphone user interface. To maximize eye image resolution, a zoom lens and three infrared LEDs are adopted. Our proposed method has following novelties. Firstly, appropriate camera specification and image resolution are analyzed in order to smartphone based gaze tracking method. Secondly, facial movement is allowable in case of one eye region is included in image. Thirdly, the proposed method can be operated in case of both landscape and portrait screen modes. Fourthly, only two LED reflective positions are used in order to calculate gaze position on the basis of 2D geometric relation between reflective rectangle and screen. Fifthly, a prototype mock-up design module is made in order to confirm feasibility for applying to actual smart-phone. Experimental results showed that the gaze estimation error was about 31 pixels at a screen resolution of $480{\times}800$ and the average hit ratio of a $5{\times}4$ icon grid was 94.6%.

• International Journal of Precision Engineering and Manufacturing
• /
• 제4권2호
• /
• pp.30-38
• /
• 2003

This paper proposed PID controller for torch slider and PD controller for motor right wheel. to control the motion of two-wheeled welding mobile robot with seam tracking sensor touched on welding line. The motion control is realized in the view of keeping constant welding velocity and precise seam tracking even though the target welding line is on straight line or curved line. The position and direction of the body of the mottle robot are controlled by using signal errors between seam tracking sensor and body positioning sensor attached on the end of torch slider and body side of the mobile robot, respectively. In turning motion, the body and the torch slider are controlled by using the kinematic model related with two motions of body turning and torch sliding. The straight locomotion is controlled according to eleven control patterns obtained from displacements between two sensors of the seam tracking sensor and the body positioning sensor. The effectiveness is proven through the experimental results fur lattice type welding line. Through the experimental results, we can see that the position value of the electrode end point and the welding velocity are controlled almost constantly both in straight and turning locomotion.

• 한국신재생에너지학회:학술대회논문집
• /
• 한국신재생에너지학회 2009년도 춘계학술대회 논문집
• /
• pp.121-125
• /
• 2009

There have been many developed systems for harnessing the solar energy such as solar water heaters, solar thermal power systems, PV systems, daylighting and solar hydrogen systems. all of them are capable of reducing $CO_2$ emission. However, the efficiency of those systems which work without a solar tracker is lower. This paper is a step by step procedure for fabrication and a performance test of a solar tracking system. The system developed in this study consists of motion controllers, motor drives, step-motors, feedback devices and application. CdS sensors are introduced into the solar tracking system for playing a primary role in poor conditions for tracking due to a gear backlash and a strong wind. Mini-dish was used as a concentrator for collecting sun light. The solar position data, in terms of azimuth and elevation, sunrise and sunset times was compared with those of KASI(Korea Astronomy & Space Science Institute). The results presented in this article provide the high accuracy of the present system in solar tracking and indicate a potential for energy savings.