• Journal of Institute of Control, Robotics and Systems
• /
• v.9 no.12
• /
• pp.1033-1041
• /
• 2003

A new visual tracking scheme is proposed for a mobile robot that tracks a moving object in 3D space in real time. Visual tracking is to control a mobile robot to keep a moving target at the center of input image at all time. We made it possible by simplifying the relationship between the 2D image frame captured by a single camera and the 3D workspace frame. To precisely calculate the input vector (orientation and distance) of the mobile robot, the speed vector of the target is determined by eliminating the speed component caused by the camera motion from the speed vector appeared in the input image. The problem of temporary disappearance of the target form the input image is solved by selecting the searching area based on the linear prediction of target motion. The experimental results have shown that the proposed scheme can make a mobile robot successfully follow a moving target in real time.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.14 no.4
• /
• pp.676-683
• /
• 2011

In this paper, we propose a robust method which can detect and track a high-speed small approaching target in a cluttered environment for Korean Active Protection System. The proposed method uses a temporal and spatial filter, tracking filter to detect and track a single target in consecutive order. And it is comprised of a candidate target detection step, a prior target selection step and a target tracking. Field tests on real infrared image sequences show that the proposed method could stably track a high speed and small target in complex background and target occlusion.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.3
• /
• pp.840-860
• /
• 2023

Aiming at the serious occlusion and slow tracking speed in pedestrian target tracking and recognition in complex scenes, a target tracking method based on improved YOLO v5 combined with Deep SORT is proposed. By merging the attention mechanism ECA-Net with the Neck part of the YOLO v5 network, using the CIoU loss function and the method of CIoU non-maximum value suppression, connecting the Deep SORT model using Shuffle Net V2 as the appearance feature extraction network to achieve lightweight and fast speed tracking and the purpose of improving tracking under occlusion. A large number of experiments show that the improved YOLO v5 increases the average precision by 1.3% compared with other algorithms. The improved tracking model, MOTA reaches 54.3% on the MOT17 pedestrian tracking data, and the tracking accuracy is 3.7% higher than the related algorithms and The model presented in this paper improves the FPS by nearly 5 on the fps indicator.

• Proceedings of the KIEE Conference
• /
• 2006.10c
• /
• pp.312-314
• /
• 2006

This paper describes performance of the modified gain scheduling controller by speed control of a DC motor. The modified gain scheduling controller can perform tracking at more than one equilibrium points. The modified gain scheduling controller which considers transient response according to added zero shows better result of tracking performance than the unmodified gain scheduling controller shows.

• International Journal of Control, Automation, and Systems
• /
• v.3 no.2
• /
• pp.252-257
• /
• 2005

In this work, we propose a simple but efficient method to design a target temperature trajectory for pulling speed tracking control of the crystal grower in the Czochralski crystallization process. In the suggested method, the model predictive control strategy is used to incorporate the complex dynamic effect of the heater temperature on the pulling speed into the temperature trajectory design quantitatively. The feedforward trajectories designed by the proposed method were implemented on 200 mm and 300 mm silicon crystal growers in the commercial Czochralski process. The application results have demonstrated its excellent and consistent tracking performance of pulling speed along whole bulk crystal growth.

• 제어로봇시스템학회:학술대회논문집
• /
• 1995.10a
• /
• pp.484-487
• /
• 1995

An interacting multiple model (IMM) approach which merges two hypotheses for the situations of constant speed and constant acceleration model is considered for the tracking of maneuvering target. The inflexibility of uncertainty which lies in the kinematic constraint (KC) represented by pseudomeasurement noise variance is compensated by the mixing of estimates from two model Kalman tracker: one with KC and one without KC. The numerically simulated tracking performance is compared for the "great circular like turning" trajectory maneuver by the single model tracker with constant speed KC and two model tracker which is developed in this paper.his paper.

• Physical Therapy Korea
• /
• v.10 no.3
• /
• pp.71-79
• /
• 2003

Manual tracking is an experimental paradigm that can be used to study information processing in continuous movements involving accurate, ongoing control of motor performance. The purpose of this study was to identify the effects of knee tracking training, using the paretic side, on gait in stroke patients. Nine patients with hemiplegia participated in the study. The timed 10 m gait speed test and tracking test were administrated. The tracking test was composed with ranges of $-20^{\circ}$ to $20^{\circ}$ and $0^{\circ}$ to $60^{\circ}$. The tracking training consisted of five times every week for 4 weeks. The data were analyzed by non-parametric paired sign test of Wilcoxon. The flexion/extension error of the tracking test was significantly reduced on the paretic side, while the nonparetic side was not statistically significant. The transfer of the skill to the functional activity was shown in the significant improvement at timed 10 m gait speed test. This study shows that individuals with chronic who have impaired knee movement can be trained to improve their knee control through intensive practice at a knee movement tracking task and that the skill learned from such training is transfered to a more functional gait speed.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.1
• /
• pp.205-213
• /
• 2014

A wind generator (WG) maximum power point tracking (MPPT) system is presented here. It comprises of a variable-speed wind generator, a high-efficiency boost-type dc/dc converter and a control unit. The advantages of the aimed system are that it does not call for the knowledge of the wind speed or the optimal power characteristics and that it operates at a variable speed, thus providing high efficiency. The WG operates at variable speed and thus suffers lower stress on the shafts and gears compared to constant-speed systems. It results in a better exploitation of the available wind energy, especially in the low wind-speed range of 2.5-4.5 m/s. It does not depend on the WG wind and rotor-speed ratings or the dc/dc converter power rating. Higher reliability, lower complexity and cost, and less mechanical stress of the WG. It can be applied to battery-charging applications.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.25 no.8
• /
• pp.48-59
• /
• 2011

This paper presents a new gain scheduling speed controller of permanent magnet synchronous generators(PMSG) for MW-class direct-driven wind turbine systems. The proposed gain scheduling speed controller performs the speed tracking at more than one operating point, and the first-order torque observer estimates the turbine torque which is needed to precisely control the speed of PMSG. The proposed speed controller verifies that the PMSG can successfully follow the reference speed which is determined via the maximum power point tracking(MPPT) control and pitch control under turbulent wind conditions. The proposed speed control algorithm is simulated using Simulink and its performance is confirmed through comparison with the results by PI control method.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.40 no.3
• /
• pp.127-134
• /
• 2003

In this paper, the speed control problem of moving camera is investigated for tracking the movement of the human-face. The camera system with pan-tilt mechanism sends an image to PC and PC sends back tracking coordinate to the camera. Then the camera tracks a human face in real time. The speed of the stepping motors for moving the camera must be controlled to the target region fast enough and smoothly, In this paper, a fuzzy logic controller is proposed for driving step motors. By creating driving acceleration and deceleration speed Profile, the speed of the motors is controled fast and smoothly. Experiments are performed to show the effectiveness of the proposed method.