• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1109-1116
• /
• 2023

Object tracking is used to track a goal in a video sequence by using coordinate information provided as annotation in the first frame of the video. In this paper, we propose a tracking algorithm that combines deep features and region inference modules to improve object tracking accuracy. In order to obtain sufficient object information, a convolution neural network was designed with a Siamese network structure. For object region inference, the region proposal network and overlapping confidence module were applied and used for tracking. The performance of the proposed tracking algorithm was evaluated using the Object Tracking Benchmark dataset, and it achieved 69.1% in the Success index and 89.3% in the Precision Metrics.

• Journal of the Korean Society for Precision Engineering
• /
• v.24 no.10
• /
• pp.64-74
• /
• 2007

Because of the size and environment in the shipbuilding process, the portable type robot is required for the automatic seam tracking. For this reason, the structure of laser sensor should be considered in the initial design step and the coordinate transformation between welding robot and laser sensor, which is joint finder, must be identified exactly and the real time tracking algorithm based on these consideration could be developed. In this research, laser displacement sensor in which its structure is laser beam's vertical projection, is developed to recognize the location of weld joint. In practical applications, however, images of weld joints are often degraded because of the surface specularity or spatter. To overcome the problem, the constrained joint finding algorithm is proposed. In the approach of coordinate conversion rule for the visual feedback control among welding torch, robot body and laser sensor is applied by the same reference point method. In the real time seam tracking algorithms we propose constrained sampling method which uses look ahead distance. The RLS(Recursive Least Square) filter is applied to obtain the smooth tracking path from the sensitive edge data. From the experimental results, we could see the possibility that the developed laser sensor with proposed processing algorithm and real time seam tracking method can be used as a welding under the shipbuilding condition.

• Journal of the Korean Society for Precision Engineering
• /
• v.17 no.3
• /
• pp.90-101
• /
• 2000

In this paper, we propose a controller for differentially steered wheeled mobile robots. The controller uses input-output linearization algorithm and artificial neural network to stabilize the dynamic model and compensate uncertainties. The proposed neural network part has 6 inputs, 1 hidden layer, 2 torque outputs and features fast online learning and good performance on structure error learning basis. Simulation results show that the proposed controller perform precisely tracking of reference path and is robust to uncertainties.

• Journal of the Korean Society for Precision Engineering
• /
• v.2 no.1
• /
• pp.41-52
• /
• 1985

This study is a step in developing the sliding mode control methodology for the robust control of a class of nonlinear time-varying systems. The methodology uses in its idealized form piecewise continuous feedback control, resulting in the state trajectory "sliding" slong a time-varying sliding surface in the state space. This idealized control law achieves perfect tracking. The method is applied to the control of a two-link manipulator handling variable loads in a flexible manufacturing system environment with noise. The result through simulation is that the tracking problem of articular robot with high precision can be realized by using the variable structure system (VSS) theory. The motions of articular robot were insensitive to various payloads. payloads.

• Proceedings of the KIEE Conference
• /
• 2004.07c
• /
• pp.2083-2086
• /
• 2004

Variable Structure Controller with effective tracking performance is propose to control micro actuator system. Propsed VSC(Variable Structure Control) technique is implemented to tracking control of comb driving system having high non-linearity. The tracking performance due to VSC technique is compared to conventional PD(Proportional Derivative) control technique, reveals improved results.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.10 no.4
• /
• pp.257-264
• /
• 2015

For the tracking of the way-points of hovering AUV (HAUV), we suggest a simple PID controller. The way-points are designed to approach to a virtual underwater structure and the heading angles at each way-point are set to look at the structure in the face. The proposed controller consists of a vertical controller to maintain the depth and pitch angle, and a horizontal controller to move to the desired position as well as to adjust the heading angle of the HAUV. In the simulation using Matlab/Simulink, the HAUV with the proposed PID controller is shown to track all the way-points within 1 m range while maintaining proper heading angle at each way-point.

• Journal of the Korean Society for Precision Engineering
• /
• v.6 no.2
• /
• pp.65-76
• /
• 1989

The objective of this paper is to design the variable structure system(VSS) controller for the tracking control of excavator which is driven by electro-hydraulic servomechansim. It is generally agreed that the dynamic characteristics of the robot arm such as excavator are coupled, time varying, and highly nonlinear, and also hydraulic system contains nonlinear characteristics in itself, so performing exact position control and trajectory tracking control need remarkable consideration. To solve this porblem, this system was designed as a variable structure system. The salient feature of VSS is that the sliding mode occur on a switching surface. While in sliding mode, the system remains insensitive to parameter variations and disturbances. This control algorithm was applied to a hydraulic excavator by simulaltion and to a simulator by experiment. And its effectiveness was verified. And the results of VSS for the electro-hydraulic excavator was compared with that of the PID when load disturbances and system parameter variations exist.

• Journal of electromagnetic engineering and science
• /
• v.1 no.2
• /
• pp.131-138
• /
• 2001

The DTV (Digital TV) tuner for an 8-VSB (Vestigial Side-Band) modulation was developed to meet the requirements of the ATSC (Advanced Television Systems Committee). The double frequency conversion and the active tracking filter in the front-end were used to cancel interferences between adjacent channels and multi-channels by suppressing the IF beat and the Image frequency. However, It was impossible to get frequency mapping between the tracking filter and the first VCO (Voltage Controlled Oscillator) in the existing DTV tuner structure which differs from the NTSC (National Television Systems Committee) tuner. This paper, therefore, suggests an assailable structure and a new method for the automatic frequency selection by mapping the frequency characteristics over the tracking voltage and the combined HW which is composed of a Micro-controller, an EEPROM (Electrically Erasable Programmable Read Only Memory), a DAC (Digital-to-Analog Converter), an OP amplifier, and a switch driver.

• Current Photovoltaic Research
• /
• v.1 no.2
• /
• pp.122-125
• /
• 2013

The Floating Photovoltaic System was installed on the surface of water. There were some researches in this subject. But there was not many studies with experiment on a high waterproof Floating Photovoltaic modules. The aim of this study was to analyze the performance of the Floating Photovoltaic System. For this experiment, a high waterproof Floating Photovoltaic modules were designed and applied to the module capacity of 10 kW Tracking-Type structure. The experiment results indicated the performance of the daily production is 51.6 kW; the production capacity of Floating Photovoltaic System is expected to be 23% higher than that of the ground-mounted photovoltaic system.

• Proceedings of the KIEE Conference
• /
• 2002.07d
• /
• pp.2780-2782
• /
• 2002

In this paper Valentine Braitenberg structure based sensory motor model for object tracking control system was proposed. Conventional model based control schemes are require highly non-linear mathematical models, which require long computational time to solve complex high order equations. Contrast to conventional models proposed system simply link signal data from camera directly to the inputs of neural network, and outputs of network are directly fed into input of motor driver of camera. With simple structure of sensory motor model, real time tracking control system for dynamic object was realized successfully, and the implementation of sensory motor model can overcome the limitation of model-based control schemes.