• Journal of information and communication convergence engineering
• /
• v.11 no.3
• /
• pp.207-215
• /
• 2013

In this paper, we address the challenging computer vision problem of obtaining a reliable facial expression analysis from a naturally interacting person. We propose a system that combines a 3D generic face model, 3D head tracking, and 2D tracker to track facial landmarks and recognize expressions. First, we extract facial landmarks from a neutral frontal face, and then we deform a 3D generic face to fit the input face. Next, we use our real-time 3D head tracking module to track a person's head in 3D and predict facial landmark positions in 2D using the projection from the updated 3D face model. Finally, we use tracked 2D landmarks to update the 3D landmarks. This integrated tracking loop enables efficient tracking of the non-rigid parts of a face in the presence of large 3D head motion. We conducted experiments for facial expression recognition using both framebased and sequence-based approaches. Our method provides a 75.9% recognition rate in 8 subjects with 7 key expressions. Our approach provides a considerable step forward toward new applications including human-computer interactions, behavioral science, robotics, and game applications.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.54 no.5
• /
• pp.787-797
• /
• 2021

Yellowtail Seriola quinqueradiata tagged with a Pop-up Satellite Archival Tag (PSAT) was released off the coast of near the Moseulpo, Jeju Island and the ecological data during about 40 days was obtained. However, it is difficult to determine the spatial location of underwater ecological data. To improve the accuracy of estimating the Yellowtail migration route using temperature, suitable background field of the oceanic environment data was evaluated and used for input data. After developing of the tracking algorithm for migration route estimation, three experiment cases were estimated with ecological data among the surface layer, the mixed layer, and the whole water column. All tracking experiments move from western to eastern Jeju Island. Additionally, tracking experiment using 3D ocean numerical model reveal that it is possible to estimate the migration route using the fish ecological data of the entire water column. Therefore, using a large number of ecological data and a high-accuracy ocean numerical model to estimate the migration route seems to be a way to increase the accuracy of the tracking experiment. Moreover, the tracking algorithm of this study can be applied to small pelagic fishery using small archival electronic tags to track the migration route.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.48 no.5
• /
• pp.391-399
• /
• 2020

KASI (Korea Astronomy and Space Science Institute) has been developing the multipurpose laser tracking system with three functions of satellite laser tracking, adaptive optics and space debris laser tracking for scientific research and national space missions. The space debris laser tracking system provides the distance to space debris without a laser retro-reflector array by using a high power pulse laser, which employs a spinning disk to change the optical path between the transmit and receive beams. The spinning disk causes the collision band which is unable to reflect the returned signal to a detector and then has an effect on the tracking coverage of space debris. This study proposed the mathematical model for tracking coverage by taking into account the various specifications of spinning disk such as disk size, spinning velocity and collision rate between the disk and hole. In addition, the spinning disk specifications were analyzed in terms of tracking coverage and collision band based on the mathematical model to investigate tracking requirements of the Geochang laser tracking system.

• Journal of Korea Society of Industrial Information Systems
• /
• v.22 no.5
• /
• pp.39-49
• /
• 2017

A Space Launch Vehicle (SLV) for Launching Satellites Consists of Multi-stage Rockets for the Purpose of Efficient Flight and Accomplishes the Launch Mission through Flight Events such as Stage Separation, Engine Start and Stop. In this Process, the SLV is Supposed to Undergo the Processes of the Powered Flight Section in which the Engine Generates Thrust and the Ballistic Flight Section in which there is no Thrust Repeatedly. Because it is Difficult to Express these Flight Characteristics of the SLV as a Single Dynamics Model, much Research on Tracking Algorithms using Multiple Models has been Undertaken. In case of using the Multiple Model Tracking Algorithm, it is Expected to Improve the Tracking Performance of the SLV. However, it is Difficult to Select Proper Dynamics Models to be used and the Calculation Amount Increases due to the use of Multiple Models. In this Paper, we Propose a Method to Track the SLV with Diverse Flight Characteristics Efficiently by only Two Kalman Filters using Constant Acceleration Model and Adaptive Singer Model.

• Journal of Korean Society for Atmospheric Environment
• /
• v.33 no.3
• /
• pp.217-232
• /
• 2017

An Eulerian-Lagrangian hybrid modeling system to analyze physical and chemical processes during the transport of air parcels was developed. The Backward-tracking Model Analyzer (BMA) was designed to take advantages of both Eulerian and Lagrangian modeling approaches. Simulated trajectories from the National Oceanic and Atmospheric Administration HYSPLIT model were combined with the US Environmental Protection Agency Community Multi-scale Air Quality (CMAQ)-simulated concentrations and additional diagnostic analyses. In this study, we first introduced a generalized methodology to seamlessly match polylines (HYSPLIT) and threedimensional polygons (CMAQ), which enables mass-conservative analyses of physio-chemical processes of transporting air parcels. Two applications of the BMA were conducted: (1) a long-range transport case of pollutant plume across the Yellow Sea using CMAQ Integrated Process Rate analyses, and (2) a domestic circulation of pollutants within (and near) the South Korea based on the sulfate tracking analyzer. The first episode demonstrated a secondary formation of nitrate and ammonium during the transport over the Yellow Sea while sulfate is mostly transported after being formed over the China, and the second episode demonstrated a dominant impact of boundary condition with active sulfate formation from gas-phase oxidation near the Seoul Metropolitan Area.

• Journal of Institute of Control, Robotics and Systems
• /
• v.5 no.3
• /
• pp.275-280
• /
• 1999

This paper presents a disturbance accommodating sliding mode control for a quarter-car active suspension using an electro-hydraulic actuator. The electro-hydraulic actuator model is nonlinear and uncertain. The hardware constrains on the actuator prevent high gain in a sliding mode control, which deteriorates the force tracking performance. DAC(Disturbance Accommodating Control) is combined with the sliding mode control to improve the tracking performance. DAC observer estimates the pressure due to the actuator uncertainty. The additional control is designed to compensate the estimated pressure. Simulation results show the improved tracking performance with the Proposed control methods.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1995.10a
• /
• pp.598-601
• /
• 1995

This paper proposes a federated Kalman filter approach which utilizes information from multiple sensors and variable estimation model. Compared with the decentralized Kalman filter, the algorithm proposed in this paper demonstrates much better tracking performance in both maneuvering and constant velocity movement of the target.

• 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.

• Transactions on Control, Automation and Systems Engineering
• /
• v.3 no.2
• /
• pp.89-94
• /
• 2001

This paper presents an approach to leak detection and location of gas pipelines based on a strong tracking filter(STF). The STF has strong robustness against model uncertainties, which will deteriorate the performance of the extended Kalman filter. Hence, much faster and more accurate leak detection and location has been obtained. Computer simulation results demonstrate the effective-ness of the proposed approach.

• 전기의세계
• /
• v.31 no.2
• /
• pp.119-125
• /
• 1982

A new approach to the maneuvering target tracking problem is proposed. Its basic concept is to take the maneuver variable from the measurements. Tracking scheme based on the Kalman filter estimates the maneuver varieble from the residual and uses the estimates to update the Kalman filter. The estimation process is independent of target types and a model of the maneuver characteristics. All the filtering algorithms are processed in polor coordinate. Simulation results are presented and compared to that of the extended Kalman filter.