• Journal of Broadcast Engineering
• /
• v.26 no.6
• /
• pp.748-757
• /
• 2021

In this paper, we propose a gaze estimation network in which eye landmark position detection and gaze direction vector estimation are integrated into one deep learning network. The proposed network uses the Stacked Hourglass Network as a backbone structure and is largely composed of three parts: a landmark detector, a feature map extractor, and a gaze direction estimator. The landmark detector estimates the coordinates of 50 eye landmarks, and the feature map extractor generates a feature map of the eye image for estimating the gaze direction. And the gaze direction estimator estimates the final gaze direction vector by combining each output result. The proposed network was trained using virtual synthetic eye images and landmark coordinate data generated through the UnityEyes dataset, and the MPIIGaze dataset consisting of real human eye images was used for performance evaluation. Through the experiment, the gaze estimation error showed a performance of 3.9, and the estimation speed of the network was 42 FPS (Frames per second).

• Journal of IKEEE
• /
• v.19 no.4
• /
• pp.557-565
• /
• 2015

In this paper, a method for estimating the location of a quadcopter is proposed by applying an EKF-SLAM algorithm to its flight control, to autonomously control the flight of an unmanned quadcopter. The usefulness of this method is validated through simulations. For autonomously flying the unmanned quadcopter, an algorithm is required to estimate its accurate location, and various approaches exist for this. Among them, SLAM, which has seldom been applied to the quadcopter flight control, was applied in this study to simulate a system that estimates flight trajectories of the quadcopter.

• Proceedings of the KIPE Conference
• /
• 2015.07a
• /
• pp.491-492
• /
• 2015

본 논문에서는 영구자석 동기 전동기(PMSM)의 수학적 모델을 기반으로 한 플라이휠 에너지 저장 시스템을 매트랩/시뮬링크를 사용하여 모델링 하였다. PMSM의 센서리스 벡터 제어를 위해 속도 및 전류 제어기를 구현하였으며, PI형 상태 관측기를 이용한 역기전압 추정기와 PLL 기반의 위치/속도 추정기를 구현하였다. 초기 기동시 역기전압 추정기반 센서리스 제어 방식은 회전자의 위치를 정확히 추종 할 수 없어 Open-Loop 알고리즘을 통하여 동기 전동기를 구동시킨다. 플라이휠 에너지 저장 시스템의 센서리스 제어 알고리즘은 충전 모드와 발전 모드에서의 시뮬레이션을 통해 성능을 확인하였다.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.261-264
• /
• 2000

음향센서의 정확도 시험을 위해서는 사전 약속된 모의신호를 발생하는 기준 음향센서, 즉 모의신호 발생기가 필요하다. 모의신호 발생기는 정확도 시험의 기준이 되므로 위치가 정확하게 산출되어야 하고, 발생시키는 모의신호는 시험 목적에 부합되도록 설계되어야 한다. 본 연구에서는 모의신호 발생기의 위치 추정 및 모의신호 발생을 위한 설계 기법을 제안하고, 제안 기법에 대한 위치 추정 알고리즘을 시뮬레이션으로 고찰한다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.3
• /
• pp.8-15
• /
• 2019

The PM synchronous motor drives with vector control have been applied to wide fields of industry applications due to its high efficiency. The rotor position information for vector control of a PM synchronous motor is detected from the rotor position sensors or rotor position estimators. The sensorless control based on the mathematical model of PM synchronous motor is generally used and it can be classified into back EMF -based sensorless control and magnet flux-based sensorless control. The rotor position estimating performance of the back EMF-based sensorless control is deteriorated at low speeds since the magnitude of back EMF is proportional to the motor speed. The magnitude of the magnet flux for estimating rotor position in the flux-based sensorless control is independent on the motor speed so that the estimating performance is excellent for wide speed ranges. However, the estimation performance of the model-based sensorless control may be influenced by the motor parameter variation since the rotor position estimator uses the mathematical model of the PM synchronous motor. In this paper, the rotor position estimation performance for the back EMF based- and flux-based sensorless controls is analyzed theoretically and is compared through the simulation and experiment when the motor parameters including stator resistance and inductance are varied.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.3D
• /
• pp.307-315
• /
• 2008

The aim of this study is to develop travel time estimation model by using Self-Organized Neural network(in brief, SON) algorithm. Travel time data based on vehicles equipped with GPS and number-plate matching collected from National road number 3 (between Jangji-IC and Gonjiam-IC), which is pilot section of National Highway Traffic Management System were employed. We found that the accuracies of travel time are related to location of detector, the length of road section and land-use properties. In this paper, we try to develop travel time estimation using SON to remedy defects of existing neural network method, which could not additional learning and efficient structure modification. Furthermore, we knew that the estimation accuracy of travel time is superior to optimum located detectors than based on existing located detectors. We can expect the results of this study will make use of location allocation of detectors in highway.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.10
• /
• pp.2102-2112
• /
• 2015

In this paper, we propose a new positioning scheme for accuracy improvement of Relay-based Navigation System. The conventional relay-based system occurs larger vertical error than horizontal one due to structural characteristics that positioning references are located toward same direction and a location of user is estimated by triangulation technique. In the proposed positioning scheme, the user position is reestimated using an additional virtual reference which is generated based on position information of reference stations in navigation signals and estimated initial user position. The nearest reference station from the estimated user position is selected as a virtual reference to minimize the effect of geometrical factor. The vertical error decreases by using reference points on multi planes, therefore, accurate positioning is possible than the conventional scheme. We demonstrated that the accuracy of a user is improved through simulation results.

• 한국정보통신설비학회:학술대회논문집
• /
• 2009.08a
• /
• pp.262-265
• /
• 2009

최근 각광받고 있는 위치기반 서비스의 모델인 긴급 SOS 시스템은 기지국망을 이용한 광역위치추적과 IEEE 802.15.4를 기반으로 하는 근거리 위치추적 시스템이 결합된 새로운 형태의 하이브리드형 위치추적 기법이다. 본 시스템에서 근거리 위치추적 범위를 정확히 추정하는 것은 중요한 이슈라 할 수 있다. 따라서 본 논문에서는 IEEE 8020.15.4를 기반으로 하는 Zigbee 통신방식을 추정 할 수 있는 최대 거리를 log distance model과 two ray ground 모델을 기반으로 추정 하였다.

• Proceedings of the IEEK Conference
• /
• 2009.05a
• /
• pp.308-309
• /
• 2009

본 논문은 도로상에 매설된 자기표지의 인식을 통해 주행 중인 바이모달 트램의 위치를 추정하는 추정알고리즘 설계 및 검증에 대한 내용을 다룬다. 바이모달 트램은 자동 안내제어를 위해 도로상에 4m 간격으로 매설된 자기표지를 인식하여 차량과 기준경로사이의 경로오차를 측정하고, 이 때 측정된 정보를 이용하여 차량의 위치를 계산한다. 경로오차 측정 정보는 125msec간격으로 이산적으로 주어지며, 차량의 선형모델에 근거한 관측기를 이용하여 차량의 위치를 실시간으로 추정하는 알고리즘을 설계하고, 시뮬레이션을 통해 검증한다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.10
• /
• pp.2090-2101
• /
• 2015

We propose a robust tracking method that combines the merits of ACM(active contour model) and the color-based PF(particle filter), effectively. In the proposed method, PF and ACM track the color distribution and the contour of the target, respectively, and Decision part merges the estimate results from the two trackers to determine the position and scale of the target and to update the target model. By controlling the internal energy of ACM based on the estimate of the position and scale from PF tracker, we can prevent the snake pointers from falsely converging to the background clutters. We appled the proposed method to track the head of person in video and have conducted computer experiments to analyze the errors of the estimated position and scale.