• 제어로봇시스템학회논문지
• /
• 제9권3호
• /
• pp.210-217
• /
• 2003

We introduced a scheme for finding an optimal data association matrix that represents the relationships between the measurements and tracks in multi-target tracking (MIT). We considered the relationships between targets and measurements as Markov Random Field and assumed a priori of the associations as a Gibbs distribution. Based on these assumptions, it was possible to reduce the MAP estimate of the association matrix to the energy minimization problem. After then, we defined an energy function over the measurement space that may incorporate most of the important natural constraints. To find the minimizer of the energy function, we derived a new equation in closed form. By introducing Lagrange multiplier, we derived a compact equation for parameters updating. In this manner, a pair of equations that consist of tracking and parameters updating can track the targets adaptively in a very variable environments. For measurements and targets, this algorithm needs only multiplications for each radar scan. Through the experiments, we analyzed and compared this algorithm with other representative algorithm. The result shows that the proposed method is stable, robust, fast enough for real time computation, as well as more accurate than other method.

• 전자공학회논문지SC
• /
• 제44권3호
• /
• pp.39-44
• /
• 2007

본 논문에서는 해양 함정 환경에서 위성 신호를 수신하기 위한 위성 탐색 및 추적 방법을 제안한다. 빠른 시간 내에 위성을 탐색하기 위한 탐색 알고리즘은 위성 신호의 주엽 뿐아니라 부엽을 이용하는 방법을 제안하였으며, 안테나가 지향하고자 하는 목표 위성을 파도 등에 의한 외란에 상관없이 항상 추적하기 위한 방법으로 부반사판을 틸팅하여 고속으로 회전하여 위성 편차를 취득하는 방법을 제안하였다. 이 방법은 주반사판과 부반사판으로 구성된 카세그레인 안테나를 기반으로 코니칼 스케닝을 구현하여 고가의 자이로 센서 등의 모션센서 없이 오차 신호를 취득하여 추적 기능을 구현하였으며, 실험을 통해 그 효용성을 보였다.

• 대한전기학회논문지:전기물성ㆍ응용부문C
• /
• 제55권2호
• /
• pp.82-87
• /
• 2006

Most of electric accidents are happened in the place where activities are frequent by common people who has low electric knowledge. Also, accidents are increased in the low voltage electric equipment. So, it is increased to spread the dispersion or non-utility power generation system. It means that ordinary times observation is required for electric equipments by common people. This paper is studied for the diagnosis method of electric equipment that common people can diagnose easily Voltage is generally and exactly measured in the electric and electronic field. We suggest new analysis tools using only electric voltage. It is called the Time-Energy analysis. The Time-Energy analysis is as following First, divide measured voltage waves into same parts, Second, conducted FFT(Fast Fourier Transform) transform for each divided period, Finally, each results are reassembled after graphic treatment. We compared Time-Energy analysis with discharge form by tracking tester. As the result, tracking discharge processes distinguished clearly.

• 스마트미디어저널
• /
• 제6권3호
• /
• pp.49-56
• /
• 2017

Images and Videos that include the human face contain a lot of information. Therefore, accurately extracting human face is a very important issue in the field of computer vision. However, in real life, human faces have various shapes and textures. To adapt to these variations, A model-based approach is one of the best ways in which unknown data can be represented by the model in which it is built. However, the model-based approach has its weaknesses when the motion between two frames is big, it can be either a sudden change of pose or moving with fast speed. In this paper, we propose an enhanced human face-tracking model. This approach included human face detection and motion estimation using Cascaded Convolutional Neural Networks, and continuous human face tracking and modeling correction steps using the Active Appearance Model. A proposed system detects human face in the first input frame and initializes the models. On later frames, Cascaded CNN face detection is used to estimate the target motion such as location or pose before applying the old model and fit new target.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권8호
• /
• pp.3965-3983
• /
• 2017

We propose a novel eye tracking method that can estimate 3D world coordinates using an infrared (IR) stereo camera for indoor and outdoor environments. This method first detects dark evidences such as eyes, eyebrows and mouths by fast multi-level thresholding. Among these evidences, eye pair evidences are detected by evidential reasoning and geometrical rules. For robust accuracy, two classifiers based on multiple layer perceptron (MLP) using gradient local binary patterns (GLBPs) verify whether the detected evidences are real eye pairs or not. Finally, the 3D world coordinates of detected eyes are calculated by region-based stereo matching. Compared with other eye detection methods, the proposed method can detect the eyes of people wearing sunglasses due to the use of the IR spectrum. Especially, when people are in dark environments such as driving at nighttime, driving in an indoor carpark, or passing through a tunnel, human eyes can be robustly detected because we use active IR illuminators. In the experimental results, it is shown that the proposed method can detect eye pairs with high performance in real-time under variable illumination conditions. Therefore, the proposed method can contribute to human-computer interactions (HCIs) and intelligent transportation systems (ITSs) applications such as gaze tracking, windshield head-up display and drowsiness detection.

• ETRI Journal
• /
• 제45권6호
• /
• pp.996-1006
• /
• 2023

Renewable energy is promoted massively to overcome problems that fossil fuel power plants generate. One popular renewable energy type that offers easy installation is a photovoltaic (PV) system. However, the energy harvested through a PV system is not optimal because influenced by exposure to solar irradiance in the PV module, which is constantly changing caused by weather. The maximum power point tracking (MPPT) technique was developed to maximize the energy potential harvested from the PV system. This paper presents the MPPT technique, which is operated on a new high-gain voltage DC/DC converter that has never been tested before for the MPPT technique in PV systems. Fuzzy logic (FL) was used to operate the MPPT technique on the converter. Conventional and adaptive perturb and observe (P&O) techniques based on variables step size were also used to operate the MPPT. The performance generated by the FL algorithm outperformed conventional and variable step-size P&O. It is evident that the oscillation caused by the FL algorithm is more petite than variables step-size and conventional P&O. Furthermore, FL's tracking speed algorithm for tracking MPP is twice as fast as conventional P&O.

• 한국식품저장유통학회지
• /
• 제31권3호
• /
• pp.408-422
• /
• 2024

This study analyzed the factors that influence menu choices through eye-tracking and questionnaires in menu design. Demographic data of subjects coincided with choosing a menu and eye-tracking data. Hot Crispy Chicken Burger is the most popular menu. The study found that regardless of the selected menu, the menu name (35.5 seconds), price (21.6 seconds), and image (16.0 seconds) were viewed the longest, followed by country of origin (8.81 seconds), calories (4.6 seconds), and special indications (p<0.05). The menu name and image were checked more frequently, while calorie information was checked less often. As a result of analyzing various factors that influence menu selection through, Consumer experience and image greatly influenced menu choices. Therefore, if you want to receive a menu selection, it is considered effective to make good use of the menu name and image. In results of principal component analysis (PCA) by gender showed. Men had the longest price in the fixation duration. But, for females, there was a significant difference in gaze fixation when they took the exam, with menu names and special indications being important selection criteria. Since the results show that selection criteria and information acquisition methods differ depending on gender, this research is thought to be able to suggest directions for menu design.

• 한국통신학회논문지
• /
• 제35권4C호
• /
• pp.371-376
• /
• 2010

본 논문에서는 고차의 QAM 시스템을 위한 새로운 고속 반송파 복원 알고리즘을 제안한다. 제안된 방식은 수신 심볼 간 위상차를 이용하여 반송파 주파수 오프셋을 직접 검출하며, 이를 기존의 반송파 복원 방식에 적용함으로써 넓은 주파수 추적 범위와 빠른 수렴 속도를 제공하는 반송파 복원을 수행할 수 있다. 시뮬레이션을 통하여 제안된 반송파 복원 방식이 주파수 오프셋이 크고 신호 대 잡음비가 낮은 상황에서도 짧은 수렴 시간을 가지는 것을 확인하였다.

• 전자공학회논문지SC
• /
• 제44권6호
• /
• pp.35-41
• /
• 2007

자연스러운 머리 움직임 하에서 응시점을 추정할 수 있는 시스템을 제안하였다. 이 시스템은 하나의 카메라와 2개의 거울로 구성되어 있으며, 이 거울은 안구에서 눈동자의 영상을 언제나 카메라로 획득할 수 있도록 유지시키는 기능을 한다. 그러나 영상의 획득 속도가 초당 30 프레임이므로 거울의 제어가 빠른 머리 움직임을 보상할 수 없다. 이러한 문제점을 극복하고자 현재 안구 이미지에서 다음 안구 이미지의 위치를 추정하기 위하여 Kalman filter를 적용하였다. 그 결과 수평방향으로 평균 55cm/s, 수직 방향으로 평균 45cm/s정도의 속도의 머리 움직임에 대한 보상이 가능하였다. 그리고, 머리 움직임의 공간도 수평 60cm, 수직 30cm의 넓은 범위까지 가능하였다. 공간 해상도는 수평과 수직 각각 $4.5^{\circ}$와 $5^{\circ}$ 였고, 자연스러운 머리 움직임 아래에서의 응시점의 정확도는 92% 였다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제36권11호
• /
• pp.901-911
• /
• 2009

본 논문에서는 연속 프레임에서 움직임이 큰 얼굴을 자동으로 추적하기 위해 두 단계 합성 기울기 지형 생성 방법을 제안한다. 본 제안 방법은 다음과 같은 세 가지 단계로 이루어진다. 첫째, 활성 외곽선이 빠르게 수렴하기 위한 두 단계 해상도 기울기 맵을 생성한다. 둘째, 연속하는 프레임 간의 변위를 파악하고 주변 배경을 제거하기 위하여 이전 프레임과 현재 프레임의 합성 기울기 맵과 차별 마스크를 산정하여 가중 합성 기울기 맵을 구성한다. 셋째, 활성 외곽선이 지역적 최소값에 수렴하는 것을 막기 위해 닫기 연산을 사용하여 에너지 비탈면을 생성한다. 이 때, 닫기 연산의 계산 비용 문제는 빠른 닫기 연산을 통해 해결한다. 제안방법의 정확성을 평가하기 위해 기존 활성 외곽선 모델 기반 방법들과 제안방법의 수행 결과를 통한 육안 평가와 활성 외곽선의 평균 에너지 변화를 통한 견고성 평가를 수행하고, 수행 시간을 분석한다. 실험 결과 제안방법의 경우 배경의 영향을 받지 않으면서 얼굴의 움직임이 큰 경우에도 빠르고 정확하게 추적할 수 있었다.