• Proceedings of the Korean Society of Computer Information Conference
• /
• 2015.07a
• /
• pp.258-261
• /
• 2015

본 논문에서는 주행 중에 보행자의 인식 및 추적을 위해서 차량에서 촬영된 영상정보를 이용하여 주변의 보행자를 찾고, 사고 위험성이 있는 보행자를 인식하기 위해서 보행자 파악 및 보행자와의 거리를 측정하기 위한 연구를 하고자 한다. 본 논문에서는 차량에 정착된 카메라를 통한 보행자 인식 기술에 대해 연구 하였다. 제안한 방법은 보행자 인식 단계에서 Cascasde HOG, Haar-like 알고리즘을 적용하였고, 추적 단계에서 칼만 필터와 클러스터링 기법을 결합하여 실시간으로 보행자를 인식 및 추적하였다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.2C
• /
• pp.31-40
• /
• 2005

we propose an enhanced self-generation supervised algorithm that by combining an ART algorithm and the delta-bar-delta method. Form the input layer to the hidden layer, ART-1 and ART-2 are used to produce nodes, respectively. A winner-take-all method is adopted to the connection weight adaption so that a stored pattern for some pattern is updated. we test the recognition of student identification, a certificate of residence, and an identifier from container that require nodes of hidden layers in neural network. In simulation results, the proposed self-generation supervised learning algorithm reduces the possibility of local minima and improves learning speed and paralysis than conventional neural networks.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.1
• /
• pp.142-151
• /
• 2015

This paper proposes a method for detection of objects temporally stop moving in video sequences taken by a moving camera. Even though the consequence of missed detection of those objects could be catastrophic in terms of application level requirements, not much attention has been paid in conventional approaches. In the proposed method, we introduce cues for consistent detection and tracking of objects: motion potential, position potential, and color distribution similarity. Integration of the three cues in the graph-cut algorithm makes possible to detect objects that temporally stop moving and are newly appearing. Experiment results prove that the proposed method can not only detect moving objects but also track objects stop moving.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38A no.4
• /
• pp.318-324
• /
• 2013

For blind channel equalization, the reliability of signal estimate determines the convergence speed and steady-state performance of the equalizer. Therefore the nonlinear estimator and reference signal being used in signal estimate should be chosen appropriately. In this paper, to increase the reliability of the signal estimate, two errors were obtained by applying coarse signal points and dense signal points respectively to signal estimate, the relative reliabilities of two errors were calculated, then the equalizer was adapted deferentially utilizing the reliabilities. At this point, by applying two errors alternately, two modes of operation were smoothly combined. Through computer simulations the proposed method was confirmed to achieve fast transient state convergence and low steady-state error compared to traditional methods.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38A no.2
• /
• pp.191-200
• /
• 2013

In this paper, we propose a new estimation method of time offset, frequency offset, and signal to interference plus noise ratio (SINR) using the synchronization channel preamble to provide IEEE 802.16.1a based talk-around direct communications (TDC). The proposed scheme estimates the time offset and frequency offset both in the time domain and in the frequency domain considering the preamble structure. In addition, it improves the estimation accuracy by combining the estimated values in two domains taking into account TDC synchronization scenarios. Through numerical simulations in the TDC channel environments, the performance of the proposed algorithm is compared with those of existing techniques such as the time domain estimation and the frequency domain estimation.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.24 no.7
• /
• pp.748-751
• /
• 2013

We perform a wideband radiated pulse coupling analysis of simple building structures using the finite-deference time-domain(FDTD) method. Toward this purpose, the building structures composed of concrete and window materials are assumed and we numerically model the electrical properties of each material. In this work, we apply a dispersive FDTD algorithm for the electromagnetic analysis of building structures and investigate their shielding effectiveness in the frequency range of 50 MHz to 1 GHz.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.13 no.4
• /
• pp.56-67
• /
• 1999

In this paper, the new composition Irethod of global and local fuzzy reasoning concepts is proposed to reduce, optimize and automatically acquire the number of rules, without any lose of the general performances in conventional fuzzy controllers. In order to control the interaction between global reasoning and local reasoning, the DNA coding algorithm is introduced to the local fuzzy reasoning of the proposed composition fuzzy reasoning rrethod. The method is awlied to the real liquid level control system for the purpose of evaluating the performance. The sinru1ation results show that the proposed technique can control the system with higher accuracy and automatical1y acquire the fuzzy rules with rmre feasibility, than the conventional methods.ethods.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.22 no.12
• /
• pp.130-141
• /
• 2008

This paper presents the flow characteristics in the fluid circulation loop using the tubular type linear induction motor(TLIM) electromagnetic pump. A TLIM of thrust 40[N] is analyzed using the equivalent and genetic algorithm for the system The flow characteristics are analyzed by coupling the Maxwell equations with the Navier-Stokes equation with the thrust. The analysis algorithm is developed for analyzing the liquid metal flow in the system for laminar and turbulent flow. And the effect of thrust is analyzed for the flow characteristics.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.9
• /
• pp.2189-2196
• /
• 2014

In this paper, a VLIW(Very Long Instruction Word) vision coprocessor which can efficiently accelerate computer vision algorithm for automotive is designed. The VLIW coprocessor executes four instructions per clock cycle via 8-stage pipelined structure and has 36 integer and floating-point instructions to accelerate computer vision algorithm for pedestrian detection. The processor has about 300-MHz operating frequency and about 210,900 gates under 45nm CMOS technology and its estimated performance is 1.2 GOPS(Giga Operations Per Second). The vision system composed of vision primitive engine and eight VLIW coprocessors can execute pedestrian detection at 25~29 frames per second(FPS). Because the VLIW coprocessor has high detection rate and loosely coupled interface with host processor, it can be efficiently applicable to a wide range of vision applications.

• Proceedings of the KIPE Conference
• /
• 2007.07a
• /
• pp.71-73
• /
• 2007

본 논문에서는 새로운 연료전지용 3상 전류형 능동 클램프 DC-DC 컨버터를 제안한다. 전류형 컨버터 구조에 능동 클램프 회로를 채용하여 과도기에 발생하는 서지전압을 저감하였고 모든 스위치에서 영전압 스위칭을 하며, 그 장점으로 : 연속적인 입력전류, 전압 오버슈트 제거, 영전압 턴 온 스위칭, 고주파 변압기 1차/2차 측에 부가적인 스너버 회로의 필요성 제거, 소프트 스위칭에 의한 저속 다이오드 적용 등이 있다. 더구나 대용량 발전 시스템에 적합하도록 전류형 컨버터 구조와 3상 전력변환 회로를 결합하였다. 3상 전력변환 적용의 장점은 : 입력전류 및 출력전압 주파수의 3배 증가, 스위치에 흐르는 RMS 전류 저감, 필터소자 용량 및 부피 감소, 고주파 변압기 이용률 증가, 전력회로의 단순화에 따른 전체 사이즈 축소 및 신뢰성 향상 등이 있다. 제안하는 3상 전류형 능동 클램프 DC-DC 컨버터는 이러한 장점들 때문에 발전용 연료전지 시스템의 승압형 DC-DC 컨버터에 적합하며 대용량 태양전지 발전 시스템 및 배터리 충전기 등에도 적용할 수 있다. 새로운 3상 DC-DC 컨버터와 함께 3상 PWM 알고리즘을 제안하며, 시뮬레이션과 프로토타입 제작, 실험을 통하여 그 성능을 평가, 확인한다.