• 한국인터넷방송통신학회논문지
• /
• 제12권3호
• /
• pp.29-35
• /
• 2012

본 논문에서는 MPEG(Moving Picture Experts Group) 영상 디코더에서 영상을 압축, 비교, 복원, 저장한후 디코딩 처리하는 방법을 종래의 픽셀 단위로 처리하는 방법과는 다르게 영상의 단위 화소 주변을 군집화소로 분류한 후 이를 클러스터링하여 오버랩정도를 결정 한다. 오버랩 정도의 임계치값을 결정하는데는 패턴식별을 취한후 샘플 패턴에 대한 기하구조의 파악과 결정함수의 도출로 활용된다. 특징공간이 4차원 이상이면 주어진 패턴 구조를 시각적으로 관찰할 수 없다. 이 때, 분포구조를 고찰해 볼수 있는 방법은 군집중심간의 거리, 군집별 패턴의 수 및 표준편차 등을 이용하는 방법이다. 임계치 값을 넘는 중복화면은 소거되고 넘지않는 군집화면은 패턴인식으로 복원된후 동영상으로 구현된다. 이방법이 기존의 픽셀 단위 처리하는 방법 과는 20%정도의 메모리 감축과 15%정도의 화면 복원에 성능이 향상된 것으로 판정된다.

• 공학교육연구
• /
• 제15권4호
• /
• pp.48-52
• /
• 2012

The purpose of this paper is to design and implement the user motion pattern control system for the simulated vehicle. After analyzing the user motion patterns in the system, the patterns are used to control the moving direction of the simulated vehicle such as forward, backward, turn right, turn left etc. The patterns in the system around are sent to the simulated vehicle in real time. In order to execute the suggested user motion pattern control system, the Kinect is used for executing the system. The Kinect recognizes the specified user motion patterns and it transmits the data to the user motion pattern control system. There are nine kinds of the user motion patterns in the system for controlling the simulated vehicle. In addition to this, some sensors are used to detect the condition of the simulated vehicle. GPS is also used to estimate the current location of the simulated vehicle and to obtain the driving information.

• 한국정밀공학회지
• /
• 제24권2호
• /
• pp.58-63
• /
• 2007

This paper proposes a novel method of projecting a multiple stripe pattern whose intensity profile is sinusoidal. The sinusoidal stripe patterns are plated with chromium on a piece of glass, and the glass is placed within an optical projection system. By linearly moving the glass along the direction of the stripe pattern, the projection system generates the motion blurring effect, and as a result, produces a blurred stripe pattern whose intensity profile is sinusoidal along the perpendicular direction of the stripe pattern. The sinusoidal pattern improves the measurement accuracy of phase-shifting method. Experimental results are provided for three different types of stripe patterns: rectangle, diamond, and sinusoid.

• 한국군사과학기술학회지
• /
• 제10권3호
• /
• pp.43-50
• /
• 2007

A range-frequency interference pattern is analyzed in the course of the propagation of ship noise in shallow water. It has been shown to exhibit striated bands of intensity maxima and minima in the spectrogram. The slope of the striations is an invariant of the modal interference and is described by a waveguide invariant parameter $\beta$. It turns out that this interference pattern is useful for identifying the physical properties of the waveguide such as seabed properties. In this article, the interference pattern is analyzed using image processing techniques to produce the distribution of the beta and the effects of sediment types and geoacoustic parameters on beta distribution are examined and characterized by moments of the distributions.

• 한국의류학회지
• /
• 제25권1호
• /
• pp.91-102
• /
• 2001

The purpose of this study is to suggest a individually fitted slacks pattern in order to help ourselves prepared for the days of the order-based production like the EC in the apparel industry. A pattern was designed to make the personal fit improved based on the present study and the analysis of the measurements and the body shapes. The main characteristics of this newly designed slacks pattern are as follows. To improve fitting, the pattern requires more detailed data such as front and back waist arc, front and back hip arc, hip depth, the gradient of hip. And for personal fitted pattern, knee girth was established in the proportion to the hip girth and the crotch curve was adjusted to the measurements after drawing and the side seam curve was changed according to the front hip type and the ease in waist and hip was established by the percentage. Slacks pattern was developed into an automatic drafting program. Through the sensory evaluation for the appearance and moving fitness, newly designed slacks pattern was turned out to be improved in personal fit espacially for the body type out of the average.

• 한국멀티미디어학회논문지
• /
• 제10권8호
• /
• pp.967-980
• /
• 2007

동영상에서의 관심 객체를 추출하는 것은 비디오 내용 분석과 비디오 검색 및 압축의 성능을 개선시키는데 큰 역할을 한다. 관심 객체는 단순히 사람 눈의 시선을 끄는 대상물이 아니라 내용전개의 중심이 되거나 제작자가 표현하려고 하는 핵심 객체를 의미한다. 이러한 관심 객체는 움직이는 객체뿐만 아니라 정지해 있는 객체도 될 수 있으나, 사람의 관심을 절차적으로 표현하는 것이 어렵기 때문에 관심 객체를 명확하게 정의하기가 곤란하다. 이에, 본 논문에서는 동영상 샷에서의 움직이는 객체의 위치, 크기, 움직임 패턴의 변화에 대한 조건을 정의하여 필터링에 의해 사람의 관심을 끄는 움직임 관심 객체를 추출하는 방법을 제시하고, 아울러 동영상 샷에서 정지되어 있는 객체에 대해서도 컬러/텍스처 특이성, 위치, 크기, 출현 빈도 등에 대한 조건을 정의하여 정지 관심 객체도 추출할 수 있는 방법을 제안한다. 제안한 방법을 50개의 동영상 샷에 대하여 실험한 결과, 사람이 선정한 움직임 및 정지 관심 객체를 84% 정도 추출할 수 있음을 확인할 수 있었다.

• 환경위생공학
• /
• 제5권2호
• /
• pp.100-104
• /
• 1990

The geometrical branching pattern was studied through the time by a few parameters: the branching lengths, angles and number of branches. Ratios of moving amounts of nutrients between branches was decreased more in a terminal branch than in a proximal one. As the time increased, the more branches and leaves were also increased, while the influx of sunlight was decreased in the lower portion of inner crown which increased the mortality rate of branches.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1998년도 추계종합학술대회 논문집
• /
• pp.955-958
• /
• 1998

This paper describes the algorithm which extracts moving vehicles from sequential images and tracks those vehicles using Kalman filter. This work is composed of a motion segmentation stage which extracts moving objects from sequential images and gets features of objects, and a motion estimation stage which estimates the position and the motion of moving objects using Kalman filter. In the motion estimation stage, applying to affine motion model we divided the Kalman filter into position filter and velocity filter to employ linear Kalman filter. Multi-target tracking requires a data association component that decides which measurement to use for updating the state of which object. We use pattern recognition method to solve this problem.

• International Journal of Control, Automation, and Systems
• /
• 제4권4호
• /
• pp.466-479
• /
• 2006

This paper addresses a formation navigation issue for a group of mobile robots passing through an environment with either static or moving obstacles meanwhile keeping a fixed formation shape. Based on Lyapunov function and graph theory, a NN formation control is proposed, which guarantees to maintain a formation if the formation pattern is $C^k,\;k\geq1$. In the process of navigation, the leader can generate a proper trajectory to lead formation and avoid moving obstacles according to the obtained information. An evolutionary computational technique using particle swarm optimization (PSO) is proposed for motion planning so that the formation is kept as $C^1$ function. The simulation results demonstrate that this algorithm is effective and the experimental studies validate the formation ability of the multiple mobile robots system.

• 한국윤활학회:학술대회논문집
• /
• 한국윤활학회 1997년도 제26회 추계학술대회
• /
• pp.135-144
• /
• 1997

This wear debris can be harvested from the lubricants of operating machinery and its morphology is directly related to the damage to the interacting surfaces from which the particles originated. The morphologies of the wear particles are therefore directly indica- rive of wear processes occuring in machinery and their severity. The neural network was applied to identify wear debris generated from the lubricated moving system. The four parameter(50% volumetric diameter, aspect, roundness and reflectivity) of wear debris are used as inputs to the network and learned the friction condition of five values(material 3, applied load 1, sliding distance 1). It is shown that identification results depend on the ranges of these shape parameter learned. The three kinds of the wear debris had a different pattern characteristic and recognized the friction condition and materials very well by neural network. We dicuss how the network determines difference in wear debris feature, and this approach can be applied to condition diagnosis of the lubricated moving system.