• 전자공학회논문지SC
• /
• 제46권6호
• /
• pp.14-20
• /
• 2009

영상 처리의 목표는 관찰자를 위하여 영상의 시각적인 측면을 개선하는 것이다. 히스토그램은 디지털 영상 처리의 기초 자료로 사용될 수 있는 중요한 도구이다. 그러므로 히스토그램을 효과적으로 관리하는 것은 디지털 영상 처리에 있어 매우 중요하다. 현재 머신 비전 검사 시스템은 여러 외관 검사 분야에서 사용되어지고 있다. 하지만 머신 비전 시스템에 의한 외관 검사 결과는 작업장의 조명에 의한 영향을 많이 받는다. 본 논문에서는 이러한 영향을 극복하기 위한 방법으로 히스토그램 변환을 이용해서 머신 비전 검사의 정확성을 향상시키는 방법을 제안하였다. 제안하는 방법은 영상 내에서 개선이 필요한 영역에 대한 히스토그램 변환을 수행함으로써, 이들 영역의 특징들을 향상시키는 효과를 거둘 수 있다. 본 논문에서 제안된 방법은 지그 플레이트의 외관 검사를 통해 검증하였다.

• 전자공학회논문지CI
• /
• 제47권5호
• /
• pp.61-66
• /
• 2010

스테레오 비전은 서로 다른 이미지 쌍을 사용하여 주변 환경에 대한 보다 세부화된 3차원 지도를 제공할 수 있기 때문에 소형 로봇이나 홈네트워크 분야에서 많은 활용이 가능하다. 스테레오 비전 시스템의 영역기반 정합방법 중 하나인 SAD 정합 알고리즘은 구조적인 규칙성을 가짐으로써 풍부한 병렬성을 제공하여 많이 사용된다. 본 논문에서는 SAD 알고리즘을 사용하여 스테레오 비전 시스템을 구현하는데 있어 응용분야에 따라 성능과 하드웨어 자원 소모량 등 제약조건이 서로 다른 변형 SAD 알고리즘을 제안하고 비교 분석하였다. 변이도 축약 알고리즘과 윈도우 축약 알고리즘의 경우 하드웨어 자원 소모량을 줄여 소형화와 저가격화를 지향하는 경우에 적합하다. 또한 사용 환경의 객체 형태에 따라서 윈도우 형태 알고리즘의 사용을 고려해 볼 만하며 높은 정합율이 필요한 경우 가변 윈도우 알고리즘을 사용할 수 있다.

• 한국정밀공학회지
• /
• 제22권9호
• /
• pp.99-106
• /
• 2005

In recent years, vision sensors are widely used to mobile robot for navigation or exploration. The analog signal transmission of visual data being used in this area, however, has some disadvantages including noise weakness in view of the data storage. A large amount of data also makes it difficult to use this method for a mobile robot. In this paper, a digital data compressing technology based on MPEG4 which substitutes for analog technology is proposed to overcome the disadvantages by using DWT(Discreate Wavelet Transform) instead of DCT(Discreate Cosine Transform). The TI Company's DSP chip, TMS320C6711, is used for the image encoder, and the performance of the proposed method is evaluated by PSNR(Peake Signal to Noise Rates), QP(Quantization Parameter) and bitrate.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2010년도 하계학술대회 논문집
• /
• pp.293-293
• /
• 2010

In this paper, we propose a stereo vision based monitoring concept for passenger's safety on railroad platform. In general, basic concept of stereo image processing technique uses the correlations between left and right images, and extracts additional distance information. It provides easy removal of ambient illumination changes, which has been difficult to achieve with conventional 2D based image processing technique. In the paper, we present developed stereo camera and stereo vision based detection algorithm in order to monitor possible accidents at platform area, and verified the detection performance of proposed system with experimental results.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 2000년도 THE THIRD INTERNATIONAL CONFERENCE ON AGRICULTURAL MACHINERY ENGINEERING. V.II
• /
• pp.354-362
• /
• 2000

In Korea, researches on year-round leaf vegetables production system are in progress, most of them focused on environmental control. Therefore, automation technologies for harvesting, transporting, and grading are in great demand. A robot system for harvesting lettuces, composed of a 3-DOF (degree of freedom) manipulator, an end-effector, a lettuce feeding conveyor, an air blower, a machine vision system, six photoelectric sensors, and a fuzzy logic controller, was developed. A fuzzy logic control was applied to determine appropriate grip force on lettuce. Leaf area index and height were used as input variables and voltage as an output variable for the fuzzy logic controller. Success rate of the lettuce harvesting was 94.12%, and average harvesting time was approximately 5 seconds per lettuce.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 1996년도 International Conference on Agricultural Machinery Engineering Proceedings
• /
• pp.658-667
• /
• 1996

A computer vision system was developed to automatically detect and locate the oyster hinge line, one step in shucking an oyster. The computer vision system consisted of a personal computer, a color frame grabber, a color CCD video camera with a zoom lens, two video monitor, a specially designed fixture to hold the oyster, a lighting system to illuminate the oyster and the system software. The software consisted of a combination of commercially available programs and custom designed programs developed using the Microsoft CTM . Test results showed that the image resolution was the most important variable influencing hinge detection efficiency. Whether or not the trimmed -off-flat-white surface area was dry or wet, the oyster size relative to the image size selected , and the image processing methods used all influenced the hinge locating efficiency. The best computer software and hardware combination used successfully located 97% of the oyster hinge lines tested. This efficienc was achieve using camera field of view of 1.9 by 1.5cm , a 180 by 170 pixel image window, and a dry trimmed -off oyster hinge end surface.

• Journal of Biosystems Engineering
• /
• 제19권4호
• /
• pp.369-379
• /
• 1994

A computer vision system consisted of a microscope, a CCD camera, a frame grabber and a personal computer was used to analyze spraying pattern. An algorithm was developed for the system to measure size of droplets including overlapped droplets, to count number of droplets, and to estimate spray deposition in a certain area from the data obtained. A series of experiment was carried out to test validity of the algorithm. The experiment resulted that accuracy of the droplet size measurement, accuracy of counting the number of droplets and the estimation of spray deposition were within an acceptable range. It was concluded from the results that the computer vision system operated by the developed algorithm is very useful tool to analyze spraying pattern.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2002년도 추계학술대회 논문집
• /
• pp.554-557
• /
• 2002

This paper describes power potential field method for the collision-free path planning of stereo-vision based mobile robot. Area based stereo matching is performed for obstacle detection in uncertain environment. The repulsive potential is constructed by distributing source points discretely and evenly on the boundaries of obstacles and superposing the power potential which is defined so that the source potential will have more influence on the robot than the sink potential when the robot is near to source point. The mobile robot approaches the goal point by moving the robot directly in negative gradient direction of the main potential. We have investigated the possibility of power potential method for the collision-free path planning of mobile robot through various experiments.

• 디지털산업정보학회논문지
• /
• 제4권1호
• /
• pp.25-31
• /
• 2008

In this paper, we propose a new method that separates background and foreground from stereo images. This method can be improved automatic target tracking system by using disparity map of the stereo vision system and background-separating mask, which can be obtained camera configuration parameters. We use disparity map and camera configuration parameters to separate object from background. Disparity map is made with block matching algorithm from stereo images. A morphology filter is used to compensate disparity error that can be caused by occlusion area. We could obtain a separated object from background when the proposed method was applied to real stereo cameras system.

• 융복합기술연구소 논문집
• /
• 제3권2호
• /
• pp.31-37
• /
• 2013

This paper proposes a vision-based inspection algorithm for a punch which is used when forming the head of the small screws. To maintain good quality of punch, the precise inspection of its dimension and the depth of the punch head is important. A CCD camera and an illumination dome light are used to measure its dimensions. And a structured line laser is also used to measure the depth of the punch head. Resolution and visible area depend on setup between laser and camera which is determined using CAD-based simulation. The proposed method is successfully evaluated using experiment on #2 punch.