• Title/Summary/Keyword: digital light processing

Search Result 193, Processing Time 0.025 seconds

A Study For Automobile License Plate Extraction Using DCT and Correlation (DCT와 Correlation을 이용한 자동차번호판 추출에 관한 연구)

  • 경보현;손태주;남궁연;남궁재찬
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.25 no.7A
    • /
    • pp.1050-1056
    • /
    • 2000
  • In this paper, We Propose the automobile license plate extraction method using Discrete Cosin Transform and Correlation fem automobile image obtained through digital camera. The automobile license plate is consisted of the character and rectangle background of it. We extracted the automobile edge image by the DCT processing of automobile image and Obtained the automobile license plate from the automobile edge image by Correlation processing. We separated characters from automobile license plate using the projection histogram. Compare to the previous methods, we obtained the good result from extracting the automobile license plate at night, very strong light and bad weather.

  • PDF

A study on detection method of traffic lights using Spotlights and MSER regions detection (Spotlights와 Maximally Stable Extremal Regions)영역 검출 기반의 조도변화에 강인한 교통신호등 검출 방안)

  • Kim, Jong-Bae;Jiang, Ji-Woog
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2013.11a
    • /
    • pp.1709-1712
    • /
    • 2013
  • 교통 신호등은 운전자 혹은 보행자들의 뚜렷한 시인성 확보를 위해 가능한 주위 배경과 구분되는 색상, 모양, 질감 등으로 구성하여 설치되어 있는 특징을 가지고 있다. 결국 기존 교통 신호등 검출 연구들에서는 대부분 교통 신호등의 색상과 모양을 기반으로 한 검출 연구가 주류를 이루고 있는 것이 사실이다. 하지만, 외부 날씨, 복잡한 시내, 다른 물체와의 겹침 등의 문제로 인해 색상 및 모양 기반의 교통 신호등, motion blur, 검출 오류가 증가 되고 있다. 따라서 본 연구에서는 입력 영상에서 색상정보를 배제하고 motion blur나 밝기 변화에 덜 민감하고 먼 거리에서도 뛰어난 시인성을 가진 spot light 검출을 통해 입력 영상에서 가장 밝은 교통표지판 후보 영역들을 검출한다. 그리고 교통 신호등의 특징인 가능한 원형을 유지하고 있으며 원형 외부 색상과 내부 색상이 현저하게 두드러지는 영역을 maximally stable extremal regions (MSER) 알고리즘을 사용하여 입력 영상에서 후보 영역을 선택한다. 마지막으로, 검출된 영역들에서 교통 신호등 영역을 검출하기 위해 템플릿 매칭 방법을 적용한다. 제안한 방법을 도로 상에서 실험한 결과, 평균 94% 이상의 검출율을 제시하였고, 특히 야간 시간대에 검출율이 비교적 높게 제시되었다.

Development of Frost Thickness Measurement Method Using Optical Technique (광학적 기법에 의한 Frost 두께 측정방법의 개발)

  • Jeong, Jae-Hong;Yoon, Sang-Youl;Kim, Kyung-Chun
    • Proceedings of the KSME Conference
    • /
    • 2001.06d
    • /
    • pp.654-659
    • /
    • 2001
  • A new non-contact method of the frost thickness measurement has been developed. The method is based on the digital image processing technique to identify the reflection edge of the image captured by a CCD camera under laser sheet light illumination. To insure the accuracy of frost layer thickness, an in-situ calibration procedure is carried out with a calibration target with 0.5mm holes. Using the mapping function obtained by the calibration procedure, the contour of frost surface can be estimated with sub-pixel resolutions. The developed method is applied to study the effect of cooling plate temperature on the frost thickness in a small low speed wind tunnel.

  • PDF

Improvement of Calibration Method of Thermochromic Liquid Crystal Reflecting Measurement Angle (측정각도를 고려한 액정교정기법의 개선)

  • Yoon, Soon-Hyun;Sim, Jae-Kyung;Woo, Chang-Soo
    • Transactions of the Korean Society of Mechanical Engineers B
    • /
    • v.24 no.2
    • /
    • pp.188-194
    • /
    • 2000
  • Thermochromic liquid crystal reflect a unique color at even temperature. Therefore, they have been successfully applied to non-intrusive heat transfer research. Hue capturing method is widely used in the quantitative measurement from the TLC image. However it is affected by several measurement conditions. The distances of camera and light source have little influence on the color, but the value of hue is seriously affected by the measurement angle. In this study, the hue capturing method is improved by considering the effect of measurement angle. This improved calibration method can diminish the misreading of temperature caused by curvature of test surface.

BREAKUP LENGTH OF CONICAL EMULSION SHEET DISCHARGED BY PRESSURE-SWIRL ATOMIZER

  • Rhim, Jung-Hyun;No, Soo-Young
    • International Journal of Automotive Technology
    • /
    • v.2 no.3
    • /
    • pp.103-107
    • /
    • 2001
  • Many researches on pressure-swirl injectors due to the variety of application have been conducted on the effects of nozzle design, operating conditions, properties of liquid and ambient conditions on the flow and spray characteristics. The breakup length of conical emulsified fuel sheet resulting from pressure-swirl atomizer using in the oil burner was investigated with the digital image processing method with neat light oil and emulsion with water content of lotto% and the surfactant content of 1-3%. The injection pressure ranged from 0.1 to 1.2 MPa was selected. The various regimes for the stage of spray development within the experimental conditions selected in this study is newly suggested in terms of Ohnesorge number and injection pressure. The breakup length for both criteria show the same tendency even though the random nature of perforation and disintegration process of liquid sheet. The stage of spray development is widely different with the physical properties of liquid atomized, mainly viscosity of liquid. The breakup length decreases smoothly with increase in the injection pressure for the lower viscous liquid.

  • PDF

디지탈 영상처리를 이용한 광탄성 프린지의 세선화처리

  • 백태현
    • Proceedings of the Korean Society of Precision Engineering Conference
    • /
    • 2001.10a
    • /
    • pp.127-133
    • /
    • 2001
  • Photoelastic isochromatic fringes related to the difference of principal stresses have some bandwidth whose light intensities are not constant and unsymmetrical in experimental image. Hence it is difficult to measure fringe order accurately at a data point by visual observation. In this study, the method of fringe sharpening, which can extract sharpened lines from both full-and half-order fringes by digital image processing, is developed. To test the method, various simple photoelastic fringe patterns are simulated and their image are processed to yield sharpened lines. The method is than applied to general problem such as image of a circular disk compressed by concentrated loads and a cylinder subjected to internal pressure. The procedure is proved to be capable of extracting sharpened lines accurately from photoelastic isochromatic fringes.

An Optimal Design Method for Optical Fiber Filter of Lattice Structure (격자형 광파이버필터의 최적설계에 관한 연구)

  • 이채욱;문병현;우홍채
    • Journal of the Korean Institute of Telematics and Electronics B
    • /
    • v.30B no.5
    • /
    • pp.34-42
    • /
    • 1993
  • Due to the low loss, broadband and accurate short time delay properties of optical fiber, it has attracted as a delay medium for high speed and broad-band signal processing. In this paper, we consider the coherent optical fiber filter of lattice structure, which uses coherent light sources and consists of directional couplers and optical fiber delay elements.The differences between the optical fiber filter and the ordinary digital filter are 1) the coupling coefficients of directional couplers are restricted between 0 and 1. 2) the optical signal is divided into ${j\sqrt{a}}and\;{j\sqrt{1-a}}$ at the directional coupler. Considering these restrictions, the design formulae and condition of realibility for optical fiber filter of lattice structure which makes the optimal use of optical signal energy are derived.

  • PDF

Vision-Based Indoor Localization Using Artificial Landmarks and Natural Features on the Ceiling with Optical Flow and a Kalman Filter

  • Rusdinar, Angga;Kim, Sungshin
    • International Journal of Fuzzy Logic and Intelligent Systems
    • /
    • v.13 no.2
    • /
    • pp.133-139
    • /
    • 2013
  • This paper proposes a vision-based indoor localization method for autonomous vehicles. A single upward-facing digital camera was mounted on an autonomous vehicle and used as a vision sensor to identify artificial landmarks and any natural corner features. An interest point detector was used to find the natural features. Using an optical flow detection algorithm, information related to the direction and vehicle translation was defined. This information was used to track the vehicle movements. Random noise related to uneven light disrupted the calculation of the vehicle translation. Thus, to estimate the vehicle translation, a Kalman filter was used to calculate the vehicle position. These algorithms were tested on a vehicle in a real environment. The image processing method could recognize the landmarks precisely, while the Kalman filter algorithm could estimate the vehicle's position accurately. The experimental results confirmed that the proposed approaches can be implemented in practical situations.

A Study on the Process Optimization by a Beadless Stamping (노비드스탬핑 공법을 이용한 공정최적화에 관한 연구)

  • Kim, S.H.;Shim, H.B.
    • Transactions of Materials Processing
    • /
    • v.21 no.8
    • /
    • pp.485-492
    • /
    • 2012
  • As the shape of stamped part is complicated and as the trend toward light weight continues, the higher level of difficulty is required in making stamping die because of inevitably poor formability. The poor formability can be improved if the material flow during the stamping is carefully controlled. Application of drawbead became commonsense used to retard metal flow of blank into the die cavity at the region where wrinkle is expected. In the study, the concept of beadless stamping process is proposed and the method how to realize the beadless stamping process is presented. The validity of the proposed method is confirmed by the application of the real auto part.

A Study on Optimum Lighting Conditions for Effective Coordnate Measuring Machine (효율적인 CMM을 위한 조명 조건 개선에 관한 연구)

  • Bae, Jun-Young;Ban, Kap-Soo
    • Journal of the Korean Society of Industry Convergence
    • /
    • v.17 no.3
    • /
    • pp.184-193
    • /
    • 2014
  • Machine vision systems is applied for various industries such as optimize your spending, automate your production and maximize your efficiency. This research is effective for most optimal light condition of machine vision that technology was applied bald outside human visual acuity. Image processing converts a target image captured by a CCD camera into a digital signal and then performs various arithmetic operations on the signal to extract the characteristics of the target, such as points, lines, circles, area and length. The mathematical concepts of convolution and the kernel matrix are used to apply filters to signals, to perform functions such as extracting edges and reducing unwanted noise. This research analyze and compares matching ratio with reference image and search for optimal lighting condition in accuracy that user wants coming input image according to brightness change of lighting.