DOI QR코드

DOI QR Code

Study on Performance Variation of Machine Vision according to Velocity of an Object and Precision Improvement by Linear Compensation

측정물의 속도에 따른 머신비젼의 성능변화와 선형보상에 의한 정밀도 향상

  • Received : 2018.09.18
  • Accepted : 2018.12.07
  • Published : 2018.12.31

Abstract

In this paper, performance analysis of machine vision techniques is presented to improve the convenience and speed of automatic inspection in the industrial field when machine vision is applied to the image not taken in the stationary state, but in the moving state on a conveyer. When the length of cylindrical rods used for automobiles was measured using the edge detection method, the conveying speed increased, and the uncertainty of the boundary between the background and the part image increased, which resulted in a shorter image of the object taken. This paper proposes a linear compensation method to predict the biased errors of the length measurements after examining the pattern of biased and random errors, respectively, with 6 different types of specimens and 7 velocity stages. The length measurement corrected by the linear compensation method had the same accuracy as the stationary state within the speed range of 30 cm/s and could enhance the application capability in automatic inspections.

본 연구에서는 산업현장의 생산라인에서 자동검사의 편이성과 속도를 높이기 위해서 정지상태가 아닌 컨베이어에서 부품이 이송되는 과정에서 촬영한 영상 이미지에 머신비젼 기법을 적용했을 때 나타나는 측정 성능변화를 실제 실험결과를 바탕으로 분석한다. 자동차 부품인 원통형 로드의 길이를 에지검출 기법으로 계측했을 시 이송속도가 높아지면 배경과 부품 이미지 경계의 불확실성이 높아지므로 인하여 이미지 길이도 작아짐을 알 수 있었다. 돌출형과 비돌출형을 포함하여 6 종류의 시편과 7 단계의 속도변화를 통해서 실험을 수행하였고 실험결과에 대해서 속도에 따른 길이측정 편이오차와 확률오차 분석을 수행하였다. 이를 통해서 속도가 증가함에 따라 편이오차와 확률오차가 증가함을 확인하였고 이중에서 편이오차를 줄이기 위한 선형 보상법을 제시하였다. 선형 보상법으로 보정된 원통형 로드의 길이 측정값은 확률오차가 반복정밀도를 넘지않는 30 cm/s 의 속도 구간안에서는 정지상태와 동일한 정밀도를 나타내었다. 따라서 제안된 머신비젼의 분석과 보정기법은 산업현장에서 머신비젼 기반 자동검사의 응용성을 확대할 수 있을 것으로 기대된다.

Keywords

SHGSCZ_2018_v19n12_903_f0001.png 이미지

Fig. 1. Photos of rods used for solenoid valves

SHGSCZ_2018_v19n12_903_f0002.png 이미지

Fig. 2. Experimental setup for machine vision to measure the length of rods on a moving conveyor

SHGSCZ_2018_v19n12_903_f0003.png 이미지

Fig. 3. Gray image of a rod with line ROI

SHGSCZ_2018_v19n12_903_f0004.png 이미지

Fig. 4. Flow diagram of automatic inspection based on machine vision.

SHGSCZ_2018_v19n12_903_f0005.png 이미지

Fig. 5. Gradient profile of pixel values along line ROIin three velocities (①: 0 cm/s, ②: 15 cm/s, ③:36 cm/s)

SHGSCZ_2018_v19n12_903_f0006.png 이미지

Fig. 6. Rod lengths (mm) estimated by machine vision when the velocity of rods increased

SHGSCZ_2018_v19n12_903_f0007.png 이미지

Fig. 7. Average bias (pixel) in length measurements when the velocity of rods increased

SHGSCZ_2018_v19n12_903_f0008.png 이미지

Fig. 8. Standard deviation (pixel) in measurements when the velocity of rods increased

SHGSCZ_2018_v19n12_903_f0009.png 이미지

Fig. 9. Estimated length of extruded rods (mm) ▴: before compensation, ▪: after compensation (Type A, Type B, Type C)

SHGSCZ_2018_v19n12_903_f0010.png 이미지

Fig. 10. Estimated length of non-extruded rods (mm) ▴: before compensation, ▪: after compensation (Type D, Type E, Type F)

SHGSCZ_2018_v19n12_903_f0011.png 이미지

Fig. 11. Biased error (pixel) of rod lengths after compensation according to the velocity of objects

Table 1. Dimensions of rod-specimens measured by vernier caliper

SHGSCZ_2018_v19n12_903_t0001.png 이미지

Table 2. Specification of camera system

SHGSCZ_2018_v19n12_903_t0002.png 이미지

Table 3. Rod lengths calculated by machine vision in stationary state

SHGSCZ_2018_v19n12_903_t0003.png 이미지

Table 4. Biased errors of rod lengths after compensation

SHGSCZ_2018_v19n12_903_t0004.png 이미지

References

  1. J. H. Kim, "Machine Vision Technology Trends and Future," iCROS, Vol. 19, No. 4, pp. 23-31, 2013.
  2. Y. S. Jung And K. H. Park, "O-ring Size Measurement Based on a Small Machine Vision Inspection Equipment," Journal of the Korea Industrial Information Systems Research, Vol. 19, No. 4, pp. 41-52, 2014. https://doi.org/10.9723/JKSIIS.2014.19.4.041
  3. S. O. Lee, Y. S. Kim And Y. T. Do, "Vision System for Inspecting Steel Bearing Ball Surface," iCROS, Vol. 15, No. 9, pp. 919-922, 2009.
  4. Y. J. Park, "The Lens Aberration Correction Method for Laser Precision Machining in Machine Vision System," J. of Digital Convergence, Vol. 10, No. 10, PP. 301-306, 2012. https://doi.org/10.14400/JDPM.2012.10.10.301
  5. C. H. Lee, Y. E. Lim, K. Park and S. W. Ra, "Design and Analysis of Illumination Optics for Image Uniformity in Omnidirectional Vision Inspection System for Screw Threads," J. of KSPE, Vol. 31, No. 3, pp. 261-268, 2014. https://doi.org/10.7736/KSPE.2014.31.3.261
  6. D.-X Zhao and Y.-X Cui, "Research on the method of tracking and measuring moving object based on machine vision, Proc. Int. Conf. on Computational Intelligence and Software Engineering, pp. 1-4, 2010.
  7. M. Arsalan and A. Aziz, "Low-cost machine vision system for dimension measurement of fast moving conveyor products", Proc. Int. Conf. on Open source systems and technologies, pp. 22-27, 2012.
  8. E. O. Doebelin, Measurement Systems: Application and Design, McGraw-Hill Book Co, 2003.