Advance Search
ZHAO Weidong, CHEN Xiangmei, CHENG Xing. 3D Vision Inspection Technology Based on Improved Structured Light Stripe Centre Extraction[J]. Journal of Anhui University of Technology(Natural Science), 2023, 40(1): 82-88. DOI: 10.12415/j.issn.1671-7872.22075
Citation: ZHAO Weidong, CHEN Xiangmei, CHENG Xing. 3D Vision Inspection Technology Based on Improved Structured Light Stripe Centre Extraction[J]. Journal of Anhui University of Technology(Natural Science), 2023, 40(1): 82-88. DOI: 10.12415/j.issn.1671-7872.22075

3D Vision Inspection Technology Based on Improved Structured Light Stripe Centre Extraction

  • Aiming at the problem of uneven gray distribution of laser stripe images collected in the surface quality inspection of industrial metal parts, a 3D inspection technology based on line structure horizontal scanning combined with improved laser stripe center extraction was proposed. The 3D computer vision technology based on modulated linear structured light was used to calibrate the position and attitude transformation of industrial cameras, the linear structured light planes and horizontal scanning continuous frames. The method of laser stripe centerline extraction was improved by using 2D dynamic threshold gray scale weighting based on window, and the accuracy of centerline extraction was improved. The experimental results show that the 3D vision inspection technology with improved structured light stripe centreline extraction is used to reconstruct the point cloud of smooth ceramic floor surface, and the standard deviation of depth is 0.09 mm. This technology is used to detect the surface morphology of metal standard blocks with a height of 10 mm, and the detection accuracy is better than 0.3 mm, and the error is within a reasonable range. The proposed 3D inspection technology can efficiently and undamaged realize the three-dimensional detection of high-precision industrial metal parts.
  • loading

Catalog

    Turn off MathJax
    Article Contents

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return