首页|基于偏振视觉的环形构件表面形貌重构

基于偏振视觉的环形构件表面形貌重构

扫码查看
为了增强对环形构件表面的质量检测能力,提出一种基于单目DoFP偏振相机的FSV偏振检测方法.根据偏振反射分离出的漫反射信息,对基于FSV的偏振三维重建模型进行校正.利用偏振数据得到增强的二维表面图像,并进行相应的偏振三维建模.实验结果表明,与传统成像系统和非FSV偏振成像系统相比,所提出的检测方法测得的DoP图像在图像评价指标上提升3%以上,重建的三维模型和真实检测表面的均方根误差为0.35,大大提高了对环形构件表面的质量检测能力.
Surface Topography Reconstruction of Ring Components Based on Polarization Vision
In order to enhance the quality inspection of ring component surfaces,a FSV polarisation detection method based on a monocular DoFP polarisation camera was proposed.The FSV-based polarimetric 3D reconstruction model was calibrated based on the diffuse reflection information separated from the polarimetric reflections.Enhanced 2D surface images were obtained using the polarisati-on data and the corresponding polarisation 3D modelling was performed.The experimental results show that the DoP images measured by the proposed detection method are more than 3%better in terms of image evaluation index compared to conventional imaging systems and non-FSV polarisation imaging systems,and the root-mean-square error between the reconstructed 3D model and the real inspection surface is 0.35,which greatly improves the quality inspection capability of the ring components surface.

ring componentspolarization imagingfull Stokes vector(FSV)polarised reflection separationpolarization 3D recon-struction

朱乾皓、陈景铭、张礼华、汪振耀

展开 >

张家港中环海陆高端装备股份有限公司,江苏张家港 215626

江苏科技大学机械工程学院,江苏镇江 212114

环形构件 偏振成像 全斯托克斯矢量(FSV) 偏振反射分离 偏振三维重构

2024

机床与液压
中国机械工程学会 广州机械科学研究院有限公司

机床与液压

CSTPCD北大核心
影响因子:0.32
ISSN:1001-3881
年,卷(期):2024.52(12)
  • 5