A Hybrid Algorithm for the Laser Stripe Centreline Extraction

Zirui Mao, Yuanping Xu*, Benjun Guo, Tukun Li, Xiangqian Jiang, Yajing Shi, Yanlong Cao, Zhijie Xu, Chaolong Zhang, Jian Huang

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review

7 Citations (Scopus)

Abstract

Centreline extraction is one of the critical processes of structured light systems that play an increasingly important role in industry 4.0. This paper proposes a novel algorithm to extract the centreline by combining an improved skeleton thinning algorithm to extract the initial centreline and an improved grey centroid algorithm to establish the final centreline. It consists of several steps: Firstly, an image difference operation and a thresholding operation are undertaken, and the Canny edge detection algorithm is applied to locate the approximate position of the laser stripe to reduce the image matrix calculation cost; Secondly, an initial centreline is extracted via the use of an image morphology operation and a skeleton thinning algorithm; Finally, a high-power grey centroid method is employed to acquire the centreline at the sub-pixel level. Experiments together with a comparison with other mainstream methods is conducted to test the validity and practicability of the proposed hybrid algorithm. The experimental results show that the speed of the proposed algorithm is 50% faster than the Steger algorithm, and the root-mean-square error is 40% lower than the grey centroid method.

Original languageEnglish
Pages (from-to)30-35
Number of pages6
JournalProcedia CIRP
Volume114
DOIs
Publication statusPublished - 2022
Externally publishedYes
Event17th CIRP Conference on Computer Aided Tolerancing, CAT 2022 - Metz, France
Duration: 15 Jun 202217 Jun 2022

Keywords

  • Centreline extraction
  • Grey centroid method
  • Line structured light
  • Skeleton thinning

Fingerprint

Dive into the research topics of 'A Hybrid Algorithm for the Laser Stripe Centreline Extraction'. Together they form a unique fingerprint.

Cite this