TY - GEN
T1 - Plane Defect Detection Based on 3D Point Cloud
AU - Bai, Mingsong
AU - Wu, Shuang
AU - Ma, Hongbin
AU - Jin, Ying
N1 - Publisher Copyright:
© 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
PY - 2024
Y1 - 2024
N2 - In the production of industrial products, surface defect detection is mostly carried out through manual inspection. However, this detection method has several shortcomings, such as low efficiency, limited accuracy, and high inspection costs. To address these issues, we design an improved random sampling consistency (RANSAC) algorithm based on adaptive parameters of 3D point cloud data for plane defect detection. The main steps of our algorithm include the down sampling function which contains adaptive parameters, optimized based on KD-tree proximity substitution method. Our algorithm also includes the RANSAC segmentation and fitting plane function of adaptive parameters. Experimental results demonstrate that our algorithm can accurately identify protrusions or indentations defects of 1 mm or larger in those planes based on point clouds data, with a recognition rate more than 90%. The experimental results validate the suitability of our algorithm for industrial applications, offering an efficient and cost-effective solution for plane defect detection.
AB - In the production of industrial products, surface defect detection is mostly carried out through manual inspection. However, this detection method has several shortcomings, such as low efficiency, limited accuracy, and high inspection costs. To address these issues, we design an improved random sampling consistency (RANSAC) algorithm based on adaptive parameters of 3D point cloud data for plane defect detection. The main steps of our algorithm include the down sampling function which contains adaptive parameters, optimized based on KD-tree proximity substitution method. Our algorithm also includes the RANSAC segmentation and fitting plane function of adaptive parameters. Experimental results demonstrate that our algorithm can accurately identify protrusions or indentations defects of 1 mm or larger in those planes based on point clouds data, with a recognition rate more than 90%. The experimental results validate the suitability of our algorithm for industrial applications, offering an efficient and cost-effective solution for plane defect detection.
KW - Defect Detection
KW - Point Cloud
KW - Random Sample Consensus
UR - http://www.scopus.com/inward/record.url?scp=85176948993&partnerID=8YFLogxK
U2 - 10.1007/978-981-99-7593-8_6
DO - 10.1007/978-981-99-7593-8_6
M3 - Conference contribution
AN - SCOPUS:85176948993
SN - 9789819975921
T3 - Communications in Computer and Information Science
SP - 57
EP - 69
BT - Advanced Computational Intelligence and Intelligent Informatics - 8th International Workshop, IWACIII 2023, Proceedings
A2 - Xin, Bin
A2 - Kubota, Naoyuki
A2 - Chen, Kewei
A2 - Dong, Fangyan
PB - Springer Science and Business Media Deutschland GmbH
T2 - 8th International Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2023
Y2 - 3 November 2023 through 5 November 2023
ER -