Hot Paper - Research on Visual Detection Algorithm for Groove Feature Sizes by Means of Structured Light Projection

Research on Visual Detection Algorithm for Groove Feature Sizes by Means of Structured Light Projection

基于结构光投影的凹槽特征尺寸视觉检测算法研究
構造化光投影による溝特徴サイズの視覚的検出アルゴリズムに関する研究
Structured Light Projection을 통한 Groove Feature Size의 Visual Detection Algorithm 연구
Investigación sobre el algoritmo de detección visual para tamaños de características de ranura mediante proyección de luz estructurada
Recherche sur l'algorithme de détection visuelle des tailles de caractéristiques de rainure au moyen d'une projection de lumière structurée
Исследование алгоритма визуального обнаружения размеров элементов канавки с помощью проекции структурированного света

ZHA Anfei 查安飞 ¹, LU Yonghua 陆永华 ¹, WANG Mingxin 王明昕 ², ZHU Huayu 朱华煜 ¹

¹ College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, P. R. China
中国南京南京航空航天大学机电学院
² Nanjing Atekon Automation Technology Co., Ltd., Nanjing 210012, P. R. China
中国南京傲拓科技股份有限公司

http://dx.doi.org/10.16356/j.1005⁃1120.2022.03.011

http://tnuaa.nuaa.edu.cn/njhkhten/article/html/202203011

Transactions of Nanjing University of Aeronautics & Astronautics, 12 July 2022

Abstract

The visual inspection is an economical and effective method for welding. For measuring the feature sizes of grooves, a method based on line structured light is presented.

Firstly, an adaptive algorithm to extract the sub-pixel centerline of structured light stripes is introduced to deal with the uneven width and grayscale distributions of laser stripes, which is based on the quadratic weighted grayscale centroid. By means of region-of-interest（ROI）division and image difference, an image preprocessing algorithm is developed for filtering noise and improving image quality.

Furthermore, to acquire geometrical dimensions of various grooves and groove types precisely, the sub-pixel feature point extraction algorithm of grooves is designed. Finally, experimental results of feature size measuring show that the absolute error of measurement is 0.031—0.176 mm， and the relative error of measurement is 0.2%—3.6%.

Transactions of Nanjing University of Aeronautics & Astronautics_1

Transactions of Nanjing University of Aeronautics & Astronautics_2

Transactions of Nanjing University of Aeronautics & Astronautics_3

Reviews and Discussions