6D pose measurement of metal parts based on virtual geometric feature point matching. (11th October 2021)

• Record Type: Journal Article
• Authors: He, Zaixing; Wuxi, Feng; Zhao, Xinyue; Zhang, Shuyou; Tan, Jianrong
• Is Part Of: Measurement science & technology. Volume 32:Number 12(2021)
• Publication Date: 2021-10-11
• Subjects: pose estimation -- textureless part -- virtual geometric feature point -- monocular image; Physical measurements -- Periodicals; Scientific apparatus and instruments -- Periodicals; Equipment and Supplies -- Periodicals; Science -- instrumentation -- Periodicals; Technology -- instrumentation -- Periodicals; Mesures physiques -- Périodiques; Physical measurements; Scientific apparatus and instruments; Periodicals; 502.87
• DOI: 10.1088/1361-6501/ac2a85
• Languages: English
• ISSNs: 0957-0233

Abstract

Abstract: The 6D pose measurement of metal parts is of significance in intelligent manufacturing. This paper proposes a new method which provides a solution through the utilization of geometric features for pose measurement problem in intelligent manufacturing. The proposed method extracts the geometric features in the image and then calculates and matches the virtual geometric feature points according to the pose relation of the geometric features. We propose an algorithm to implement the method. Specifically, the straight lines and ellipses are extracted from the edges and the holes of parts as the geometric features. The crosspoints of the lines and the centers of the ellipses are calculated and utilized as virtual geometric feature points. In addition, to address the fact that the geometric features cannot be easily detected in a single image, this paper proposes a feature extraction method based on multi-image fusion. The experimental results demonstrate that the proposed method can achieve high robustness and accuracy.