Surface Defect Identification using Bayesian Filtering on a 3D Mesh

2025-01-30

AI Summary

To address insufficient surface defect localization accuracy in industrial 3D quality inspection, this paper proposes a CAD-point-cloud fusion Bayesian geometric filtering method. The core innovation lies in modeling CAD mesh vertices as Bayesian state variables and performing unified fusion of multi-source heterogeneous sensor data (stereo/depth camera point clouds) within a geometric prior space. High-density triangular mesh representation, weighted least-squares state estimation, and iterative registration enable efficient and robust estimation over regions of interest. With only approximately 50 sparse point cloud frames, the method achieves sub-millimeter localization accuracy (standard deviation <1 mm). Crucially, this work is the first to embed Bayesian filtering directly into the CAD geometric structure space—thereby significantly improving both accuracy and generalizability of 3D defect identification under limited-sample conditions.

Technology Category

• Intelligent Robots: State Estimation
• Computer Vision: 3D Computer Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services

Abstract

This paper presents a CAD-based approach for automated surface defect detection. We leverage the a-priori knowledge embedded in a CAD model and integrate it with point cloud data acquired from commercially available stereo and depth cameras. The proposed method first transforms the CAD model into a high-density polygonal mesh, where each vertex represents a state variable in 3D space. Subsequently, a weighted least squares algorithm is employed to iteratively estimate the state of the scanned workpiece based on the captured point cloud measurements. This framework offers the potential to incorporate information from diverse sensors into the CAD domain, facilitating a more comprehensive analysis. Preliminary results demonstrate promising performance, with the algorithm achieving convergence to a sub-millimeter standard deviation in the region of interest using only approximately 50 point cloud samples. This highlights the potential of utilising commercially available stereo cameras for high-precision quality control applications.

Problem

• 3D Model
• Surface Defects
• Quality Inspection

Innovation

• Bayesian Filtering
• CAD Integration
• 3D Quality Inspection