Piston Crown Defect Inspection Using 3D Multi-Angle Projection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional visual inspection apparatuses fail to improve inspection accuracy when the inspection target is imaged at multiple posture angles, and may reduce accuracy if defects are not detected at certain angles.
Innovation Solution
A visual inspection method that detects defect candidates at multiple posture angles, determines their three-dimensional positions, applies perspective projection transformation to estimate two-dimensional positions, and inspects using feature amounts to enhance accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the inspection target is imaged at multiple posture angles, then the inspection accuracy can be improved, but the inspection accuracy may reduce if there is an image at an angle where a defect candidate is not detected
Solution Approach 1:
The patent introduces an image synthesis unit that acts as an intermediary to combine defect candidate information from multiple captured images taken at different posture angles. This synthesis process integrates detection results across different angles, ensuring that defects not visible at certain angles can still be detected through their appearance in other angles, thereby maintaining reliable defect detection while utilizing multi-angle imaging to improve inspection accuracy.
Solution Approach 2:
The patent transitions from two-dimensional defect detection in single images to three-dimensional defect characterization by incorporating multiple posture angles. By synthesizing defect candidate information across different angular dimensions, the system creates a more comprehensive defect assessment that leverages spatial dimensionality to improve both inspection accuracy and detection reliability.
2Measurement precision
If the inspection target is inspected by being imaged at a plurality of posture angles, then the inspection accuracy may be improved, but the complexity of the inspection process increases
Solution Approach 1:
The patent merges multiple captured images taken at different posture angles into a unified inspection result through the image synthesis unit. By combining defect candidate information from multiple sources into a single synthesized output, the system manages the complexity of multi-angle imaging while achieving improved inspection accuracy through integrated analysis.
Solution Approach 2:
The patent creates synthesized copies of defect candidate information from multiple captured images. Instead of manually analyzing each individual image, the system generates synthesized representations that consolidate defect data across different angles, simplifying the inspection process while maintaining the benefits of multi-angle imaging for improved accuracy.
Data Source
AI summary
A visual inspection apparatus detects a defect candidate for each of captured images of a crown surface of a piston that are captured at a plurality of posture angles different from one another, locates a three-dimensional position of the defect candidate based on a two-dimensional position of the defect candidate detected from at least one captured image among the captured images captured at the plurality of posture angles, applies a perspective projection transformation on the three-dimensional position of the defect candidate to acquire a two-dimensional position of the defect candidate for each of the captured images captured at the plurality of posture angles, determines a feature amount regarding the defect candidate based on the two-dimensional position of the defect candidate for each of the captured images captured at the plurality of posture angles, and inspects the crown surface of the piston using the feature amount regarding the defect candidate.