Image Matching for Sleeve Position Inspection Using Ellipses
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Sleeve inspection in construction projects is inaccurate and labor-intensive, leading to potential installation errors and increased man-hours, especially in large structures.
Innovation Solution
An image matching device and method that detects ellipses around sleeves in images, maps them to design drawing circles, and measures position errors using ellipse detection and matching units, optionally with IMU sensor data for enhanced accuracy and speed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual measurement with measuring tape is used for sleeve inspection, then the inspection process is simple to perform, but the measurement accuracy is poor and installation errors occur
Solution Approach 1:
The patent replaces the mechanical measuring tape system with an optical imaging system (camera) and image processing algorithm. The ellipse detection unit detects ellipses around sleeve top surfaces from images, and the ellipse matching unit maps these ellipses to circles in design drawings, automatically calculating position errors without manual measurement.
Solution Approach 2:
The patent creates a digital copy of the physical sleeve positions through image capture and ellipse detection. The detected ellipses from the camera image are mapped to corresponding circles in the design drawing, creating a digital representation that can be precisely measured and compared without physical contact.
2Measurement precision
If sleeve markers are installed on each sleeve for position inspection, then the inspection accuracy is improved, but the man-hours required for inspection increase significantly
Solution Approach 1:
The patent enables the sleeves to serve themselves by utilizing their inherent physical characteristics (circular top surfaces that appear as ellipses in angled images) for identification and positioning. The ellipse detection unit automatically detects these natural geometric features without requiring any additional markers or labels to be installed on the sleeves.
Solution Approach 2:
The patent extracts and utilizes the inherent geometric feature (elliptical appearance of circular sleeve tops in perspective images) directly from the sleeve structure itself, eliminating the need for external markers. The system takes out only the essential geometric information needed for positioning from the complex image data.
3Loss of time
If manual inspection of each sleeve is performed, then the inspection process is straightforward, but the time required for inspection increases with larger structures
Solution Approach 1:
The patent implements continuous automated inspection by capturing images of multiple sleeves and processing them through the ellipse detection and matching units in sequence. The system continuously processes image data to generate position error measurements for all sleeves, enabling efficient inspection of large structures without manual intervention for each sleeve.
Solution Approach 2:
The patent replaces the manual mechanical inspection process with an automated optical-mechanical system consisting of camera imaging, digital image processing, and automated calculation. This substitution enables rapid processing of multiple sleeves simultaneously, dramatically reducing total inspection time for large structures.
Data Source
AI summary
The image matching device includes an ellipse detection unit which detects ellipses around a top surface for each sleeve from an image of a plurality of sleeves, an ellipse matching unit which maps each detected ellipse to a circle of the sleeve shown in a design drawing, frontalizes the ellipses based on a correspondence relation, and measures a position error between each frontalized ellipse and corresponding circle in the design drawing, and a matching result display unit which displays the frontalized ellipses and the circles in the design drawing.