Monocular Workpiece Detection With Height-Based Re-Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing workpiece detection devices using monocular cameras struggle to accurately measure the position of workpieces due to inaccuracies in height measurement, leading to potential process failures and stops in workpiece holding robots.
Innovation Solution
A workpiece detection device and method that includes a trapezoid correction unit, pattern matching units for selecting the most matching model size and angle, a primary detection unit for initial position and angle detection, an actual load height calculation unit, and a secondary detection unit for re-detection using a reduced set of models based on the calculated height, ensuring high accuracy in workpiece positioning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a monocular camera is used to photograph the workpiece, then the device complexity is reduced, but the measurement precision of workpiece height and position deteriorates
Solution Approach 1:
The system performs preliminary actions by having the robot gripper approach the workpiece to a predetermined position before actual measurement. The robot moves the gripper to a known reference position, establishes a reference image, and then uses this reference to calculate the workpiece top surface position. This preliminary positioning and reference establishment enables the monocular camera to achieve accurate measurements without complex multi-camera systems.
2Device complexity
If simple monocular camera detection is used, then the device complexity is reduced, but the reliability of workpiece holding deteriorates due to inaccurate position detection
Solution Approach 1:
The system implements feedback by using the monocular camera to detect the workpiece position, calculating the deviation from the target position, and then correcting the robot's gripping position based on this feedback. The camera captures images, the processing unit calculates position deviations, and this information feeds back to adjust the robot's holding position, ensuring reliable workpiece holding despite using simple equipment.
3Measurement precision
If multiple cameras are used to achieve accurate height measurement, then the measurement precision is improved, but the device complexity increases
Solution Approach 1:
The robot gripper serves as an intermediary tool. Instead of using multiple cameras to directly measure height, the system uses the gripper to establish a reference position, and then uses the monocular camera to measure the relative position between the reference point and the workpiece top surface. This intermediary approach enables accurate height measurement with a single camera.
4Adaptability or versatility
If the robot adjusts gripping position based on inaccurate detection, then adaptability is improved, but the measurement precision requirement increases
Solution Approach 1:
The system uses feedback to improve adaptability. The monocular camera detects workpiece position, the processing unit calculates the deviation from the target position, and this feedback information is used to adjust the robot's gripping position. This feedback loop enables the robot to adapt to workpiece position variations while maintaining measurement precision through iterative correction.
Data Source
AI summary
A pattern matching unit carries out a pattern matching between a photographed image obtained by photographing a workpiece with a monocular camera and a first plurality of models having a plurality of sizes and a plurality of angles, and selects a model having a size and an angle with the highest degree of matching. A primary detection unit detects a position and an angle of an uppermost workpiece based on the selected model. An actual load height calculation unit calculates an actual load height of the uppermost workpiece based on a hand height. A secondary detection unit re-detects the position and the angle of the uppermost workpiece based on a model having a size and an angle with the highest degree of matching selected by carrying out a pattern matching between the photographed image and a second plurality of models selected or newly created based on the actual load height.