Structured Light Touch Detection Using Multi-Pitch Epipolar Patterns
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing image recognition technology for detecting finger contact with a screen has low position detection accuracy in the depth direction, resulting in low touch recognition accuracy.
Innovation Solution
An image recognition device that projects a first linear pattern and a second linear pattern with different pitches along an epipolar line, allowing for accurate detection of object positions and touch recognition by determining measurement target points and distinguishing phase wrapping.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a single linear pattern is projected for touch detection, then the device complexity is low, but the position detection accuracy in the depth direction is insufficient
Solution Approach 1:
The patent divides the detection pattern into multiple linear patterns (first linear pattern and second linear pattern) with different pitches. Each pattern provides depth information at different resolution levels, allowing accurate depth detection through segmented analysis of pattern displacements caused by finger contact.
Solution Approach 2:
The patent introduces multiple pitch dimensions (first pitch and second pitch) along the epipolar line to enhance depth detection capability. By analyzing pattern displacements at different pitch scales, the system achieves accurate three-dimensional position detection, effectively adding a dimensional aspect to the detection process.
2Reliability
If multiple linear patterns with different pitches are projected, then the touch recognition accuracy is improved, but the device complexity increases
Solution Approach 1:
The patent segments the touch detection process into multiple stages: first detecting coarse position information using the first linear pattern with larger pitch, then refining the detection using the second linear pattern with smaller pitch. This segmented approach improves reliability while managing processing complexity through hierarchical analysis.
Solution Approach 2:
The patent applies partial action by using two specific linear patterns with different pitches rather than projecting all possible patterns. This selective approach provides sufficient accuracy for touch recognition while avoiding the excessive complexity that would result from using more patterns or higher resolutions throughout.
3Measurement precision
If the pitch of the linear pattern is decreased for higher resolution, then the position detection precision is improved, but the phase wrapping occurs more frequently
Solution Approach 1:
The patent segments the pitch values into two levels: a first pitch for broader spatial coverage and a second pitch for finer detail detection. By using the larger first pitch for initial detection, phase wrapping is minimized, while the smaller second pitch provides enhanced precision where needed without suffering from frequent wrapping across the entire detection area.
Solution Approach 2:
The patent resolves the pitch contradiction by introducing a multi-pitch dimensional approach. Instead of using a single pitch value, the system analyzes pattern displacements across multiple pitch dimensions, allowing it to achieve high precision through the second pitch while the first pitch prevents widespread phase wrapping issues.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The solution enables high-accuracy touch recognition by reducing phase wrapping and improving depth analysis, enhancing the precision of determining whether an object is in contact with the image display surface.
Implementation Method 1
an imaging device adapted to image an image display surface
Implementation Method 2
a detecting image display device adapted to display a detecting image on the image display surface
Data Source
AI summary
An image recognition device, an image recognition method and an image recognition unit are capable of performing touch recognition high in accuracy. The image recognition device includes a measurement point determination section adapted to determine a fingertip from an image obtained by a camera, a pattern display section adapted to make a projector display a first pattern having a first linear pattern varying in luminance with a first pitch along a direction parallel to an epipolar line passing through the fingertip, and a second linear pattern varying in luminance with a second pitch along a direction parallel to the epipolar line, and a position detection section adapted to perform touch recognition based on a variation of the first pattern from the image including the first pattern.