Virtual Touch Screen Depth Data Noise Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Projection-based user interfaces using depth cameras face challenges with noise-induced inaccuracies, particularly global and local variations in depth camera data, which affect the detection of touch events and lead to issues like touch jitter and incorrect finger identification.
Innovation Solution
A two-pass method is employed to model global and local variations in depth data, using plane-fitting for global trends and Gaussian distribution for local noise modeling, along with adaptive thresholding based on finger posture and inclination to enhance touch event detection precision and reduce jitter.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a depth camera is used to detect touch events in a projection-based user interface, then the flexibility of the input mechanism is improved, but measurement precision deteriorates due to noise-induced inaccuracies
Solution Approach 1:
The patent introduces an intermediary processing system that mediates between the depth camera's noisy output and the touch event detection. This includes multiple processing stages: initial touch candidate identification, verification against projected UI elements, temporal filtering, and spatial validation. The intermediary processing layer filters out noise-induced false positives while preserving genuine touch events, thus maintaining measurement precision without sacrificing the flexibility of the projection-based interface.
Solution Approach 2:
The system implements feedback mechanisms where detected touch events are validated against the projected user interface state and previous frame data. The verification process provides feedback to confirm or reject touch candidates, and the system continuously refines its detection thresholds based on accumulated data. This feedback loop stabilizes detection precision by compensating for depth camera noise and variations.
2Measurement precision
If adaptive thresholding based on finger posture is implemented, then detection precision is improved, but device complexity increases
Solution Approach 1:
The patent segments the finger detection process into distinct analytical stages: identifying touch candidates, determining finger posture characteristics, selecting appropriate verification thresholds, and validating against UI elements. Each segment handles a specific aspect of the detection process independently, which organizes the complexity into manageable modules. This segmentation allows the system to implement sophisticated adaptive thresholding without overwhelming processing complexity, as each module can be optimized and debugged separately.
Data Source
AI summary
Techniques for providing a virtual touch screen are described. An example of a computing device with a virtual touch screen includes a projector to project a user interface image onto a touch surface, and a depth camera to generate a depth image representing objects in a vicinity of the user interface image, and a touch mask generator. The computing device also includes a touch detection module to analyze the touch mask to detect touch events. The touch detection module is configured to identify a finger in the touch mask, identify a centroid region of the finger and compute a distance of the centroid region from a touch surface, and compare the distance to a threshold distance to identify a touch event.