Touch Gesture Recognition Using Depth Sensor Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current touchless control technologies for user interfaces face challenges in accurately recognizing touch gestures without physical contact, particularly in distinguishing between background and touch objects using proximity sensors, temperature, and image capture methods.
Innovation Solution
A method involving a depth sensor to capture depth images, learn background areas, and detect touch inputs by tracking changes in touch objects within defined detection areas, allowing for robust gesture recognition even with movement of the background.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If proximity sensors, temperature sensors, and image capture methods are used for touchless control, then user interaction convenience is improved, but measurement precision and reliability of gesture recognition deteriorate due to difficulty in distinguishing background from touch objects
Solution Approach 1:
The patent transitions from 2D image capture to 3D depth image acquisition using a depth sensor. This dimensional change enables the system to distinguish touch objects from background based on depth information, solving the precision problem while maintaining touchless operation convenience.
Solution Approach 2:
The patent changes the detection parameter from 2D spatial coordinates to 3D depth coordinates. By acquiring depth images and analyzing depth values, the system can accurately identify touch objects regardless of background complexity, thereby improving measurement precision without sacrificing ease of operation.
2Area of stationary object
If the entire background area is monitored for touch inputs, then detection coverage is improved, but device complexity and processing load increase
Solution Approach 1:
The patent segments the background area into multiple regions and selectively monitors only those regions where touch objects are likely to appear. This segmentation reduces processing complexity while maintaining adequate detection coverage by focusing computational resources on relevant areas.
Solution Approach 2:
The patent applies different processing qualities to different regions of the background area. High-precision depth analysis is applied only to regions identified as potential touch zones, while other regions receive minimal or no processing. This local quality approach reduces overall device complexity while preserving detection effectiveness.
3Measurement precision
If depth sensors are used to capture depth images for accurate touch detection, then measurement precision is improved, but use of energy and device complexity increase
Solution Approach 1:
The patent implements periodic depth image acquisition at optimized intervals rather than continuous capture. This periodic action maintains measurement precision for gesture recognition while significantly reducing energy consumption compared to continuous depth sensing.
Solution Approach 2:
The system uses the depth sensor's inherent capabilities to automatically distinguish touch objects from background without requiring additional processing power or energy-intensive algorithms. The depth information itself provides the discrimination needed, making the system self-sufficient and energy-efficient.
Data Source
AI summary
A method and an apparatus for recognizing a touch gesture are disclosed, in which the apparatus may obtain a depth image in which a touch object and a background area are captured, detect a touch input applied by the touch object to the background area in a touch detection area, and recognize a touch gesture associated with the touch input by tracking a change in the touch input.