Gesture Recognition via Motion History Data Sampling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing gesture recognition technologies rely on physical buttons or interfaces, which can be inaccurate and prone to issues like fingerprint blurring on touch-screens, and struggle to effectively detect gestures from motion history data at a single snapshot in time.
Innovation Solution
The solution involves generating motion history data for moving objects and sampling values at adjacent points to identify patterns, such as circular shapes, allowing for enhanced gesture detection and recognition without physical interface interaction, using camera-based input to eliminate blurring effects and improve user input accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If physical buttons or touch-screen interfaces are used for gesture recognition, then user input can be obtained, but accuracy is reduced due to fingerprint blurring and other issues
Solution Approach 1:
The patent replaces physical touch interfaces with optical motion detection. Instead of relying on touch-screen contact that suffers from fingerprint blurring, the system uses a camera to capture motion history data and detect gestures through optical flow analysis, substituting mechanical/tactile interaction with optical sensing.
Solution Approach 2:
The patent introduces motion history data as an intermediary between the user's physical gesture and the system's recognition. Rather than directly interpreting touch-screen contact, the system captures sequential images, processes them into motion history data, and then detects gestures from this intermediate representation, which eliminates the fingerprint blurring problem.
2Reliability
If traditional gesture detection methods are used, then physical interface interaction is required, but the system becomes less accurate and more prone to errors
Solution Approach 1:
The patent replaces physical interface interaction with optical motion capture. The system uses a camera to detect gestures in the air space without requiring physical contact, substituting mechanical interface operations with optical sensing and motion analysis.
Solution Approach 2:
The patent creates a digital copy of the user's physical gesture through motion history data. By capturing sequential images and processing them into motion history representations, the system creates a faithful digital replica of the gesture that can be analyzed without requiring physical interface contact.
3Measurement precision
If motion history data is analyzed at multiple time points, then gesture recognition may be improved, but processing complexity and time increase
Solution Approach 1:
The patent performs preliminary processing by capturing multiple sequential images and converting them into motion history data before gesture detection. This preliminary action of creating motion history representations allows the actual gesture recognition to focus on pattern matching rather than raw image processing, reducing the time required at the critical detection stage.
Solution Approach 2:
The patent extracts only the essential motion information from sequential images by creating motion history data. Instead of processing all image data at multiple time points, the system extracts and retains only the motion-related features in the motion history representation, reducing processing complexity while maintaining gesture detection accuracy.
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
This approach enables accurate and efficient gesture recognition based on motion history data, allowing for improved user input by recognizing gestures like circular motions without the need for physical buttons, enhancing accuracy and interface usability.
Implementation Method 1
optical flow has been used to detect motion of an object by analyzing multiple images of the object taken successively in time
Data Source
AI summary
The enhanced detection of a circular engagement gesture, in which a shape is defined within motion data, and the motion data is sampled at points that are aligned with the defined shape. It is determined whether a moving object is performing a gesture correlating to the defined shape based on a pattern exhibited by the sampled motion data. An application is controlled if determining that the moving object is performing the gesture.