Gesture Sensing Signal Normalization for Cross-Condition Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing gesture sensing systems face challenges in accurately recognizing gestures due to variations in signal intensity and position, especially when training data is collected under different conditions, leading to reduced recognition accuracy.
Innovation Solution
A gesture sensing system that includes a preprocessing unit to correct signal intensity and position using training data, and a classification unit utilizing a convolution neural network and long short-term memory to classify gestures based on uniformized input information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If training data is collected under different conditions, then the system can handle more varied scenarios, but recognition accuracy deteriorates due to signal intensity and position variations
Solution Approach 1:
The patent applies parameter changes by normalizing signal intensity values to a uniform range (e.g., 0-1) and standardizing position coordinates to consistent reference frames. This transformation allows the system to handle varied scanning conditions while maintaining recognition accuracy, as the normalized parameters eliminate the adverse effects of different signal strengths and positional variations across training and verification phases.
2Device complexity
If signal intensity and position are not uniformized, then the system structure remains simple, but recognition accuracy deteriorates when training and verification conditions differ
Solution Approach 1:
The patent implements preliminary action by performing normalization and standardization of signal parameters during the data preprocessing stage, before the actual gesture recognition process. This advance preparation ensures that both training and verification data are in a uniform format, eliminating the need for complex adaptive mechanisms during runtime while maintaining high recognition accuracy across different conditions.
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
Enhances gesture recognition accuracy by normalizing signal intensity and position, allowing high recognition rates even when training and verification conditions differ.
Implementation Method 1
Millimeter waves have a high-band frequency of 30 gigahertz (GHz) to 300 GHz. The millimeter waves have strong straight-line properties and are not affected by weather such as rain or fog
Implementation Method 2
since an antenna that transmits and receives the millimeter waves may be miniaturized, the millimeter waves may also be used for monitoring traffic and crime prevention sensors for surveillance
Data Source
AI summary
A gesture sensing system includes: a sensing unit, which senses a gesture of an object and generates and outputs input information including a plurality of sensing signals; a preprocessing unit, which detects a peak signal among the plurality of sensing signals and converts the input information into correction input information using information associated with the peak signal; and a classification unit, which is trained using training data and classifies the gesture based on the correction input information. The information associated with the peak signal includes information related to a position of the peak signal and an intensity of the peak signal, and the position of the peak signal and the intensity of the peak signal are uniformized to a uniform range and then provided to the classification unit.