Doppler Signal Segmentation for Gesture Discrimination
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for detecting and discriminating gestures, such as those used to open vehicle trunks or tailgates, often suffer from false positives and non-detections, making it difficult to accurately distinguish between voluntary and involuntary gestures.
Innovation Solution
A method involving a signal processing module that splits a basic Doppler shift signal into first and second components, applies a first discrimination algorithm to the first component for gesture detection, and a second discrimination algorithm to the second component for voluntary vs. involuntary gesture discrimination, using a recurrent computation of standard deviation to improve voluntary gesture detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a basic discrimination algorithm is used to detect gestures, then the device complexity is low, but the measurement precision of voluntary vs. involuntary gesture discrimination is insufficient
Solution Approach 1:
The basic signal is split into two components: a first component processed by a first discrimination algorithm and a second component processed by a second discrimination algorithm. This segmentation allows each algorithm to focus on specific aspects of gesture detection, improving overall precision without requiring a single overly complex algorithm.
Solution Approach 2:
The patent introduces a temporal dimension by applying recurrent computation of standard deviation over a sliding time window to the second component. This transforms the discrimination from a static signal analysis to a dynamic temporal analysis, enabling better distinction between voluntary and involuntary gestures without significantly increasing computational complexity.
2Measurement precision
If a complex discrimination algorithm is used to improve gesture discrimination, then the measurement precision improves, but the loss of time increases
Solution Approach 1:
By dividing the signal processing into two components with two specialized algorithms, the computation is distributed and optimized. The first algorithm handles basic gesture detection while the second focuses on voluntary/involuntary discrimination, reducing the computational burden compared to a single comprehensive complex algorithm.
Solution Approach 2:
The second discrimination algorithm applies recurrent computation of standard deviation only to the second component of the signal over a sliding time window, rather than processing the entire signal. This partial action approach achieves improved precision while limiting the time loss to only the necessary portion of signal analysis.
3Reliability
If traditional discrimination methods are used, then the device complexity is low, but false positives and non-detections occur frequently
Solution Approach 1:
The signal is segmented into two components, each processed by a dedicated discrimination algorithm. This segmentation allows the system to cross-validate gestures through multiple analysis paths, reducing false positives and non-detections while maintaining reasonable processing complexity.
Solution Approach 2:
The recurrent computation of standard deviation in the second discrimination algorithm provides continuous feedback over the sliding time window, allowing the system to adaptively distinguish between voluntary and involuntary gestures. This feedback mechanism significantly improves reliability by confirming gestures through temporal patterns rather than relying on a single measurement.
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 significantly improves the discrimination of voluntary and involuntary gestures, reducing false positives and non-detections, while maintaining a fast response time and avoiding the need for complex algorithms like neural networks.
Implementation Method 1
determining a frequency shift, called Doppler shift, between the incident radiofrequency signal and the return radiofrequency signal, the Doppler shift being a function of a movement of elements located in the detection zone
Data Source
AI summary
A method for discriminating gestures of a user, implemented within a motor vehicle for controlling the unlocking of an opening when a predetermined voluntary gesture is detected, comprising:obtaining a basic signal, representing an evolution of a determined Doppler shift following the transmission of an incident radiofrequency signal and the reception of a reception echo;splitting the basic signal into a first component (Cp1) at the output of a low-pass filter, and, in addition, a second component (Cp2);applying a first algorithm (Algo1) to the first component (Cp1) in order to obtain a first discrimination result;applying a second algorithm (Algo2) to the second component (Cp1) in order to obtain a second discrimination result;the second algorithm comprising a recurrent computation of standard deviation (σ(k)) carried out based on a sequence of values of the second component and the second discrimination result indicating a voluntary gesture when the computation of standard deviation is below a predetermined threshold.