Millimeter Wave Gesture Recognition via Doppler Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing gesture recognition methods, such as sound wave and image analysis, suffer from low accuracy in noisy environments and dim light conditions, respectively.
Innovation Solution
A method utilizing a millimeter wave apparatus that processes reflected millimeter waves using two types of time arrays and Doppler estimation to extract signal characteristic values, enabling accurate gesture recognition by identifying motion characteristics and controlling applications accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sound wave gesture recognition is used, then gesture recognition function is provided, but recognition accuracy greatly reduces in noisy environment
Solution Approach 1:
The patent introduces millimeter wave radar as an intermediary detection device that indirectly measures gesture motions through electromagnetic wave reflection, avoiding direct acoustic interference. The radar system transmits millimeter waves that reflect off the user's hand movements, converting acoustic gesture recognition into electromagnetic wave-based detection, thereby eliminating noise environment interference while maintaining gesture recognition functionality.
Solution Approach 2:
The patent replaces the acoustic mechanical system (sound wave propagation and detection) with an electromagnetic wave system (millimeter wave transmission and reception). By substituting the detection medium from acoustic waves to electromagnetic waves, the system achieves immunity to acoustic noise while preserving the ability to detect gesture motions through reflected wave analysis.
2Measurement precision
If image analysis of visible light camera is used, then gesture recognition function is provided, but recognition accuracy reduces in dim light or zero light environment
Solution Approach 1:
The patent replaces the optical imaging system (visible light camera requiring photons) with an active electromagnetic wave emission system (millimeter wave radar). The radar actively transmits electromagnetic waves and detects reflections, eliminating dependence on ambient light conditions. This substitution allows gesture recognition to function accurately in complete darkness by using self-generated electromagnetic illumination rather than passive light detection.
Solution Approach 2:
The patent implements preliminary action by having the millimeter wave radar proactively transmit electromagnetic waves before gesture detection is needed. The system continuously emits millimeter waves and maintains ready-to-detect reflected signals from hand movements, ensuring that gesture recognition can immediately occur regardless of ambient lighting conditions, unlike passive camera systems that require sufficient light to be present.
3Measurement precision
If millimeter wave apparatus with two types of time arrays and Doppler estimation is used, then gesture recognition accuracy improves, but device complexity increases
Solution Approach 1:
The patent applies segmentation by dividing the signal processing into two distinct time array dimensions: fast time array for capturing immediate signal characteristics and slow time array for tracking temporal evolution. This segmentation of processing timelines allows the complex Doppler estimation to be broken into manageable computational stages, improving accuracy while organizing complexity into structured, separable processing modules.
Solution Approach 2:
The patent introduces another dimension by implementing two types of time arrays that process signals in different temporal dimensions. The fast time array operates on short-time signal variations while the slow time array captures long-term gesture evolution, creating a multi-dimensional signal space. This dimensional expansion enables more accurate gesture recognition by analyzing signals from multiple temporal perspectives simultaneously, transforming complex 1D signal processing into 2D temporal analysis.
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
Improves gesture recognition accuracy by effectively processing millimeter waves to determine subtle gesture motions, enhancing user interaction in various scenarios, including contactless photography and device control.
Implementation Method 1
the Doppler estimation comprises a Doppler effect and a principle of frequency modulation continuous wave
Implementation Method 2
the Doppler estimation comprises a Doppler effect and a principle of frequency modulation continuous wave
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method for gesture recognition, a terminal, and a storage medium are provided by the embodiments of the present application. The method may include: receiving, through the millimeter wave apparatus, a first millimeter wave, where the first millimeter wave is a reflected wave formed after a second millimeter wave transmitted by the millimeter wave apparatus is modulated via a gesture motion; processing the first millimeter wave based on two types of time arrays and Doppler estimation to obtain at least one set of signal characteristic values corresponding to the first millimeter wave, where each set of signal characteristic values of the at least one set of signal characteristic values correspond to one frame of signal in the first millimeter wave; identifying the at least one set of signal characteristic values using a correspondence library of standard characteristic values and control instructions, and obtaining a first control instruction corresponding to the gesture motion; and controlling a first application to implement a corresponding function using the first control instruction.