# US 2026/0073735 A1 · Liveness detection method and apparatus, electronic device, and storage medium

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0073735 A1
- Document ID: US20260073735A1
- Status: Published application
- Kind: A1
- Application number: 19/391,784
- Filed: 2025-11-17
- Published: 2026-03-12
- Earliest claimed: 2021-06-15
- Assignees: Tencent Technology (Shenzhen) Company Limited
- Applicants: Tencent Technology (Shenzhen) Company Limited
- Inventors: Jia MENG; Dongheng ZHANG; Jian ZHANG; Mingwei BI; Xinzhe DENG; Shouhong DING; Jilin LI
- Web page: https://patentgrep.com/patent/US20260073735A1

## CPC

- G01S 15/88: Sonar systems specially adapted for specific applications (seismic or acoustic prospecting or detecting G01V1/00)
- G06V 40/45: {Detection of the body part being alive}
- G01S 7/539: using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S 15/58: Velocity or trajectory determination systems; Sense-of-movement determination systems {(velocity measurement in imaging systems G01S15/8979)}
- G01S 15/86: Combinations of sonar systems with lidar systems; Combinations of sonar systems with systems not using wave reflection
- G06F 18/253: {of extracted features}
- G06T 7/246: using feature-based methods, e.g. the tracking of corners or segments
- G06V 10/431: {Frequency domain transformation; Autocorrelation}
- G06V 10/776: Validation; Performance evaluation
- G06V 10/806: {of extracted features}
- G06V 10/82: using neural networks
- G06V 20/46: {Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames}
- G06V 20/95: {Pattern authentication; Markers therefor; Forgery detection}
- G06V 40/171: {Local features and components; Facial parts (eye characteristics G06V40/18); Occluding parts, e.g. glasses; Geometrical relationships}
- G06V 40/40: Spoof detection, e.g. liveness detection
- G06T 2207/10016: Video; Image sequence
- G06T 2207/30201: Face
- G06T 2207/30241: Trajectory
- G06V 40/172: {Classification, e.g. identification}
- G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A liveness detection method includes: obtaining a reflected audio signal and video data of a object in response to receiving a liveness detection request; performing signal processing and time-frequency analysis on the reflected audio signal to obtain time-frequency information of a processed audio signal, and extracting motion trajectory information of the object from the video data; respectively extract features from the time-frequency information and the motion trajectory information to obtain an audio feature and a motion feature of the object; calculating first global attention information of the object according to the audio feature, and calculating second global attention information of the object according to the motion feature; and fusing the first global attention information with the second global attention information to obtain fused global information, and determining a liveness detection result of the object based on the fused global information.

## Claims

### Claim 1

A liveness detection method, performed by an electronic device, the method comprising:
obtaining a reflected audio signal and video data of an object to be detected in response to receiving a liveness detection request;
extracting time-frequency information from the reflected audio signal;
extracting motion trajectory information of the object from the video data;
extracting features respectively from the time-frequency information and the motion trajectory information to obtain an audio feature and a motion feature of the object;
calculating, according to the audio feature, first global attention information of the object indicating a global correlation of the audio feature, and calculating, according to the motion feature, second global attention information of the object indicating a global correlation of the motion feature; and
determining a liveness detection result of the object by fusing the first global attention information with the second global attention information.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the obtaining a reflected audio signal and video data of an object comprises:
transmitting an initial audio signal to the object, and receiving the reflected audio signal reflected by the object; and
acquiring the video data of the object.

### Claim 3 (depends on 2)

The method according to claim 2, further comprising:
superimposing target audio signals of a plurality of tones to obtain a superimposed audio signal; and
randomizing a carrier frequency of the superimposed audio signal, to generate the initial audio signal.

### Claim 4 (depends on 1)

The method according to claim 1, wherein the extracting time-frequency information from the reflected audio signal comprises:
performing signal processing on the reflected audio signal to obtain a processed audio signal; and
performing time-frequency analysis on the processed audio signal to obtain the time-frequency information of the processed audio signal.

### Claim 5 (depends on 4)

The method according to claim 4, wherein the performing signal processing on the reflected audio signal to obtain a processed audio signal, and performing time-frequency analysis on the processed audio signal to obtain the time-frequency information of the processed audio signal comprises:
performing space-domain enhancement processing on the reflected audio signal to obtain a space-domain enhancement signal; and
performing signal extraction processing on the space-domain enhancement signal to obtain the processed audio signal, and performing the time-frequency analysis on the processed audio signal to obtain the time-frequency information of the processed audio signal.

### Claim 6 (depends on 5)

The method according to claim 5, wherein the performing space-domain enhancement processing on the reflected audio signal to obtain a space-domain enhancement signal comprises:
performing quadrature demodulation on the reflected audio signal to obtain an analytic signal; and
performing the space-domain enhancement processing on the analytic signal by using a preset space-domain matrix to obtain the space-domain enhancement signal.

### Claim 7 (depends on 5)

The method according to claim 5, wherein the performing signal extraction processing on the space-domain enhancement signal to obtain the processed audio signal, and performing the time-frequency analysis on the processed audio signal to obtain the time-frequency information of the processed audio signal comprises:
differentiating the space-domain enhancement signal based on a time axis of the space-domain enhancement signal, to obtain a differentiated audio signal;
determining propagation time of the object in a medium based on amplitude of the differentiated audio signal;
extracting a target audio signal from the space-domain enhancement signal according to the propagation time, and performing high-pass filtering on the target audio signal to obtain the processed audio signal; and
performing short time Fourier transform on the processed audio signal to obtain the time-frequency information of the processed audio signal.

### Claim 8 (depends on 1)

The method according to claim 1, wherein the video data comprises at least one image frame; and the extracting motion trajectory information of the object from the video data comprises:
performing key point detection on the at least one image frame in the video data to obtain key point information corresponding to the at least one image frame; and
determining the motion trajectory information of the object based on the key point information of the at least one image frame.

### Claim 9 (depends on 4)

The method according to claim 4, wherein the processed audio signal comprises at least one audio frame signal; the audio feature comprises at least one audio frame feature; the video data comprises at least one image frame; the motion feature comprises at least one image frame feature; and the calculating first global attention information of the object according to the audio feature, and calculating second global attention information of the object according to the motion feature comprises:
interpolating a first global feature to the audio feature, and using the first global feature as an audio frame feature of the processed audio signal;
calculating attention information of the at least one audio frame feature in the audio feature to the first global feature by using a first transformer encoder of a trained detection model, to obtain the first global attention information;
interpolating a second global feature to the motion feature, and using the second global feature as an image frame feature of the video data; and
calculating attention information of the at least one image frame feature in the motion feature to the second global feature by using a second transformer encoder of the trained detection model, to obtain the second global attention information.

### Claim 10 (depends on 9)

The method according to claim 9, wherein the calculating attention information of the at least one audio frame feature in the audio feature to the first global feature by using a first transformer encoder of a trained detection model to obtain the first global attention information comprises: for an audio frame feature of the at least one audio frame feature:
generating, according to the audio feature, a first query vector, a first key vector and a first value vector corresponding to the audio frame feature;
performing point-by-point integration on the first query vector of the audio frame feature and a first key vector of the first global feature to obtain a self-attention vector set of the first global feature; and
multiplying the self-attention vector set of the first global feature with a first value vector corresponding to the first global feature, and performing weighted summation on results obtained by the multiplication to obtain the first global attention information.

### Claim 10 (depends on 1)

The method according to claim 1, further comprising:
calculating first attention feature information of the object according to the audio feature, and calculating second attention feature information of the object according to the motion feature, the first attention feature information indicating a correlation of the audio feature, and the second attention information indicating a correlation of the motion feature; and
performing consistency verification on the reflected audio signal and the video data of the object based on the first attention feature information and the second attention feature information, to obtain a verification result; and determining, according to the verification result, whether the liveness detection result is correct.

### Claim 12 (depends on 11)

The method according to claim 11, wherein the extracting time-frequency information from the reflected audio signal comprises: performing signal processing on the reflected audio signal to obtain a processed audio signal, and performing time-frequency analysis on the processed audio signal to obtain the time-frequency information of the processed audio signal; the processed audio signal comprises at least one audio frame signal; the audio feature comprises at least one audio frame feature; the video data comprises at least one image frame; the motion feature comprises at least one image frame feature; and the calculating first attention feature information of the object according to the audio feature, and calculating second attention feature information of the object according to the motion feature comprises:
calculating attention information of a correlation between the at least one audio frame feature in the audio feature by using a first transformer encoder of a trained detection model to obtain the first attention feature information; and
calculating attention information of a correlation between the at least one image frame feature in the motion feature by using a second transformer encoder of the trained detection model to obtain the second attention feature information.

### Claim 13 (depends on 11)

The method according to claim 11, wherein the performing consistency verification on the reflected audio signal and the video data of the object based on the first attention feature information and the second attention feature information, and determining, according to a verification result, whether the liveness detection result is correct comprises:
calculating mutual attention information between the first attention feature information and the second attention feature information by using a transformer decoder of the trained detection model; and
performing consistency verification on the mutual attention information by using a verification network of the trained detection model, to obtain a verification result; and
determining, when the verification result succeeds, that the liveness detection result is correct.

### Claim 14

A liveness detection apparatus, comprising: at least one memory storing a computer program, and at least one processor coupled to the memory, the at least one processor being configured to execute the computer program and perform:
obtaining a reflected audio signal and video data of an object to be detected in response to receiving a liveness detection request;
extracting time-frequency information from the reflected audio signal;
extracting motion trajectory information of the object from the video data;
extracting features respectively from the time-frequency information and the motion trajectory information to obtain an audio feature and a motion feature of the object;
calculating, according to the audio feature, first global attention information of the object indicating a global correlation of the audio feature, and calculating, according to the motion feature, second global attention information of the object indicating a global correlation of the motion feature; and
determining a liveness detection result of the object by fusing the first global attention information with the second global attention information.

### Claim 15 (depends on 14)

The apparatus according to claim 14, wherein the obtaining a reflected audio signal and video data of an object comprises:
transmitting an initial audio signal to the object, and receiving the reflected audio signal reflected by the object; and
acquiring the video data of the object.

### Claim 16 (depends on 15)

The apparatus according to claim 15, wherein the at least one processor is further configured to perform:
superimposing target audio signals of a plurality of tones to obtain a superimposed audio signal; and
randomizing a carrier frequency of the superimposed audio signal, to generate the initial audio signal.

### Claim 17 (depends on 14)

The apparatus according to claim 14, wherein the performing signal processing on the reflected audio signal to obtain a processed audio signal, and performing time-frequency analysis on the processed audio signal to obtain time-frequency information of the processed audio signal comprises:
performing space-domain enhancement processing on the reflected audio signal to obtain a space-domain enhancement signal; and
performing signal extraction processing on the space-domain enhancement signal to obtain the processed audio signal, and performing the time-frequency analysis on the processed audio signal to obtain the time-frequency information of the processed audio signal.

### Claim 18 (depends on 17)

The apparatus according to claim 17, wherein the performing space-domain enhancement processing on the reflected audio signal to obtain a space-domain enhancement signal comprises:
performing quadrature demodulation on the reflected audio signal to obtain an analytic signal; and
performing the space-domain enhancement processing on the analytic signal by using a preset space-domain matrix to obtain the space-domain enhancement signal.

### Claim 19 (depends on 17)

The apparatus according to claim 17, wherein the performing signal extraction processing on the space-domain enhancement signal to obtain the processed audio signal, and performing the time-frequency analysis on the processed audio signal to obtain the time-frequency information of the processed audio signal comprises:
differentiating the space-domain enhancement signal based on a time axis of the space-domain enhancement signal, to obtain a differentiated audio signal;
determining propagation time of the object in a medium based on amplitude of the differentiated audio signal;
extracting a target audio signal from the space-domain enhancement signal according to the propagation time, and performing high-pass filtering on the target audio signal to obtain the processed audio signal; and
performing short time Fourier transform on the processed audio signal to obtain the time-frequency information of the processed audio signal.

### Claim 20

A non-transitory computer-readable storage medium, storing a plurality of instructions, the instructions being loaded by at least one processor and causing the at least one processor to perform:
obtaining a reflected audio signal and video data of an object to be detected in response to receiving a liveness detection request;
extracting time-frequency information from the reflected audio signal;
extracting motion trajectory information of the object from the video data;
extracting features respectively from the time-frequency information and the motion trajectory information to obtain an audio feature and a motion feature of the object;
calculating, according to the audio feature, first global attention information of the object indicating a global correlation of the audio feature, and calculating, according to the motion feature, second global attention information of the object indicating a global correlation of the motion feature; and
determining a liveness detection result of the object by fusing the first global attention information with the second global attention information.
