CN111427031B - Identity and gesture recognition method based on radar signals - Google Patents
Identity and gesture recognition method based on radar signals Download PDFInfo
- Publication number
- CN111427031B CN111427031B CN202010274512.2A CN202010274512A CN111427031B CN 111427031 B CN111427031 B CN 111427031B CN 202010274512 A CN202010274512 A CN 202010274512A CN 111427031 B CN111427031 B CN 111427031B
- Authority
- CN
- China
- Prior art keywords
- gesture
- radar
- identity
- signal
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- 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
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
-
- G—PHYSICS
- G01—MEASURING; TESTING
- 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
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
- G01S13/06—Systems determining position data of a target
- G01S13/42—Simultaneous measurement of distance and other co-ordinates
-
- G—PHYSICS
- G01—MEASURING; TESTING
- 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
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
- G01S13/50—Systems of measurement based on relative movement of target
-
- G—PHYSICS
- G01—MEASURING; TESTING
- 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
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
- G01S13/50—Systems of measurement based on relative movement of target
- G01S13/58—Velocity or trajectory determination systems; Sense-of-movement determination systems
- G01S13/583—Velocity or trajectory determination systems; Sense-of-movement determination systems using transmission of continuous unmodulated waves, amplitude-, frequency-, or phase-modulated waves and based upon the Doppler effect resulting from movement of targets
-
- G—PHYSICS
- G01—MEASURING; TESTING
- 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
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/35—Details of non-pulse systems
- G01S7/352—Receivers
- G01S7/354—Extracting wanted echo-signals
-
- G—PHYSICS
- G01—MEASURING; TESTING
- 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
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/417—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section involving the use of neural networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72448—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions
- H04M1/72454—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions according to context-related or environment-related conditions
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72448—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions
- H04M1/72463—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions to restrict the functionality of the device
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Signal Processing (AREA)
- Environmental & Geological Engineering (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses an identity and gesture recognition method based on radar signals, which comprises the steps of reading radar echo signals received by a radar sensor and obtained by various gestures of a tester through reflection; mixing the radar echo signal with a radar transmitting signal; after filtering and centralizing the signals after frequency mixing, respectively training to obtain a neural network capable of carrying out identity verification and a neural network capable of carrying out gesture recognition; in the real-time detection process, firstly, the identity of the user is verified, if the identity verification is passed, the gesture of the user is effective, the gesture of the user is verified, and corresponding operation is performed according to the corresponding relation between the gesture of the user and the operation. According to the invention, the gesture identification and the identity verification can be carried out at the same time through only one gesture operation, whether the operation corresponding to the gesture is carried out can be judged according to whether the gesture belongs to the corresponding user, and the convenience and the safety of the gesture identification are improved.
Description
Technical Field
The invention relates to the field of identity recognition, in particular to an identity and gesture recognition method based on radar signals.
Background
Gesture recognition refers to the entire process of tracking human gestures, recognizing their representations, and translating into semantically meaningful commands. As an important component of human-computer interaction, research and development of the human-computer interaction influence the naturalness and flexibility of the human-computer interaction. With the development of the technology in the prior art, the application of gesture recognition on various devices is increasing.
Traditional gesture recognition usually adopts the camera to gather gesture information, has a certain waste in the energy consumption, and the information quantity that the gesture image contains is huge also often has privacy aspects such as information leakage problem easily. In addition, in the gesture recognition adopted at present, before the device is not unlocked, whether the device is unlocked is often controlled by an additional identity verification method, and the gesture recognition can be continuously performed after the device is successfully unlocked, which is relatively complicated. And when the equipment is unlocked, any person can produce the same effect by doing the same gesture on the equipment, and the situation has certain risk.
Therefore, how to perform gesture recognition and identity verification on equipment at the same time is a problem which needs to be solved urgently at present, and the convenience and safety of gesture recognition are improved.
Disclosure of Invention
In view of the above, the present invention provides an identity and gesture recognition method based on radar signals, which can solve the technical problems that an additional unlocking step is required in gesture recognition and any person performing the same gesture on a device after the device is unlocked can generate the same effect.
In order to solve the technical problems, the invention provides the following technical scheme: an identity and gesture recognition method based on radar signals comprises the following steps:
step 1, reading radar echo signals received by a radar sensor and obtained by reflection of various gestures of a tester;
step 2, mixing the radar echo signal with a radar transmitting signal;
step 3, filtering the mixed signal by adopting a high-pass filter;
step 4, performing centralized operation on the filtered signal data;
step 5, designing a neural network model suitable for radar signal characteristics, and training the model by using the signal preprocessed in the step 4 and an identity information label of a tester to obtain a neural network A capable of performing identity verification;
step 6, obtaining distance, speed and angle information according to the signals preprocessed in the step 4 and radar sensor parameters, and calculating to obtain a three-dimensional coordinate and a Doppler value of the moving target;
step 7, dividing the space above the radar by adopting a space grid method; mapping the space region into a three-dimensional matrix, and accumulating the Doppler value of the three-dimensional coordinate and the Doppler value obtained in the step (6) in a matrix unit corresponding to the grid according to the grid position in the space to which the three-dimensional coordinate and the Doppler value belong as the size of the matrix unit element; sending the matrix and the gesture information label into a designed neural network to train to obtain a neural network B capable of performing gesture recognition;
step 8, performing constant false alarm detection on the radar echo signals detected in real time to judge whether gesture recognition is performed by people, and performing step 9 if the gesture recognition is performed by people; if not, continuing to wait for detection;
step 9, preprocessing the detected radar echo signals from the step 2 to the step 4; the processed signals are sent to the neural network A trained in the step 5 to extract features for analysis; verifying the identity of the user through identity information contained in the characteristics, if the identity information passes the verification, the gesture of the user is effective, and performing the step 10, otherwise, continuing to wait for detection;
and step 10, after the data preprocessed in the steps 2 to 4 are processed in the steps 6 and 7, inputting the data into the neural network B to judge the gesture of the user, and performing corresponding operation according to the corresponding relation between the gesture of the user and the operation.
Further, the radar sensor adopts FMCW millimeter wave radar with the frequency interval of 57.4GHz to 62.6 GHz.
Further, in step 2, if the radar sensor has a plurality of receiving channels, the obtained corresponding waveforms are averaged and then filtered.
Further, in the step 3, an eighth-order butterworth high-pass filter with a cut-off frequency of 31250Hz is adopted to filter the mixed signal, so as to filter out large direct current and low-frequency noise while keeping effective information.
Further, in step 6, according to the signal and the radar sensor parameter preprocessed in step 4, the distance information R is obtained through fast time dimension FFT:
and then obtaining speed information v through a slow time dimension FFT:
wherein f ismovingBeatAnd fstaticBeatFrequency of beat signal, f, in moving and stationary states of the object, respectivelydIs the Doppler frequency, fcFor sweep bandwidth, R is the target distance, C is the speed of light, tcF is the central frequency of a Chirp signal, and v is the target speed;
obtaining angle information θ from a plurality of transmitting and receiving antennas of the radar sensor:
where Δ d is a distance difference between any two receiving antennas and the target, Δ Φ is a phase difference corresponding to signals received by the two antennas, L is a distance corresponding to the two antennas, and λ is a wavelength.
Further, in the step 7, a region with a spatial size of Xcm × Ycm × Zcm is mapped to a three-dimensional matrix with a size of (X × k1) × (Y × k2) × (Z × k3), where X, Y, and Z are length, width, and height corresponding to the space, and k1, k2, and k3 are mapping coefficients of the length, width, and height of the actual space and the three-dimensional matrix.
Further, the effective user establishes a corresponding relationship between a predetermined gesture and an operation during training, when a specific gesture of the effective user is recognized as a certain predetermined gesture in step 10, the operation corresponding to the predetermined gesture is executed, and if the recognized gesture is not in the predetermined gesture, the operation is not generated.
Furthermore, the method is applied to a mobile phone, a radar sensor is arranged in the mobile phone, the identity information and the gesture information of an equipment owner are stored in advance, and part of the gesture information corresponds to an App operation instruction; on the premise of locking the screen of the mobile phone, if the person performing the gesture authentication is the owner of the mobile phone, unlocking the mobile phone, judging gesture information, opening an App corresponding to the gesture, and if the gesture does not correspond to the App, not performing any operation; if the gesture does not belong to the equipment owner, the mobile phone maintains the screen locking; and under the condition that the mobile phone is unlocked, if the gesture does not belong to the equipment owner or the gesture made by the equipment owner is not in the specified gesture, the corresponding operation is not carried out.
The invention has the following beneficial effects: according to the identity and gesture recognition method based on the radar signals, the radar is used for signal acquisition, energy consumption is effectively reduced, and privacy of users is guaranteed. On the premise of only performing one gesture operation, whether the operation corresponding to the gesture is performed or not can be judged according to whether the gesture belongs to the corresponding user or not. The method greatly improves the convenience and safety of gesture recognition.
Drawings
FIG. 1 is a flow diagram of an offline training process for identity and gesture recognition based on radar signals;
FIG. 2 is a use of a millimeter wave radar sensor;
FIG. 3 is a flow chart of an online identification process for identification and gesture recognition based on radar signals.
Detailed Description
The following detailed description of embodiments of the invention refers to the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating embodiments of the invention, are given by way of illustration and explanation only, not limitation.
Without loss of generality, the embodiment provides an identity and gesture recognition method based on radar signals. An FMCW millimeter wave radar with the frequency interval of 57.4GHz to 62.6GHz is adopted, the frame rate of a transmitted signal is 60 frames/second, and each frame of data is divided into 8 Chirp signals. The radar signal based identity and gesture recognition method is performed on 21 individuals in total.
The off-line training partial flow is shown in fig. 1 and mainly comprises the following steps:
step 1, placing the radar sensor on a plane, making N gestures and interference gestures (i.e. gestures other than the N gestures) specified by a tester above the radar sensor according to the mode of fig. 2, reading radar echo signals received by the radar sensor and reflected by the gestures, and recording the radar echo signals as S1;
Step 2, radar echo signal S1With radar transmitted signal S2Mixing the frequency, obtaining the signal after mixing Wherein ω is1And ω2Respectively representing the frequencies of the transmitted signal and the reflected signal via the palm,andthe phases of the two signals are shown, respectively, and the mixed signal is denoted as D. The millimeter wave radar adopted in the example is provided with a plurality of receiving channels, a plurality of corresponding waveforms can be obtained, an averaging measure is taken for the waveforms, and the obtained signals are recorded as D';
and 3, filtering the signal D' by adopting an eighth-order Butterworth high-pass filter with the cut-off frequency of 31250Hz to obtain signal data M, wherein the filter is selected mainly to filter out larger direct current and low-frequency noise while retaining effective information.
And 4, performing centralization operation on the filtered signal data, wherein M' is M-mu, and averaging the dataWhere n is the size of the data volume.
Step 5, designing a neural network model suitable for radar signal characteristics (an input layer of the neural network needs to be adapted to parameters of data collection preset by a radar), and putting the preprocessed signal M' and an identity information label of a tester into the neural network model for training to obtain a neural network A capable of performing identity verification;
step 6, obtaining distance information R through fast time dimension FFT according to M' and radar sensor parameters:
and then obtaining speed information v through a slow time dimension FFT:
wherein f ismovingBeatAnd fstaticBeatFrequency of beat signal, f, in moving and stationary states of the object, respectivelyd
Is the Doppler frequency, fcFor sweep bandwidth, R is the target distance, C is the speed of light, tcF is the center frequency of the Chirp signal, and v is the target speed.
Obtaining angle information θ from a plurality of transmitting and receiving antennas of the radar sensor:
where Δ d is a distance difference between any two receiving antennas and the target, Δ Φ is a phase difference corresponding to signals received by the two antennas, L is a distance corresponding to the two antennas, and λ is a wavelength. Finally, according to the distance information R, the speed information v and the angle information theta, three-dimensional coordinates (x, y, z) and Doppler values of the moving target are deduced;
and 7, dividing the space above the radar by adopting a space grid method.
Regions of space size Xcm Ycm × Zcm were mapped into a three-dimensional matrix of size (X × k1) (Y × k2) (Z × k 3). Wherein, X, Y and Z are the length, width and height corresponding to the space, and k1, k2 and k3 are the mapping coefficients of the length, width and height of the actual space and the three-dimensional matrix. Specifically, a 20cm by 10cm real space can be selected and mapped to a 20cm by 10 three-dimensional matrix (i.e., 1cm by 20cm by 10 cm)3The spatial grid corresponds to one element cell in the matrix).
And (4) accumulating the Doppler values of the data (three-dimensional coordinates and corresponding Doppler values) obtained in the step (6) in the corresponding matrix unit of the grid as the size of the matrix unit element according to the grid position in the space to which the data belongs. Correspondingly sending the matrix S and the gesture information label into a designed neural network to obtain a neural network B capable of performing gesture recognition;
the flow of the online identification part is shown in fig. 3, and mainly comprises the following steps:
step 8, performing constant false alarm detection on the detected radar echo signals to judge whether gesture recognition is performed by people, and performing step 9 if the gesture recognition is performed by people; if not, continuing to wait for detection;
step 9, preprocessing the detected radar echo signals from the step 2 to the step 4; the processed signals are sent to the neural network A trained in the step 5 to extract features for analysis; verifying the identity of the user through identity information contained in the characteristics, if the identity verification is passed (the classification result of the information by the neural network is the category of the valid user identified by the user), the gesture of the user is valid, and performing the step 10, otherwise, continuing to wait for detection;
and step 10, processing the data after the preprocessing from the step 2 to the step 4 in the steps 6 and 7, sending the data into the neural network B, judging which gesture the user makes, and performing subsequent corresponding operation, wherein if the gesture made is not in the N predefined gestures, no operation is generated.
An application scenario for starting App at a mobile phone terminal is given below, but not limited to this:
a radar sensor is arranged in the mobile phone, the identity information and the gesture information of an equipment owner are stored in advance, and part of the gesture information corresponds to an App operation instruction; on the premise of locking the screen of the mobile phone, if the person performing the gesture authentication is the owner of the mobile phone, unlocking the mobile phone, judging gesture information, opening an App corresponding to the gesture, and if the person does not have the corresponding gesture, not performing any operation; if the gesture does not belong to the equipment owner, the mobile phone keeps locking the screen. And under the condition that the mobile phone is unlocked, if the gesture does not belong to the equipment owner or the gesture made by the equipment owner is not in the specified gesture, the corresponding operation is not carried out. The identity authentication and the gesture recognition can be simultaneously performed through one gesture. Thus, the whole identification and gesture recognition process based on the radar signals is completed. Through a plurality of experiments, the invention can achieve the recognition accuracy rate of about 90%.
In summary, the identity and gesture recognition method based on radar signals provided by the invention collects signals through radar, effectively reduces energy consumption and ensures privacy of users. After a series of effective preprocessing, the neural network is adopted to extract features, whether the operation corresponding to the gesture is carried out or not can be judged according to whether the gesture belongs to a corresponding user, and the gesture recognition safety is improved by the means. The whole process does not need extra unlocking steps, only needs one gesture operation, and enables gesture recognition to be more convenient and faster.
The foregoing is a more detailed description of the present invention in connection with specific preferred embodiments thereof, and it is not intended that the invention be limited to the specific embodiments thereof. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the scope of the invention.
Claims (8)
1. An identity and gesture recognition method based on radar signals is characterized by comprising the following steps:
step 1, reading radar echo signals received by a radar sensor and obtained by reflection of various gestures of a tester;
step 2, mixing the radar echo signal with a radar transmitting signal;
step 3, filtering the mixed signal by adopting a high-pass filter;
step 4, performing centralized operation on the filtered signal data;
step 5, designing a neural network model suitable for radar signal characteristics, and training the model by using the signal preprocessed in the step 4 and an identity information label of a tester to obtain a neural network A capable of performing identity verification;
step 6, obtaining distance, speed and angle information according to the signals preprocessed in the step 4 and radar sensor parameters, and calculating to obtain a three-dimensional coordinate and a Doppler value of the moving target;
step 7, dividing the space above the radar by adopting a space grid method; mapping the space region into a three-dimensional matrix, and accumulating the Doppler value of the three-dimensional coordinate and the Doppler value obtained in the step (6) in a matrix unit corresponding to the grid according to the grid position in the space to which the three-dimensional coordinate and the Doppler value belong as the size of the matrix unit element; sending the matrix and the gesture information label into a designed neural network to train to obtain a neural network B capable of performing gesture recognition;
step 8, performing constant false alarm detection on the radar echo signals detected in real time to judge whether gesture recognition is performed by people, and performing step 9 if the gesture recognition is performed by people; if not, continuing to wait for detection;
step 9, preprocessing the detected radar echo signals from the step 2 to the step 4; the processed signals are sent to the neural network A trained in the step 5 to extract features for analysis; verifying the identity of the user through identity information contained in the characteristics, if the identity information passes the verification, the gesture of the user is effective, and performing the step 10, otherwise, continuing to wait for detection;
and step 10, after the data preprocessed in the steps 2 to 4 are processed in the steps 6 and 7, inputting the data into the neural network B to judge the gesture of the user, and performing corresponding operation according to the corresponding relation between the gesture of the user and the operation.
2. The radar signal-based identity and gesture recognition method of claim 1, wherein the radar sensor employs an FMCW millimeter wave radar with a frequency range of 57.4GHz to 62.6 GHz.
3. The radar signal based identity and gesture recognition method of claim 1, wherein in the step 2, if the radar sensor has a plurality of receiving channels, the obtained corresponding waveforms are averaged and then filtered.
4. The radar signal-based identity and gesture recognition method according to claim 1, wherein in the step 3, the mixed signal is filtered by an eighth-order butterworth high-pass filter with a cut-off frequency of 31250Hz, so that the effective information is retained and the large direct current and low frequency noise are filtered.
5. The radar signal-based identity and gesture recognition method according to claim 1, wherein in step 6, distance information R is obtained through fast time dimension FFT according to the signal and radar sensor parameters preprocessed in step 4:
and then obtaining speed information v through a slow time dimension FFT:
wherein f ismovingBeatAnd fstaticBeatFrequency of beat signal, f, in moving and stationary states of the object, respectivelydIs the Doppler frequency, fcFor sweep bandwidth, R is the target distance, C is the speed of light, tcF is the central frequency of a Chirp signal, and v is the target speed;
obtaining angle information θ from a plurality of transmitting and receiving antennas of the radar sensor:
where Δ d is a distance difference between any two receiving antennas and the target, Δ Φ is a phase difference corresponding to signals received by the two antennas, L is a distance corresponding to the two antennas, and λ is a wavelength.
6. The radar signal based identity and gesture recognition method of claim 1, wherein in the step 7, the region with a spatial size of Xcm Ycm X Zcm is mapped to a three-dimensional matrix with a size of (X k1) X (Y k2) X (Z k3), wherein X, Y, Z are the corresponding length and width height of the space, and k1, k2, k3 is the mapping coefficient of the actual space length, width and height and the three-dimensional matrix.
7. The method as claimed in claim 1, wherein the valid user establishes a corresponding relationship between a predetermined gesture and an operation during training, and if the specific gesture of the valid user is a predetermined gesture in step 10, the operation corresponding to the predetermined gesture is performed, and if the gesture is not in the predetermined gesture, no operation is performed.
8. The radar signal-based identity and gesture recognition method according to claim 1, wherein the method is applied to a mobile phone, a radar sensor is arranged in the mobile phone, identity information and gesture information of an equipment owner are stored in advance, and part of the gesture information corresponds to an App operation instruction; on the premise of locking the screen of the mobile phone, if the person performing the gesture authentication is the owner of the mobile phone, unlocking the mobile phone, judging gesture information, opening an App corresponding to the gesture, and if the gesture does not correspond to the App, not performing any operation; if the gesture does not belong to the equipment owner, the mobile phone maintains the screen locking; and under the condition that the mobile phone is unlocked, if the gesture does not belong to the equipment owner or the gesture made by the equipment owner is not in the specified gesture, not performing the corresponding operation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010274512.2A CN111427031B (en) | 2020-04-09 | 2020-04-09 | Identity and gesture recognition method based on radar signals |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010274512.2A CN111427031B (en) | 2020-04-09 | 2020-04-09 | Identity and gesture recognition method based on radar signals |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111427031A CN111427031A (en) | 2020-07-17 |
CN111427031B true CN111427031B (en) | 2021-12-07 |
Family
ID=71556052
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010274512.2A Active CN111427031B (en) | 2020-04-09 | 2020-04-09 | Identity and gesture recognition method based on radar signals |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111427031B (en) |
Families Citing this family (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111857354A (en) * | 2020-08-04 | 2020-10-30 | RealMe重庆移动通信有限公司 | Unlocking method and device, electronic equipment and storage medium |
CN112183429B (en) * | 2020-10-12 | 2024-01-19 | 苏州晴森模具有限公司 | 3D gesture recognition system and method |
CN114488153A (en) * | 2020-11-13 | 2022-05-13 | 华为技术有限公司 | Radar authentication method and device, and computer storage medium |
CN112686094B (en) * | 2020-12-03 | 2021-08-10 | 华中师范大学 | Non-contact identity recognition method and system based on millimeter wave radar |
CN112198966B (en) * | 2020-12-08 | 2021-03-16 | 中南大学 | Stroke identification method and system based on FMCW radar system |
CN114661142A (en) * | 2020-12-22 | 2022-06-24 | 华为技术有限公司 | Gesture recognition method and device |
US11474232B2 (en) | 2021-03-19 | 2022-10-18 | KaiKuTek Inc. | Range doppler angle detection method and range doppler angle detection device |
TWI756122B (en) * | 2021-04-30 | 2022-02-21 | 開酷科技股份有限公司 | Distance Doppler Radar Angle Sensing Method and Device |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103345360A (en) * | 2013-06-21 | 2013-10-09 | 广东欧珀移动通信有限公司 | Method for recognizing intelligent terminal touch screen gestures |
CN106339618A (en) * | 2015-07-13 | 2017-01-18 | 广州杰赛科技股份有限公司 | Authentication method based on gestures |
CN107430189A (en) * | 2015-02-27 | 2017-12-01 | 德州仪器公司 | Recognized using the gesture of frequency modulated continuous wave radar |
CN108344995A (en) * | 2018-01-25 | 2018-07-31 | 宁波隔空智能科技有限公司 | A kind of gesture identifying device and gesture identification method based on microwave radar technology |
CN109765539A (en) * | 2019-01-28 | 2019-05-17 | 珠海格力电器股份有限公司 | Indoor user behavior monitoring method and device, electrical equipment and home monitoring system |
CN109885194A (en) * | 2017-11-17 | 2019-06-14 | 麦格纳覆盖件有限公司 | For sliding/tapping touch and the gesture plate of access authentication system |
CN110799927A (en) * | 2018-08-30 | 2020-02-14 | Oppo广东移动通信有限公司 | Gesture recognition method, terminal and storage medium |
KR20200023670A (en) * | 2018-08-14 | 2020-03-06 | 전자부품연구원 | Apparatus and Method for Recognizing Gestures and Finger Spellings using Cluster Radar and 3D Convolution Neural Network |
CN110941331A (en) * | 2018-09-21 | 2020-03-31 | 国际商业机器公司 | Gesture recognition using 3D millimeter wave radar |
-
2020
- 2020-04-09 CN CN202010274512.2A patent/CN111427031B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103345360A (en) * | 2013-06-21 | 2013-10-09 | 广东欧珀移动通信有限公司 | Method for recognizing intelligent terminal touch screen gestures |
CN107430189A (en) * | 2015-02-27 | 2017-12-01 | 德州仪器公司 | Recognized using the gesture of frequency modulated continuous wave radar |
CN106339618A (en) * | 2015-07-13 | 2017-01-18 | 广州杰赛科技股份有限公司 | Authentication method based on gestures |
CN109885194A (en) * | 2017-11-17 | 2019-06-14 | 麦格纳覆盖件有限公司 | For sliding/tapping touch and the gesture plate of access authentication system |
CN108344995A (en) * | 2018-01-25 | 2018-07-31 | 宁波隔空智能科技有限公司 | A kind of gesture identifying device and gesture identification method based on microwave radar technology |
KR20200023670A (en) * | 2018-08-14 | 2020-03-06 | 전자부품연구원 | Apparatus and Method for Recognizing Gestures and Finger Spellings using Cluster Radar and 3D Convolution Neural Network |
CN110799927A (en) * | 2018-08-30 | 2020-02-14 | Oppo广东移动通信有限公司 | Gesture recognition method, terminal and storage medium |
CN110941331A (en) * | 2018-09-21 | 2020-03-31 | 国际商业机器公司 | Gesture recognition using 3D millimeter wave radar |
CN109765539A (en) * | 2019-01-28 | 2019-05-17 | 珠海格力电器股份有限公司 | Indoor user behavior monitoring method and device, electrical equipment and home monitoring system |
Non-Patent Citations (4)
Title |
---|
TS-I3D Based Hand Gesture Recognition Method With Radar Sensor;wang yong 等;《SPECIAL SECTION ON ARTIFICIAL INTELLIGENCE FOR PHYSICAL-LAYER WIRELESS COMMUNICATIONS》;20190304;第22902-22913页 * |
基于手势识别的智能手机身份认证;刘卜瑜;《万方》;20180920;正文全文 * |
基于手势识别的智能电视交互专利技术综述;杨欣怡 等;《科技创新与应用》;20181231(第24期);第11-13页 * |
基于手机携带行为分析的身份认证方法设计与实现;孙龙寿;《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》;20200215(第02期);正文全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN111427031A (en) | 2020-07-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111427031B (en) | Identity and gesture recognition method based on radar signals | |
US11947002B2 (en) | Method for recognizing identity and gesture based on radar signals | |
CN109444911B (en) | Unmanned ship water surface target detection, identification and positioning method based on monocular camera and laser radar information fusion | |
Yu et al. | Noninvasive human activity recognition using millimeter-wave radar | |
Sakamoto et al. | Hand gesture recognition using a radar echo I–Q plot and a convolutional neural network | |
CN108307767B (en) | Detection of obstacles obstacle avoidance system and method suitable for full-automatic weeder | |
CN106127145B (en) | Pupil diameter and tracking | |
CN108510734A (en) | A kind of information of vehicles matching process of roadside unit and a kind of roadside unit | |
JP2018163096A (en) | Information processing method and information processing device | |
CN112686094B (en) | Non-contact identity recognition method and system based on millimeter wave radar | |
CN111541511B (en) | Communication interference signal identification method based on target detection in complex electromagnetic environment | |
CN113609976B (en) | Direction-sensitive multi-gesture recognition system and method based on WiFi equipment | |
CN111738060A (en) | Human gait recognition system based on millimeter wave radar | |
CN113408328B (en) | Gesture segmentation and recognition algorithm based on millimeter wave radar | |
CN111476058A (en) | Gesture recognition method based on millimeter wave radar | |
CN112612365B (en) | Gesture recognition method and device, electronic equipment and storage medium | |
CN110097011A (en) | A kind of signal recognition method and device | |
CN114814832A (en) | Millimeter wave radar-based real-time monitoring system and method for human body falling behavior | |
CN115508821A (en) | Multisource fuses unmanned aerial vehicle intelligent detection system | |
Zhang et al. | Deformable deep convolutional generative adversarial network in microwave based hand gesture recognition system | |
CN116386120A (en) | Noninductive monitoring management system | |
CN113900101A (en) | Obstacle detection method and device and electronic equipment | |
CN108932468A (en) | One kind being suitable for psychologic face recognition method | |
CN107578036A (en) | A kind of depth image tumble recognizer based on wavelet moment | |
CN208367913U (en) | A kind of roadside unit |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |