CN112034446A - Gesture recognition system based on millimeter wave radar - Google Patents
Gesture recognition system based on millimeter wave radar Download PDFInfo
- Publication number
- CN112034446A CN112034446A CN202010876506.4A CN202010876506A CN112034446A CN 112034446 A CN112034446 A CN 112034446A CN 202010876506 A CN202010876506 A CN 202010876506A CN 112034446 A CN112034446 A CN 112034446A
- Authority
- CN
- China
- Prior art keywords
- signals
- millimeter wave
- wave radar
- module
- gesture recognition
- 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.)
- Pending
Links
- 238000012545 processing Methods 0.000 claims abstract description 37
- 238000013528 artificial neural network Methods 0.000 claims abstract description 20
- 230000000007 visual effect Effects 0.000 claims abstract description 6
- 238000010586 diagram Methods 0.000 claims description 13
- 238000012360 testing method Methods 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 4
- 230000004888 barrier function Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- TVZRAEYQIKYCPH-UHFFFAOYSA-N 3-(trimethylsilyl)propane-1-sulfonic acid Chemical compound C[Si](C)(C)CCCS(O)(=O)=O TVZRAEYQIKYCPH-UHFFFAOYSA-N 0.000 claims 2
- 230000008901 benefit Effects 0.000 abstract description 7
- 238000012549 training Methods 0.000 abstract description 7
- 239000013598 vector Substances 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000000034 method Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
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
- 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
- G01S13/584—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 adapted for simultaneous range and velocity measurements
-
- 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
- G01S7/415—Identification of targets based on measurements of movement associated with the 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses a gesture recognition system based on a millimeter wave radar, which comprises a power supply module, the millimeter wave radar and a PC (personal computer) terminal; the power module provides a working power supply for the millimeter wave radar, the millimeter wave radar module is composed of a receiving and transmitting antenna, a radio frequency receiving and transmitting module (BSS) and a signal processing module, and the PC end displays a gesture recognition result in real time through a visual interface (GUI). And for the received digital signals, obtaining a radar Doppler-distance-antenna radar cube through distance FFT, Doppler FFT and angle FFT, extracting a characteristic vector from the radar cube, inputting gesture characteristic information into an Artificial Neural Network (ANN), training the network by utilizing a Back Propagation (BP) algorithm, and outputting a gesture recognition result. The gesture sensor adopted by the invention is a millimeter wave radar, has the advantages of high resolution, strong anti-interference performance and the like, and the gesture characteristics are trained by using a two-layer neural network, so that the gesture actions can be effectively classified.
Description
Technical Field
The invention relates to a gesture recognition system based on a millimeter wave radar, and belongs to the technical field of digital signal processing.
Background
With the coming and developing of intelligent life, more and more researchers begin to research human-computer interaction (HCI) so as to more conveniently control intelligent equipment and improve the life quality of people. Gesture recognition is popular among many researchers as an important way of human-computer interaction. The most common gesture recognition approaches at present are mainly vision-based and sensor-based methods. Gesture recognition based on vision is the most common, and one common mode is to collect static or dynamic gestures through a camera, and finally realize gesture recognition through processing of algorithms such as mode recognition and neural network. The gesture image based on vision can well describe information such as gesture outline and shape, has the advantages of visual expression and high recognition rate, but the mode is not only easily limited by visual equipment sight distance, and the image processing algorithm is also relatively complex, is easily influenced by external light, and is difficult to work under the conditions of strong light and dark light. Sensor technology can solve the above problems well and pay attention to protect user privacy.
Currently, the sensing technologies commonly used include ultrasonic, infrared, video imaging, laser radar, millimeter wave radar and the like. The millimeter wave radar can measure targets in a large range, is short in response time, is slightly influenced by environments such as rain, snow and haze, has a plurality of advantages besides being slightly influenced by weather, and has the advantages that firstly, the size of a system component (such as an antenna) required for processing millimeter wave signals can be small, and the other advantage is high accuracy. A millimeter wave system with an operating frequency of 76-81 GHz (corresponding to a wavelength of about 4mm) will be able to detect movements as small as a few tenths of a millimeter. Therefore, the millimeter wave radar technology has a very considerable research prospect in the application of gesture recognition.
An Artificial Neural Network (ANN) does not need to determine a mathematical equation of a mapping relation between input and output in advance, and learns a certain rule by continuously training a self network so as to obtain a result closest to an expected output value, wherein the core of the function is an algorithm. The BP neural network is a multi-layer feedforward network trained according to an error back propagation algorithm, and the learning idea is a gradient descent method, and the weight and the threshold of the network are continuously adjusted through the back propagation algorithm to ensure that the sum of squares of errors of the network is minimum. The BP neural network is widely applied to a plurality of fields such as image recognition, voice analysis and the like, and is one of the most widely applied neural network models at present.
Disclosure of Invention
The purpose of the invention is as follows: in order to overcome the defects of the prior art, the invention provides a gesture recognition method based on millimeter wave radar, which can effectively recognize predefined gestures through the high-speed resolution, the high-distance resolution, the high-angle resolution and the anti-interference capability of a millimeter wave radar sensor and by combining a neural network, thereby improving the recognition efficiency.
The technical scheme is as follows: in order to achieve the purpose, the invention provides a gesture recognition system based on a millimeter wave radar, which comprises a power supply module, the millimeter wave radar and a PC (personal computer) terminal; the power module provides a working power supply for the millimeter wave radar, the millimeter wave radar module is composed of a receiving and transmitting antenna, a radio frequency receiving and transmitting module BSS and a signal processing module, and the PC end displays a gesture recognition result in real time through a visual interface GUI.
The transceiving antenna comprises two transmitting antennas Tx1, Tx2 and four receiving antennas Rx1, Rx2, Rx3 and Rx4, and is equivalent to 8 virtual antennas.
The signal processing module comprises a digital signal processing subsystem DSS module and a main subsystem MSS module.
The DSS module completes low-level signal processing of signals through a digital signal processing DSP core, and transmits data to the MSS module for high-level signal processing in a memory sharing mode.
The system transmits signals through a millimeter wave radar, a frequency synthesizer generates original LFMCW signals at a transmitting end, the original LFMCW signals are subjected to frequency multiplication to reach specified frequency through a frequency multiplier, then the LFMCW signals are divided into two paths of signals, one path of transmitting signals are sent to an inlet of a frequency mixer at a receiving end, and the transmitting signals wait for frequency mixing with received signals; the other path of transmitting signal is amplified by a power amplifier and transmitted out through a transmitting antenna;
the transmitted electromagnetic wave signals return after encountering barriers, are received by a receiving antenna, the received signals firstly pass through a low-noise amplifier to filter noise influence, then are mixed with one path of transmitting signals to generate intermediate frequency IF analog signals, the intermediate frequency signals are converted into intermediate frequency IF digital signals through A/D conversion, and the intermediate frequency IF digital signals are stored in an ADC buffer area and wait for signal processing.
The DSP system firstly transfers IF data in the ADC buffer area to a temporary storage of the DSP, and performs distance dimension FFT, velocity Doppler dimension FFT, cell average-constant false alarm rate detection CA-CFAR and angle dimension FFT baseband signal processing on the IF signals to obtain distance, velocity and azimuth angle parameters of the gesture target, and further obtains a radar cubic characteristic diagram.
And the MSS subsystem executes higher-level algorithm processing on the signals transmitted by the DSP subsystem, namely, a radar distance-Doppler-antenna range-Doppler-antenna characteristic diagram is constructed, gesture characteristics are extracted from the characteristic diagram, a two-layer neural network is trained, then the trained neural network is used for identifying the test sample, and finally, an identification result is output. Has the advantages that: compared with the prior art, the gesture recognition system based on the millimeter wave radar has the following advantages:
1. according to the gesture recognition method provided by the invention, the predefined gesture can be effectively recognized through the high-speed resolution, the high-distance resolution, the high-angle resolution and the anti-interference capability of the millimeter wave radar sensor and the combination of the neural network, so that the recognition efficiency is improved.
Drawings
FIG. 1 is a schematic diagram of six gestures predefined to be recognized;
FIG. 2 is a block diagram of the overall architecture of the present invention;
FIG. 3 is a block diagram of an algorithm flow for performing gesture recognition in accordance with the present invention;
fig. 4 is a diagram showing the effect of the system of the present invention.
Detailed Description
The invention provides a gesture recognition system based on a millimeter wave radar, which comprises a power supply module, the millimeter wave radar and a PC (personal computer) terminal; the system comprises a power supply module, a millimeter wave radar module, a signal processing module and a PC (personal computer) end, wherein the power supply module provides a working power supply for the millimeter wave radar, the millimeter wave radar module consists of a receiving and transmitting antenna, a radio frequency receiving and transmitting module (BSS) and the signal processing module, and the PC end displays a gesture recognition result in real time through a visual interface (GUI); the transceiving antenna comprises two transmitting antennas Tx1, Tx2 and four receiving antennas Rx1, Rx2, Rx3 and Rx4, and is equivalent to 8 virtual antennas; the signal processing module comprises a digital signal processing subsystem (DSS) module and a main subsystem (MSS) module, wherein the DSS module completes low-level signal processing on signals through a Digital Signal Processing (DSP) core, and transmits data to the MSS module for high-level signal processing in a memory sharing mode.
The system transmits signals through a millimeter wave radar, a frequency synthesizer generates original LFMCW signals at a transmitting end, the original LFMCW signals are subjected to frequency multiplication to reach specified frequency through a frequency multiplier, then the LFMCW signals are divided into two paths of signals, one path of transmitting signals are sent to an inlet of a frequency mixer at a receiving end, and the transmitting signals wait for frequency mixing with received signals; the other path of transmitting signal is amplified by a power amplifier and transmitted out through a transmitting antenna;
the transmitted electromagnetic wave signals return after encountering barriers, are received by a receiving antenna, the received signals firstly pass through a low noise amplifier to filter noise influence, then are mixed with one path of transmitting signals to generate Intermediate Frequency (IF) analog signals, the intermediate frequency signals are converted into Intermediate Frequency (IF) digital signals through A/D conversion, and the intermediate frequency digital signals are stored in an ADC buffer area to wait for signal processing.
The DSP system firstly transfers IF data in the ADC buffer area to a temporary memory of the DSP, and performs distance dimension FFT, speed (Doppler) dimension FFT, cell average-constant false alarm detection (CA-CFAR) and angle dimension FFT baseband signal processing on the IF signal to obtain distance, speed and azimuth angle parameters of a gesture target, and further obtain a radar cubic characteristic diagram;
the MSS subsystem executes higher-level algorithm processing on signals transmitted by the DSP subsystem, namely a radar distance-Doppler-antenna (range-Doppler-antenna) feature diagram is constructed, gesture features are extracted from the feature diagram, a two-layer neural network is trained, then the trained neural network is used for identifying a test sample, and finally an identification result is output.
Example 1
A gesture recognition system based on millimeter wave radar comprises the following steps:
A. six gestures which need to be recognized are designed according to actual requirements, as shown in fig. 1, including: six gestures of sliding from left to right, sliding from right to left, sliding from bottom to top, sliding from top to bottom, rotating the finger clockwise, and rotating the finger counterclockwise.
B. The radar is connected with the power supply module and the PC end by using the USB data line, a tested person needs to sit at a position of about 0.2m in front of the radar, and the palm is arranged in front of the radar, so that gestures can be captured by the radar.
C. The configuration of radio frequency front end parameters is realized by using an ARM, an emitting end is set to emit a sawtooth wave modulated FMCW wave, the starting frequency is 77GH, the rising slope is 30MHZ/us, the number of ADC sampling points is 256 per sweep frequency, the number of radar sweep frequency signals is 128 per frame, the time of each frame is 40ms, and a receiving end acquires echo signals.
D. As shown in fig. 2, the receiving end first performs ADC sampling on the received signal and stores the signal in an ADC buffer.
E. In the DSP subsystem, baseband signal processing is needed, firstly, data in an ADC buffer memory is transferred to a temporary memory of the DSP, windowing processing is carried out on the data, a windowing function is used for reducing frequency spectrum leakage, then distance FFT is carried out on the data, and finally the FFT result is stored in a memory. This step is repeated for all chirp signals (chirp) within a frame until the end.
F. As shown in fig. 3, after all the chirp signals in one frame have been subjected to distance FFT and stored in the memory, the DSP extracts the distance FFT result corresponding to each distance unit, performs windowing and velocity dimension FFT on the distance FFT result, then modulo the velocity dimension FFT result, takes 2 logarithms, and adds the results of 8 virtual antennas. And then carrying out unit average-constant false alarm detection (CA-CFAR) on the velocity dimension, marking a velocity unit with a target on the velocity unit, carrying out distance dimension CA-CFAR on the marked velocity unit, and finally further carrying out peak value focusing on the distance unit with the target and the Doppler unit. After the peak value is focused, the distance and the speed of the gesture target can be determined according to the distance unit and the Doppler unit, then angle FFT is needed to be conducted on 8 virtual antennas corresponding to the distance and speed unit where the target is located, the target angle is solved, and the target angle is converted into an X-Y coordinate form (with radar as an origin) and stored in a memory.
G. After the baseband signal algorithm processing of the IF signal is executed in the DSP, the distance, speed, and angle dimension information of the corresponding target can be obtained, and then the following 6 features corresponding to each gesture can be extracted using the feature extraction function: weighted average distance (Weighted Range), Weighted average Doppler (Weighted Doppler), instantaneous energy (InstEnergy), Weighted average Azimuth (Weighted Azimuth), Weighted average Elevation (Weighted Elevation), azimuthal Doppler Correlation (Azimuth Doppler Correlation).
H. Once these feature vector computations are complete, they may be passed to the MSS subsystem. In the MSS subsystem, feature vectors are trained as inputs through a two-layer neural network.
I. And (G) storing and storing the gesture characteristic information extracted in the step (G), randomly dividing the sample data into training samples and testing samples, wherein the training samples are used for training the two-layer neural network. And then, recognizing the gesture test sample by using the trained neural network, and finally outputting a gesture recognition result. For six gestures of sliding from left to right, sliding from right to left, sliding from bottom to top, sliding from top to bottom, rotating the finger clockwise, and rotating the finger counterclockwise, each gesture is repeated 100 times, and 600 groups of samples are provided, wherein the training samples are 360 groups and comprise 60 groups of each gesture, and the test samples are 240 groups and comprise 40 groups of each gesture. The test results are shown in table 1.
J. In summary, the invention uses the millimeter wave radar as the gesture sensor, and the real-time and high-accuracy gesture recognition can be finally realized after the echo signal is processed by the baseband signal processing and the neural network training.
Claims (7)
1. The utility model provides a gesture recognition system based on millimeter wave radar which characterized in that: the device comprises a power supply module, a millimeter wave radar and a PC (personal computer) terminal; the power module provides a working power supply for the millimeter wave radar, the millimeter wave radar module is composed of a receiving and transmitting antenna, a radio frequency receiving and transmitting module BSS and a signal processing module, and the PC end displays a gesture recognition result in real time through a visual interface GUI.
2. The millimeter wave radar-based gesture recognition system of claim 1, wherein: the transceiving antenna comprises two transmitting antennas Tx1, Tx2 and four receiving antennas Rx1, Rx2, Rx3 and Rx4, and is equivalent to 8 virtual antennas.
3. The millimeter wave radar-based gesture recognition system of claim 1, wherein: the signal processing module comprises a digital signal processing subsystem DSS module and a main subsystem MSS module.
4. The millimeter wave radar-based gesture recognition system of claim 3, wherein: the DSS module completes low-level signal processing of signals through a digital signal processing DSP core, and transmits data to the MSS module for high-level signal processing in a memory sharing mode.
5. The millimeter wave radar-based gesture recognition system of claim 1, wherein: the system transmits signals through a millimeter wave radar, a frequency synthesizer generates original LFMCW signals at a transmitting end, the original LFMCW signals are subjected to frequency multiplication to reach specified frequency through a frequency multiplier, then the LFMCW signals are divided into two paths of signals, one path of transmitting signals are sent to an inlet of a frequency mixer at a receiving end, and the transmitting signals wait for frequency mixing with received signals; the other path of transmitting signal is amplified by a power amplifier and transmitted out through a transmitting antenna;
the transmitted electromagnetic wave signals return after encountering barriers, are received by a receiving antenna, the received signals firstly pass through a low-noise amplifier to filter noise influence, then are mixed with one path of transmitting signals to generate intermediate frequency IF analog signals, the intermediate frequency signals are converted into intermediate frequency IF digital signals through A/D conversion, and the intermediate frequency IF digital signals are stored in an ADC buffer area and wait for signal processing.
6. The millimeter wave radar-based gesture recognition system of claim 4, wherein: the DSP system firstly transfers IF data in the ADC buffer area to a temporary storage of the DSP, and performs distance dimension FFT, velocity Doppler dimension FFT, cell average-constant false alarm rate detection CA-CFAR and angle dimension FFT baseband signal processing on the IF signals to obtain distance, velocity and azimuth angle parameters of the gesture target, and further obtains a radar cubic characteristic diagram.
7. The millimeter wave radar-based gesture recognition system of claim 3, wherein: and the MSS subsystem executes higher-level algorithm processing on the signals transmitted by the DSP subsystem, namely, a radar distance-Doppler-antenna range-Doppler-antenna characteristic diagram is constructed, gesture characteristics are extracted from the characteristic diagram, a two-layer neural network is trained, then the trained neural network is used for identifying the test sample, and finally, an identification result is output.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010876506.4A CN112034446A (en) | 2020-08-27 | 2020-08-27 | Gesture recognition system based on millimeter wave radar |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010876506.4A CN112034446A (en) | 2020-08-27 | 2020-08-27 | Gesture recognition system based on millimeter wave radar |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112034446A true CN112034446A (en) | 2020-12-04 |
Family
ID=73580924
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010876506.4A Pending CN112034446A (en) | 2020-08-27 | 2020-08-27 | Gesture recognition system based on millimeter wave radar |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112034446A (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112949447A (en) * | 2021-02-25 | 2021-06-11 | 北京京东方技术开发有限公司 | Gesture recognition method, system, apparatus, device, and medium |
CN113031777A (en) * | 2021-03-26 | 2021-06-25 | 深圳市华杰智通科技有限公司 | Password input control device based on gesture recognition |
CN113031778A (en) * | 2021-03-26 | 2021-06-25 | 深圳市华杰智通科技有限公司 | Man-machine interface control device based on gesture recognition |
CN113030947A (en) * | 2021-02-26 | 2021-06-25 | 北京京东方技术开发有限公司 | Non-contact control device and electronic apparatus |
CN113050797A (en) * | 2021-03-26 | 2021-06-29 | 深圳市华杰智通科技有限公司 | Method for realizing gesture recognition through millimeter wave radar |
CN113147669A (en) * | 2021-04-02 | 2021-07-23 | 淮南联合大学 | Gesture motion detection system based on millimeter wave radar |
CN113791411A (en) * | 2021-09-07 | 2021-12-14 | 北京航空航天大学杭州创新研究院 | Millimeter wave radar gesture recognition method and device based on trajectory judgment |
CN113822795A (en) * | 2021-09-17 | 2021-12-21 | 惠州视维新技术有限公司 | Virtual key projection method and device based on millimeter wave radar and electronic equipment |
CN113963441A (en) * | 2021-10-25 | 2022-01-21 | 中国科学技术大学 | Cross-domain enhancement-based millimeter wave radar gesture recognition method and system |
CN114114223A (en) * | 2021-12-01 | 2022-03-01 | 长春理工大学 | Millimeter wave sitting posture detection intelligent desk lamp based on convolutional neural network |
CN114280565A (en) * | 2021-11-12 | 2022-04-05 | 苏州豪米波技术有限公司 | Gesture recognition method based on millimeter wave radar |
WO2022134989A1 (en) * | 2020-12-22 | 2022-06-30 | 华为技术有限公司 | Gesture recognition method and apparatus |
CN114970618A (en) * | 2022-05-17 | 2022-08-30 | 西北大学 | Environmental robust sign language identification method and system based on millimeter wave radar |
WO2023029390A1 (en) * | 2021-09-01 | 2023-03-09 | 东南大学 | Millimeter wave radar-based gesture detection and recognition method |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN109188414A (en) * | 2018-09-12 | 2019-01-11 | 北京工业大学 | A kind of gesture motion detection method based on millimetre-wave radar |
CN109583436A (en) * | 2019-01-29 | 2019-04-05 | 杭州朗阳科技有限公司 | A kind of gesture recognition system based on millimetre-wave radar |
US20190115916A1 (en) * | 2017-10-17 | 2019-04-18 | Trustees Of Dartmouth College | Infrared-Based Gesture Sensing And Detection Systems, And Apparatuses, Software, And Methods Relating To Same |
CN110133610A (en) * | 2019-05-14 | 2019-08-16 | 浙江大学 | ULTRA-WIDEBAND RADAR action identification method based on time-varying distance-Doppler figure |
CN110275616A (en) * | 2019-06-14 | 2019-09-24 | Oppo广东移动通信有限公司 | Gesture identification mould group, control method and electronic device |
CN110765974A (en) * | 2019-10-31 | 2020-02-07 | 复旦大学 | Micro-motion gesture recognition method based on millimeter wave radar and convolutional neural network |
CN110988863A (en) * | 2019-12-20 | 2020-04-10 | 北京工业大学 | Novel millimeter wave radar gesture signal processing method |
CN111104960A (en) * | 2019-10-30 | 2020-05-05 | 武汉大学 | Sign language identification method based on millimeter wave radar and machine vision |
US20200217930A1 (en) * | 2018-08-30 | 2020-07-09 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Method for gesture recognition, terminal, and storage medium |
-
2020
- 2020-08-27 CN CN202010876506.4A patent/CN112034446A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20190115916A1 (en) * | 2017-10-17 | 2019-04-18 | Trustees Of Dartmouth College | Infrared-Based Gesture Sensing And Detection Systems, And Apparatuses, Software, And Methods Relating To Same |
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 |
US20200217930A1 (en) * | 2018-08-30 | 2020-07-09 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Method for gesture recognition, terminal, and storage medium |
CN109188414A (en) * | 2018-09-12 | 2019-01-11 | 北京工业大学 | A kind of gesture motion detection method based on millimetre-wave radar |
CN109583436A (en) * | 2019-01-29 | 2019-04-05 | 杭州朗阳科技有限公司 | A kind of gesture recognition system based on millimetre-wave radar |
CN110133610A (en) * | 2019-05-14 | 2019-08-16 | 浙江大学 | ULTRA-WIDEBAND RADAR action identification method based on time-varying distance-Doppler figure |
CN110275616A (en) * | 2019-06-14 | 2019-09-24 | Oppo广东移动通信有限公司 | Gesture identification mould group, control method and electronic device |
CN111104960A (en) * | 2019-10-30 | 2020-05-05 | 武汉大学 | Sign language identification method based on millimeter wave radar and machine vision |
CN110765974A (en) * | 2019-10-31 | 2020-02-07 | 复旦大学 | Micro-motion gesture recognition method based on millimeter wave radar and convolutional neural network |
CN110988863A (en) * | 2019-12-20 | 2020-04-10 | 北京工业大学 | Novel millimeter wave radar gesture signal processing method |
Non-Patent Citations (2)
Title |
---|
张杰: "海洋遥感探测技术与应用", 31 August 2017, 武汉大学出版社, pages: 223 - 225 * |
李楚杨: "基于毫米波雷达的手势识别算法研究", 中国优秀硕士学位论文全文数据库 信息科技辑, pages 1 - 69 * |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2022134989A1 (en) * | 2020-12-22 | 2022-06-30 | 华为技术有限公司 | Gesture recognition method and apparatus |
CN112949447A (en) * | 2021-02-25 | 2021-06-11 | 北京京东方技术开发有限公司 | Gesture recognition method, system, apparatus, device, and medium |
CN113030947A (en) * | 2021-02-26 | 2021-06-25 | 北京京东方技术开发有限公司 | Non-contact control device and electronic apparatus |
CN113031777A (en) * | 2021-03-26 | 2021-06-25 | 深圳市华杰智通科技有限公司 | Password input control device based on gesture recognition |
CN113031778A (en) * | 2021-03-26 | 2021-06-25 | 深圳市华杰智通科技有限公司 | Man-machine interface control device based on gesture recognition |
CN113050797A (en) * | 2021-03-26 | 2021-06-29 | 深圳市华杰智通科技有限公司 | Method for realizing gesture recognition through millimeter wave radar |
CN113147669B (en) * | 2021-04-02 | 2022-08-02 | 淮南联合大学 | Gesture motion detection system based on millimeter wave radar |
CN113147669A (en) * | 2021-04-02 | 2021-07-23 | 淮南联合大学 | Gesture motion detection system based on millimeter wave radar |
WO2023029390A1 (en) * | 2021-09-01 | 2023-03-09 | 东南大学 | Millimeter wave radar-based gesture detection and recognition method |
CN113791411A (en) * | 2021-09-07 | 2021-12-14 | 北京航空航天大学杭州创新研究院 | Millimeter wave radar gesture recognition method and device based on trajectory judgment |
CN113791411B (en) * | 2021-09-07 | 2024-05-28 | 北京航空航天大学杭州创新研究院 | Millimeter wave radar gesture recognition method and device based on track judgment |
CN113822795A (en) * | 2021-09-17 | 2021-12-21 | 惠州视维新技术有限公司 | Virtual key projection method and device based on millimeter wave radar and electronic equipment |
CN113822795B (en) * | 2021-09-17 | 2024-02-09 | 惠州视维新技术有限公司 | Virtual key projection method and device based on millimeter wave radar and electronic equipment |
CN113963441A (en) * | 2021-10-25 | 2022-01-21 | 中国科学技术大学 | Cross-domain enhancement-based millimeter wave radar gesture recognition method and system |
CN113963441B (en) * | 2021-10-25 | 2024-04-02 | 中国科学技术大学 | Millimeter wave radar gesture recognition method and system based on cross-domain enhancement |
CN114280565A (en) * | 2021-11-12 | 2022-04-05 | 苏州豪米波技术有限公司 | Gesture recognition method based on millimeter wave radar |
CN114114223A (en) * | 2021-12-01 | 2022-03-01 | 长春理工大学 | Millimeter wave sitting posture detection intelligent desk lamp based on convolutional neural network |
CN114970618A (en) * | 2022-05-17 | 2022-08-30 | 西北大学 | Environmental robust sign language identification method and system based on millimeter wave radar |
CN114970618B (en) * | 2022-05-17 | 2024-03-19 | 西北大学 | Sign language identification method and system based on millimeter wave radar and with environment robustness |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112034446A (en) | Gesture recognition system based on millimeter wave radar | |
Dekker et al. | Gesture recognition with a low power FMCW radar and a deep convolutional neural network | |
Yi et al. | Track-before-detect strategies for radar detection in G0-distributed clutter | |
Sun et al. | Oriented ship detection based on strong scattering points network in large-scale SAR images | |
CN110348288A (en) | A kind of gesture identification method based on 77GHz MMW RADAR SIGNAL USING | |
Wu et al. | Dynamic hand gesture recognition using FMCW radar sensor for driving assistance | |
Xia et al. | Time-space dimension reduction of millimeter-wave radar point-clouds for smart-home hand-gesture recognition | |
Zhou et al. | Efficient high cross-user recognition rate ultrasonic hand gesture recognition system | |
CN110687816A (en) | Intelligent household control system and method based on millimeter wave radar | |
Du et al. | Enhanced multi-channel feature synthesis for hand gesture recognition based on CNN with a channel and spatial attention mechanism | |
CN106772352A (en) | A kind of PD radars extension Weak target detecting method based on Hough and particle filter | |
CN113963441A (en) | Cross-domain enhancement-based millimeter wave radar gesture recognition method and system | |
Gan et al. | Gesture recognition system using 24 GHz FMCW radar sensor realized on real-time edge computing platform | |
CN113064483A (en) | Gesture recognition method and related device | |
Qu et al. | Dynamic hand gesture classification based on multichannel radar using multistream fusion 1-D convolutional neural network | |
Song et al. | Efficient through-wall human pose reconstruction using UWB MIMO radar | |
CN112147584A (en) | MIMO radar extended target detection method based on non-uniform clutter | |
Song et al. | Multi-view HRRP generation with aspect-directed attention GAN | |
Jin et al. | Interference-robust millimeter-wave radar-based dynamic hand gesture recognition using 2D CNN-transformer networks | |
Xie et al. | Lightweight midrange arm-gesture recognition system from mmwave radar point clouds | |
Regani et al. | Handwriting tracking using 60 GHz mmWave radar | |
Li et al. | Digital gesture recognition based on millimeter wave radar | |
Song et al. | Dual-task human activity sensing for pose reconstruction and action recognition using 4d imaging radar | |
Su et al. | Nearest neighbor data association algorithm based on robust Kalman filtering | |
Qu et al. | Enhanced CNN-based small target detection in sea clutter with controllable false alarm |
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 |