CN114280565A - Gesture recognition method based on millimeter wave radar - Google Patents
Gesture recognition method based on millimeter wave radar Download PDFInfo
- Publication number
- CN114280565A CN114280565A CN202111336250.9A CN202111336250A CN114280565A CN 114280565 A CN114280565 A CN 114280565A CN 202111336250 A CN202111336250 A CN 202111336250A CN 114280565 A CN114280565 A CN 114280565A
- Authority
- CN
- China
- Prior art keywords
- speed
- distance
- gesture recognition
- time
- millimeter wave
- 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
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000001514 detection method Methods 0.000 claims abstract description 8
- 238000001914 filtration Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000005286 illumination Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
Images
Landscapes
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses a gesture recognition method based on a millimeter wave radar. The distance characteristics and the speed characteristics obtained by each frame are spliced to form distance-time characteristics, speed-time characteristics and speed-distance characteristics, the distance-time characteristics represent the movement trend of the target relative to the radar according to the distance-time characteristics, namely the approaching or the departing of the target is detected, the speed-time characteristics represent the movement speed of the target relative to the radar, the distance-speed characteristics reflect the distribution of the target speed on different distances, and therefore the movement track of the target is obtained to realize action judgment and further realize gesture recognition. The system can realize all-weather moving target control, the detection distance can reach 3-50 m, the intelligent guiding experience of a user is improved, the time cost of the user is saved, the operation is simple, vivid and vivid, and the system is suitable for various occasions.
Description
Technical Field
The invention relates to the field of vehicle-mounted radars, in particular to a gesture recognition method based on a millimeter wave radar.
Background
The gesture recognition has the characteristics of liveliness, vividness, intuition and the like, and has stronger visual characteristics. In the gesture recognition technology, the visual recognition technology is greatly influenced by factors such as light, weather and application site background, and the privacy of a user is easily revealed by recognition in the form of video or images; in addition, in other gesture recognition schemes, the scheme based on the wearable data sensor needs to be in contact with a human body, is complex to operate and not easy to wear, and is not used in daily life use scenes; the scheme based on ultrasonic waves is obviously influenced by propagation speed and diffraction, and the scheme based on non-broadband wireless communication signals such as Wi-Fi is difficult to remove background noise during gesture recognition and low in resolution. And the gesture recognition technology based on the millimeter wave radar scheme has non-contact, is not influenced by factors such as illumination, a sky starting place and the like, can protect the privacy of a user, and can ensure the use in the whole period. The vehicle can be controlled remotely under severe weather conditions such as rain and snow or under the limited condition that indoor illumination conditions such as production workshops and warehouses are insufficient.
Disclosure of Invention
In order to overcome the defects in the prior art, the embodiment of the invention provides a gesture recognition method based on a millimeter wave radar, which can solve one or more problems in the background art, and can realize remote recognition of gestures through the millimeter wave radar, so that the gesture recognition method is improved.
The embodiment of the application discloses: a gesture recognition method based on a millimeter wave radar comprises the following steps:
s1, acquiring and processing echo signals to obtain intermediate frequency signal data;
s2, extracting intermediate frequency signal data, arranging the data in the same frame according to a Chirp signal to obtain a plurality of first information matrixes, and performing windowing processing and FFT processing on the data in the same Chirp signal to obtain distance dimension information of a target object;
s3, filtering the binary data acquired by the radar to obtain a second information matrix, and then performing FFT processing on Chirp in each frame to obtain speed dimension information of the target object;
s4, processing the speed dimension information and the distance dimension information by adopting a constant false alarm detector to obtain the distance characteristic and the speed characteristic of the target object in each frame;
s5, splicing the distance characteristics and the speed characteristics obtained by each frame to form distance-time characteristics, speed-time characteristics and speed-distance characteristics, representing the movement trend of the target relative to the radar according to the distance-time characteristics, namely detecting the approaching or the departing of the target, wherein the speed-time characteristics represent the movement speed of the target relative to the radar, the positive is approaching, and the negative is departing, the distance-speed characteristics reflect the distribution of the target speed on different distances, so that the movement track of the target is obtained to realize action judgment, and further realize gesture recognition;
and S6, remotely controlling the vehicle based on the gesture recognition result.
Further, parameter setting is carried out on the millimeter wave radar, and the parameters comprise frequency modulation starting frequency f0Chirp slope K, transmit antenna start time TTX-startIdle time TidleTime of frequency modulation TrampIntegral chirp period Tc, ADC effective start time TADC-startDistance resolution dresMaximum measurable velocity vmaxAnd velocity resolution vres;
wherein: b is the effective bandwidth of the tone, i.e. the bandwidth in the sampling time, which can be expressed as:c is the speed of light, and lambda is the wavelength corresponding to the center of frequency modulation.
Further, the constant false alarm detector adopts CA-CFAR, and data larger than a threshold value T is filtered out in the detection process.
Further, the bandwidth of the effective frequency modulation bandwidth is not less than 2 GHz.
Further, the threshold T satisfies the following formula:
T=a·Pn,
where a represents the threshold factor and Pn represents the power noise estimate.
Further, the frequency modulation starting frequency f in the parameter0Chirp slope K, transmit antenna start time TTX-startIdle time TidleTime of frequency modulation TrampIntegral chirp period Tc, ADC effective start time TADC-startDistance resolution dresMaximum measurable velocity vmaxAnd velocity resolution vres。
Further, the threshold factor is a preset value.
Further, the threshold factor is stored in the learning network, and the threshold factor is continuously corrected through the learning network, so that the detection precision of the movement track of the target object is improved.
The invention has the following beneficial effects: the gesture recognition method based on the millimeter wave radar can capture the moving track of a target object through the millimeter wave radar, realize gesture recognition, realize all-weather moving target control, improve the intelligent guiding experience of a user by the detection distance of 3-50 m, save the time cost of the user, be simple to operate, be vivid and vivid, and be suitable for various occasions.
In order to make the aforementioned and other objects, features and advantages of the invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic diagram of the frequency modulation cycle of a millimeter wave radar.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In a preferred embodiment of the present invention, a gesture recognition method based on millimeter wave radar includes the following steps:
s1, acquiring and processing echo signals to obtain intermediate frequency signal data;
s2, extracting intermediate frequency signal data, arranging the data in the same frame according to a Chirp signal to obtain a plurality of first information matrixes, and performing windowing processing and FFT processing on the data in the same Chirp signal to obtain distance dimension information of a target object;
s3, filtering the binary data acquired by the radar to obtain a second information matrix, and then performing FFT processing on Chirp in each frame to obtain speed dimension information of the target object;
s4, processing the speed dimension information and the distance dimension information by adopting a constant false alarm detector to obtain the distance characteristic and the speed characteristic of the target object in each frame;
s5, splicing the distance characteristics and the speed characteristics obtained by each frame to form distance-time characteristics, speed-time characteristics and speed-distance characteristics, representing the movement trend of the target relative to the radar according to the distance-time characteristics, namely detecting the approaching or the departing of the target, wherein the speed-time characteristics represent the movement speed of the target relative to the radar, the positive is approaching, and the negative is departing, the distance-speed characteristics reflect the distribution of the target speed on different distances, so that the movement track of the target is obtained to realize action judgment, and further realize gesture recognition;
and S6, remotely controlling the vehicle based on the gesture recognition result.
In a frequency modulation period, the FMCW signal transmitted by the radar can be expressed as:
where t denotes the fast time index in a frequency modulation period, ATRepresenting the amplitude of the transmitted signal, fc representing the carrier center frequency, and K representing the chirp rate of the signal.
The target scene reflection signal can be represented by the transmit signal as:
wherein A isRDenotes the received signal amplitude, Δ t denotes the signal line time, Δ t is 2R/C, R denotes the radial distance of the target from the radar, C denotes the speed of light, K (τ - Δ t) denotes the received signal frequency at time τ, Δ f denotes the received signal frequency at time τdIndicating the doppler shift.
The receiver mixes and low-pass filters the echo signal reflected by the target scene with the transmitting signal to obtain an intermediate frequency signal which is approximately sIF(t)=fLPF{sT(t)sR(t)}=AT·ARcos{2π[fcΔt+(fIF-Δfd)t]}
Wherein f isIFK Δ t represents the frequency of the intermediate frequency signal at time t. Therefore, the phase of the obtained intermediate frequency signal can be expressed as phi ═ 2 pi [ f ═ fcΔt+(fIF-Δfd)t]In the formula (f)cThe term Δ t, which is a constant with respect to fast time, can be considered as the initial phase. And fIFOnly with respect to the corresponding fast time index within the frequency modulation period, since Tc is small, it is usually assumed that the doppler shift Δ f within one frequency modulation period isdIf the frequency spectrum is constant, the frequency spectrum analysis of the intermediate frequency signal related to the target distance can be obtained by performing fast Fourier transform on the fast time domain. When f is different frequency modulation periodIFAt constant, i.e. the same distance,. DELTA.fdOnly with respect to the corresponding slow time index between the frequency modulation periods, so that performing a fast fourier transform in the slow time domain results in a doppler shift profile related to the target velocity.
In the above embodiment, the method further includes setting parameters of the millimeter wave radar, as shown in fig. 1, where the parameters include a frequency modulation starting frequency f0Chirp slope K, transmit antenna start time TTX-startIdle time TidleTime of frequency modulation TrampIntegral chirp period Tc, ADC effective start time TADC-startDistance resolution dresMaximum measurable velocity vmaxAnd velocity resolution vres;
wherein: b is the effective bandwidth of the tone, i.e. the bandwidth in the sampling time, which can be expressed as:c is the speed of light, and lambda is the wavelength corresponding to the center of frequency modulation.
In practical implementation, among the parameters, the frequency modulation starting frequency f077-79GHz, frequency modulation slope K of 20MHz/us, and start time of transmitting antenna of TTX-startIs 10us, idle time Tidle20us, frequency modulation time Tramp100us, overall chirp period Tc130us, ADC effective start time TADC-start15us, distance resolution dres7.5cm, maximum measurable velocity vmaxIs + -14 m/s, velocity resolution vresIs 0.068 m/s.
In the above embodiment, the constant false alarm detector employs CA-CFAR to filter out data greater than the threshold T during the detection process.
In the above embodiment, the bandwidth of the effective bandwidth is not less than 2 GHz. The higher the bandwidth of the effective bandwidth modulation is actually implemented, the better the bandwidth is, if the bandwidth of the effective bandwidth modulation is lower than 2GHz, the requirement of the distance resolution cannot be met, the deviation value of the distance judgment of the target object is increased, and the correct judgment of the target object track cannot be realized.
In the above embodiment, the threshold value T satisfies the following formula:
T=a·Pn,
where a represents the threshold factor and Pn represents the power noise estimate.
In the above embodiment, the threshold factor is stored in the learning network, and the threshold factor is continuously corrected by the learning network, so as to improve the detection accuracy of the movement track of the target object. In practice, the threshold factor may be manually switched to a preset value according to the working environment, and the preset value includes a plurality of point values preset according to the actual environment.
The principle and the implementation mode of the invention are explained by applying specific embodiments in the invention, and the description of the embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (8)
1. A gesture recognition method based on a millimeter wave radar is characterized by comprising the following steps:
s1, acquiring and processing echo signals to obtain intermediate frequency signal data;
s2, extracting intermediate frequency signal data, arranging the data in the same frame according to a Chirp signal to obtain a plurality of first information matrixes, and performing windowing processing and FFT processing on the data in the same Chirp signal to obtain distance dimension information of a target object;
s3, filtering the binary data acquired by the radar to obtain a second information matrix, and then performing FFT processing on Chirp in each frame to obtain speed dimension information of the target object;
s4, processing the speed dimension information and the distance dimension information by adopting a constant false alarm detector to obtain the distance characteristic and the speed characteristic of the target object in each frame;
s5, splicing the distance characteristics and the speed characteristics obtained by each frame to form distance-time characteristics, speed-time characteristics and speed-distance characteristics, representing the movement trend of the target relative to the radar according to the distance-time characteristics, namely detecting the approaching or the departing of the target, wherein the speed-time characteristics represent the movement speed of the target relative to the radar, the positive is approaching, and the negative is departing, the distance-speed characteristics reflect the distribution of the target speed on different distances, so that the movement track of the target is obtained to realize action judgment, and further realize gesture recognition;
and S6, remotely controlling the vehicle based on the gesture recognition result.
2. The millimeter wave radar-based gesture recognition method according to claim 1, further comprising setting parameters of the millimeter wave radar, wherein the parameters comprise a frequency modulation starting frequency f0Chirp slope K, transmit antenna start time TTX-startIdle time TidleTime of frequency modulation TrampIntegral chirp period Tc, ADC effective start time TADC-startDistance resolution dresMaximum measurable velocity vmaxAnd velocity resolution vres;
3. The millimeter wave radar-based gesture recognition method according to claim 2, wherein the constant false alarm detector employs CA-CFAR to filter out data larger than a threshold T during detection.
4. The millimeter wave radar-based gesture recognition method according to claim 2, wherein a bandwidth of the effective bandwidth is not less than 2 GHz.
5. The millimeter wave radar-based gesture recognition method according to claim 2, wherein the threshold T satisfies the following formula:
T=a·Pn,
where a represents the threshold factor and Pn represents the power noise estimate.
6. The millimeter wave radar-based gesture recognition method according to claim 2, wherein the parameter is a frequency modulation starting frequency f077-79GHz, frequency modulation slope K of 20MHz/us, starting time of transmitting antenna TTX-start10us, idle time Tidle20us, frequency modulation time Tramp100us, overall chirp period Tc130us, ADC effective start time TADC-start15us, distance resolution dres7.5cm, maximum measurable velocity vmaxIs + -14 m/s, velocity resolution vresIs 0.068 m/s.
7. The millimeter wave radar-based gesture recognition method according to claim 5, wherein the threshold factor is a preset value.
8. The millimeter wave radar-based gesture recognition method according to claim 6, wherein the threshold factor is stored in a learning network, and the threshold factor is continuously corrected by the learning network, so that the detection accuracy of the movement track of the target object is improved.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111336250.9A CN114280565A (en) | 2021-11-12 | 2021-11-12 | Gesture recognition method based on millimeter wave radar |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111336250.9A CN114280565A (en) | 2021-11-12 | 2021-11-12 | Gesture recognition method based on millimeter wave radar |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114280565A true CN114280565A (en) | 2022-04-05 |
Family
ID=80869066
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111336250.9A Pending CN114280565A (en) | 2021-11-12 | 2021-11-12 | Gesture recognition method based on millimeter wave radar |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114280565A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117519474A (en) * | 2023-11-06 | 2024-02-06 | 中国人民解放军陆军工程大学 | Radar gesture feature acquisition method considering motion priori |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
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 |
CN112034446A (en) * | 2020-08-27 | 2020-12-04 | 南京邮电大学 | Gesture recognition system based on millimeter wave radar |
CN112782662A (en) * | 2021-01-30 | 2021-05-11 | 湖南森鹰智造科技有限公司 | Dynamic gesture recognition monitoring facilities |
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 |
-
2021
- 2021-11-12 CN CN202111336250.9A patent/CN114280565A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
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 |
CN112034446A (en) * | 2020-08-27 | 2020-12-04 | 南京邮电大学 | Gesture recognition system based on millimeter wave radar |
CN112782662A (en) * | 2021-01-30 | 2021-05-11 | 湖南森鹰智造科技有限公司 | Dynamic gesture recognition monitoring facilities |
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 |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117519474A (en) * | 2023-11-06 | 2024-02-06 | 中国人民解放军陆军工程大学 | Radar gesture feature acquisition method considering motion priori |
CN117519474B (en) * | 2023-11-06 | 2024-05-14 | 中国人民解放军陆军工程大学 | Radar gesture feature acquisition method considering motion priori |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110765974B (en) | Micro gesture recognition method based on millimeter wave radar and convolutional neural network | |
CN103176178B (en) | Radar moving target radon-fractional Fourier transform long-time phase-coherent accumulation detection method | |
Hyun et al. | Moving and stationary target detection scheme using coherent integration and subtraction for automotive FMCW radar systems | |
WO2021077287A1 (en) | Detection method, detection device, and storage medium | |
CN107167797B (en) | Digital railway hump speed measuring radar and anti-interference method thereof | |
CN112764036A (en) | Adaptive multi-mode vehicle-mounted radar system and design method | |
CN109474890A (en) | A kind of indoor objects passive tracking method based on WiFi Doppler frequency shift | |
CN214041733U (en) | Self-adaptive multi-mode vehicle-mounted radar system | |
CN110320509A (en) | A kind of millimetre-wave radar object detection method and system | |
CN103529438A (en) | System and method for monitoring moving target on ground by marine radar | |
CN113963441A (en) | Cross-domain enhancement-based millimeter wave radar gesture recognition method and system | |
CN114280565A (en) | Gesture recognition method based on millimeter wave radar | |
Cai et al. | Foreign objects intrusion detection using millimeter wave radar on railway crossings | |
CN110531332B (en) | Low-altitude slow-speed small target detection method based on segmentation threshold | |
CN111316126B (en) | Target detection method, radar, vehicle, and computer-readable storage medium | |
Darlis et al. | Performance Analysis of 77 GHz mmWave Radar Based Object Behavior. | |
CN107783132B (en) | Anti-collision millimeter wave radar system for automatic driving automobile and signal processing method | |
CN109085568B (en) | Frequency modulation continuous wave multi-target detection method based on secondary frequency mixing | |
CN112859059A (en) | Target detection and tracking system and method | |
CN111781561A (en) | Method for controlling upper computer and displaying target of civil millimeter wave radar | |
CN103605128B (en) | A kind of speed-measuring method and device | |
CN115792884A (en) | Personnel detection system and method based on FMCW radar | |
CN111699409B (en) | Millimeter wave radar weather detection method, millimeter wave radar and movable platform | |
KR20140064489A (en) | Target recognition based on track information | |
KR101617433B1 (en) | Apparatus and method for detecting intruder based on frequency modulated continuous wave |
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 |