CN116992266A - Living body detection method applied to vehicle and electronic equipment - Google Patents
Living body detection method applied to vehicle and electronic equipment Download PDFInfo
- Publication number
- CN116992266A CN116992266A CN202311253828.3A CN202311253828A CN116992266A CN 116992266 A CN116992266 A CN 116992266A CN 202311253828 A CN202311253828 A CN 202311253828A CN 116992266 A CN116992266 A CN 116992266A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- living body
- radar
- determining
- scene
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 claims abstract description 38
- 230000036391 respiratory frequency Effects 0.000 claims abstract description 24
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 16
- 230000004044 response Effects 0.000 claims abstract description 9
- 238000012545 processing Methods 0.000 claims description 23
- 230000003068 static effect Effects 0.000 claims description 13
- 230000000694 effects Effects 0.000 claims description 12
- 238000009434 installation Methods 0.000 claims description 10
- 239000007787 solid Substances 0.000 claims description 10
- 230000003595 spectral effect Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000009467 reduction Effects 0.000 claims description 5
- 230000002708 enhancing effect Effects 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 230000035565 breathing frequency Effects 0.000 abstract 1
- 238000004891 communication Methods 0.000 description 5
- 230000035484 reaction time Effects 0.000 description 5
- 230000001960 triggered effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000029058 respiratory gaseous exchange Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000001105 regulatory effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000001276 controlling effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 230000002829 reductive effect Effects 0.000 description 2
- 230000000284 resting effect Effects 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 241000282412 Homo Species 0.000 description 1
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 230000002238 attenuated effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000037237 body shape Effects 0.000 description 1
- 230000002612 cardiopulmonary effect Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000005684 electric field Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000001121 heart beat frequency Effects 0.000 description 1
- 238000001727 in vivo Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000241 respiratory effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000005236 sound signal Effects 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The application provides a living body detection method and electronic equipment applied to a vehicle, wherein the method comprises the steps of acquiring a key radar signal, and detecting whether a living body exists or not according to the key radar and a preset frequency range; determining a living body position of the living body with respect to the vehicle-mounted radar in response to the detected living body; if the living body position is in the vehicle, extracting respiratory frequency data in the key radar signal; determining the age of the living body according to the scattering sectional area, the breathing frequency data and the trained convolutional neural network of the living body, which are acquired by the vehicle-mounted radar; if the age of the living body falls within the preset age range, detecting the current vehicle scene of the vehicle and triggering corresponding scene operation according to the detected current vehicle scene. Accurately detecting whether children exist in the vehicle or not through the combination of the radar and a network model algorithm, further detecting the current vehicle scene, and triggering corresponding scene operation; the tragedy caused by the fact that the child is forgotten in the vehicle is avoided, and meanwhile riding experience of the child in the vehicle can be improved.
Description
Technical Field
The application relates to the technical field of automobile safety, in particular to a living body detection method and electronic equipment applied to a vehicle.
Background
With the development of economy, the maintenance quantity of motor vehicles is higher and higher, the motor vehicle market is continuously developed, and the motor vehicle has a plurality of convenience and potential safety hazards.
At present, a solution to the problem of child carryover in automobiles is related, wherein one part is a contact type solution, and the other part is a non-contact type solution; in the non-contact scheme, the camera scheme generally has the problem of privacy information safety, and meanwhile, is easily influenced by shielding, illumination and the like to cause inaccurate detection; while millimeter wave radar schemes have no privacy problem and are little affected by shielding, illumination and the like, millimeter wave radars have the problems of undefined radio frequency band regulations and higher hardware cost for the inside of the vehicle, compared with UWB radars which have no radio frequency band regulation problem and lower hardware cost. However, in the prior art, whether it is a millimeter wave radar or a UWB radar, it is generally only possible to detect whether or not a living body is present in a vehicle, but it is impossible to determine the position of the living body in the vehicle and to estimate the age to distinguish children from adults.
Disclosure of Invention
Based on the above, it is necessary to provide a living body detection method and an electronic device for a vehicle to detect the age of a living body in the vehicle and trigger a corresponding operation according to the age of the living body in the vehicle, so as to solve the problem of child carry-over and increase the experience of the child in the use process of the vehicle.
In a first aspect, the present application provides a living body detection method applied to a vehicle, the method comprising:
acquiring a key radar signal, and detecting whether a living body exists or not according to the key radar and a preset frequency range;
determining a living body position of the living body with respect to an in-vehicle radar in response to the detected living body;
if the living body position is in the vehicle, extracting respiratory frequency data in the key radar signal;
determining the age of the living body according to the scattering sectional area of the living body, the respiratory frequency data and the trained convolutional neural network, which are acquired by the vehicle-mounted radar;
and if the age of the living body falls within a preset age range, detecting the current vehicle scene of the vehicle and triggering corresponding scene operation according to the detected current vehicle scene.
In some embodiments, the determining the living body position of the living body relative to the vehicle-mounted radar includes:
determining a living body angle of the living body relative to the vehicle-mounted radar according to an incident angle of a living body radar signal returned by the living body and received by the vehicle-mounted radar;
determining a living body distance of the living body relative to the vehicle-mounted radar according to the waiting time of the living body radar signal returned by the living body received by the vehicle-mounted radar;
And determining the living body position of the living body relative to the vehicle-mounted radar according to the living body angle and the living body distance.
In some embodiments, the determining the living body position of the living body relative to the vehicle-mounted radar according to the living body angle and the living body distance includes:
if the number of the vehicle-mounted radars is one, dividing the cabin space of the vehicle into four quadrants according to the installation positions of the vehicle-mounted radars;
determining the quadrant position of the living body according to the living body angle and the living body distance of the living body relative to the vehicle-mounted radar;
in some embodiments, the determining the living body position of the living body relative to the vehicle-mounted radar according to the living body angle and the living body distance includes:
if the number of the vehicle-mounted radars is not one, respectively calculating the power spectral density and/or the energy entropy of the vehicle-mounted radars arranged on each row of seats so as to eliminate the influence of the vehicle-mounted radars on the seats other than the vehicle-mounted radars, wherein a plurality of the vehicle-mounted radars are arranged on the central axis of the vehicle and are positioned above each row of seats;
and determining the position of the saddle to which the living body belongs according to the living body angle and the living body distance of the living body relative to the vehicle-mounted radar installed on each row of saddle.
In some embodiments, the calculation of the scattering cross-sectional area of the living body includes:
calculating the power reflected by the living body to the vehicle-mounted radar at each unit solid angle;
and calculating the scattering sectional area of the living body according to the ratio of the power reflected to the vehicle-mounted radar by the living body to the power incident to the living body by the vehicle-mounted radar under each unit solid angle.
In some embodiments, the determining the living body position of the living body relative to the vehicle-mounted radar according to the living body angle and the living body distance further includes:
determining a vehicle body limit according to the cabin space of the vehicle and the installation position of the vehicle-mounted radar, wherein the vehicle body limit comprises the distance of the vehicle body at any angle relative to the vehicle-mounted radar;
and comparing the living body distance under the living body angle with the vehicle body limit, if the living body distance is smaller than or equal to the vehicle body limit, determining that the living body position is in the vehicle, otherwise, determining that the living body position is out of the vehicle.
In some embodiments, the method further comprises:
if the living body position is an off-vehicle position, generating a warning signal;
and triggering a vehicle warning mode according to the generated warning signal, and sending the warning signal to a mobile terminal of a vehicle owner to warn so as to prompt the vehicle owner that suspicious personnel exist outside the vehicle.
In some embodiments, before the acquiring the critical radar signal and detecting whether the living body exists according to the critical radar and the preset frequency range, the method further includes:
starting to set one or more vehicle-mounted radars to acquire original radar signals;
noise reduction processing is carried out on the original radar signals to obtain key radar signals, and the method comprises the following steps:
removing static signal components in the original radar signals, and carrying out normalization processing on the original radar signals after removing the static signals to generate first radar signals;
enhancing vital signs within the first radar signal according to an automatic gain control algorithm to generate a second radar signal;
and eliminating radar signal components with more noise and less vital signs in the second radar signal to generate a key radar signal.
In some embodiments, if the age of the living body falls within a preset age range, detecting a current vehicle scene of the vehicle and triggering a corresponding scene operation according to the detected current vehicle scene, including:
if the current vehicle scene of the vehicle is detected to be an unattended scene, triggering alarm operation;
and triggering a pacifying operation if the current vehicle scene of the vehicle is detected to be a safe activity scene.
In some embodiments, the triggering the alarm operation if the current vehicle scene of the vehicle is detected as an unattended scene includes:
acquiring the current vehicle temperature, the locking time of the current vehicle and the relative distance between the vehicle owner and the vehicle;
and determining the level of the safety alarm and carrying out graded alarm according to the current vehicle temperature, the locking time, the relative distance and the feedback signal of the vehicle owner.
In a second aspect, the present application provides a living body detection system applied to a vehicle, the system comprising:
the data acquisition module is used for acquiring key radar signals;
the vital signal detection module is used for detecting whether a living body exists or not according to the key radar and a preset frequency range;
a living body positioning module for determining a living body position of the living body with respect to an in-vehicle radar in response to the detected living body;
the respiration signal analysis module is used for extracting respiration frequency data in the key radar signal when the living body position is in the vehicle;
the convolutional neural network module is used for determining the age of the living body according to the scattering sectional area of the living body, the respiratory frequency data and the trained convolutional neural network, which are acquired by the vehicle-mounted radar;
And the result processing module is used for detecting the current vehicle scene of the vehicle and triggering corresponding scene operation according to the detected current vehicle scene when the age of the living body falls within a preset age range.
In a third aspect, the present application provides an electronic device, including:
one or more processors;
and a memory associated with the one or more processors, the memory for storing program instructions that, when read for execution by the one or more processors, perform the following:
acquiring a key radar signal, and detecting whether a living body exists or not according to the key radar and a preset frequency range;
determining a living body position of the living body with respect to an in-vehicle radar in response to the detected living body;
if the living body position is in the vehicle, extracting respiratory frequency data in the key radar signal;
determining the age of the living body according to the scattering sectional area of the living body, the respiratory frequency data and the trained convolutional neural network, which are acquired by the vehicle-mounted radar;
and if the age of the living body falls within a preset age range, detecting the current vehicle scene of the vehicle and triggering corresponding scene operation according to the detected current vehicle scene.
The beneficial effects achieved by the application are as follows:
the application provides a living body detection method applied to a vehicle, which comprises the steps of acquiring a key radar signal, and detecting whether a living body exists or not according to the key radar and a preset frequency range; determining a living body position of the living body with respect to an in-vehicle radar in response to the detected living body; if the living body position is in the vehicle, extracting respiratory frequency data in the key radar signal; determining the age of the living body according to the scattering sectional area of the living body, the respiratory frequency data and the trained convolutional neural network, which are acquired by the vehicle-mounted radar; and if the age of the living body falls within a preset age range, detecting the current vehicle scene of the vehicle and triggering corresponding scene operation according to the detected current vehicle scene. The method has the advantages that whether children exist in the vehicle or not is accurately detected through the combination of the radar and the network model algorithm, the current vehicle scene of the vehicle is further detected, and when the current vehicle scene is an unattended scene, alarming operation is timely triggered, so that tragedy caused by the fact that the children are forgotten in the vehicle is effectively avoided; and when the current vehicle scene is a safe activity scene, the pacifying operations such as playing the baby songs are triggered, so that the riding experience of children in the vehicle is improved.
Furthermore, the application can accurately detect the living body position in the vehicle only according to the vehicle-mounted radar arranged in the vehicle without depending on professional medical equipment, thereby reducing the equipment cost.
Furthermore, the application also provides two radar installation schemes and corresponding living body position determining methods, so that the living body detection method provided by the application can be applied to various vehicles, and the applicability of the method provided by the application is improved.
Furthermore, the application also provides a method for estimating the age of the left living body by combining the radar scattering sectional area, the respiratory frequency data and the neural network model so as to prevent the situation that the vehicle is wrongly reported due to the fact that an adult is resting in the vehicle, and further can provide the information of children in the vehicle so as to facilitate the subsequent rescue of the left children.
Furthermore, the application also provides that the detection of the personnel outside the vehicle is realized by utilizing the overflowed radar signal when the position of the living body is detected. When the distance is smaller than the vehicle body limit, the living body is judged to be outside the vehicle, and suspicious personnel approaching the vehicle window are considered to move at the moment to trigger warning so as to provide anti-theft protection for the vehicle.
Furthermore, the application also provides that the original radar signal is processed for a plurality of times, static signal components and noise in the original radar signal are removed, vital signs in the original radar signal are enhanced, and the accuracy of a detection result of whether a living body exists or not according to the finally obtained key radar signal is improved.
Drawings
For a clearer description of the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, it being obvious that the drawings in the description below are only some embodiments of the present application, and that other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art, wherein:
FIG. 1 is a schematic diagram of a living body detection method according to an embodiment of the present application;
FIG. 2 is a schematic illustration of a confirmation of a location of a living body according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a convolutional neural network according to an embodiment of the present application;
FIG. 4 is a schematic view of a scattering cross-sectional area according to an embodiment of the present application;
FIG. 5 is a flowchart of a method for in-vivo detection provided by an embodiment of the present application;
FIG. 6 is a schematic diagram of a living body detection system according to an embodiment of the present application;
Fig. 7 is a block diagram of an electronic device according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be understood that throughout this specification and the claims, unless the context clearly requires otherwise, the words "comprise", "comprising", and the like, are to be construed in an inclusive sense as opposed to an exclusive or exhaustive sense; that is, it is the meaning of "including but not limited to".
It should also be appreciated that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Furthermore, in the description of the present application, unless otherwise indicated, the meaning of "a plurality" is two or more.
It should be noted that the terms "S1", "S2", and the like are used for the purpose of describing the steps only, and are not intended to be construed to be specific as to the order or sequence of steps, nor are they intended to limit the present application, which is merely used to facilitate the description of the method of the present application, and are not to be construed as indicating the sequence of steps. In addition, the technical solutions of the embodiments may be combined with each other, but it is necessary to base that the technical solutions can be realized by those skilled in the art, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be considered to be absent and not within the scope of protection claimed in the present application.
As described in the background art, with the development of the motor vehicle market, the safety of the motor vehicle needs to be paid attention to, and especially, the situation that children remain in the motor vehicle to cause the death of the children occurs at present. Therefore, the application provides a living body detection method applied to a vehicle, which carries out safety warning when detecting that the child exists in the vehicle and is in an unattended scene; when the existence of the left child in the car is detected, but in a safe activity scene, a pacifying operation is triggered to improve the riding experience of the child.
Example 1
The embodiment of the application provides a living body detection method applied to a vehicle, and particularly as shown in fig. 1, the detection of a legacy child by using the living body detection method disclosed by the embodiment of the application comprises the following steps:
s1, acquiring a key radar signal, and processing the key radar signal according to a preset frequency range to detect whether a living body exists in a radar irradiation range.
In particular, according to the pseudo-periodic characteristics of cardiopulmonary movements such as human respiration and heartbeat, the application proposes to lock the key radar signal containing effective information within a preset frequency range, for example, within 0.1 to 2 hertz. According to the existing research results in the medical aspect, the frequency range of the physiological signals of the human body is generally lower, and the spectrum analysis proves that the frequency spectrum of other electrophysiological signals is generally lower except that the frequency spectrum component of the sound signals (such as heart sounds) is higher; for example, normal humans have heart beat frequencies between 0.8 and 2 hertz and respiratory frequencies between 0.1 and 0.5 hertz. If radar components in a preset frequency range exist in the key radar signals, indicating that living bodies exist in a radar irradiation range; if radar components within a preset range are not present in the key radar signals, the fact that no living body exists in the radar irradiation range is indicated.
The acquisition of the key radar signals comprises the following steps:
the original radar signals are directly obtained through the vehicle-mounted radar arranged in the vehicle, noise reduction processing is carried out on the original radar signals to obtain key radar signals, and then preprocessing of the original radar signals is completed. Specifically, if a living body exists in the coverage area of the vehicle-mounted radar, the vehicle-mounted radar can acquire a comprehensive signal combined by a plurality of signals such as vital signs, static background clutter, additive white noise of a radar system source, unstable rapid DC, multipath effect noise, reflected radar signals and the like; in order to remove clutter in an original radar signal as much as possible, further acquiring a relatively clean key radar signal containing key information such as vital signs and spatial information; the application provides a series of radar signal processing algorithms such as range profile subtraction, singular value decomposition and the like to filter out parts with smaller changes and remove rapidly-changing noise or interference, thereby extracting more remarkable characteristics.
A specific implementation may be to process by filtering the static signal components generated by multipath reflections of the human extremities, torso and stationary objects and independent of vital signs, and then to perform linear trend removal. And further carrying out normalization processing on the original radar signal with the static signal components removed, and eliminating the influence of calculation errors caused by the difference between the characteristics to generate a first radar signal. Further, because the physiological signal of the human body is weak, the environmental noise signal is large, the large noise signal is required to be attenuated, and the physiological signal of the human body is amplified to generate a second radar signal, which can be realized through an AGC (Automatic Gain Control ) algorithm; along with the continuous change of the input first radar signal, the gain is changed along with the continuous change, the proper gain factor and the gain weight of each frequency are regulated, and then each frequency is multiplied by the final gain weight after regulation, so that the optimal demodulation effect is achieved. Finally, the second radar signal is removed for calculation, the signal components with more noise and less vital signs are removed, and the signal components with less vital signs are very difficult to extract effective information due to low signal-to-noise ratio, so that the radar signal components with less vital signs can be removed without further analysis of the signal components, and the purpose of solving resources is realized. Through the processing, the original radar signals are subjected to noise reduction processing to obtain key radar signals, so that weak vital signs are enhanced, and the signal to noise ratio is further improved.
It will be appreciated that there are two types of radar mounting schemes for the vehicle, including a single radar scheme and a multiple radar scheme, where the choice of mounting scheme is determined by the size of the vehicle model. If the vehicle is a four-seat small-sized vehicle, only one vehicle-mounted radar is needed to be installed in the middle of the vehicle, for example, the radar is installed at a central reading lamp in the front row of the vehicle; because the cabin space of the vehicle is smaller, the radar wave can cover the whole vehicle by only using one vehicle-mounted radar and a common omni-directional antenna so as to meet the living body detection requirement. If the vehicle is a large vehicle, such as a three-row SUV, then a single radar signal is insufficient to cover the entire vehicle, resulting in a fault in detecting a legacy living body, i.e., a failure to detect whether a radar blind area exists. In order to uniformly cover the whole vehicle range, when the vehicle is a large-sized vehicle, the application provides that a vehicle-mounted radar is arranged on the central axis of the vehicle and above each row of vehicle seats so as to realize directional detection and further provide a more accurate detection result. Of course, if cost considerations are not taken into account, a multiple radar solution may be used in a small vehicle, i.e. one vehicle radar mounted above both the front and rear seats. In terms of the present technology, the above-mentioned vehicle radar may be a millimeter wave radar or a UWB radar, without excluding other types of radar that may occur in the future. However, for reasons of regulatory control over cost and legitimacy of use, the present application may specify the use of UWB radar in a living body detection method because UWB radar does not have radio frequency regulatory problems with respect to millimeter wave radar and the hardware cost is low.
S2, if the existence of the living body in the radar irradiation range is detected, determining the living body position of the living body.
Specifically, the living body position determination process includes: the living body angle of the vehicle-mounted radar is determined according to the incidence angle of the living body radar signal returned by the living body received by the vehicle-mounted radar, namely, the receiving direction of the living body radar signal is calculated by calculating the phase difference value of the living body radar signal reaching the receiving antennas at different positions, so that the living body angle of the living body relative to the vehicle-mounted radar is determined. Determining the living body distance of the living body relative to the vehicle-mounted radar according to the waiting time of a living body radar signal returned by the vehicle-mounted radar, namely calculating according to the waiting time and the signal propagation speed; further, a living body position of the living body with respect to the in-vehicle radar is determined based on the determined living body angle and living body distance.
It will be appreciated that there are two radar mounting schemes for the disclosed living body detection method, and correspondingly, as shown in fig. 2, there are two living body position determining methods. In the single radar scheme, that is, the number of the vehicle-mounted radars is one, the determining the living body position of the living body relative to the vehicle-mounted radars according to the determined living body angle and the living body distance specifically includes: dividing the cabin space of the vehicle into four quadrants according to the installation position of the vehicle-mounted radar, namely taking the vehicle-mounted radar as an origin, dividing the vehicle-mounted radar on an X-Y axis plane according to angles, for example, setting 0-90 degrees as a first quadrant (corresponding to the left side position of a first row), setting 90-180 degrees as a second quadrant (corresponding to the right side position of the first row), setting 180-270 degrees as a third quadrant (corresponding to the right side position of the second row), and setting 270-360 degrees as a fourth quadrant (corresponding to the left side position of the second row); at this time, the X-Y axis plane (the reference plane can be controlled by the antenna arrangement) is calculated as a horizontal plane, and the quadrant position of the living body is determined by calculating the angle of the living body relative to the radar.
In the multi-radar scheme, that is, the number of the vehicle-mounted radars is not one, the determining the living body position of the living body relative to the vehicle-mounted radars according to the determined living body angle and the living body distance specifically includes: firstly, respectively calculating the power spectral density (PSD, power Spectral Density, PSD) and/or the energy entropy of the vehicle-mounted radar installed on each vehicle seat; when determining radar signals received by the current vehicle-mounted radar on the vehicle seat of the vehicle, screening all received radar signals based on the calculated power spectral density and/or energy entropy of the current radar, and selecting a radar signal matched with the power spectral density and/or the energy entropy of the current radar as an original radar signal so as to eliminate the influence of the vehicle-mounted radar on the non-self vehicle seat. Then, the position of the saddle to which the living body belongs is determined based on the living body angle and the living body distance of the living body with respect to the vehicle-mounted radar mounted on each row of the saddle. For example, assuming that the test vehicle is a 2-row 4-seat domestic car, two radars are respectively responsible for a front row and a rear row, the dual-directional antenna radar judges whether a living body is in the front row or the rear row according to the distance of a living body signal, then the dual-antenna calculates the receiving direction of the signal by calculating the phase difference value of the signal reaching the receiving antenna at different positions so as to determine the direction (the angle on the X-Z axis plane) of the signal relative to the self, and comprehensively judges which side of which row the living body is in, thereby determining the living body position of the living body.
Further, after the position of the living body is determined, it is also necessary to determine whether the determined position of the living body is in the vehicle. At this time, whether the living body position of the living body is in the vehicle is determined based on the living body distance between the living body and the vehicle-mounted radar and the vehicle body limit, which is the vehicle body limit determined based on the cabin space of the vehicle and the installation position of the vehicle-mounted radar, that is, the distance of the vehicle body to the vehicle-mounted radar at each angle. Specifically, the living body distance and the vehicle body limit at the same living body angle are compared, if the living body distance of the living body at each angle does not exceed the vehicle body limit, the living body position of the living body is determined to be in the vehicle, whereas if the living body distance of the living body at each angle exceeds the vehicle body limit, the living body position of the living body is determined to be out of the vehicle.
And S3, if the living body position is in the vehicle, determining the age of the living body according to the acquired scattering sectional area and respiratory frequency data convolution neural network of the living body.
Considering the possibility of an adult resting in a vehicle, the application proposes to take Radar Cross-sectional area data as a main part and respiratory frequency data as an auxiliary part, and send the Radar Cross-sectional area data into a trained convolutional neural network, wherein the trained convolutional neural network is a convolutional neural network module trained by a large number of data sets consisting of RCS values (Radar Cross-Section) and respiratory frequency data, and the output result is an age interval which is classified in advance. As shown in fig. 3, firstly, processing a convolution layer on characteristic data of an input convolution neural network, wherein the convolution layer is composed of a plurality of convolution units, and parameters of each convolution unit are optimized by a back propagation algorithm; after convolution operation, filtering processing is carried out to remove the same data in the characteristic data, and then maximum pooling and average pooling operations are carried out to extract the characteristics, so that the data quantity transferred to the next stage is reduced. As convolutional layers increase, the multi-layer network can extract more complex data features, and finally, the processed feature data (i.e., the extracted features) are fully connected, and the extracted extracts are non-linearly combined to obtain a final output, i.e., the age of the living body. In which, as shown in fig. 4, since the human body shapes are similar, we can estimate whether the target is an adult or a child through RCS differences caused by obvious body type differences between adults and children, so the present application proposes to select the scattering sectional area as the output of the convolutional neural network. The calculation of the scattering sectional area specifically comprises the following steps: using the formula Calculating the power reflected by the living body to the vehicle-mounted radar (specifically, radar receiving antenna) under the unit solid angle, and then calculating the ratio of the power reflected by the living body to the vehicle-mounted radar under the unit solid angle to the power density (per square meter) of the living body, so as to obtain the RCS value of the living body target in the vehicle; which is a kind ofIn the process, the liquid crystal display device comprises a liquid crystal display device,PscatandPincrespectively representing scattering power and incident power of living objects in the vehicle,E inc is the intensity of the incident electric field,η 0 is the wave impedance in a vacuum,f（θ,ϕ）is a scattering amplitude function of a living object in the vehicle, and K is a natural number. The respiratory frequency data can be extracted from the key radar signal by a butterworth filter limited by a specific frequency, wherein the specific frequency is determined according to the respiratory frequency range of a normal person and is 0.1-0.5 Hz, and the specific frequency can be further reduced for acquiring more accurate data.
S4, detecting the current vehicle scene of the vehicle and triggering corresponding scene operation according to the detected current vehicle scene when the age of the living body falls within a preset age range.
The preset age range can be set when the vehicle leaves the factory, and can be preferably set to be 1-10 years old, and the specific preset age range is not limited by the application; if the detected age of the living body falls within a preset age range, i.e. the living body in the vehicle is currently detected as a child, the current vehicle scene in which the vehicle is located is detected to trigger a series of measures for the child. If the current vehicle scene of the vehicle is detected to be an unattended scene, triggering alarm operation; and triggering a pacifying operation if the current vehicle scene of the vehicle is detected to be a safe activity scene.
Detection of a specific vehicle scenario may be achieved by detecting whether a locking operation is present on the vehicle. If the locking operation of the vehicle is detected, the vehicle owner leaves the interior of the vehicle, and the current vehicle scene is determined to be an unattended scene, and an alarm operation is needed. Further, as the temperature of the vehicle, the distance between the driver and the vehicle and the locking time are directly related to the degree of danger left by children, if the output living body age falls within a preset age range, the current vehicle temperature, the locking time of the current vehicle and the relative distance between the vehicle owner and the vehicle are obtained so as to carry out graded warning; the above-mentioned hierarchical alarms can be further divided into initial alarms, medium-level alarms and high-level alarms; when the locking time is less than or equal to a first preset time period, the vehicle temperature is less than or equal to a first preset temperature, and the relative distance is less than or equal to a first preset distance, triggering an initial alarm, and sending alarm information to a mobile terminal of a vehicle owner in a network mode and the like at the moment, wherein the alarm information is mainly reminded in an acousto-optic mode; the first preset time period can be set according to requirements, preferably 20S, the first preset temperature is also set according to requirements, preferably 26 degrees, and the first preset distance is also set according to requirements, preferably 200 meters; the alarm information comprises any one or more of a living body position and a carry-over state, wherein the carry-over state is determined by analyzing the radar wave Doppler effect of a radar signal caused by living body respiration, and comprises a sleep-promoting rest state and a wake-up activity state. If the vehicle owner does not confirm the alarm information within a first preset reaction time after the primary alarm occurs, namely the vehicle owner feedback signal is not received within the first preset reaction time, triggering a middle-level alarm at the moment, and sending the alarm information to the vehicle owner's mobile terminal again, wherein the first preset reaction time is set according to actual conditions, and is preferably set to 1 minute; if the vehicle owner does not confirm the alarm information within the second preset reaction time after the occurrence of the medium-level alarm, namely the vehicle owner feedback signal is not received within the second preset reaction time, the high-level alarm is triggered at the moment, and the vehicle owner actively starts an air conditioner and carries out alarm processing. If the locking operation of the vehicle is not detected, determining that the current vehicle scene is a safe activity scene, and triggering some pacifying operations, such as playing a baby song or playing an animation.
S5, if the living body position is outside the vehicle, determining the age of the living body according to the acquired scattering sectional area and respiratory frequency data convolution neural network of the living body.
Generating a warning signal at this time if the living body position is detected to be outside the vehicle; triggering a vehicle warning mode according to the generated warning signal and sending the warning signal to a mobile terminal of a vehicle owner to prompt the vehicle owner that suspicious personnel exist outside the vehicle; in some scenarios, the vehicle camera may also be turned on directly to record the vehicle surroundings.
It can be understood that the method for detecting living body in the vehicle provided by the application can be started in a mode of one-key buttons, and can be selected by the personnel in the vehicle to confirm whether the method is started or not, or can be displayed in a vehicle-mounted display screen in a mode of man-machine interaction to prompt the personnel in the vehicle to confirm whether the method is started or not, or in a mode of voice prompt to prompt the personnel in the vehicle whether the method is started or not.
Example two
Corresponding to the first embodiment, the present application further provides a living body detection method applied to a vehicle, and the method specifically includes:
5100. acquiring a key radar signal, and detecting whether a living body exists or not according to the key radar and a preset frequency range;
Preferably, before the acquiring the key radar signal and detecting whether the living body exists according to the key radar and the preset frequency range, the method further includes:
5110. starting to set one or more vehicle-mounted radars to acquire original radar signals;
5120. noise reduction processing is carried out on the original radar signals to obtain key radar signals, and the method comprises the following steps:
5130. removing static signal components in the original radar signals, and carrying out normalization processing on the original radar signals after removing the static signals to generate first radar signals;
5140. enhancing vital signs within the first radar signal according to an automatic gain control algorithm to generate a second radar signal;
5150. and eliminating radar signal components with more noise and less vital signs in the second radar signal to generate a key radar signal.
5200. Determining a living body position of the living body with respect to an in-vehicle radar in response to the detected living body;
preferably, the determining the living body position of the living body with respect to the vehicle-mounted radar includes:
5210. determining a living body angle of the living body relative to the vehicle-mounted radar according to an incident angle of a living body radar signal returned by the living body and received by the vehicle-mounted radar;
5220. Determining a living body distance of the living body relative to the vehicle-mounted radar according to the waiting time of the living body radar signal returned by the living body received by the vehicle-mounted radar;
5230. and determining the living body position of the living body relative to the vehicle-mounted radar according to the living body angle and the living body distance.
Preferably, the determining the living body position of the living body relative to the vehicle-mounted radar according to the living body angle and the living body distance includes:
5231. if the number of the vehicle-mounted radars is one, dividing the cabin space of the vehicle into four quadrants according to the installation positions of the vehicle-mounted radars;
5232. determining the quadrant position of the living body according to the living body angle and the living body distance of the living body relative to the vehicle-mounted radar;
preferably, the determining the living body position of the living body relative to the vehicle-mounted radar according to the living body angle and the living body distance includes:
5233. if the number of the vehicle-mounted radars is not one, respectively calculating the power spectral density and/or the energy entropy of the vehicle-mounted radars arranged on each row of seats so as to eliminate the influence of the vehicle-mounted radars on the seats other than the vehicle-mounted radars, wherein a plurality of the vehicle-mounted radars are arranged on the central axis of the vehicle and are positioned above each row of seats;
5234. And determining the position of the saddle to which the living body belongs according to the living body angle and the living body distance of the living body relative to the vehicle-mounted radar installed on each row of saddle.
Preferably, the determining the living body position of the living body relative to the vehicle-mounted radar according to the living body angle and the living body distance further includes:
5235. determining a vehicle body limit according to the cabin space of the vehicle and the installation position of the vehicle-mounted radar, wherein the vehicle body limit comprises the distance of the vehicle body at any angle relative to the vehicle-mounted radar;
5236. and comparing the living body distance under the living body angle with the vehicle body limit, if the living body distance is smaller than or equal to the vehicle body limit, determining that the living body position is in the vehicle, otherwise, determining that the living body position is out of the vehicle.
5300. If the living body position is in the vehicle, extracting respiratory frequency data in the key radar signal;
5400. determining the age of the living body according to the scattering sectional area of the living body, the respiratory frequency data and the trained convolutional neural network, which are acquired by the vehicle-mounted radar;
preferably, the calculation of the scattering cross-sectional area of the living body includes:
5410. Calculating the power reflected by the living body to the vehicle-mounted radar at each unit solid angle;
5420. and calculating the scattering sectional area of the living body according to the ratio of the power reflected to the vehicle-mounted radar by the living body to the power incident to the living body by the vehicle-mounted radar under each unit solid angle.
5500. And if the age of the living body falls within a preset age range, detecting the current vehicle scene of the vehicle and triggering corresponding scene operation according to the detected current vehicle scene.
Preferably, if the age of the living body falls within a preset age range, detecting a current vehicle scene of the vehicle and triggering a corresponding scene operation according to the detected current vehicle scene, including:
5510. if the current vehicle scene of the vehicle is detected to be an unattended scene, triggering alarm operation;
preferably, if the current vehicle scene of the detected vehicle is an unattended scene, an alarm operation is triggered, including:
5511. acquiring the current vehicle temperature, the locking time of the current vehicle and the relative distance between the vehicle owner and the vehicle;
5512. and determining the level of the safety alarm and carrying out graded alarm according to the current vehicle temperature, the locking time, the relative distance and the feedback signal of the vehicle owner.
5520. And triggering a pacifying operation if the current vehicle scene of the vehicle is detected to be a safe activity scene.
Preferably, the method further comprises:
5600. if the living body position is an off-vehicle position, generating a warning signal;
5700. and triggering a vehicle warning mode according to the generated warning signal, and sending the warning signal to a mobile terminal of a vehicle owner to warn so as to prompt the vehicle owner that suspicious personnel exist outside the vehicle.
Example III
Corresponding to the first and second embodiments, as shown in fig. 6, an embodiment of the present application further provides a living body detection system applied to a vehicle, including:
a data acquisition module 610, configured to acquire a key radar signal;
a vital signal detection module 620, configured to detect whether a living body exists according to the key radar and a preset frequency range;
a living body positioning module 630 for determining a living body position of the living body with respect to an in-vehicle radar in response to the detected living body;
the respiratory signal analysis module 640 is configured to extract respiratory frequency data in the key radar signal when the living body position is in the vehicle;
a convolutional neural network module 650 for determining an age of the living body according to the scattering cross-sectional area of the living body acquired by the vehicle-mounted radar, the respiratory frequency data, and a trained convolutional neural network;
The result processing module 660 is configured to detect a current vehicle scene of a vehicle and trigger a corresponding scene operation according to the detected current vehicle scene when the age of the living body falls within a preset age range.
In some implementations, the living body positioning module 630 is further configured to determine a living body angle of the living body relative to the vehicle-mounted radar according to an incident angle of the living body radar signal received by the vehicle-mounted radar; the living body positioning module is also used for determining the living body distance of the living body relative to the vehicle-mounted radar according to the waiting time of the living body radar signal returned by the living body and received by the vehicle-mounted radar; the living body positioning module is also used for determining the living body position of the living body relative to the vehicle-mounted radar according to the living body angle and the living body distance.
In some implementations, the living body positioning module 630 is further configured to divide the cabin space of the vehicle into four quadrants according to the installation position of the vehicle-mounted radar when the number of the vehicle-mounted radars is one; and determining the quadrant position of the living body according to the living body angle and the living body distance of the living body relative to the vehicle-mounted radar.
In some implementations, the living body positioning module 630 is further configured to calculate, when the number of the vehicle-mounted radars is not one, a power spectral density and/or an energy entropy of the vehicle-mounted radars mounted on each row of seats to exclude an influence of the vehicle-mounted radars on non-self-row seats, where a plurality of the vehicle-mounted radars are mounted on a central axis of the vehicle and above each row of seats; and determining the position of the saddle to which the living body belongs according to the living body angle and the living body distance of the living body relative to the vehicle-mounted radar installed on each row of saddle.
In some implementations, the system further includes a cross-sectional scattering area calculation module 670 for calculating power reflected by the living body to the vehicle radar per unit solid angle; and calculating the scattering sectional area of the living body according to the ratio of the power reflected to the vehicle-mounted radar by the living body to the power incident to the living body by the vehicle-mounted radar under each unit solid angle.
In some implementations, the living positioning module 630 is further configured to determine a body boundary from a cabin space of the vehicle and a mounting location of the onboard radar, wherein the body boundary includes a distance of the body at any angle relative to the onboard radar; the living body positioning module is further used for comparing the living body distance under the living body angle with the vehicle body limit, if the living body distance is smaller than or equal to the vehicle body limit, determining that the living body position is in the vehicle, otherwise, determining that the living body position is out of the vehicle.
In some embodiments, the result processing module 660 is further configured to generate an alert signal when the living body position is an off-vehicle position; and triggering a vehicle warning mode according to the generated warning signal, and sending the warning signal to a mobile terminal of a vehicle owner to warn so as to prompt the vehicle owner that suspicious personnel exist outside the vehicle.
In some implementations, the data acquisition module 610 is further configured to reject a static signal component in the original radar signal, and normalize the original radar signal after the static signal is rejected to generate a first radar signal; enhancing vital signs within the first radar signal according to an automatic gain control algorithm to generate a second radar signal; and eliminating radar signal components with more noise and less vital signs in the second radar signal to generate a key radar signal.
In some implementation scenarios, the result processing module 660 is further configured to trigger an alarm operation when it is detected that the current vehicle scenario of the vehicle is an unattended scenario; and triggering a pacifying operation when detecting that the current vehicle scene of the vehicle is a safe activity scene.
In some implementations, the result processing module 66 is further configured to obtain a current vehicle temperature, a current vehicle locking time, and a relative distance between the vehicle owner and the vehicle; and determining the level of the safety alarm and carrying out graded alarm according to the current vehicle temperature, the locking time, the relative distance and the feedback signal of the vehicle owner.
Example IV
Corresponding to all the embodiments described above, an embodiment of the present application provides an electronic device, including: one or more processors; and a memory associated with the one or more processors, the memory for storing program instructions that, when read for execution by the one or more processors, perform the following:
acquiring a key radar signal, and detecting whether a living body exists or not according to the key radar and a preset frequency range;
determining a living body position of the living body with respect to an in-vehicle radar in response to the detected living body;
if the living body position is in the vehicle, extracting respiratory frequency data in the key radar signal;
determining the age of the living body according to the scattering sectional area of the living body, the respiratory frequency data and the trained convolutional neural network, which are acquired by the vehicle-mounted radar;
and if the age of the living body falls within a preset age range, detecting the current vehicle scene of the vehicle and triggering corresponding scene operation according to the detected current vehicle scene.
Fig. 7 illustrates an architecture of an electronic device, which may include a processor 710, a video display adapter 711, a disk drive 712, an input/output interface 713, a network interface 714, and a memory 720, among others. The processor 710, the video display adapter 711, the disk drive 712, the input/output interface 713, the network interface 714, and the memory 720 may be communicatively connected via a bus 730.
The processor 710 may be implemented by a general-purpose CPU (Central Processing Unit ), a microprocessor, an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, etc., for executing related programs to implement the technical scheme provided by the present application.
The Memory 720 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory ), static storage device, dynamic storage device, or the like. The memory 720 may store an operating system 721 for controlling the execution of the electronic device 700, and a Basic Input Output System (BIOS) 722 for controlling the low-level operation of the electronic device 700. In addition, a web browser 723, a data storage management system 724, an icon font processing system 725, and the like may also be stored. The icon font processing system 725 may be an application program that specifically implements the operations of the foregoing steps in the embodiment of the present application. In general, when the technical solution provided by the present application is implemented by software or firmware, relevant program codes are stored in the memory 720 and invoked by the processor 710 for execution.
The input/output interface 713 is used to connect with an input/output module to enable information input and output. The input/output module may be configured as a component in a device (not shown) or may be external to the device to provide corresponding functionality. Wherein the input devices may include a keyboard, mouse, touch screen, microphone, various types of sensors, etc., and the output devices may include a display, speaker, vibrator, indicator lights, etc.
The network interface 714 is used to connect communication modules (not shown) to enable communication interactions of the device with other devices. The communication module may implement communication through a wired manner (such as USB, network cable, etc.), or may implement communication through a wireless manner (such as mobile network, WIFI, bluetooth, etc.).
Bus 730 includes a path to transfer information between various components of the device (e.g., processor 710, video display adapter 711, disk drive 712, input/output interface 713, network interface 714, and memory 720).
In addition, the electronic device 700 may also obtain information of specific acquisition conditions from the virtual resource object acquisition condition information database, for performing condition judgment, and so on.
It should be noted that although the above devices illustrate only the processor 710, the video display adapter 711, the disk drive 712, the input/output interface 713, the network interface 714, the memory 720, the bus 730, etc., the device may include other components necessary to achieve normal execution in an implementation. Furthermore, it will be appreciated by those skilled in the art that the apparatus may include only the components necessary to implement the present application, and not all of the components shown in the drawings.
From the above description of embodiments, it will be apparent to those skilled in the art that the present application may be implemented in software plus a necessary general hardware platform. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., and includes several instructions for causing a computer device (which may be a personal computer, a cloud server, or a network device, etc.) to execute the method described in the embodiments or some parts of the embodiments of the present application.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for a system or system embodiment, since it is substantially similar to a method embodiment, the description is relatively simple, with reference to the description of the method embodiment being made in part. The systems and system embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present application without undue burden.
The foregoing description of the preferred embodiments of the application is not intended to limit the application to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the application are intended to be included within the scope of the application.
Claims (10)
1. A living body detection method applied to a vehicle, characterized by comprising:
acquiring a key radar signal, and detecting whether a living body exists or not according to the key radar signal and a preset frequency range;
determining a living body position of the living body with respect to an in-vehicle radar in response to the detected living body;
if the living body position is in the vehicle, extracting respiratory frequency data in the key radar signal;
determining the age of the living body according to the scattering sectional area of the living body, the respiratory frequency data and the trained convolutional neural network, which are acquired by the vehicle-mounted radar;
and if the age of the living body falls within a preset age range, detecting the current vehicle scene of the vehicle and triggering corresponding scene operation according to the detected current vehicle scene.
2. The method of claim 1, wherein the determining the living body position of the living body relative to an in-vehicle radar comprises:
determining a living body angle of the living body relative to the vehicle-mounted radar according to an incident angle of a living body radar signal returned by the living body and received by the vehicle-mounted radar;
determining a living body distance of the living body relative to the vehicle-mounted radar according to the waiting time of the living body radar signal returned by the living body received by the vehicle-mounted radar;
And determining the living body position of the living body relative to the vehicle-mounted radar according to the living body angle and the living body distance.
3. The method according to claim 2, wherein the determining the living body position of the living body with respect to the vehicle-mounted radar based on the living body angle and the living body distance includes:
if the number of the vehicle-mounted radars is one, dividing the cabin space of the vehicle into four quadrants according to the installation positions of the vehicle-mounted radars;
and determining the quadrant position of the living body according to the living body angle and the living body distance of the living body relative to the vehicle-mounted radar.
4. The method according to claim 2, wherein the determining the living body position of the living body with respect to the vehicle-mounted radar based on the living body angle and the living body distance includes:
if the number of the vehicle-mounted radars is not one, respectively calculating the power spectral density and/or the energy entropy of the vehicle-mounted radars arranged on each row of seats so as to eliminate the influence of the vehicle-mounted radars on the seats other than the vehicle-mounted radars, wherein a plurality of the vehicle-mounted radars are arranged on the central axis of the vehicle and are positioned above each row of seats;
and determining the position of the saddle to which the living body belongs according to the living body angle and the living body distance of the living body relative to the vehicle-mounted radar installed on each row of saddle.
5. The method according to claim 1, wherein the calculation of the scattering cross-sectional area of the living body includes:
calculating the power reflected by the living body to the vehicle-mounted radar at each unit solid angle;
and calculating the scattering sectional area of the living body according to the ratio of the power reflected to the vehicle-mounted radar by the living body to the power incident to the living body by the vehicle-mounted radar under each unit solid angle.
6. The method according to claim 2, wherein the determining the living body position of the living body with respect to the vehicle-mounted radar based on the living body angle and the living body distance further includes:
determining a vehicle body limit according to the cabin space of the vehicle and the installation position of the vehicle-mounted radar, wherein the vehicle body limit comprises the distance of the vehicle body at any angle relative to the vehicle-mounted radar;
and comparing the living body distance under the living body angle with the vehicle body limit, if the living body distance is smaller than or equal to the vehicle body limit, determining that the living body position is in the vehicle, otherwise, determining that the living body position is out of the vehicle.
7. The method according to claim 6, further comprising:
If the living body position is an off-vehicle position, generating a warning signal;
and triggering a vehicle warning mode according to the generated warning signal, and sending the warning signal to a mobile terminal of a vehicle owner to warn so as to prompt the vehicle owner that suspicious personnel exist outside the vehicle.
8. The method of any of claims 1-7, wherein the acquiring the critical radar signal and detecting whether a living organism is present based on the critical radar signal and a predetermined frequency range, the method further comprises:
starting to set one or more vehicle-mounted radars to acquire original radar signals;
noise reduction processing is carried out on the original radar signals to obtain key radar signals, and the method comprises the following steps:
removing static signal components in the original radar signals, and carrying out normalization processing on the original radar signals after removing the static signals to generate first radar signals;
enhancing vital signs within the first radar signal according to an automatic gain control algorithm to generate a second radar signal;
and eliminating radar signal components with more noise and less vital signs in the second radar signal to generate a key radar signal.
9. The method according to any one of claims 1 to 7, wherein if the age of the living body falls within a preset age range, detecting a current vehicle scene of a vehicle and triggering a corresponding scene operation according to the detected current vehicle scene, comprising:
If the current vehicle scene of the vehicle is detected to be an unattended scene, triggering alarm operation;
and triggering a pacifying operation if the current vehicle scene of the vehicle is detected to be a safe activity scene.
10. An electronic device, the electronic device comprising:
one or more processors;
and a memory associated with the one or more processors, the memory for storing program instructions that, when read for execution by the one or more processors, perform the method of any of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311253828.3A CN116992266A (en) | 2023-09-27 | 2023-09-27 | Living body detection method applied to vehicle and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311253828.3A CN116992266A (en) | 2023-09-27 | 2023-09-27 | Living body detection method applied to vehicle and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116992266A true CN116992266A (en) | 2023-11-03 |
Family
ID=88523537
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311253828.3A Pending CN116992266A (en) | 2023-09-27 | 2023-09-27 | Living body detection method applied to vehicle and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116992266A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018183546A1 (en) * | 2017-03-28 | 2018-10-04 | Sri International | Identification system for subject or activity identification using range and velocity data |
| CN111856592A (en) * | 2020-08-20 | 2020-10-30 | 江西商思伏沌科技有限公司 | Indoor living body monitoring device and method |
| CN212540743U (en) * | 2020-08-20 | 2021-02-12 | 江西商思伏沌科技有限公司 | In-vehicle living body loss monitoring device |
| CN113805165A (en) * | 2021-09-18 | 2021-12-17 | 无锡威孚高科技集团股份有限公司 | In-vehicle life body remaining detection method and device and vehicle safety control method and device |
| CN114527463A (en) * | 2022-04-24 | 2022-05-24 | 南京楚航科技有限公司 | In-vehicle living body detection method and device by utilizing phase matching |
| CN115067915A (en) * | 2022-05-27 | 2022-09-20 | 芜湖易来达雷达科技有限公司 | In-vehicle living body detection and alarm method based on millimeter wave radar |
| CN217468806U (en) * | 2022-07-06 | 2022-09-20 | 宁波均联智行科技股份有限公司 | Dual-band WiFi antenna and wireless communication device |
| US20230192035A1 (en) * | 2021-12-21 | 2023-06-22 | Veoneer Us, Llc | Child presence detection warning suppression |
-
2023
- 2023-09-27 CN CN202311253828.3A patent/CN116992266A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018183546A1 (en) * | 2017-03-28 | 2018-10-04 | Sri International | Identification system for subject or activity identification using range and velocity data |
| CN111856592A (en) * | 2020-08-20 | 2020-10-30 | 江西商思伏沌科技有限公司 | Indoor living body monitoring device and method |
| CN212540743U (en) * | 2020-08-20 | 2021-02-12 | 江西商思伏沌科技有限公司 | In-vehicle living body loss monitoring device |
| CN113805165A (en) * | 2021-09-18 | 2021-12-17 | 无锡威孚高科技集团股份有限公司 | In-vehicle life body remaining detection method and device and vehicle safety control method and device |
| US20230192035A1 (en) * | 2021-12-21 | 2023-06-22 | Veoneer Us, Llc | Child presence detection warning suppression |
| CN114527463A (en) * | 2022-04-24 | 2022-05-24 | 南京楚航科技有限公司 | In-vehicle living body detection method and device by utilizing phase matching |
| CN115067915A (en) * | 2022-05-27 | 2022-09-20 | 芜湖易来达雷达科技有限公司 | In-vehicle living body detection and alarm method based on millimeter wave radar |
| CN217468806U (en) * | 2022-07-06 | 2022-09-20 | 宁波均联智行科技股份有限公司 | Dual-band WiFi antenna and wireless communication device |
Non-Patent Citations (1)
| Title |
|---|
| 高欣宇;张文博;姬红兵;欧阳成;: "新型雷达辐射源识别", 中国图象图形学报, no. 06 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110023780B (en) | Polarized radar system and method for detecting and classifying vehicle occupants and other objects within a vehicle | |
| US11262233B2 (en) | System and method for detecting surface vibrations | |
| US8593279B2 (en) | System for detecting persons in a defined space | |
| US10322728B1 (en) | Method for distress and road rage detection | |
| US8957779B2 (en) | Drowsy driver detection system | |
| US20190046120A1 (en) | In vehicle non-contact heartbeat and breath sensing system | |
| CN105452898A (en) | Radar sensing of vehicle occupancy | |
| CN113945913A (en) | Method for detecting personnel in vehicle based on millimeter wave radar point cloud | |
| US20160189547A1 (en) | Driving Safety System and Barrier Screening Method Thereof | |
| US20200298731A1 (en) | Vehicle seat operation | |
| US20210209386A1 (en) | Radar-based monitoring in a vehicle | |
| US10422874B2 (en) | Method and system for spatial modeling of an interior of a vehicle | |
| CN116992266A (en) | Living body detection method applied to vehicle and electronic equipment | |
| CN113406613B (en) | Personnel detection method, device, equipment and storage medium | |
| CN111232778B (en) | Method and device for counting number of people in elevator car | |
| JP2021122300A (en) | Biological condition detector, and biological condition detection method | |
| ho Huh et al. | Seat belt reminder system in vehicle using IR-UWB radar | |
| Saeed et al. | A novel extension for e-Safety initiative based on developed fusion of biometric traits | |
| CN106379230A (en) | Vehicle sound reminding system | |
| US20230326324A1 (en) | In-vehicle monitoring device, in-vehicle monitoring system, and in-vehicle monitoring method | |
| US10836256B2 (en) | Enhanced touchscreen operation | |
| CN114460658A (en) | Biological detection device | |
| JP2021071326A (en) | Signal processing system and sensor system | |
| CN112614308A (en) | Life detecting system in vehicle | |
| CN111564044A (en) | Parking space state detection method and system |
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 |