Height measurement method, device and equipment based on millimeter wave radar and storage medium

Abstract

The invention discloses a height measuring method, device and equipment based on a millimeter wave radar and a storage medium. The method comprises the following steps: acquiring a radar echo signal of a target indoor space; performing target detection according to the radar echo signal to obtain initial point cloud data; performing target tracking according to the initial point cloud data to obtain target point cloud data; identifying a target motion state according to the radar echo signal and the target point cloud data; determining a target body posture according to the target point cloud data; and determining height measurement data according to the corresponding target point cloud data when the target motion state and the target body posture meet a preset measurement condition. According to the technical scheme provided by the invention, the height can be continuously, automatically and effectively measured in a complex home environment, a user does not need to assemble in any form or have special technical knowledge, other help is not needed, and the measurement requirement is reduced.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of measurement technology, and in particular to a height measurement method, device, equipment and storage medium based on millimeter wave radar. Background Art

[0002] Height measurement is a basic anthropometric task, which has important application value in many fields such as medicine, sports, clothing design and ergonomics. Accurate height data is essential for assessing the physical health and development level of an individual, and it can also serve as an important reference for formulating personalized plans. In modern society, with the increasing attention paid to individual needs, accurate height data has become a basic element to support more efficient and accurate services in these fields.

[0003] Traditional height measurement methods have many limitations in terms of accuracy and convenience. When using a height meter or tape measure for manual measurement, it is easily affected by the operator's subjective error and is difficult to complete independently. Although laser rangefinders improve measurement accuracy, they are expensive and require certain technical operations, which increases the complexity of use. Although visual sensors such as depth cameras and mobile phones can capture three-dimensional contours, they are prone to interference in poor lighting conditions or complex backgrounds, affecting the accuracy of measurements. Although ultrasonic sensors can perform non-contact measurements, they are prone to misjudgment in the presence of environmental noise and obstacles, reducing the reliability of measurements. On the other hand, height measurement usually requires the subject to remain stationary and requires the subject to be measured according to certain constraints. For elderly people at home, changes in height will reflect their physical aging changes or physical illnesses, and are a must-check item for physical examinations. In this case, traditional height measurement technology has great limitations. Summary of the invention

[0004] The embodiments of the present invention provide a height measurement method, device, equipment and storage medium based on millimeter wave radar to achieve continuous, automatic and effective measurement of height in a complex home environment without restraining the body of the measured object.

[0005] In a first aspect, an embodiment of the present invention provides a height measurement method based on millimeter wave radar, the method comprising:

[0006] Acquire radar echo signals of the target indoor space;

[0007] Perform target detection according to the radar echo signal to obtain initial point cloud data;

[0008] Perform target tracking according to the initial point cloud data to obtain target point cloud data;

[0009] Identify the target motion state according to the radar echo signal and the target point cloud data;

[0010] determining a target body posture according to the target point cloud data;

[0011] The height measurement data is determined according to the target point cloud data corresponding to the target motion state and the target body posture when the preset measurement conditions are met.

[0012] Optionally, before performing target detection according to the radar echo signal, the method further includes:

[0013] Preprocessing the radar echo signal;

[0014] The pre-processing comprises:

[0015] Clutter suppression is performed based on a single frame echo signal, and a fast Fourier transform in a slow time dimension is performed to obtain a first echo signal;

[0016] Clutter suppression is performed based on the accumulation of multiple frames of echo signals, and a fast Fourier transform in the slow time dimension is performed to obtain a second echo signal.

[0017] Optionally, performing target detection according to the radar echo signal to obtain initial point cloud data includes:

[0018] According to the first echo signal and the second echo signal, a constant false alarm algorithm is used to detect and obtain target range-Doppler information;

[0019] Based on the target range-Doppler information, according to the first echo signal and the second echo signal, a spatial domain beamforming algorithm is used to estimate the target angle information;

[0020] The initial point cloud data in a rectangular coordinate system is generated according to the target range-Doppler information and the target angle information.

[0021] Optionally, the identifying the target motion state according to the radar echo signal and the target point cloud data includes:

[0022] Averaging the first echo signal with respect to the antenna dimension to obtain a range-Doppler signal;

[0023] Acquire the distance unit of the target point cloud data;

[0024] The target distance units corresponding to the range-Doppler signal in the distance units are superimposed and accumulated in multiple frames to obtain a time-frequency diagram;

[0025] Determine the sum of signal energy within a preset frequency threshold according to the time-frequency diagram;

[0026] The signal energy sum is compared with a corresponding preset threshold, and the target motion state is determined according to the comparison result.

[0027] Optionally, determining the target body posture according to the target point cloud data includes:

[0028] Constructing a covariance matrix according to the target point cloud data;

[0029] Performing eigenvalue decomposition on the covariance matrix to obtain an eigenvector;

[0030] Calculating the angle between the characteristic vector and a preset normal line as a tilt angle;

[0031] Determine the height difference between the highest point cloud and the lowest point cloud, and the number of point clouds according to the target point cloud data;

[0032] The target body posture is determined by using a trained classifier according to the height difference, the number of point clouds and the tilt angle.

[0033] Optionally, determining height measurement data according to the target point cloud data corresponding to the target motion state and the target body posture when the preset measurement conditions are met includes:

[0034] If the target motion state and the target body posture meet the preset measurement conditions, start calculating the height of the single-frame target point cloud data until the target motion state changes, and obtain the original height sequence;

[0035] Collecting a plurality of the original height sequences and merging them to obtain a target height sequence;

[0036] The maximum value in the target height sequence is used as the first cluster center for clustering to divide the target height sequence into multiple clusters, and the arithmetic mean of the highest cluster data is taken as the height measurement data.

[0037] In a second aspect, an embodiment of the present invention further provides a height measurement device based on millimeter wave radar, the device comprising:

[0038] A signal acquisition module, used to acquire radar echo signals of the target indoor space;

[0039] A target detection module, used to perform target detection according to the radar echo signal to obtain initial point cloud data;

[0040] A target tracking module, used to track the target according to the initial point cloud data to obtain target point cloud data;

[0041] A state recognition module, used for identifying the target motion state according to the radar echo signal and the target point cloud data;

[0042] A posture determination module, used to determine the target body posture according to the target point cloud data;

[0043] The height measurement module is used to determine the height measurement data according to the target point cloud data corresponding to the target motion state and the target body posture when the preset measurement conditions are met.

[0044] In a third aspect, an embodiment of the present invention further provides a computer device, the computer device comprising:

[0045] one or more processors;

[0046] A memory for storing one or more programs;

[0047] When the one or more programs are executed by the one or more processors, the one or more processors implement the height measurement method based on millimeter wave radar provided in any embodiment of the present invention.

[0048] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the height measurement method based on millimeter-wave radar provided in any embodiment of the present invention.

[0049] In a fifth aspect, an embodiment of the present invention further provides a computer program product, which includes a computer program, and when the program is executed by a processor, it implements the height measurement method based on millimeter wave radar provided by any embodiment of the present invention.

[0050] The embodiment of the present invention provides a height measurement method based on millimeter wave radar, firstly obtains the radar echo signal of the target indoor space, then performs target detection according to the radar echo signal, obtains the initial point cloud data, then performs target tracking according to the initial point cloud data, obtains the target point cloud data, then identifies the target motion state according to the radar echo signal and the target point cloud data, and determines the target body posture according to the target point cloud data, so as to determine the height measurement data according to the corresponding target point cloud data when the target motion state and the target body posture meet the preset measurement conditions. The height measurement method based on millimeter wave radar provided by the embodiment of the present invention automatically identifies the motion state and body posture of the measured object based on the radar echo data, and automatically calculates the height measurement data when the specified conditions are met, so as to realize the continuous, automatic and effective measurement of height in a complex home environment, and does not require the user to perform any form of assembly or have special technical knowledge, and does not require the help of others, thereby reducing the measurement requirements. In addition, the advantages of the radar itself are combined, the measurement process does not infringe on personal privacy, is not sensitive to light, dust, smoke and temperature, that is, the measurement result is not easily affected by environmental factors, and can work all day and all weather. This enables more accurate, quick and convenient height measurement, provides an important basis for individual health assessment and personalized services, and lays the foundation for intelligent health management. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A flowchart of a height measurement method based on millimeter wave radar provided in Embodiment 1 of the present invention;

[0052] Figure 2 A schematic diagram of the structure of a height measurement device based on millimeter wave radar provided in Embodiment 2 of the present invention;

[0053] Figure 3 This is a schematic diagram of the structure of a computer device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0054] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0055] It should be mentioned before discussing the exemplary embodiments in more detail that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe the steps as sequential processes, many of the steps therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of the steps can be rearranged. The process can be terminated when its operation is completed, but can also have additional steps not included in the accompanying drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0056] Embodiment 1

[0057] Figure 1 This is a flowchart of a height measurement method based on millimeter wave radar provided in the first embodiment of the present invention. This embodiment can be applied to the situation where the height of the measured object is continuously, automatically and effectively measured in various indoor environments, even in complex indoor environments. The method can be performed by a height measurement device based on millimeter wave radar provided in the embodiment of the present invention, which can be implemented by hardware and / or software, and can generally be integrated into a computer device. Figure 1 As shown, the specific steps include:

[0058] S11. Acquire a radar echo signal of the target indoor space.

[0059] Specifically, the radar echo signal required can be obtained by setting a radar radio frequency module in the target indoor space, such as a room where the specified measurement object is located for a long time. The model of the radar radio frequency module is not limited. For example, a 3-transmitter 4-receiver MIMO radar module can be selected. With the continuous development of microelectronics and semiconductor technology, radars are gradually becoming highly integrated, miniaturized, low-cost and low-power, with the advantages of high resolution and low cost.

[0060] S12. Perform target detection according to the radar echo signal to obtain initial point cloud data.

[0061] Specifically, for the radar echo signal, any target detection algorithm can be used to detect the target object in the target indoor space, so as to obtain the position information of the target object, and the initial point cloud data can be generated according to the position information for subsequent processing.

[0062] Optionally, before performing target detection based on the radar echo signal, it also includes: preprocessing the radar echo signal; the preprocessing includes: performing clutter suppression based on a single-frame echo signal, and performing a fast Fourier transform in a slow-time dimension to obtain a first echo signal; performing clutter suppression based on accumulated multi-frame echo signals, and performing a fast Fourier transform in a slow-time dimension to obtain a second echo signal.

[0063] Specifically, for the acquired radar echo signal, clutter suppression can be performed first to eliminate the influence of clutter. In indoor daily life scenes, the activity states of human targets are diverse, which can be mainly divided into large-motion states (such as walking, running, jumping, etc.) and micro-motion states (such as standing, sitting, lying). Among them, the large-motion state can be understood as a state of movement in which the body presents a large change in height, and the micro-motion state can be understood as a state in which the body presents a small change in height, that is, the micro-motion state is more suitable for height measurement. When the target object in the target indoor space is in a large-motion state, the energy of the echo signal received by the radar is high, and when the target object in the target indoor space is in a micro-motion state, the energy of the echo signal received by the radar is relatively low. If only the traditional clutter suppression method is used, the target object in the micro-motion state is easily submerged by clutter, making it difficult to detect. Therefore, on the one hand, the single-frame echo signal can be subjected to clutter suppression to obtain the processed signal y m (m, r, k), this signal can highlight large moving targets with high signal-to-noise ratio, and on the other hand, it can accumulate multiple frames of echo signals for clutter suppression, and obtain y S (m, r, k), this signal can highlight the micro-moving target with a low signal-to-noise ratio. Through these two processing methods of radar echo signals, not only can the large-moving target signal be retained, but also the micro-moving target signal will not be missed. Then y m (m,r,k) and y S (m, r, k) performs a fast Fourier transform in the slow time dimension to obtain the first echo signal y in the range-Doppler-antenna dimension m (f,r,k) and the second echo signal y S (f, r, k), where f is the Doppler frequency. Accordingly, in subsequent processing, the pre-processed radar echo signal can be directly used to make the processing result more accurate.

[0064] Further optionally, performing target detection according to the radar echo signal to obtain initial point cloud data includes: using a constant false alarm algorithm to detect and obtain target range-Doppler information according to the first echo signal and the second echo signal; based on the target range-Doppler information, using a spatial domain beamforming algorithm to estimate target angle information according to the first echo signal and the second echo signal; and generating the initial point cloud data in a rectangular coordinate system according to the target range-Doppler information and the target angle information.

[0065] Specifically, the Constant False Alarm Rate (CFAR) algorithm can effectively identify the target and suppress false alarms to a certain extent. The CFAR algorithm can be used to process the first echo signal y obtained by preprocessing. m (f,r,k) and the second echo signal yS (f, r, k) to detect the target and obtain the target range-Doppler information. MIMO millimeter wave radar has the ability to measure angles. Common methods include Angle-FFT, Capon algorithm, and MUSIC algorithm. Based on the obtained target range-Doppler information, the spatial domain beamforming algorithm can be used to measure the first echo signal y m (f,r,k) and the second echo signal y S (f, r, k) is used to estimate the two-dimensional angle, and obtain the target angle information such as azimuth and pitch angle, so that the target distance-Doppler information can be combined to first generate a 4D point cloud containing four-dimensional information of distance, Doppler, azimuth, and pitch angle to retain the Doppler information of each point cloud. Then, the 4D point cloud can be converted to a rectangular coordinate system through coordinate transformation to obtain the initial point cloud data, in which the indoor space point cloud is P (x, y, z, v), where x and y represent the two-dimensional position information of the point cloud, z represents the height information of the point cloud, and v represents the speed information of the point cloud, thereby obtaining more intuitive spatial information.

[0066] S13. Tracking a target according to the initial point cloud data to obtain target point cloud data.

[0067] Specifically, due to the limitations of the target detection algorithm used, false alarms and missed alarms may occur. At the same time, the parameter estimation used in the process of generating the initial point cloud data may cause certain errors in the point cloud related parameters (distance, speed, etc.) of the target object. Therefore, further target tracking can be performed based on the obtained initial point cloud data to obtain the target point cloud data for subsequent processing to reduce the impact of false alarms and missed alarms. The estimated point cloud related parameters can also be corrected to establish a stable target tracking trajectory.

[0068] Target tracking mainly includes two parts: data association and tracking filtering. Data association is the process of associating point cloud measurement values ​​with known trajectories. Specifically, a tracking gate can be set first. The point cloud measurement values ​​falling within the tracking gate will be used in the subsequent association process. Common tracking gate shapes include rectangles, ellipses, and sectors, etc. Then, the data in two or more point cloud measurement data sets can be associated and matched with the previously generated trajectory. Common data association algorithms include nearest neighbor data association algorithm, probabilistic data association algorithm, global nearest neighbor data association, etc. Tracking filtering is mainly used to estimate the target state, and the Kalman filter algorithm can be used specifically. First, a reasonable mathematical model of the target motion in the scene is established as an important basis and necessary prerequisite for subsequent filtering and the entire target tracking process. The mathematical model can use a two-dimensional uniform linear motion model. Then, based on the established target motion model, the Kalman filter can use the input point cloud measurement information to estimate the state of the target object. It can be divided into two stages: prediction and update. The prediction stage mainly predicts the position and speed of the target at the current moment based on the state estimation value and state equation of the target at the previous moment. The update stage adjusts the prediction value according to the point cloud measurement information and related noise statistics to obtain the optimal state estimation.

[0069] S14. Identify the target motion state according to the radar echo signal and the target point cloud data.

[0070] Specifically, as mentioned above, the target motion state may include a large motion state and a micro-motion state, wherein the micro-motion state is more suitable for height measurement. Therefore, after tracking the target object, it is possible to first identify whether the target object is in a micro-motion state.

[0071] Optionally, identifying the target motion state according to the radar echo signal and the target point cloud data includes: averaging the first echo signal in the antenna dimension to obtain a range-Doppler signal; obtaining the distance unit of the target point cloud data; superimposing the target distance units corresponding to the range-Doppler signal in the distance unit and accumulating multiple frames to obtain a time-frequency diagram; determining the sum of signal energy within a preset frequency threshold according to the time-frequency diagram; comparing the sum of signal energy with a corresponding preset threshold, and determining the target motion state according to the comparison result.

[0072] Specifically, the first echo signal y obtained by preprocessing can be used m (f, r, k) is averaged over the antenna dimension to obtain the range-Doppler signal y m (f, r), on the other hand, the distance unit of the target point cloud data can be obtained, and then the distance-Doppler signal y m The target distance units corresponding to (f,r) are superimposed and multi-frame accumulation is performed to obtain the time-frequency map Z(t,f d). Then, the power bust curve (PBC) of the time-frequency diagram can be used to adaptively identify the micro-motion state, and the sum of the signal energy within the preset frequency threshold (Doppler frequency lower limit f1 to upper limit f2) is used as the target PBC value. The calculation formula is as follows:

[0073]

[0074] Similarly, the PBC value of the remaining background noise outside the preset frequency threshold can be calculated, which obeys the Gaussian distribution. Then, the mean μ and variance σ of the PBC value of the remaining background noise can be calculated, and the empirical value k is set, so that the PBC threshold is calculated according to the mean μ, variance σ and empirical value k as the preset threshold corresponding to the target PBC value. The calculation formula is as follows:

[0075]

[0076] When the target PBC value is lower than the PBC threshold γ, it can be considered that the target object is in a slight motion state, otherwise it is in a large motion state.

[0077] S15. Determine the target body posture according to the target point cloud data.

[0078] Specifically, as mentioned above, the target body posture in the micro-motion state may include standing, sitting, lying, etc., among which the standing state is more suitable for height measurement. Therefore, after tracking the target object, it is also possible to first determine whether the target object is in a standing state.

[0079] Optionally, determining the target body posture according to the target point cloud data includes: constructing a covariance matrix according to the target point cloud data; performing eigenvalue decomposition on the covariance matrix to obtain an eigenvector; calculating the angle between the eigenvector and a preset normal as an inclination angle; determining the height difference between the highest point cloud and the lowest point cloud, and the number of point clouds according to the target point cloud data; and determining the target body posture using a trained classifier according to the height difference, the number of point clouds and the inclination angle.

[0080] Specifically, principal component analysis (PCA) can be used to calculate the inclination angles of the three states of standing, sitting and lying in the body posture. Specifically, the covariance matrix can be constructed using the centralized target point cloud data, and then the eigenvalue decomposition of the covariance matrix can be performed to obtain the eigenvector, which represents the main direction of the point cloud data in the three-dimensional space. Subsequently, the normal direction of the ground can be determined as the preset normal, and the angle between the obtained eigenvector and the preset normal can be calculated as the inclination angle. On the other hand, the height difference between the highest point cloud and the lowest point cloud, as well as the number of point clouds, can be calculated based on the target point cloud data, and the obtained height difference, number of point clouds and inclination angle can be input into the trained classifier to determine the target body posture.

[0081] The problem of body posture determination is a classification problem, and the naive Bayes classifier can be used to complete the classification task. First, the classifier can be trained, and multi-dimensional sample features can be similarly extracted, including height features, point cloud quantity features, and angle features. Among them, the height feature can be the arithmetic mean of the height difference between the highest point cloud and the lowest point cloud in multiple frames when the target object is in a continuous micro-motion state, the point cloud quantity feature can be the arithmetic mean of the number of point clouds between the multi-frame thresholds T1 and T2, and the angle feature can be the arithmetic mean of the tilt angle calculated in multiple frames. At the same time, labels are added to the extracted multi-dimensional sample features so that they can be used as input data for training the classifier, and then the trained classifier can be used for body posture determination.

[0082] S16, determining height measurement data according to the target point cloud data corresponding to the target motion state and the target body posture when the preset measurement conditions are met.

[0083] Specifically, the preset measurement condition may be that the target object is in a slightly moving state and in a standing state. When the preset measurement condition is met, the corresponding target point cloud data can be used to calculate the height. For example, the height of the target point cloud data can be used as the height of the target object.

[0084] Optionally, determining height measurement data based on the target point cloud data corresponding to the target when the target motion state and the target body posture meet preset measurement conditions includes: if the target motion state and the target body posture meet the preset measurement conditions, starting to calculate the height of a single frame of target point cloud data until the target motion state changes, to obtain an original height sequence; collecting multiple original height sequences and merging them to obtain a target height sequence; clustering the maximum value in the target height sequence as the first clustering center to divide the target height sequence into multiple clusters, and taking the arithmetic mean of the highest cluster data as the height measurement data.

[0085] Specifically, the height measurement can be started when the target object is detected to be in a micro-motion state and in a standing state. Specifically, the height of the corresponding single-frame target point cloud data can be calculated successively, and multiple frames can be accumulated until the target motion state changes to obtain the original height sequence. Among them, the tracking point cloud can be sorted from large to small according to the height z in a single frame, and the high-level point cloud can be selected in combination with the point cloud signal-to-noise ratio to improve the accuracy of the height calculation of the target point cloud data. Similarly, multiple original height sequences can be collected. Since the high-level point cloud may not be the head of the target object, data representing the head height can be further screened from multiple original height sequences to improve the accuracy of the final height measurement data. Then, multiple original height sequences can be merged to obtain the target height sequence. Then find the maximum value in the target height sequence, and cluster the maximum value as the first cluster center. The clustering algorithm can use the K-means++ algorithm, and the target height sequence can be divided into three clusters by clustering, and then the arithmetic mean of the highest cluster data is taken as the final height measurement data.

[0086] The technical solution provided by the embodiment of the present invention first obtains the radar echo signal of the target indoor space, then performs target detection according to the radar echo signal to obtain initial point cloud data, then performs target tracking according to the initial point cloud data to obtain target point cloud data, then identifies the target motion state according to the radar echo signal and the target point cloud data, and determines the target body posture according to the target point cloud data, so as to determine the height measurement data according to the corresponding target point cloud data when the target motion state and the target body posture meet the preset measurement conditions. By automatically identifying the motion state and body posture of the measured object based on the radar echo data, and automatically calculating the height measurement data when the specified conditions are met, the height is continuously, automatically and effectively measured in a complex home environment, and the user does not need to perform any form of assembly or have special technical knowledge, and does not need the help of others, which reduces the measurement requirements. In addition, the advantages of the radar itself are combined, the measurement process does not infringe on personal privacy, is not sensitive to light, dust, smoke and temperature, that is, the measurement result is not easily affected by environmental factors, and can work all day and all weather. This enables more accurate, quick and convenient height measurement, provides an important basis for individual health assessment and personalized services, and lays the foundation for intelligent health management.

[0087] Embodiment 2

[0088] Figure 2 This is a schematic diagram of the structure of a height measurement device based on millimeter wave radar provided in the second embodiment of the present invention. The device can be implemented by hardware and / or software, and can generally be integrated into a computer device to execute the height measurement method based on millimeter wave radar provided in any embodiment of the present invention. Figure 2As shown, the device comprises:

[0089] A signal acquisition module 21 is used to acquire a radar echo signal of a target indoor space;

[0090] A target detection module 22 is used to perform target detection according to the radar echo signal to obtain initial point cloud data;

[0091] A target tracking module 23 is used to perform target tracking according to the initial point cloud data to obtain target point cloud data;

[0092] A state recognition module 24, used to recognize the target motion state according to the radar echo signal and the target point cloud data;

[0093] A posture determination module 25, used to determine the target body posture according to the target point cloud data;

[0094] The height measurement module 26 is used to determine height measurement data according to the target point cloud data corresponding to the target motion state and the target body posture when the preset measurement conditions are met.

[0095] The technical solution provided by the embodiment of the present invention first obtains the radar echo signal of the target indoor space, then performs target detection according to the radar echo signal to obtain initial point cloud data, then performs target tracking according to the initial point cloud data to obtain target point cloud data, then identifies the target motion state according to the radar echo signal and the target point cloud data, and determines the target body posture according to the target point cloud data, so as to determine the height measurement data according to the corresponding target point cloud data when the target motion state and the target body posture meet the preset measurement conditions. By automatically identifying the motion state and body posture of the measured object based on the radar echo data, and automatically calculating the height measurement data when the specified conditions are met, the height is continuously, automatically and effectively measured in a complex home environment, and the user does not need to perform any form of assembly or have special technical knowledge, and does not need the help of others, which reduces the measurement requirements. In addition, the advantages of the radar itself are combined, the measurement process does not infringe on personal privacy, is not sensitive to light, dust, smoke and temperature, that is, the measurement result is not easily affected by environmental factors, and can work all day and all weather. This enables more accurate, quick and convenient height measurement, provides an important basis for individual health assessment and personalized services, and lays the foundation for intelligent health management.

[0096] On the basis of the above technical solution, optionally, the height measurement device based on millimeter wave radar further includes:

[0097] A preprocessing module, used for preprocessing the radar echo signal before performing target detection according to the radar echo signal;

[0098] The pre-processing comprises:

[0099] Clutter suppression is performed based on a single frame echo signal, and a fast Fourier transform in a slow time dimension is performed to obtain a first echo signal;

[0100] Clutter suppression is performed based on the accumulation of multiple frames of echo signals, and a fast Fourier transform in the slow time dimension is performed to obtain a second echo signal.

[0101] On the basis of the above technical solution, optionally, the target detection module 22 is specifically used for:

[0102] According to the first echo signal and the second echo signal, a constant false alarm algorithm is used to detect and obtain target range-Doppler information;

[0103] Based on the target range-Doppler information, according to the first echo signal and the second echo signal, a spatial domain beamforming algorithm is used to estimate the target angle information;

[0104] The initial point cloud data in a rectangular coordinate system is generated according to the target range-Doppler information and the target angle information.

[0105] On the basis of the above technical solution, optionally, the state identification module 24 is specifically used for:

[0106] Averaging the first echo signal with respect to the antenna dimension to obtain a range-Doppler signal;

[0107] Acquire the distance unit of the target point cloud data;

[0108] The target distance units corresponding to the range-Doppler signal in the distance units are superimposed and accumulated in multiple frames to obtain a time-frequency diagram;

[0109] Determine the sum of signal energy within a preset frequency threshold according to the time-frequency diagram;

[0110] The signal energy sum is compared with a corresponding preset threshold, and the target motion state is determined according to the comparison result.

[0111] On the basis of the above technical solution, optionally, the posture determination module 25 is specifically used for:

[0112] Constructing a covariance matrix according to the target point cloud data;

[0113] Performing eigenvalue decomposition on the covariance matrix to obtain an eigenvector;

[0114] Calculating the angle between the characteristic vector and a preset normal line as a tilt angle;

[0115] Determine the height difference between the highest point cloud and the lowest point cloud, and the number of point clouds according to the target point cloud data;

[0116] The target body posture is determined by using a trained classifier according to the height difference, the number of point clouds and the tilt angle.

[0117] On the basis of the above technical solution, optionally, the height measurement module 26 is specifically used for:

[0118] If the target motion state and the target body posture meet the preset measurement conditions, start calculating the height of the single-frame target point cloud data until the target motion state changes, and obtain the original height sequence;

[0119] Collecting a plurality of the original height sequences and merging them to obtain a target height sequence;

[0120] The maximum value in the target height sequence is used as the first cluster center for clustering to divide the target height sequence into multiple clusters, and the arithmetic mean of the highest cluster data is taken as the height measurement data.

[0121] The height measurement device based on millimeter wave radar provided in the embodiment of the present invention can execute the height measurement method based on millimeter wave radar provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0122] It is worth noting that in the above-mentioned embodiment of the height measurement device based on millimeter-wave radar, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0123] Embodiment 3

[0124] Figure 3 The schematic diagram of the structure of the computer device provided for the third embodiment of the present invention shows a block diagram of an exemplary computer device suitable for implementing the implementation mode of the present invention. Figure 3 The computer device shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention. Figure 3 As shown, the computer device includes a processor 31, a memory 32, an input device 33 and an output device 34; the number of processors 31 in the computer device can be one or more. Figure 3 Taking a processor 31 as an example, the processor 31, memory 32, input device 33 and output device 34 in the computer device can be connected through a bus or other means. Figure 3 The example of connecting through bus is taken in the following.

[0125] The memory 32 is a computer-readable storage medium that can be used to store software programs, computer executable programs and modules, such as the program instructions / modules corresponding to the height measurement method based on millimeter wave radar in the embodiment of the present invention (for example, the signal acquisition module 21, the target detection module 22, the target tracking module 23, the state recognition module 24, the posture determination module 25 and the height measurement module 26 in the height measurement device based on millimeter wave radar). The processor 31 executes various functional applications and data processing of the computer device by running the software programs, instructions and modules stored in the memory 32, that is, realizing the above-mentioned height measurement method based on millimeter wave radar.

[0126] The memory 32 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 32 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 32 may further include a memory remotely arranged relative to the processor 31, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0127] The input device 33 may be used to obtain radar echo signals of the target indoor space, and to generate key signal inputs related to user settings and function controls of the computer device, etc. The output device 34 may include a display screen, which may be used to display the measured height measurement data, etc. to the user.

[0128] Embodiment 4

[0129] Embodiment 4 of the present invention further provides a storage medium containing computer executable instructions, which, when executed by a computer processor, is used to execute a height measurement method based on millimeter wave radar, the method comprising:

[0130] Acquire radar echo signals of the target indoor space;

[0131] Perform target detection according to the radar echo signal to obtain initial point cloud data;

[0132] Perform target tracking according to the initial point cloud data to obtain target point cloud data;

[0133] Identify the target motion state according to the radar echo signal and the target point cloud data;

[0134] determining a target body posture according to the target point cloud data;

[0135] The height measurement data is determined according to the target point cloud data corresponding to the target motion state and the target body posture when the preset measurement conditions are met.

[0136] The storage medium may be any of various types of memory devices or storage devices. The term "storage medium" is intended to include: installation media, such as CD-ROM, floppy disk or tape device; computer system memory or random access memory, such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc.; non-volatile memory, such as flash memory, magnetic media (such as hard disk or optical storage); registers or other similar types of memory elements, etc. The storage medium may also include other types of memory or combinations thereof. In addition, the storage medium may be located in the computer system in which the program is executed, or may be located in a different second computer system, which is connected to the computer system via a network (such as the Internet). The second computer system may provide program instructions to the computer for execution. The term "storage medium" may include two or more storage media that may reside in different locations (e.g., in different computer systems connected via a network). The storage medium may store program instructions (e.g., embodied as a computer program) that may be executed by one or more processors.

[0137] Of course, the storage medium containing computer executable instructions provided in an embodiment of the present invention is not limited to the method operations described above, and the computer executable instructions can also execute related operations in the height measurement method based on millimeter wave radar provided in any embodiment of the present invention.

[0138] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0139] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0140] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0141] Embodiment 5

[0142] Embodiment 5 of the present invention also provides a computer program product, which includes a computer program (also referred to as code, instruction), which can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it is used to execute the height measurement method based on millimeter wave radar provided in any of the above embodiments, and has the corresponding beneficial effects of the execution method.

[0143] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A height measurement method based on millimeter wave radar, characterized in that: include: Acquire radar echo signals of the target indoor space; Perform target detection according to the radar echo signal to obtain initial point cloud data; Perform target tracking according to the initial point cloud data to obtain target point cloud data; Identify the target motion state according to the radar echo signal and the target point cloud data; determining a target body posture according to the target point cloud data; The height measurement data is determined according to the target point cloud data corresponding to the target motion state and the target body posture when the preset measurement conditions are met.

2. The height measurement method based on millimeter wave radar according to claim 1, characterized in that: Before performing target detection according to the radar echo signal, the method further includes: Preprocessing the radar echo signal; The pre-processing comprises: Clutter suppression is performed based on a single frame echo signal, and a fast Fourier transform in a slow time dimension is performed to obtain a first echo signal; Clutter suppression is performed based on the accumulation of multiple frames of echo signals, and a fast Fourier transform in the slow time dimension is performed to obtain a second echo signal.

3. The height measurement method based on millimeter wave radar according to claim 2 is characterized in that: The step of performing target detection according to the radar echo signal to obtain initial point cloud data includes: According to the first echo signal and the second echo signal, a constant false alarm algorithm is used to detect and obtain target range-Doppler information; Based on the target range-Doppler information, according to the first echo signal and the second echo signal, a spatial domain beamforming algorithm is used to estimate the target angle information; The initial point cloud data in a rectangular coordinate system is generated according to the target range-Doppler information and the target angle information.

4. The height measurement method based on millimeter wave radar according to claim 2, characterized in that: The identifying the target motion state according to the radar echo signal and the target point cloud data includes: Averaging the first echo signal with respect to the antenna dimension to obtain a range-Doppler signal; Acquire the distance unit of the target point cloud data; The target distance units corresponding to the range-Doppler signal in the distance units are superimposed and accumulated in multiple frames to obtain a time-frequency diagram; Determine the sum of signal energy within a preset frequency threshold according to the time-frequency diagram; The signal energy sum is compared with a corresponding preset threshold, and the target motion state is determined according to the comparison result.

5. The height measurement method based on millimeter wave radar according to claim 1, characterized in that: Determining the target body posture according to the target point cloud data includes: Constructing a covariance matrix according to the target point cloud data; Performing eigenvalue decomposition on the covariance matrix to obtain an eigenvector; Calculating the angle between the characteristic vector and a preset normal line as a tilt angle; Determine the height difference between the highest point cloud and the lowest point cloud, and the number of point clouds according to the target point cloud data; The target body posture is determined by using a trained classifier according to the height difference, the number of point clouds and the tilt angle.

6. The height measurement method based on millimeter wave radar according to claim 1, characterized in that: The determining of height measurement data according to the target point cloud data corresponding to the target motion state and the target body posture when the preset measurement conditions are met includes: If the target motion state and the target body posture meet the preset measurement conditions, start calculating the height of the single-frame target point cloud data until the target motion state changes, and obtain the original height sequence; Collecting a plurality of the original height sequences and merging them to obtain a target height sequence; The maximum value in the target height sequence is used as the first cluster center for clustering to divide the target height sequence into multiple clusters, and the arithmetic mean of the highest cluster data is taken as the height measurement data.

7. A height measurement device based on millimeter wave radar, characterized in that: include: A signal acquisition module, used to acquire radar echo signals of the target indoor space; A target detection module, used to perform target detection according to the radar echo signal to obtain initial point cloud data; A target tracking module, used to track the target according to the initial point cloud data to obtain target point cloud data; A state recognition module, used for identifying the target motion state according to the radar echo signal and the target point cloud data; A posture determination module, used to determine the target body posture according to the target point cloud data; The height measurement module is used to determine the height measurement data according to the target point cloud data corresponding to the target motion state and the target body posture when the preset measurement conditions are met.

8. A computer device, characterized in that: include: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the height measurement method based on millimeter wave radar as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the height measurement method based on millimeter wave radar as described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the computer program implements the height measurement method based on millimeter wave radar as described in any one of claims 1 to 6.

Images