A method, system and storage medium for detecting group motion consistency

Abstract

The present invention relates to a method, system, and storage medium for detecting group motion consistency. The method comprises: collecting group motions of a target group using a millimeter-wave radar to obtain raw radar data; preprocessing the raw radar data to obtain a range-Doppler spectrum; detecting the frequency consistency of the group motion using the range-Doppler spectrum; and outputting the consistency detection result. Millimeter-wave radar is a non-contact device. During group motion training, each member can maintain their original limb weight and a certain distance, eliminating any fear of harming the device and reducing the cost of damage caused by motion. Millimeter-wave radar has excellent range and angle resolution, allowing signals to propagate within the group, thereby better detecting each occupant in the group motion and resolving the issue of visual image obstruction.

Description

Technical Field

[0001] The present application relates to the field of radar detection technology, and specifically to a group movement consistency detection method, system and storage medium based on radar range-Doppler spectrum for indoor dance, aerobics, Tai Chi, military boxing and other movement guidance. Background Art

[0002] In fields like team sports and dance performances, the consistency of group movements is a key indicator of teamwork and rapport. When team members maintain consistency in movement execution and timing, teamwork and rapport are significantly enhanced. When watching team sports or dance performances, audiences often resonate with the team's collaboration and consistency, becoming more easily moved by the team's collaboration and rapport, sensing the close connection and shared effort among team members, which in turn increases their appreciation and emotional engagement with the performance.

[0003] The consistency of group movements directly impacts the effectiveness and quality of a team's performance. When team members maintain consistency in movement execution and timing, the overall team performance exhibits greater unity and precision. This consistency in group movement enables a more engaging and fluid performance, enhancing the overall visual appeal and artistry. This significantly impacts a team's competitive performance and the overall quality of their dance work, helping them stand out.

[0004] Currently, existing technical solutions for group action recognition can be categorized into two types: contact and non-contact. The contact method uses wireless sensors worn by team members to record the data generated by their movements and upload it to a server for processing. The non-contact method uses information carriers such as videos, images, and laser point clouds captured from different camera angles as a direct data source for signal processing. Multiple frames of key actions captured simultaneously are captured and detected using traditional deep learning-based pose estimation methods.

[0005] The existing technology has the following disadvantages: (1) The contact wearable device has a certain weight, which will increase the burden on the limbs of the team members during training. When the training results reach the group consistency under monitoring, the members still need a certain amount of time to adapt after taking off the device, and the change in the weight of the limbs may cause the movement to be deformed. (2) The contact wearable device has a certain cost. When the members are training, they will worry about damaging the detection equipment, which will cause psychological pressure and make them afraid to train freely, resulting in substandard movements. The damage to the equipment during training will also increase the cost. (3) The non-contact method requires setting up multiple cameras for shooting at the same time. In this way, the number of shooting equipment and lidar equipment to be prepared will increase, which will lead to an increase in cost. (4) For visual images, even if many cameras are set up, there is still the problem of "occlusion", which cannot detect group movements well. (5) Using visual images for consistency detection requires the use of deep learning algorithms to train the model. Group movements are characterized by complex movements and frequent changes, which requires a large-scale data set when training the model. If this problem is not solved, the trained model will have serious overfitting problems. Summary of the Invention

[0006] In view of the above problems, the present application provides a group motion consistency detection method, system and storage medium based on radar distance-Doppler spectrum, which solves the problem that the existing group motion consistency detection affects the movements of group members through contact detection or the non-contact detection using video is blocked.

[0007] To achieve the above objectives, the inventors provide a method for detecting group motion consistency based on radar range-Doppler spectrum, comprising:

[0008] The millimeter-wave radar is used to collect the group movements of the target group and obtain the radar raw data;

[0009] Perform data preprocessing on the radar raw data to obtain the range-Doppler spectrum;

[0010] Frequency consistency detection of group motions through range-Doppler spectrogram;

[0011] Output consistency test results.

[0012] In some embodiments, preprocessing the radar raw data to obtain a range-Doppler spectrum specifically includes the following steps:

[0013] Perform windowing operations on the range dimension and Doppler dimension of the radar raw data;

[0014] Then a two-dimensional fast Fourier transform is performed to obtain the range-Doppler spectrum.

[0015] In some embodiments, before performing the windowing operation on the range dimension and the Doppler dimension of the radar raw data, the method further includes:

[0016] The radar raw data is processed by static elimination algorithm to eliminate environmental noise.

[0017] In some embodiments, the frequency consistency detection of group motions using the range-Doppler spectrum specifically includes:

[0018] On the range-Doppler spectrum, the Doppler spectrum with the most targets is filtered to obtain the region of interest;

[0019] Perform peak detection on the region of interest;

[0020] Detect whether there are multiple Doppler spectra at the peak point;

[0021] If there is only one Doppler spectrum, it means that the group moves in unison;

[0022] If there are multiple Doppler spectra, it means that the group movements are inconsistent.

[0023] In some embodiments, performing peak detection on the region of interest further comprises:

[0024] Eliminate false detection targets through a constant false alarm rate algorithm.

[0025] In some embodiments, the frequency consistency detection of group motions using the range-Doppler spectrum specifically further includes:

[0026] When detecting inconsistent group movements, the Doppler spectrum with the most peak points is taken as the main spectrum, and the remaining spectra are inconsistent spectra;

[0027] Data with inconsistent spectra are marked in the range-Doppler spectrum.

[0028] In some embodiments, outputting the consistency test result specifically includes the following steps:

[0029] By processing the range-Doppler spectrum, point cloud data is obtained;

[0030] Use clustering algorithms to separate the point cloud clusters corresponding to each member of the target group;

[0031] The point cloud clusters corresponding to the coordinates of inconsistent individuals are marked, and a visual point cloud image is generated and output.

[0032] In some embodiments, the step of obtaining point cloud data by processing the range-Doppler spectrum specifically includes the following steps:

[0033] Perform Doppler compensation and velocity disambiguation on the processed range-Doppler spectrum;

[0034] Then perform the angular Fourier transform of the third dimension;

[0035] The three-dimensional coordinates and speed of the target group are calculated based on the distance, azimuth and pitch angle of the target group from the radar to generate point cloud data.

[0036] Another technical solution is also provided, a storage medium storing a computer program, which, when executed by a processor, executes the above-mentioned group motion consistency detection method based on radar range-Doppler spectrum.

[0037] Another technical solution is also provided, a group motion consistency detection system based on radar range-Doppler spectrum, including millimeter wave radar, server and terminal equipment;

[0038] The millimeter wave radar is connected to the server side, and is used to collect group movements of the target group to obtain radar raw data;

[0039] The server side includes the above-mentioned storage medium, and the server side is used to execute the computer program in the storage medium;

[0040] The terminal device is connected to the server terminal, and is used to receive the consistency detection result output by the server terminal.

[0041] Different from the existing technology, the above technical solution, when it is necessary to detect the consistency of the movements of each member of the target group, collects the group movement of the target group through millimeter-wave radar, that is, collects the movement of each occupant in the target group, obtains the radar raw data, and then preprocesses the radar raw data to obtain the distance-Doppler spectrum, and then uses the distance-Doppler spectrum to detect the frequency consistency of the group movement, and outputs the consistency detection result. The millimeter-wave radar is a non-contact device. During the movement training of each member in the group, the members can maintain the original weight of their limbs and maintain a certain distance, eliminating the members' psychological fear of causing harm to the equipment, and reducing the cost of equipment movement damage. The use of millimeter-wave radar has good distance resolution and angle resolution, and the signal can be transmitted in the group, thereby better detecting each occupant in the group movement, solving the problem of obstruction of visual images.

[0042] The above-mentioned records related to the content of the invention are only an overview of the technical solution of this application. In order to enable ordinary technicians in this field to understand the technical solution of this application more clearly, and then implement it according to the text of the specification and the contents recorded in the drawings, and to make the above-mentioned purposes and other purposes, features and advantages of this application easier to understand, the following is an explanation in combination with the specific implementation methods and drawings of this application. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings are only used to illustrate the principles, implementation methods, applications, characteristics and effects of the specific embodiments of this application and other related contents, and are not to be considered as limiting this application.

[0044] In the drawings of the specification:

[0045] Figure 1 A schematic flow chart of a method for detecting group motion consistency based on radar range-Doppler spectrum described in the background art;

[0046] Figure 2 A schematic diagram of a frequency-consistent range-Doppler spectrum according to a specific embodiment;

[0047] Figure 3 A schematic diagram of a frequency-inconsistent range-Doppler spectrum according to a specific embodiment;

[0048] Figure 4 A schematic diagram of a visualized point cloud image when the frequencies described in the specific implementation are consistent;

[0049] Figure 5 A schematic diagram of a visualized point cloud image when the frequencies are inconsistent as described in the specific implementation manner;

[0050] Figure 6 Another flowchart of the group motion consistency detection method based on radar range-Doppler spectrum described in the background technology;

[0051] Figure 7 A schematic structural diagram of a group motion consistency detection system based on radar range-Doppler spectrum according to a specific embodiment;

[0052] Figure 8 This is a schematic diagram of an application scenario of the group motion consistency detection system based on radar range-Doppler spectrum described in the specific implementation method. DETAILED DESCRIPTION

[0053] In order to explain in detail the possible application scenarios, technical principles, specific solutions that can be implemented, and the purpose and effects of this application, the following is a detailed description of the specific embodiments listed in conjunction with the accompanying drawings. The embodiments described herein are only used to more clearly illustrate the technical solutions of this application and are therefore only examples and are not intended to limit the scope of protection of this application.

[0054] References to "embodiments" herein mean that the specific features, structures, or characteristics described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the word "embodiment" in various places in the specification does not necessarily refer to the same embodiment, nor does it particularly limit its independence or relevance to other embodiments. In principle, in this application, as long as there are no technical contradictions or conflicts, the various technical features mentioned in the embodiments can be combined in any manner to form a corresponding implementable technical solution.

[0055] Unless otherwise defined, the technical terms used herein have the same meanings as those generally understood by those skilled in the art to which this application belongs; the use of relevant terms herein is only for describing specific embodiments and is not intended to limit this application.

[0056] In the description of this application, the term "and / or" is used to describe a logical relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A exists, B exists, and both A and B exist. In addition, the character " / " in this document generally indicates that the objects before and after are in a logical "or" relationship.

[0057] In this application, terms such as "first" and "second" are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual quantity, priority or sequence relationship between these entities or operations.

[0058] Without further limitations, in this application, the words "include", "comprise", "have" or other similar expressions used in the sentences are intended to cover non-exclusive inclusion. These expressions do not exclude the presence of additional elements in the process, method or product including the elements, so that the process, method or product including a series of elements may include not only those defined elements, but also other elements not explicitly listed, or elements inherent to such process, method or product.

[0059] Consistent with the understanding in the Examination Guidelines, in this application, expressions such as "greater than," "less than," and "exceed" are understood to exclude the number itself; expressions such as "above," "below," and "within" are understood to include the number itself. Furthermore, in the description of the embodiments of this application, "multiple" means more than two (including two), and similar expressions related to "multiple" are also understood in this manner, such as "multiple groups," "multiple times," etc., unless otherwise specifically defined.

[0060] In the description of the embodiments of the present application, the space-related expressions used, such as "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "vertical", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicate the orientation or position relationship based on the orientation or position relationship shown in the specific embodiments or drawings, and are only for the convenience of describing the specific embodiments of the present application or facilitating the reader's understanding, and do not indicate or imply that the device or component referred to must have a specific position, a specific orientation, or be constructed or operated in a specific orientation. Therefore, it should not be understood as a limitation on the embodiments of the present application.

[0061] Unless otherwise expressly specified or limited, in the description of the embodiments of the present application, the terms "installed", "connected", "connected", "fixed", "set", etc. used should be understood in a broad sense. For example, the "connection" can be a fixed connection, a detachable connection, or an integrated setting; it can be a mechanical connection, an electrical connection, or a communication connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be the internal connection of two elements or the interaction relationship between two elements. For those skilled in the art of the present application, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0062] See also Figure 1 This embodiment provides a method for detecting group motion consistency based on radar range-Doppler spectrum, including:

[0063] Step S110: collecting group movements of the target group through millimeter wave radar to obtain radar raw data;

[0064] Step S120: Preprocessing the radar raw data to obtain a range-Doppler spectrum;

[0065] Step S130: detecting the frequency consistency of group movements through the range-Doppler spectrum;

[0066] Step S140: Output the consistency detection result.

[0067] When it is necessary to detect the consistency of the movements of each member of the target group, the millimeter-wave radar is used to collect the group movements of the target group, that is, to collect the movements of each occupant in the target group, to obtain the radar raw data, and then the radar raw data is preprocessed to obtain the range-Doppler spectrum. The frequency consistency of the group movement is then detected through the range-Doppler spectrum, and the consistency detection result is output. The millimeter-wave radar is a non-contact device. During the movement training of each member in the group, the members can maintain the original weight of their limbs and maintain a certain distance, eliminating the members' psychological fear of causing harm to the equipment and reducing the cost of equipment movement damage. The use of millimeter-wave radar has good distance resolution and angle resolution, and the signal can be transmitted in the group, thereby better detecting each occupant in the group movement and solving the problem of visual image obstruction.

[0068] In some embodiments, preprocessing the radar raw data to obtain a range-Doppler spectrum specifically includes the following steps:

[0069] Perform windowing operations on the range dimension and Doppler dimension of the radar raw data;

[0070] Then a two-dimensional fast Fourier transform is performed to obtain the range-Doppler spectrum.

[0071] Data is collected through millimeter-wave radar and uploaded to the server. The millimeter-wave radar uses FMCW millimeter-wave radar to collect radar raw data about group movements and transmit the data file to the PC host computer (i.e. the server side) for radar signal processing.

[0072] If the collected radar raw data is: the intermediate frequency signal after K targets are superimposed can be expressed as: Where t represents the duration of the signal, l represents the lth linear frequency modulation signal chirp, k represents the target number, K is the total number of detected targets, A k is the amplitude of the kth target intermediate frequency signal, S is the frequency change rate of the linear frequency modulation chirp signal, τ k,l represents the delay time of the radar signal reflected by the kth target, f c is the starting frequency of the FMCW signal.

[0073] The RDM is obtained by sampling the IF signal in the range and Doppler dimensions and then performing a two-dimensional Fourier transform (FFT), as follows:

[0074]

[0075] Among them, f R and f DThey represent the frequency components in the distance dimension and Doppler dimension in RDM respectively, n represents the nth sampling point in a chirp signal, l represents the sequence number of the chirp signal, N is the total number of sampling points in a chirp signal, L is the total number of chirps in signal processing, T s and T cri are the sampling time intervals of the range dimension and Doppler dimension respectively.

[0076] In some embodiments, before performing the windowing operation on the range dimension and the Doppler dimension of the radar raw data, the method further includes:

[0077] The radar raw data is processed by static elimination algorithm to eliminate environmental noise.

[0078] In order to avoid the influence of environmental noise, after collecting the radar raw data, the radar raw data is processed by a static elimination algorithm to eliminate the environmental noise.

[0079] In some embodiments, the frequency consistency detection of group motions using the range-Doppler spectrum specifically includes:

[0080] On the range-Doppler spectrum, the Doppler spectrum with the most targets is filtered to obtain the region of interest;

[0081] Perform peak detection on the region of interest;

[0082] Detect whether there are multiple Doppler spectra at the peak point;

[0083] If there is only one Doppler spectrum, it means that the group moves in unison;

[0084] If there are multiple Doppler spectra, it means that the group movements are inconsistent.

[0085] The consistency of group movements is determined by performing peak detection on the data in the range-Doppler spectrum. Specifically, on the range-Doppler spectrum, the Doppler spectrum with the most targets is filtered using a filter to obtain the area of interest. Then, peak detection is performed on the area to detect whether there are multiple spectra at the peak point. If there is only one Doppler spectrum, such as Figure 2 If the distance-Doppler spectrum with the same frequency is shown, it means that the movements of the group of people are in the same Doppler spectrum and the movements are consistent; otherwise, Figure 3 The range-Doppler spectrum with inconsistent frequencies shows multiple Doppler spectra, indicating that the movements of people are not in the same Doppler spectrum, and the movements are inconsistent.

[0086] In some embodiments, performing peak detection on the region of interest further comprises:

[0087] Eliminate false detection targets through a constant false alarm rate algorithm.

[0088] To prevent the impact of falsely detected targets on detection results, a constant false alarm rate (CFAR) algorithm is used to eliminate these false detections. CFAR stands for Constant False-Alarm Rate (CFAR). In radar signal detection, when the intensity of external interference changes, the radar automatically adjusts its sensitivity to maintain a constant false alarm probability. This characteristic is known as the constant false alarm rate (CFAR). There are two methods for obtaining the CFAR: parametric and non-parametric.

[0089] In some embodiments, the frequency consistency detection of group motions using the range-Doppler spectrum specifically further includes:

[0090] When detecting inconsistent group movements, the Doppler spectrum with the most peak points is taken as the main spectrum, and the remaining spectra are inconsistent spectra;

[0091] Data with inconsistent spectra are marked in the range-Doppler spectrum.

[0092] When inconsistent group movements are detected, the Doppler spectrum with the most peak points is taken as the main spectrum, that is, the Doppler spectrum corresponding to the members with most consistent movements in the distance-Doppler spectrum is taken as the main spectrum, and the Doppler spectrum corresponding to the other members with inconsistent movements in the distance-Doppler spectrum is the inconsistent spectrum. The data on the inconsistent spectrum is marked in the distance-Doppler spectrum, so that the coach can obtain the group inconsistency through marking and make further movement guidance.

[0093] In some embodiments, outputting the consistency test result specifically includes the following steps:

[0094] By processing the range-Doppler spectrum, point cloud data is obtained;

[0095] Use clustering algorithms to separate the point cloud clusters corresponding to each member of the target group;

[0096] The point cloud clusters corresponding to the coordinates of inconsistent individuals are marked, and a visual point cloud image is generated and output.

[0097] In order to help the coach know which members have inconsistent movements, the distance-Doppler spectrum after marking is processed to obtain point cloud data; then the point cloud cluster corresponding to each member of the target group is separated by clustering algorithm, and the point cloud cluster corresponding to the coordinates of the inconsistent individuals is marked to generate a visual point cloud image and output it, such as Figure 4Visual point cloud images when the frequencies shown are consistent, and Figure 5 The visual point cloud image when the frequency is inconsistent is shown, where Figure 5 The darker point cloud clusters correspond to members with inconsistent movements, so that the coach can know whether the movements of the members in the target group are consistent based on the visualized point cloud image. If not, the coach can identify which members have inconsistent movements and provide corresponding guidance.

[0098] Specifically, the step of obtaining point cloud data by processing the range-Doppler spectrum includes the following steps:

[0099] Perform Doppler compensation and velocity disambiguation on the processed range-Doppler spectrum;

[0100] Then perform the angular Fourier transform of the third dimension;

[0101] The three-dimensional coordinates and speed of the target group are calculated based on the distance, azimuth and pitch angle of the target group from the radar to generate point cloud data.

[0102] To obtain point cloud data, Doppler compensation and velocity disambiguation are performed on the processed RDM. A third-dimensional angle FFT is then performed. The x, y, and z coordinates and velocity of the target group are calculated based on their distance from the radar, azimuth, and elevation angles to generate a point cloud. A clustering algorithm is then used to separate the point cloud clusters corresponding to each individual in the group and remove point cloud noise. Different RGB values are used to represent the coordinates of inconsistent individuals.

[0103] Among them, the angle FFT is:

[0104] f R 、f D and f A They represent the frequency components in the distance dimension, Doppler dimension, and antenna dimension, respectively. n represents the nth sampling point in a chirp signal, l is the serial number of the chirp signal, and i represents the i-th receiving antenna. N, L, and I represent the number of sampling points, the total number of chirps, and the total number of receiving antennas contained in the chirp signal in signal processing, respectively. T s 、T cri and T A They are represented as the sampling time intervals of the range dimension, Doppler dimension and antenna dimension respectively.

[0105] The three-dimensional coordinates of the real Cartesian coordinate system point cloud are obtained by the following formula:

[0106]

[0107] See also Figure 6In another embodiment, a method for detecting group motion consistency based on radar range-Doppler spectrum includes:

[0108] 1. Data collection and upload

[0109] Collect data and upload it to the server. Use FMCW millimeter-wave radar to collect raw radar data about group movements and transfer the data files to the PC host computer for radar signal processing.

[0110] 2. Range-Doppler spectrum acquisition

[0111] The radar raw data is preprocessed to generate a range-Doppler spectrum (RDM). A static elimination algorithm is applied to the data to remove ambient noise. The data is then windowed in both the range and Doppler dimensions, followed by a fast Fourier transform (FFT) in both dimensions to generate the RDM.

[0112] 3. Frequency consistency detection

[0113] Peak detection and a constant false alarm rate (CFAR) algorithm are performed on the RDM data to determine group motion consistency. On the RDM, the Doppler spectrum with the most targets is filtered to obtain a region of interest. Peak detection is then performed in this region. The CFAR algorithm is used to eliminate falsely detected targets. The presence of multiple spectra at the peak point is detected. If only one Doppler spectrum exists, the group members' movements fall within the same Doppler spectrum, indicating consistency. Otherwise, some individuals' movements fall outside the same Doppler spectrum, indicating inconsistency. If individuals exhibit inconsistent movements, the spectrum with the most peak points is considered the primary spectrum, and the remaining spectra are considered inconsistent. Data on these inconsistent spectra are then marked.

[0114] 4. Point cloud image acquisition

[0115] The data is further processed to obtain point cloud data. To obtain point cloud data, Doppler compensation and velocity disambiguation are performed on the processed RDM. A third-dimensional angle FFT is then performed. The target's x, y, and z coordinates and velocity are calculated based on the target group's distance from the radar, azimuth, and elevation angles to generate a point cloud. A clustering algorithm is used to separate the point cloud clusters corresponding to each individual in the group, and point cloud noise is removed. The coordinates of inconsistent individuals are represented by different RGB values.

[0116] Compared with methods that use contact wearable devices and visual image processing technology to determine group motion consistency, the group motion consistency detection method based on range-Doppler spectrogram has the following advantages:

[0117] (1) Radar sensors are non-contact devices. During the training process of team members, they can allow members to maintain their original limb weight and keep a certain distance, eliminating the members' psychological fear of causing harm to the equipment and reducing the cost of equipment movement damage.

[0118] (2) Use radar sensors to obtain data. Radar sensors have good distance resolution and angle resolution. The signal can propagate among the crowd, thereby better detecting each member of the group action and solving the problem of visual image occlusion.

[0119] (3) When the number of people in a group is too large, the visual image will be more obstructed, and the number of sensors required will also increase, which will seriously increase the cost. In this case, the radar sensor may fail to detect members due to the attenuation of the signal-to-noise ratio. However, this problem can be solved by adding a small number of radar sensors in the radial and lateral directions, which is more cost-effective.

[0120] (4) A method for detecting group movement consistency based on the distance-Doppler spectrum can detect whether the group movement is consistent by comparing the Doppler consistency of the distance-Doppler signal generated by the group movement. After discovering inconsistencies, the positions of the people with inconsistent frequencies can still be marked through point cloud visualization, so that the coach can discover the differences in skills of individual members in the team.

[0121] Therefore, compared with the traditional group motion consistency detection method, the group motion consistency detection method based on range-Doppler spectrum has a wider application scenario, lower cost and faster processing speed.

[0122] In another embodiment, a storage medium stores a computer program, and when the computer program is executed by a processor, the method for detecting group motion consistency based on radar range-Doppler spectrum is executed.

[0123] When it is necessary to detect the consistency of the movements of each member of the target group, the millimeter-wave radar is used to collect the group movements of the target group, that is, to collect the movements of each occupant in the target group, to obtain the radar raw data, and then the radar raw data is preprocessed to obtain the range-Doppler spectrum. The frequency consistency of the group movement is then detected through the range-Doppler spectrum, and the consistency detection result is output. The millimeter-wave radar is a non-contact device. During the movement training of each member in the group, the members can maintain the original weight of their limbs and maintain a certain distance, eliminating the members' psychological fear of causing harm to the equipment and reducing the cost of equipment movement damage. The use of millimeter-wave radar has good distance resolution and angle resolution, and the signal can be transmitted in the group, thereby better detecting each occupant in the group movement and solving the problem of visual image obstruction.

[0124] See also Figure 7 ,In another embodiment, a group motion consistency detection system based on radar range-Doppler spectrum, includes a millimeter wave radar, a server and a terminal device;

[0125] The millimeter wave radar is connected to the server end, and the millimeter wave radar adopts FMCW millimeter wave radar, and the millimeter wave radar is used to collect group movements of the target group to obtain radar raw data;

[0126] The server side includes the above-mentioned storage medium, and the server side is used to execute the computer program in the storage medium;

[0127] The terminal device is connected to the server terminal, and is used to receive the consistency detection result output by the server terminal.

[0128] like Figure 8 In the application scenario of a group motion consistency detection system based on radar range-Doppler spectra, a millimeter-wave radar is placed at a certain distance from the group, raised to a certain height, and tilted downward to cover all group members within the radar's detection range. The radar uploads the collected data to the server, which processes the raw radar data in real time to generate a range-Doppler spectrogram (RDM). The RDM is then used to detect group motion frequency inconsistencies, and the data of inconsistent individuals is RGB-colored. All data is then processed to generate a visual point cloud image. The server then sends the generated point cloud data to the coach's terminal device, which uses methods including, but not limited to, visual point cloud images and voice broadcasts to enable the coach to locate individuals with inconsistent movements in real time based on the coordinates of the colored point cloud data.

[0129] When it is necessary to detect the consistency of the movements of each member of the target group, the millimeter-wave radar is used to collect the group movements of the target group, that is, to collect the movements of each occupant in the target group, to obtain the radar raw data, and then the radar raw data is preprocessed to obtain the range-Doppler spectrum. The frequency consistency of the group movement is then detected through the range-Doppler spectrum, and the consistency detection result is output. The millimeter-wave radar is a non-contact device. During the movement training of each member in the group, the members can maintain the original weight of their limbs and maintain a certain distance, eliminating the members' psychological fear of causing harm to the equipment and reducing the cost of equipment movement damage. The use of millimeter-wave radar has good distance resolution and angle resolution, and the signal can be transmitted in the group, thereby better detecting each occupant in the group movement and solving the problem of visual image obstruction.

[0130] Finally, it should be noted that although the above embodiments have been described in the specification and drawings of this application, this does not limit the scope of patent protection of this application. All technical solutions generated by replacing or modifying equivalent structures or equivalent processes based on the essential concepts of this application using the contents recorded in the specification and drawings of this application, as well as directly or indirectly implementing the technical solutions of the above embodiments in other related technical fields, are included in the scope of patent protection of this application.

Claims

1. A method for detecting group motion consistency based on radar range-Doppler spectrum, characterized in that: include: The millimeter-wave radar is used to collect the group movements of the target group and obtain the radar raw data; Perform data preprocessing on the radar raw data to obtain the range-Doppler spectrum; Frequency consistency detection of group motions through range-Doppler spectrogram; Output consistency test results; The frequency consistency detection of group motions using the range-Doppler spectrum specifically includes: On the range-Doppler spectrum, the Doppler spectrum with the most targets is filtered to obtain the region of interest; Perform peak detection on the region of interest; Detect whether there are multiple Doppler spectra at the peak point; If there is only one Doppler spectrum, it means that the group moves in unison; If there are multiple Doppler spectra, it means that the group movements are inconsistent.

2. The method for detecting group motion consistency based on radar range-Doppler spectrum according to claim 1, characterized in that: The data preprocessing of the radar raw data to obtain the range-Doppler spectrum specifically includes the following steps: Perform windowing operations on the range dimension and Doppler dimension of the radar raw data; Then a two-dimensional fast Fourier transform is performed to obtain the range-Doppler spectrum.

3. The method for detecting group motion consistency based on radar range-Doppler spectrum according to claim 2, characterized in that: Before performing the windowing operation on the range dimension and the Doppler dimension of the radar raw data, the following steps are further included: The radar raw data is processed by static elimination algorithm to eliminate environmental noise.

4. The method for detecting group motion consistency based on radar range-Doppler spectrum according to claim 1, characterized in that: The peak detection of the region of interest also includes; Eliminate false detection targets through a constant false alarm rate algorithm.

5. The method for detecting group motion consistency based on radar range-Doppler spectrum according to claim 1, characterized in that: The frequency consistency detection of group movements by using the range-Doppler spectrum specifically includes: When detecting inconsistent group movements, the Doppler spectrum with the most peak points is taken as the main spectrum, and the remaining spectra are inconsistent spectra; Data with inconsistent spectra are marked in the range-Doppler spectrum.

6. The method for detecting group motion consistency based on radar range-Doppler spectrum according to claim 1, characterized in that: Outputting the consistency test result specifically includes the following steps: By processing the range-Doppler spectrum, point cloud data is obtained; Use clustering algorithms to separate the point cloud clusters corresponding to each member of the target group; The point cloud clusters corresponding to the coordinates of inconsistent individuals are marked, and a visual point cloud image is generated and output.

7. The method for detecting group motion consistency based on radar range-Doppler spectrum according to claim 6, characterized in that: The step of obtaining point cloud data by processing the range-Doppler spectrum specifically includes the following steps: Perform Doppler compensation and velocity disambiguation on the processed range-Doppler spectrum; Then perform the angular Fourier transform of the third dimension; The three-dimensional coordinates and speed of the target group are calculated based on the distance, azimuth and pitch angle of the target group from the radar to generate point cloud data.

8. A storage medium storing a computer program, wherein when the computer program is executed by a processor, the method for detecting group motion consistency based on radar range-Doppler spectrum according to any one of claims 1 to 7 is executed.

9. A group motion consistency detection system based on radar range-Doppler spectrum, characterized in that: Including millimeter wave radar, server and terminal equipment; The millimeter wave radar is connected to the server side, and is used to collect group movements of the target group to obtain radar raw data; The server side includes the storage medium according to claim 8, and the server side is used to execute the computer program in the storage medium; The terminal device is connected to the server terminal, and is used to receive the consistency detection result output by the server terminal.

Images