A method for identifying a movement mode of a target object and a related device

Abstract

Embodiments of the present application provide a target object motion mode recognition method and related device, by collecting microwave signals of each scene element in a target scene, respectively performing corresponding signal processing, determining target motion signals corresponding to the target object in the target scene, and based on the signal-to-noise ratio and amplitude-frequency change rate of the target motion signals, determining the motion mode of the target object in the target scene, based on the above unified signal processing and signal analysis process, the category detection and the corresponding motion mode detection of the target object are realized synchronously, the utilization rate of the microwave radar is greatly improved, the deployment resource cost required for target detection is significantly reduced, and the resource utilization rate of target detection is improved.

Description

Technical Field

[0001] The present invention relates to the field of computers, and more particularly to a method for identifying the motion pattern of a target object and a related device. Background Art

[0002] Radar, a wireless sensor that uses electromagnetic waves to detect targets, has been widely used in civilian applications in recent years. Microwave radar, a type of radar, uses microwaves in the 1mm-1m range to detect targets. However, because microwave radar cannot selectively detect elements in the target environment, its detection is easily affected by environmental interference, often resulting in low detection accuracy.

[0003] For example, when microwave radar is used to detect target objects on the road, environmental factors including trees will be taken as detection targets at the same time, and ideal detection results cannot be obtained.

[0004] In order to eliminate environmental interference factors, the related technology requires video capture of the target object detected by the microwave radar, and then image analysis and processing of the captured video information to finally determine the category of the target object. However, this method still has the following drawbacks:

[0005] 1. Low resource utilization.

[0006] Under relevant technologies, additional video acquisition equipment and image analysis and processing equipment are needed to reprocess the information detected by the microwave radar. The microwave radar only plays the role of judging whether there is a target intrusion, and its resource utilization rate is low.

[0007] 2. Poor synchronization.

[0008] Under relevant technologies, the scene must be detected through microwave radar. After confirming the existence of the target object, the target object must be collected and analyzed using video acquisition equipment and image analysis and processing equipment before the category of the target object can be determined and environmental interference can be eliminated. This makes it impossible to simultaneously determine the presence and classification of the target object. Summary of the Invention

[0009] The embodiments of the present application provide a method for identifying the motion mode of a target object and a related device, which are used to accurately and synchronously identify the target object and its motion mode in an environment with interference factors.

[0010] In a first aspect, an embodiment of the present application provides a method for identifying a target object's motion pattern, comprising:

[0011] The microwave radar is used to collect data on a target scene with interference factors to obtain multiple microwave signal groups contained in the target scene; wherein each microwave signal group corresponds to each scene element.

[0012] Based on the signal frequencies corresponding to the microwave signals in the multiple microwave signal groups, the signal discreteness of each microwave signal is determined respectively, and the target microwave signals whose signal discreteness meets the set discrete conditions are selected. The signal frequencies and corresponding signal discreteness of each target microwave signal are fitted to obtain the corresponding target motion signal.

[0013] Based on the signal frequencies of the microwave signals, the noise energy of the noise elements contained in the target scene is determined, and based on the signal energy of the target motion signal, the corresponding target signal-to-noise ratio is obtained.

[0014] The motion mode of the target object is determined based on the target signal-to-noise ratio and the amplitude-frequency change rate of the target motion signal.

[0015] In a second aspect, an embodiment of the present application provides a device for identifying a target object's motion pattern, comprising:

[0016] The acquisition module is configured to collect data from a target scene with interference factors using a microwave radar, obtaining multiple microwave signal groups contained in the target scene; each microwave signal group corresponds to a scene element. The fitting module is configured to determine the signal discreteness of each microwave signal based on the signal frequencies corresponding to each microwave signal in the multiple microwave signal groups, select target microwave signals whose signal discreteness meets a set discreteness condition, and perform fitting on the signal frequencies and corresponding signal discreteness of each target microwave signal to obtain the corresponding target motion signal.

[0017] The signal-to-noise module is used to determine the noise energy of the noise elements contained in the target scene based on the signal frequencies of the respective microwave signals, and to obtain the corresponding target signal-to-noise ratio based on the signal energy of the target motion signal.

[0018] The determination module is used to determine the motion mode of the target object based on the target signal-to-noise ratio and the amplitude-frequency change rate of the target motion signal.

[0019] In an optional embodiment, when determining the signal discreteness of each microwave signal corresponding to each signal frequency of each microwave signal in a plurality of microwave signal groups, the fitting module is specifically configured to:

[0020] For multiple microwave signal groups, perform the following operations:

[0021] Based on the signal frequencies of the respective microwave signals in a microwave signal group, a corresponding signal frequency mean value of the microwave signal group is determined.

[0022] Based on the signal frequency mean, the signal frequencies of the microwave signals are debiased to obtain corresponding debiased signal frequencies.

[0023] Based on the frequencies of the respective de-biased signals, corresponding signal transformations are performed on the respective microwave signals to determine the signal dispersion of the respective microwave signals.

[0024] In an optional embodiment, when determining the noise energy of noise elements contained in the target scene based on the signal frequencies of the microwave signals, the signal-to-noise module is specifically configured to:

[0025] Based on the signal frequencies of the microwave signals, a microwave signal that meets a preset frequency condition is selected from the microwave signals as a corresponding noise signal.

[0026] Based on the signal energy of each noise signal, a corresponding noise energy value is obtained, and the noise energy value is used as the noise energy of the noise element included in the target scene.

[0027] In an optional embodiment, when selecting a microwave signal that meets a preset frequency condition from each microwave signal based on the signal frequency of each microwave signal as the corresponding noise signal, the signal-to-noise module is specifically configured to:

[0028] The signal frequencies of the microwave signals are sorted in descending order, and the noise frequency range corresponding to the target scene is determined based on the sorting position of the target microwave signal in the microwave signals.

[0029] Based on the signal frequencies of the microwave signals, the microwave signals whose signal frequencies belong to the noise frequency interval are selected as corresponding noise signals.

[0030] In an optional embodiment, when determining the noise frequency interval corresponding to the target scene based on the signal frequency of the corresponding target microwave signal and the sorting position in each microwave signal, the signal-to-noise module is specifically configured to:

[0031] If the ranking position of the target microwave signal in each microwave signal is not less than a preset first threshold, a first frequency interval starting from the ranking position is determined to be the noise frequency interval corresponding to the target scene.

[0032] If the ranking position of the target microwave signal in each microwave signal is smaller than a preset second threshold, a second frequency interval starting from the ranking position and moving backward is determined to be the noise frequency interval corresponding to the target scene.

[0033] If the sorting position of the target microwave signal in each microwave signal is less than the first threshold and not less than the second threshold, a third frequency interval forward from the sorting position and a fourth frequency interval backward from the sorting position are determined as noise frequency intervals corresponding to the target scene.

[0034] In an optional embodiment, when determining the motion mode of the target object based on the target signal-to-noise ratio and the amplitude-frequency change rate of the target motion signal, the determination module is specifically configured to:

[0035] If the target signal-to-noise ratio is not greater than the preset signal-to-noise threshold, it is further determined whether the target object is associated with the target scene for the first time. If so, the target motion mode of the target object is determined to be: the target object is stationary; otherwise, the target motion mode of the target object is determined to be: the historical motion mode of the corresponding target object has been saved.

[0036] If the target signal-to-noise ratio is greater than the signal-to-noise threshold, the motion mode of the target object is determined based on the amplitude-frequency change rate of the target motion signal.

[0037] In an optional embodiment, when determining the motion mode of the target object based on the amplitude-frequency change rate of the target motion signal, the determination module is specifically configured to:

[0038] If the amplitude-frequency change rate of the target motion signal belongs to the preset first amplitude-frequency interval, the motion mode of the target object is determined to be: the target object is approaching.

[0039] If the amplitude-frequency change rate of the target motion signal belongs to the preset second amplitude-frequency interval, it is determined that the motion mode of the target object is: the target object is moving away.

[0040] If the amplitude-frequency change rate of the target motion signal does not belong to the first amplitude-frequency interval and does not belong to the second amplitude-frequency interval, it is further determined whether the target object is associated with the target scene for the first time. If so, the target motion mode of the target object is determined to be: the target object is stationary; otherwise, the target motion mode of the target object is determined to be: the historical motion mode of the corresponding target object has been saved.

[0041] In a third aspect, an embodiment of the present application further provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the processor implements any one of the target object motion modes identified in the first aspect above.

[0042] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for identifying the motion mode of a target object according to the first aspect is implemented.

[0043] The technical effects brought about by any implementation method in the second to fourth aspects can refer to the technical effects brought about by the corresponding implementation method in the first aspect, and will not be repeated here.

[0044] The embodiments of the present application provide a method and related device for identifying the motion mode of a target object. The method collects the microwave signals of each scene element in the target scene, performs corresponding signal processing on each of the elements, and determines the target microwave signal corresponding to the target object in the target scene based on the signal discreteness of each microwave signal. The motion mode of the target object in the target scene is determined based on the signal-to-noise ratio and amplitude-frequency change rate of the target microwave signal. Based on the above-mentioned unified signal processing and signal analysis process, the method for identifying the motion mode of a target object proposed in the embodiments of the present application can simultaneously realize the category detection of the target object and the corresponding motion mode detection, thereby greatly improving the utilization rate of the microwave radar, thereby significantly reducing the deployment resource cost required for target detection and improving the resource utilization rate of target detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A schematic diagram of a possible application scenario provided by an embodiment of the present application;

[0046] Figure 2 A schematic diagram of a target scenario provided in an embodiment of the present application;

[0047] Figure 3 A flow chart of a method for identifying the motion mode of a target object provided in an embodiment of the present application;

[0048] Figure 4 A schematic diagram of a target object motion scene provided in an embodiment of the present application;

[0049] Figure 5 A flow chart of a method for determining noise energy provided in an embodiment of the present application;

[0050] Figure 6 A flow chart of a method for moving a target object provided in an embodiment of the present application;

[0051] Figure 7 A logical diagram of a target object's motion mode provided in an embodiment of the present application;

[0052] Figure 8 A schematic diagram of a device for identifying the motion pattern of a target object provided in an embodiment of the present application;

[0053] Figure 9 A schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0054] The following will be combined with the accompanying drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0055] The terms "first," "second," and the like in the specification and claims of this application and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, such that the embodiments of the application described herein can be practiced in orders other than those illustrated or described herein.

[0056] In order to improve the resource utilization of target detection and ensure the synchronization of target object category detection, the embodiment of the present application provides a method and related device for identifying the motion mode of a target object. By collecting the microwave signals of each scene element in the target scene, corresponding signal processing is performed respectively, and the target microwave signal corresponding to the target object in the target scene is determined based on the signal discreteness of each microwave signal, and the motion mode of the target object in the target scene is determined based on the signal-to-noise ratio and amplitude-frequency change rate of the target microwave signal. Based on the above-mentioned unified signal processing and signal analysis process, the target object motion mode identification method proposed in the embodiment of the present application can simultaneously realize the category detection of the target object and its corresponding motion mode detection, greatly improving the utilization rate of the microwave radar, thereby significantly reducing the deployment resource cost required for target detection and improving the resource utilization rate of target detection.

[0057] In addition, the above method enables the microwave radar to quickly determine the corresponding detection results based on the analysis of the signal frequency of each microwave signal while collecting relevant microwave signals, which significantly reduces the demand for sample data volume for target detection and further improves the analysis efficiency of target detection.

[0058] See Figure 1 As shown, a possible application scenario diagram provided by an embodiment of the present application is provided. The scenario diagram includes a microwave radar 110 and a service device 120, wherein the microwave radar 110 is used to collect various microwave signals in the target scene and analyze and process each microwave signal to implement the target object motion mode identification method proposed in the embodiment of the present application, and the service device 120 is used to obtain the target object motion mode analyzed by the microwave radar 110 and present the corresponding analysis results.

[0059] In an optional embodiment, the microwave radar can establish a communication connection that can be used for data transmission with one or more mobile terminals, computer terminals or similar computing devices, including but not limited to mobile phones, tablets, PCs, media players, smart wearable devices, smart TVs, vehicle-mounted devices and other electronic devices. Based on the established communication connection, the above-mentioned one or more electronic devices and the corresponding microwave radar can jointly implement the method for identifying the motion mode of the target object proposed in the embodiment of the present application. In other words, the method for identifying the motion mode of the target object proposed in the embodiment of the present application can be implemented by the microwave radar, or it can be implemented by a combination of the microwave radar and related electronic devices.

[0060] Based on the above scenario description, see Figure 2 As shown, it is a schematic diagram of the target scene to which the microwave radar belongs. The target scene contains target objects to be detected (such as people, animals, etc.) and environmental interference factors (such as leaves, obstacles, etc.). The microwave radar transmits signals to the target environment with interference factors to collect microwave signals reflected by each scene element in the target scene. Optionally, a preset sampling frequency Sampling is used to collect multiple microwave signal groups for the target scene. It is assumed that the number of Fourier transform (FFT) points determined by the microwave radar for the target scene is FFT_Num, and the amount of signal data for each microwave signal group is FFT_Data.

[0061] See Figure 3 As shown: Based on the collected microwave signal groups, the embodiment of the present application proposes a method for identifying the movement mode of a target object, including:

[0062] S301: Data is collected from a target scene with interference factors using a microwave radar to obtain multiple microwave signal groups contained in the target scene. Specifically, each microwave signal group corresponds to each scene element. The microwave radar uses a preset sampling frequency (e.g., 5.8 GHz) within a specified time range in the target scene to which the target object belongs to collect multiple microwave signal groups for the target scene. Each microwave signal group contains the microwave signals of each scene element contained in the target scene at a certain moment, and the signal data volume of each microwave signal group is the set collection data volume FFT_Data.

[0063] S302: Based on the signal frequencies corresponding to the microwave signals in the multiple microwave signal groups, the signal discreteness of each microwave signal is determined respectively, and each target microwave signal whose signal discreteness meets the set discrete condition is selected. The signal frequency and corresponding signal discreteness of each target microwave signal are fitted to obtain the corresponding target motion signal.

[0064] Specifically, to remove the DC component of each collected microwave signal, the following steps are performed for each group of microwave signals:

[0065] Step 1: Based on the signal frequencies of the respective microwave signals in a microwave signal group, determine a corresponding signal frequency mean of the microwave signal group.

[0066] Specifically, suppose that in a microwave signal group collected by a microwave radar, the corresponding microwave signals are a1~a FFT_Data , then the corresponding signal frequency mean is as follows:

[0067]

[0068] Based on the above steps, the corresponding signal frequency mean is obtained and the obtained signal frequency mean is As the DC component of the current microwave signal group.

[0069] Step 2: Based on the signal frequency mean, debias the signal frequencies of the microwave signals to obtain corresponding debiased signal frequencies.

[0070] Furthermore, debiasing is performed on each microwave signal in the current microwave signal group. In an optional embodiment, for the signal frequency of each microwave signal, a difference is taken from the corresponding signal frequency mean to determine the corresponding debiased signal frequency. Specifically, the debiased signal frequency is expressed as follows:

[0071]

[0072] Based on the above steps, the DC bias influence of the collected microwave signals is removed, and the de-biased signal frequencies corresponding to the respective microwave signals are determined.

[0073] Step 3: Based on the frequencies of the respective de-biased signals, perform corresponding signal transformations on the respective microwave signals to determine the signal dispersion of the respective microwave signals.

[0074] Specifically, based on the number of Fourier transform (FFT) points FFT_Num determined by the microwave radar for the target scene, the above microwave signals are subjected to a fast Fourier transform of FFT_Num points to obtain the corresponding signal discreteness FFT_a1~FFT_a FFT_Data .

[0075] Furthermore, for each corresponding signal discreteness of each microwave signal group, each target microwave signal whose signal discreteness meets the set discreteness condition is selected. Optionally, the microwave signal corresponding to the maximum signal discreteness in each microwave signal group is used as the corresponding target microwave signal, and the signal discreteness max_value and signal frequency max_index of each target microwave signal are recorded respectively.

[0076] Specifically, taking three microwave signal groups as an example, and in the above three microwave signal groups, the number of corresponding microwave signals is the same as the sampling frequency Sampling, then from each microwave signal group, the microwave signal corresponding to the maximum signal dispersion max_value is respectively used as the corresponding target microwave signal, and the signal frequency of the target microwave signal is recorded as max_index, as shown in the following Table 1:

[0077] Table 1

[0078] Microwave Signal Group Target microwave signal Signal dispersion Signal frequency <![CDATA[a1~a FFT_Data ]]> <![CDATA[a 1000 ]]> max_value_1 max_index_1 <![CDATA[a‘1~a’ FFT_Data ]]> <![CDATA[a’ 2000 ]]> max_value_2 max_index_2 <![CDATA[a‘’1~a‘’ FFT_Data ]]> <![CDATA[a‘’ 3000 ]]> max_value_3 max_index_3

[0079] Furthermore, differential filtering is performed on each determined target microwave signal, optionally as shown in the following formula:

[0080] output(i)=0.05*max_value(i)+0.95*output_lastvalue

[0081] output_lastvalue=output(i)

[0082] Among them, max_value(i) is the signal discreteness of the current target microwave signal, output(i) is the signal discreteness of the corresponding target microwave signal after differential filtering, and output_lastvalue is the determined historical signal discreteness.

[0083] Furthermore, since the sampling frequency of microwave radar is usually large in actual scenarios, in order to improve the computing efficiency of the data, a preset number of target microwave signals are selected from the collected microwave signals, denoted as Num_range, and the signal frequencies and signal discreteness of the above Num_range target microwave signals are fitted. Preferably, in order to improve the computing efficiency of curve fitting, a linear fitting method is used to obtain the corresponding target motion signal.

[0084] It is worth noting that the target motion signal represents the target scene element with the largest signal discreteness in the target scene, and the corresponding scene energy. By determining the standard deviation of the target motion signal, the energy change corresponding to the target scene element can be determined. The standard deviation of the target motion signal is determined by the mean of the signal discreteness of each target microwave signal. Assuming that the discreteness of each signal is The corresponding signal dispersion mean As shown in the following formula:

[0085]

[0086] The standard deviation M of the target motion signal is as follows:

[0087]

[0088] The relevant principles of target motion signals are further elaborated and explained below.

[0089] See Figure 4 As shown in FIG, in a possible scenario, the target object approaches (or moves away from) the microwave radar deployed in the target environment, and the corresponding target scene element is characterized by the above-mentioned target object. As the distance between the two becomes closer (farther), the scene energy changes more dramatically, and the standard deviation of the above-mentioned target motion signal increases accordingly. At this time, the environmental interference factors in the target scene have no effect on the signal energy of the target motion signal because they do not move radially.

[0090] In another possible scenario, only environmental interference factors move in the target scene (such as leaves blown by the wind), and the corresponding target scene elements are characterized as environmental interference. Due to the movement of the environmental interference factors, the energy of the corresponding scene is briefly increased. However, since the radial position of the environmental interference factors is often fixed and their distance from the microwave radar is fixed, their movement mode will not have a huge impact on the standard deviation of the target motion signal. Therefore, by analyzing the standard deviation of the target motion signal, it is possible to further determine whether the corresponding target scene element is characterized as a specified target object or environmental interference in the target scene.

[0091] S303: Determine the noise energy of the noise elements contained in the target scene based on the signal frequencies of the microwave signals, and obtain a corresponding target signal-to-noise ratio based on the signal energy of the target motion signal.

[0092] Specifically, a microwave signal that meets a preset frequency condition is selected from each microwave signal as the corresponding noise signal, and a corresponding noise energy value is obtained based on the signal energy of each noise signal, and the noise energy value is used as the noise energy of the noise element contained in the target scene. Optionally, a specified microwave signal group is selected from each collected microwave signal group, and a corresponding noise energy value is obtained based on the signal energy of each corresponding noise signal in the microwave signal group.

[0093] For example, based on microwave signal groups a1 to a FFT_Data , determine the corresponding noise signals, and determine the signal energy of each noise signal, wherein, refer to Figure 5 As shown in Figure 2, the noise energy contained in the target scene is determined in the following way:

[0094] S3031: Sort the signal frequencies of the microwave signals in descending order, and determine the noise frequency range corresponding to the target scene based on the sorted position of the target microwave signal in the microwave signals, where:

[0095] If the ranking position of the target microwave signal among the microwave signals is not less than the preset first threshold, the following S3032 is executed;

[0096] If the ranking position of the target microwave signal among the microwave signals is less than the preset second threshold, the following S3033 is executed;

[0097] If the ranking position of the target microwave signal among the microwave signals is smaller than the first threshold and not smaller than the second threshold, the following S3034 is executed.

[0098] The first threshold is a post-noise threshold pos_behind determined based on the specified number of protection units Np and the number of noise units N in the target scenario. In an optional embodiment, the post-noise threshold is determined based on the number of microwave signals in the current microwave signal group, the corresponding number of noise units, and the corresponding number of protection units, as shown in the following formula:

[0099] pos_behind=numel(data)-N / 2-Np / 2

[0100] Furthermore, the second threshold is a noise front threshold pos_front determined for a specified number of protection units Np and a specified number of noise units N in the target scenario. In an optional embodiment, the noise front threshold is determined based on the number of noise units and the number of protection units corresponding to the current microwave signal group, as shown in the following formula:

[0101] pos_front=N / 2+Np / 2

[0102] S3032: Determine the first frequency interval from the start of the sorting position forward as the noise frequency interval corresponding to the target scene, and select each microwave signal whose signal frequency belongs to the noise frequency interval as the corresponding noise signal.

[0103] For example, in an optional embodiment, if the sorting position max_index of the target microwave signal in each microwave signal is not less than the preset first threshold pos_behind, then starting from the sorting position max_index of the target microwave signal, after skipping Np / 2 microwave signals forward, starting from the microwave signal at max_index-Np / 2-1, the N / 2 microwave signals X1 to X1 forward from the start are sorted. N / 2 as the corresponding noise signals respectively.

[0104] S3033: Determine a second frequency domain interval from the start of the sorting position to the back, which is the noise frequency interval corresponding to the target scene, and select each microwave signal whose signal frequency belongs to the noise frequency interval as the corresponding noise signal.

[0105] For example, in an optional embodiment, if the sorting position max_index of the target microwave signal in each microwave signal is less than the preset second threshold pos_front, then starting from the sorting position max_index of the target microwave signal, after skipping Np / 2 microwave signals backward, starting from the microwave signal at max_index+Np / 2+1, the N / 2 microwave signals X from the start to the back are sorted. N / 2+1 ~X N as the corresponding noise signals respectively.

[0106] S3034: Determine the third frequency interval from the start of the sorting position forward and the fourth frequency interval from the start of the sorting position backward as the noise frequency intervals corresponding to the target scene, and select each microwave signal whose signal frequency belongs to the noise frequency interval as the corresponding noise signal.

[0107] For example, in an optional embodiment, if the ranking position max_index of the target microwave signal in each microwave signal is less than the first threshold pos_behind and not less than the second threshold pos_front, then starting from the ranking position max_index of the target microwave signal, after skipping Np / 2 microwave signals forward and backward respectively, starting from the microwave signal at max_index-Np / 2-1, or from the microwave signal at max_index+Np / 2+1, the N / 2 microwave signals X1 to X1 forward from the starting position are ranked. N / 2 , and N / 2 microwave signals X from the start to the end N / 2+1 ~X Nas the corresponding noise signals respectively.

[0108] Furthermore, after any one of the above steps S3032, S3033, and S3034 is completed, the following S3035 is executed to determine the noise energy contained in the target scene.

[0109] S3035: Obtain corresponding noise energy values ​​based on the signal energies of the respective noise signals, and use the noise energy values ​​as the noise energy of the noise elements included in the target scene.

[0110] Based on the noise signals determined in S3032, S3033, and S3034, the corresponding noise energy values ​​are determined respectively by cumulative summation. Specifically, the following situations are included:

[0111] Case 1: If each noise signal is a microwave signal belonging to the first frequency interval, then a corresponding noise energy value is obtained based on the signal energy of each of the above microwave signals, and the noise energy value is used as the noise energy of the noise element contained in the target scene.

[0112] For example, if each noise signal is N / 2 microwave signals X1 to X2 belonging to the first frequency interval, N / 2 , then the energy of each noise signal is accumulated and averaged to obtain the corresponding noise energy value, as shown in the following formula:

[0113]

[0114] Furthermore, the noise energy value Z is used as the noise energy of the noise elements contained in the target scene.

[0115] Case 2: If each noise signal is a microwave signal belonging to the second frequency interval, then a corresponding noise energy value is obtained based on the signal energy of each of the above microwave signals, and the noise energy value is used as the noise energy of the noise element contained in the target scene.

[0116] For example, if each noise signal is N / 2 microwave signals X belonging to the second frequency interval N / 2+1 ~X N , then the energy of each noise signal is accumulated and averaged to obtain the corresponding noise energy value, as shown in the following formula:

[0117]

[0118] Furthermore, the noise energy value Z is used as the noise energy of the noise elements contained in the target scene.

[0119] Case 3: If the noise signals are microwave signals belonging to the third frequency interval and the fourth frequency interval, corresponding noise energy values ​​are obtained based on the signal energies of the microwave signals, and the noise energy values ​​are used as the noise energy of the noise elements contained in the target scene.

[0120] For example, if the noise signals are N / 2 microwave signals belonging to the third frequency interval and X1 to X N / 2 , and N / 2 microwave signals X belonging to the fourth frequency interval N / 2+1 ~X N , then the energy of each noise signal is accumulated and averaged to obtain the corresponding noise energy value, as shown in the following formula:

[0121]

[0122] Furthermore, the noise energy value Z is used as the noise energy of the noise elements contained in the target scene.

[0123] Based on the above method, the noise energy contained in the target scene can be determined, and then further, based on the noise energy Z and the signal energy S of the target motion signal, the corresponding target signal-to-noise ratio SNR is obtained. Specifically, it is shown in the following formula:

[0124]

[0125] Among them, SNR is the determined target signal-to-noise ratio, Z is the noise energy contained in the target scene, and S is the signal energy of the target motion signal. In an optional embodiment, the energy corresponding to the target microwave signal in the same group as each microwave signal corresponding to the noise energy is used as the corresponding signal energy.

[0126] S304: Determine the motion mode of the target object based on the target signal-to-noise ratio and the amplitude-frequency change rate of the target motion signal.

[0127] Specifically, based on the determined target signal-to-noise ratio, the target object's motion mode is determined. Figure 6 As shown, specifically including:

[0128] S3041: Determine the target signal-to-noise ratio and the amplitude-frequency change rate of the target motion signal corresponding to the current target environment.

[0129] S3042: Determine whether the target signal-to-noise ratio is greater than a preset signal-to-noise threshold. If so, execute the following S3046; otherwise, execute S3043.

[0130] S3043: Determine whether the target object is associated with the target scene for the first time. If so, execute the following S3044; otherwise, execute S3045.

[0131] S3044: Determine the target motion mode of the target object: the target object is stationary.

[0132] S3045: Determine the target motion mode of the target object as: a historical motion mode that has been saved corresponding to the target object.

[0133] Furthermore, the motion mode of the target object is determined by the amplitude-frequency change rate and the preset first amplitude-frequency interval and second amplitude-frequency interval. Then, after S3045, the following steps are further included:

[0134] S3046: Determine whether the amplitude-frequency change rate of the target motion signal belongs to the preset first amplitude-frequency interval. If so, execute S3047; otherwise, execute S3048.

[0135] S3047: Determine the movement mode of the target object: the target object approaches.

[0136] S3048: Determine whether the amplitude-frequency change rate of the target motion signal belongs to the preset second amplitude-frequency interval. If so, execute S3049; otherwise, execute S3043.

[0137] S3049: Determine the movement mode of the target object: the target object moves away.

[0138] Specifically, if the target object is moving, the lower limit of the amplitude-frequency change rate of the target motion signal is determined to be slop, and the upper limit is mul*slop. In an optional embodiment, the first amplitude-frequency interval is determined to be (slop, mul*slop), and the second amplitude-frequency interval is determined to be (-mul*slop, -slop). When the amplitude-frequency change rate of the target motion signal belongs to the above-mentioned first amplitude-frequency interval, it is determined that the target object is close to the microwave radar in the scene; when the amplitude-frequency change rate of the target motion signal belongs to the above-mentioned second amplitude-frequency interval, it is determined that the target object is far away from the microwave radar in the scene; if the amplitude-frequency change rate of the target motion signal does not belong to the first amplitude-frequency interval and does not belong to the second amplitude-frequency interval, the movement mode of the target object cannot be determined based on the amplitude-frequency change rate. Optionally, the above-mentioned S3043 is executed to further determine whether the target object is associated with the target scene for the first time, so as to determine the movement mode of the target object based on the historical association record, as shown in the above-mentioned S3043 to S3045, which will not be repeated here.

[0139] See Figure 7As shown, it is a logical schematic diagram of the target object motion mode identification proposed in an embodiment of the present application. The microwave radar collects microwave signals in the target environment, performs corresponding signal processing on them, and determines the motion mode of the target object based on the fitted target motion signal. Among them, by collecting the standard deviation of the microwave signal, it is determined whether the target object exists in the target environment, and further by analyzing the target signal-to-noise ratio, whether the target object is moving, and further, by determining the motion mode of the target object through the amplitude-frequency change rate of the target motion signal. Based on the above method, the category detection of the target object and its corresponding motion mode detection can be achieved simultaneously, thereby greatly improving the utilization rate of the microwave radar and significantly improving the resource utilization rate of target detection.

[0140] See Figure 8 As shown, an apparatus for identifying the motion mode of a target object provided by an embodiment of the present application includes an acquisition module 801, a fitting module 802, a signal-to-noise module 803, and a determination module 804, wherein:

[0141] The acquisition module 801 is used to collect data of a target scene with interference factors through a microwave radar to obtain multiple microwave signal groups contained in the target scene; wherein each microwave signal group corresponds to each scene element.

[0142] The fitting module 802 is used to determine the signal discreteness of each microwave signal based on the signal frequencies corresponding to each microwave signal in the multiple microwave signal groups, select each target microwave signal whose signal discreteness meets the set discreteness condition, and fit the signal frequency and corresponding signal discreteness of each target microwave signal to obtain the corresponding target motion signal.

[0143] The signal-to-noise module 803 is configured to determine the noise energy of noise elements contained in the target scene based on the signal frequencies of the microwave signals, and obtain a corresponding target signal-to-noise ratio based on the signal energy of the target motion signal.

[0144] The determination module 804 is configured to determine the motion mode of the target object based on the target signal-to-noise ratio and the amplitude-frequency change rate of the target motion signal.

[0145] In an optional embodiment, when determining the signal discreteness of each microwave signal based on each signal frequency of each microwave signal in the plurality of microwave signal groups, the fitting module 802 is specifically configured to:

[0146] For multiple microwave signal groups, perform the following operations:

[0147] Based on the signal frequencies of the respective microwave signals in a microwave signal group, a corresponding signal frequency mean value of the microwave signal group is determined.

[0148] Based on the signal frequency mean, the signal frequencies of the microwave signals are debiased to obtain corresponding debiased signal frequencies.

[0149] Based on the frequencies of the respective de-biased signals, corresponding signal transformations are performed on the respective microwave signals to determine the signal dispersion of the respective microwave signals.

[0150] In an optional embodiment, when determining the noise energy of noise elements contained in the target scene based on the signal frequencies of the microwave signals, the signal-to-noise module 803 is specifically configured to:

[0151] Based on the signal frequencies of the microwave signals, a microwave signal that meets a preset frequency condition is selected from the microwave signals as a corresponding noise signal.

[0152] Based on the signal energy of each noise signal, a corresponding noise energy value is obtained, and the noise energy value is used as the noise energy of the noise element included in the target scene.

[0153] In an optional embodiment, when selecting a microwave signal that meets a preset frequency condition from the microwave signals based on the respective signal frequencies of the microwave signals as the corresponding noise signal, the signal-to-noise module 803 is specifically configured to:

[0154] The signal frequencies of the microwave signals are sorted in descending order, and the noise frequency range corresponding to the target scene is determined based on the sorting position of the target microwave signal in the microwave signals.

[0155] Based on the signal frequencies of the microwave signals, the microwave signals whose signal frequencies belong to the noise frequency interval are selected as corresponding noise signals.

[0156] In an optional embodiment, when determining the noise frequency interval corresponding to the target scene based on the signal frequency of the corresponding target microwave signal and the sorting position in each microwave signal, the signal-to-noise module 803 is specifically configured to:

[0157] If the ranking position of the target microwave signal in each microwave signal is not less than a preset first threshold, a first frequency interval starting from the ranking position is determined to be the noise frequency interval corresponding to the target scene.

[0158] If the ranking position of the target microwave signal in each microwave signal is smaller than a preset second threshold, a second frequency interval starting from the ranking position and moving backward is determined to be the noise frequency interval corresponding to the target scene.

[0159] If the sorting position of the target microwave signal in each microwave signal is less than the first threshold and not less than the second threshold, a third frequency interval forward from the sorting position and a fourth frequency interval backward from the sorting position are determined as noise frequency intervals corresponding to the target scene.

[0160] In an optional embodiment, when determining the motion mode of the target object based on the target signal-to-noise ratio and the amplitude-frequency change rate of the target motion signal, the determination module 804 is specifically configured to:

[0161] If the target signal-to-noise ratio is not greater than the preset signal-to-noise threshold, it is further determined whether the target object is associated with the target scene for the first time. If so, the target motion mode of the target object is determined to be: the target object is stationary; otherwise, the target motion mode of the target object is determined to be: the historical motion mode of the corresponding target object has been saved.

[0162] If the target signal-to-noise ratio is greater than the signal-to-noise threshold, the motion mode of the target object is determined based on the amplitude-frequency change rate of the target motion signal.

[0163] In an optional embodiment, when determining the motion mode of the target object based on the amplitude-frequency change rate of the target motion signal, the determination module 804 is specifically configured to:

[0164] If the amplitude-frequency change rate of the target motion signal belongs to the preset first amplitude-frequency interval, the motion mode of the target object is determined to be: the target object is approaching.

[0165] If the amplitude-frequency change rate of the target motion signal belongs to the preset second amplitude-frequency interval, it is determined that the motion mode of the target object is: the target object is moving away.

[0166] If the amplitude-frequency change rate of the target motion signal does not belong to the first amplitude-frequency interval and does not belong to the second amplitude-frequency interval, it is further determined whether the target object is associated with the target scene for the first time. If so, the target motion mode of the target object is determined to be: the target object is stationary; otherwise, the target motion mode of the target object is determined to be: the historical motion mode of the corresponding target object has been saved.

[0167] Based on the same inventive concept as the above-mentioned application embodiment, the present application embodiment also provides an electronic device that can be used to identify the movement of a target object. In one embodiment, the electronic device can be a server, or a terminal device or other electronic device. In this embodiment, the structure of the electronic device can be as follows: Figure 9 As shown, it includes a memory 901 , a communication interface 903 and one or more processors 902 .

[0168] Memory 901 is used to store computer programs executed by processor 902. Memory 901 may primarily include a program storage area and a data storage area. The program storage area may store an operating system and programs required for running instant messaging functions, while the data storage area may store various instant messaging messages and operating instruction sets.

[0169] Memory 901 may be a volatile memory, such as random-access memory (RAM); a non-volatile memory, such as read-only memory, flash memory, a hard disk drive (HDD), or a solid-state drive (SSD); or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto. Memory 901 may be a combination of the above memories.

[0170] The processor 902 may include one or more central processing units (CPUs) or digital processing units, etc. The processor 902 is configured to implement the above-mentioned method for identifying the motion mode of the target object when calling the computer program stored in the memory 901 .

[0171] The communication interface 903 is used to communicate with terminal devices and other servers.

[0172] The specific connection medium between the memory 901, the communication interface 903 and the processor 902 is not limited in the embodiment of the present application. Figure 9 In the embodiment, the memory 901 and the processor 902 are connected via a bus 904. Figure 9 The connections between the other components are shown in bold lines, which are only for illustration and are not intended to be limiting. The bus 904 can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, Figure 9 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0173] According to one aspect of the present application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, causing the computer device to perform any of the methods for identifying the motion pattern of a target object described in the above-described embodiments. The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0174] According to one aspect of the present application, the present application further provides a computer program product, which, when called by a computer, enables the computer to execute the method as described in the first aspect.

[0175] The embodiments of the present application provide a method and related device for identifying the motion mode of a target object. The method collects the microwave signals of each scene element in the target scene, performs corresponding signal processing on each of the elements, and determines the target microwave signal corresponding to the target object in the target scene based on the signal discreteness of each microwave signal. The motion mode of the target object in the target scene is determined based on the signal-to-noise ratio and amplitude-frequency change rate of the target microwave signal. Based on the above-mentioned unified signal processing and signal analysis process, the method for identifying the motion mode of a target object proposed in the embodiments of the present application can simultaneously realize the category detection of the target object and the corresponding motion mode detection, thereby greatly improving the utilization rate of the microwave radar, thereby significantly reducing the deployment resource cost required for target detection and improving the resource utilization rate of target detection.

[0176] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0177] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0178] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0179] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. A method for identifying the motion pattern of a target object, characterized in that: include: Collecting data of a target scene with interference factors using a microwave radar to obtain a plurality of microwave signal groups contained in the target scene; wherein each of the microwave signal groups corresponds to each scene element; Based on the signal frequencies corresponding to the microwave signals in the plurality of microwave signal groups, the signal discreteness of each of the microwave signals is determined, and each target microwave signal whose signal discreteness satisfies a set discrete condition is selected, and the signal frequency and the corresponding signal discreteness of each target microwave signal are fitted to obtain a corresponding target motion signal; Determining the noise energy of noise elements contained in the target scene based on the signal frequencies of the respective microwave signals, and obtaining a corresponding target signal-to-noise ratio based on the signal energy of the target motion signal; If the target signal-to-noise ratio is not greater than a preset signal-to-noise threshold, it is further determined whether the target object is associated with the target scene for the first time. If so, the target motion mode of the target object is determined to be: the target object is stationary; otherwise, the target motion mode of the target object is determined to be: a historical motion mode corresponding to the target object that has been saved; If the target signal-to-noise ratio is greater than the signal-to-noise threshold, the motion mode of the target object is determined based on the amplitude-frequency change rate of the target motion signal.

2. The method according to claim 1, wherein The determining, based on the respective signal frequencies corresponding to the respective microwave signals in the plurality of microwave signal groups, the signal dispersion of the respective microwave signals comprises: For each of the plurality of microwave signal groups, perform the following operations: determining a corresponding signal frequency mean of the microwave signal group based on the signal frequencies of the respective microwave signals in the microwave signal group; Based on the signal frequency mean, debiasing the signal frequencies of the microwave signals to obtain corresponding debiased signal frequencies; Based on the frequencies of the respective de-biasing signals, corresponding signal transformations are performed on the respective microwave signals to determine the signal dispersions of the respective microwave signals.

3. The method according to claim 1, wherein The determining, based on the signal frequencies of the microwave signals, the noise energy of the noise elements included in the target scene includes: Based on the signal frequencies of the microwave signals, selecting a microwave signal that meets a preset frequency condition from the microwave signals as a corresponding noise signal; Based on the signal energy of each noise signal, a corresponding noise energy value is obtained, and the noise energy value is used as the noise energy of the noise element included in the target scene.

4. The method according to claim 3, wherein The selecting, based on the signal frequencies of the microwave signals, a microwave signal that meets a preset frequency condition from the microwave signals as a corresponding noise signal includes: sorting the signal frequencies of the microwave signals in descending order, and determining a noise frequency interval corresponding to the target scene based on the sorted position of the target microwave signal in the microwave signals; Based on the signal frequencies of the microwave signals, microwave signals having signal frequencies belonging to the noise frequency interval are selected as corresponding noise signals.

5. The method according to claim 4, wherein Determining a noise frequency interval corresponding to the target scene based on a sorting position of the target microwave signal in the microwave signals includes: If the sorting position of the target microwave signal in the microwave signals is not less than a preset first threshold, determining a first frequency interval starting from the sorting position and forward as the noise frequency interval corresponding to the target scene; If the sorting position of the target microwave signal in the microwave signals is less than a preset second threshold, determining a second frequency interval starting from and backward from the sorting position as the noise frequency interval corresponding to the target scene; If the sorting position of the target microwave signal in the microwave signals is less than the first threshold and not less than the second threshold, a third frequency interval forward from the sorting position and a fourth frequency interval backward from the sorting position are determined as noise frequency intervals corresponding to the target scene.

6. The method according to claim 1, wherein The determining the motion mode of the target object based on the amplitude-frequency change rate of the target motion signal includes: If the amplitude-frequency change rate of the target motion signal belongs to a preset first amplitude-frequency interval, then the motion mode of the target object is determined to be: the target object is approaching; If the amplitude-frequency change rate of the target motion signal belongs to a preset second amplitude-frequency interval, it is determined that the motion mode of the target object is: the target object moves away; If the amplitude-frequency change rate of the target motion signal does not belong to the first amplitude-frequency interval and does not belong to the second amplitude-frequency interval, it is further determined whether the target object is associated with the target scene for the first time. If so, the target motion mode of the target object is determined to be: the target object is stationary; otherwise, the target motion mode of the target object is determined to be: the historical motion mode corresponding to the target object has been saved.

7. A device for identifying the movement of a target object, characterized in that: include: an acquisition module, configured to acquire data of a target scene with interference factors by using a microwave radar, and obtain a plurality of microwave signal groups contained in the target scene; wherein each of the microwave signal groups corresponds to each scene element; a fitting module for determining, based on the signal frequencies corresponding to the microwave signals in the plurality of microwave signal groups, the signal discreteness of each microwave signal, selecting target microwave signals whose signal discreteness satisfies a set discreteness condition, and fitting the signal frequencies and corresponding signal discreteness of each target microwave signal to obtain a corresponding target motion signal; a signal-to-noise module, configured to determine the noise energy of noise elements contained in the target scene based on the signal frequencies of the respective microwave signals, and obtain a corresponding target signal-to-noise ratio based on the signal energy of the target motion signal; a determination module, configured to, if the target signal-to-noise ratio is not greater than a preset signal-to-noise threshold, further determine whether the target object is associated with the target scene for the first time; if so, determine the target motion mode of the target object as: the target object is stationary; otherwise, determine the target motion mode of the target object as: a historical motion mode corresponding to the target object that has been saved; and if the target signal-to-noise ratio is greater than the signal-to-noise threshold, determine the motion mode of the target object based on the amplitude-frequency change rate of the target motion signal.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein: When the processor executes the computer program, the method for identifying the motion mode of a target object according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images