Target detection method and device, electronic equipment and storage medium

Abstract

The invention relates to a target detection method and device, electronic equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring corresponding energy data of a target detection area in a first time interval according to a corresponding detection signal of the target detection area in the first time interval; and determining whether a target exists in the target detection area or not according to the fluctuation condition of the energy data corresponding to the target detection area in the first time interval. By adopting the method, the accuracy of target detection can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of detection, and in particular to a target detection method and device, electronic equipment, computer readable storage medium and computer program product. BACKGROUND

[0002] With the development of computer technology, target detection technology has emerged. Target detection refers to the technology of identifying and locating specific targets in a target space. Target detection has a wide range of applications in many fields, such as autonomous driving, security monitoring, medical image analysis, etc.

[0003] In related technologies, when target detection is performed, whether there is a target in the region is usually determined by target movement tracking. However, target tracking often fails, i.e., it cannot continuously track the target, resulting in errors in target detection.

[0004] Therefore, in related technologies, there is a problem of low target detection accuracy. SUMMARY

[0005] Therefore, it is necessary to provide a target detection method, device, electronic equipment, computer readable storage medium and computer program product capable of improving target detection accuracy to solve the above technical problems.

[0006] In a first aspect, the present application provides a target detection method, comprising:

[0007] According to the detection signal corresponding to the target detection region in the first time interval, the energy data corresponding to the target detection region in the first time interval is obtained;

[0008] According to the fluctuation of the energy data corresponding to the target detection region in the first time interval, it is determined whether there is a target in the target detection region.

[0009] In a second aspect, the present application further provides a target detection method, comprising:

[0010] Display a scene calibration interface; the scene calibration interface includes a space layout diagram corresponding to an actual detection region;

[0011] In response to a region boundary calibration operation on the scene calibration interface, a calibrated target region is displayed in the scene calibration interface; wherein the region corresponding to the target region in the actual detection region is a target detection region;

[0012] displaying a target detection result corresponding to the target detection region in the target region; the target detection result is used to represent whether the target detection region has a target; whether the target detection region has a target is determined according to fluctuation of energy data corresponding to the target detection region in a first time interval; the energy data corresponding to the target detection region in the first time interval is determined according to a detection signal corresponding to the target detection region in the first time interval.

[0013] In a third aspect, the present application further provides a target detection device, comprising:

[0014] an acquisition module, configured to acquire energy data corresponding to the target detection region in a first time interval according to a detection signal corresponding to the target detection region in the first time interval;

[0015] a determination module, configured to determine whether the target detection region has a target according to fluctuation of the energy data corresponding to the target detection region in the first time interval.

[0016] In a fourth aspect, the present application further provides a target detection device, comprising:

[0017] an interface display module, configured to display a scene calibration interface; the scene calibration interface comprises a space layout diagram corresponding to an actual detection region;

[0018] a region display module, configured to display a calibrated target region in the scene calibration interface in response to a region boundary calibration operation on the scene calibration interface; wherein a region corresponding to the target region in the actual detection region is a target detection region;

[0019] a result display module, configured to display a target detection result corresponding to the target detection region in the target region; the target detection result is used to represent whether the target detection region has a target; whether the target detection region has a target is determined according to fluctuation of energy data corresponding to the target detection region in a first time interval; the energy data corresponding to the target detection region in the first time interval is determined according to a detection signal corresponding to the target detection region in the first time interval.

[0020] In a fifth aspect, the present application further provides an electronic device. The electronic device comprises a memory and a processor, the memory stores a computer program, and the computer program is executed by the processor to realize the steps of the above method.

[0021] In a sixth aspect, the present application provides a computer readable storage medium. The computer readable storage medium has a computer program stored thereon, and the computer program, when executed by a processor, implements the steps of the method described above.

[0022] In a seventh aspect, the present application provides a computer program product. The computer program product comprises a computer program, and the computer program, when executed by a processor, implements the steps of the method described above.

[0023] The target detection method, device, electronic device, storage medium and computer program product described above, by obtaining the energy data of the target detection region in the first time interval according to the detection signal corresponding to the target detection region in the first time interval, and determining whether the target detection region has a target according to the fluctuation of the energy data of the target detection region in the first time interval. In this way, by judging the fluctuation of the energy data in the target detection region in a period of time, it is determined whether the target detection region has a target. Compared with the method in the related art, the target detection region can be more accurately determined, and the target tracking loss is less likely to occur, which is beneficial to improve the accuracy of target detection. BRIEF DESCRIPTION OF DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the embodiments or the related art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0025] Figure 1 An application environment diagram of a target detection method in an embodiment;

[0026] Figure 2 A flowchart of a target detection method in an embodiment;

[0027] Figure 3 A flowchart of energy fluctuation threshold updating in an embodiment;

[0028] Figure 4 A schematic diagram of a distance-angle heat map in an embodiment;

[0029] Figure 5 A flowchart of another target detection method in an embodiment;

[0030] Figure 6 A schematic diagram of a scene calibration interface in an embodiment;

[0031] Figure 7 a flowchart of another target detection method in another embodiment;

[0032] Figure 8 a structural block diagram of a target detection device in an embodiment;

[0033] Figure 9 a structural block diagram of a target detection device in another embodiment;

[0034] Figure 10 an internal structural diagram of an electronic device in an embodiment. DETAILED DESCRIPTION

[0035] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not used to limit the present application.

[0036] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-described drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Rather, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0037] Figure 1 a schematic diagram of an implementation environment related to a target detection method. The implementation environment at least includes a gateway device 200 and a smart device 300 communicatively connected with the gateway device 200. Wherein, the number of gateway devices 200 can be at least one, and the number of smart devices 300 can be at least one. In addition, when the number of gateway devices 200 is multiple, different gateway devices 200 can also be communicatively connected. Wherein, the smart device 300 includes a target detection device 100. The target detection device 100 is used to detect whether there is a living target in a specific area (i.e. a target detection area). In some embodiments, the target detection device refers to an instrument for acquiring the surface geometric information of an object in an environment. The target detection device can include a radar device and other detection devices. Wherein, the radar device can include a laser radar and a millimeter wave radar device, etc. Wherein, the millimeter wave radar device is a radar system that uses millimeter wave frequency band for detection and measurement.

[0038] In the embodiments of the present application, the gateway device 200 can be a smart gateway for smart home control, and can implement functions such as system information collection, information input, information output, centralized control, remote control, linkage control, etc. The gateway device 200 can be responsible for specific security alarm, home appliance control, power consumption information collection, etc. The gateway device 200 can also interact with smart interactive terminals and other products through wireless means. The gateway device 200 also has wireless routing function, excellent wireless performance, network security and coverage area.

[0039] In the embodiments of the present application, the smart device 300 can include various smart home appliances, sensing devices and detection devices, etc. set in indoor spaces, such as smart televisions, smart refrigerators, smart air conditioners, temperature and humidity sensors, pressure sensors, smoke sensors, sockets, lamps, infrared emitting devices, camera devices, etc. The smart device 300 connected with the gateway device 200 can interact with the gateway device 200 in information and instructions. The gateway device 200 and the smart device 300 can be connected through communication modes such as Bluetooth, WiFi (Wireless-Fidelity), ZigBee (ZigBee), Matter, etc. Of course, the connection mode of the gateway device 200 and the smart device 300 can not be specifically limited in the embodiments of the present application.

[0040] In the embodiments of the present application, after obtaining the detection result of whether there is a target in the target detection area, the target detection device 100 can send the detection result to the gateway device 200, so that the gateway device 200 performs corresponding control or other processing, such as controlling the working state of the smart device 300 in the scene where the target detection area is located. For example, when it is determined that there is a person in the target detection area, the gateway device 200 controls the light in the scene where the target detection area is located to switch to the open state; for example, when it is determined that there is no person in the target detection area, the gateway device 200 controls the light in the scene where the target detection area is located to switch to the closed state.

[0041] Optionally, the implementation environment can also include a server 400 in communication connection with the gateway device 200. The server 400 can be a local server, a cloud server, etc. The specific server type can not be specifically limited in the embodiments of the present application. The server 400 connected with the gateway device 200 can interact with the gateway device 200 in information through wireless means. The gateway devices 200 set in different indoor spaces can be in communication connection with the same server 400 through the network to interact in information between the server 400 and the gateway device 200.

[0042] Optionally, the implementation environment can further include a terminal device 500. The terminal device 500 can be used for deploying (also understood as installing) a client associated with the smart device 300, and can include a personal computer (PC), a tablet computer, a smart phone, a personal digital assistant (PDA), and the like, which are not limited herein. The terminal device 500 can interact with the server 400 through wireless communication such as 2G / 3G / 4G / 5G / WiFi, and the like. Of course, the connection mode between the terminal device 500 and the server 400 is not limited in the embodiments of the present application. In some embodiments, the terminal device 500 can also be used for interacting with a user, so that the user can perform wireless communication between the gateway device 200 and the terminal device 500 based on the router 600 through the terminal device 500. In addition, the user can add an account information to the gateway device 200 and the terminal device 500 at the same time, and the information of the gateway device 200 and the terminal device 500 can be synchronized through the account information.

[0043] The client is associated with the smart device. In essence, a user registers an account in the client and configures the smart device 300 in the client. For example, the configuration includes adding a device identifier to the smart device 300, so that the terminal device 500 running the client can provide the user with device display and device control functions of the smart device. The client can be in the form of an application program or a web page. Correspondingly, the interface of the client for device display can be in the form of a program window or a web page, which is not limited herein.

[0044] In some embodiments, the user can set different trigger scenes or automation links through the client of the terminal device 500. As one way, the terminal device 500 can upload scene configuration information or an automation scheme to the server 400. When the trigger condition of the trigger scene or automation is reached, the server 400 can find a device corresponding to an execution action in the scene configuration information or the automation scheme according to the stored scene configuration information or the automation scheme, to notify the device to perform the execution action to meet the execution result of the trigger scene or automation. As another way, the server 400 can also send the scene configuration information or the automation scheme to the gateway device 200. The gateway device 200 can find a device corresponding to an execution action in the scene configuration information or the automation scheme according to the stored scene configuration information or the automation scheme. At the same time, the gateway device 200 can feed back the execution of the device to the server 400.

[0045] The interaction between the terminal device 500 and the intelligent device 300 can be implemented through a local area network, and can also be implemented through a wide area network. In one application scenario, the terminal device 500 establishes a communication connection in a wired or wireless manner between the router 600 and the gateway device 200, for example, the wired or wireless manner includes but is not limited to WIFI and the like, so that the terminal device 500 and the gateway device 200 are deployed in the same local area network, and then the terminal device 500 can realize the interaction with the intelligent device 300 through a local area network path. In another application scenario, the terminal device 500 establishes a communication connection in a wired or wireless manner between the server 400 and the gateway device 200, for example, the wired or wireless manner includes but is not limited to 2G, 3G, 4G, 5G, WIFI and the like, so that the terminal device 500 and the gateway device 200 are deployed in the same wide area network, and then the terminal device 500 can realize the interaction with the intelligent device 300 through a wide area network path.

[0046] The embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0047] In one exemplary embodiment, as shown in Figure 2 , a target detection method is provided, which is applied to the target detection device 100 in Figure 1 , and it can be understood that the method can also be applied to the server 400 or the terminal device 500 in Figure 1 . In this embodiment, the following steps S210 to S220 are included. Among them:

[0048] Step S210, according to the detection signal corresponding to the target detection area in the first time interval, the energy data corresponding to the target detection area in the first time interval is obtained.

[0049] Among them, the detection signal in the present application refers to the signal that can be used to detect whether there is a living target.

[0050] Among them, the first time interval can be a time interval that meets the first preset time length.

[0051] Among them, the first preset time length can be set according to actual needs.

[0052] Among them, the target detection area is an area that needs to detect whether the target exists. The target detection area can be a relatively large area, such as an office, a report hall, a cinema and the like, or a relatively small area, such as a living room, a bedroom, a sofa, a bed and the like in a house, and the size and shape of the target detection area are not limited here.

[0053] Among them, the energy data can be data containing energy values.

[0054] In specific implementations, the actual environment where the target detection region is located can be provided with a detection device (for example, a radar device, which will be taken as an example in the following description), which sends electromagnetic wave signals to the detection region corresponding to the radar device and receives electromagnetic wave signals reflected by the detection region. The detection region corresponding to the radar device contains the target detection region. It can be understood that the above-mentioned detection device can be the target detection device itself.

[0055] The detection signal corresponding to the target detection region can be obtained by preprocessing the electromagnetic wave signals reflected by the detection region. Thus, the target detection device can obtain the detection signal corresponding to the target detection region in the first time interval, and perform signal feature extraction based on the detection signal corresponding to the target detection region in the first time interval, thereby obtaining the energy data corresponding to the target detection region in the first time interval.

[0056] In some embodiments, the target detection region can be the region where the target detection device is located, or a part of the region where the target detection device is located.

[0057] Step S220, determining whether the target detection region has a target according to the fluctuation of the energy data corresponding to the target detection region in the first time interval.

[0058] In the present application, the target is a living body (such as a person, a pet, etc.). In practical applications, the target can also be named as a living body target.

[0059] In specific implementations, the target detection device can determine whether the target detection region has a target according to the fluctuation of the energy data corresponding to the target detection region in the first time interval.

[0060] In the above-mentioned target detection method, the energy data corresponding to the target detection region in the first time interval is obtained according to the detection signal corresponding to the target detection region in the first time interval, and whether the target detection region has a target is determined according to the fluctuation of the energy data corresponding to the target detection region in the first time interval. In this way, by judging the fluctuation of the energy data in the target detection region in a period of time, it is determined whether the target detection region has a target. Compared with the method in the related art, the target detection region can be more accurately determined whether the target exists in the target detection region, and the target tracking loss is less likely to occur, which is beneficial to improve the accuracy of target detection.

[0061] In one embodiment, step S210, obtaining the energy data corresponding to the target detection region in the first time interval according to the detection signal corresponding to the target detection region in the first time interval, comprises the following steps:

[0062] At step S2102, a detection signal corresponding to the target detection region at a current detection moment is obtained.

[0063] The first time interval can include the current detection moment.

[0064] Further, the first time interval can be a time interval ending at the current detection moment and satisfying a first preset time length. That is, the first time interval can be a time interval with the current detection moment as the right endpoint and satisfying the first preset time length.

[0065] The current detection moment can be a moment at which the target detection is currently performed, and can include a specific time point at which the target detection is currently performed.

[0066] As described above, the first time interval can be a time interval ending at the current detection moment and satisfying the first preset time length. In this way, the first time interval can include the current detection moment and a first historical detection moment before the current detection moment. The first historical detection moment includes a detection moment in the first time interval and before the current detection moment. The time length between the first historical detection moment and the current detection moment in the first time interval is the first preset time length.

[0067] In a specific implementation, as described above, the detection signal corresponding to the target detection region can be obtained by preprocessing the electromagnetic wave signal reflected by the detection region. In this way, the target detection device can preprocess the electromagnetic wave signal reflected by the detection region at the current detection moment, and obtain the detection signal corresponding to the target detection region at the current detection moment.

[0068] At step S2104, in a case where the current detection moment is within a preset time range, current energy data corresponding to the target detection region at the current detection moment is obtained according to the detection signal corresponding to the target detection region at the current detection moment.

[0069] The preset time range can refer to a time range preset in advance.

[0070] Specifically, the preset time range can refer to a time range after starting the target detection. The current detection moment can include a time point at which the target detection is currently performed, and the first historical detection moment can include a time point at which the target detection has been performed before and within the preset time range. For example, the preset time range can be from the 5th minute to the 50th minute after starting the target detection. If the target detection is performed once every minute, the current detection moment can be the 15th minute, and the first historical detection moment can be the 14th minute, the 13th minute, and the like, which are detection moments within the preset time range and before the current detection moment.

[0071] It can be understood that the first preset time length corresponding to the first time interval is less than or equal to the target length, and the target length refers to the length between the time of starting the target detection and the starting time in the preset time range. In the above example, the starting time of the preset time range is the 5th minute, and the first preset time length of the first time interval includes the time corresponding to the 5 detection times. For example, the first time interval can include the current detection time: the 5th minute, and the four first historical detection times before the current detection time, which are the 4th minute, the 3rd minute, the 2nd minute and the 1st minute. For example, the first time interval can include the current detection time: the 6th minute, and the four first historical detection times before the current detection time, which are the 5th minute, the 4th minute, the 3rd minute and the 2nd minute.

[0072] For example, the first preset time length of the first time interval can be the time corresponding to 4 detection times. For example, the first time interval can include the current detection time: the 5th minute, and the four first historical detection times before the current detection time, which are the 4th minute, the 3rd minute and the 2nd minute. For example, the first time interval can include the current detection time: the 6th minute, and the four first historical detection times before the current detection time, which are the 5th minute, the 4th minute and the 3rd minute.

[0073] In a specific implementation, in a case where the current detection time is in the preset time range, the target detection device can perform signal feature extraction according to the detection signal corresponding to the target detection region at the current detection time, to obtain the current energy data of the target detection region at the current detection time as the current energy data.

[0074] In step S2106, the historical energy data of the target detection region corresponding to each first historical detection time is obtained, and the energy data of the target detection region corresponding to the first time interval is obtained according to each historical energy data and the current energy data.

[0075] The historical energy data corresponding to each first historical detection time is obtained according to the detection signal corresponding to the target detection region at each first historical detection time.

[0076] In a case where the target detection device obtains the electromagnetic wave signal corresponding to one detection time, the electromagnetic wave signal corresponding to the detection time can be preprocessed, and the obtained processing result is used as the detection signal of the target detection region corresponding to the detection time. It can be understood that for each detection time in the first time interval, the above processing can be repeated to obtain the detection signal of the target detection region corresponding to each detection time in the first time interval.

[0077] The historical energy data corresponding to each first historical detection time is also energy data obtained by performing signal feature extraction on the detection signal of the target detection region corresponding to each first historical detection time.

[0078] In a specific implementation, the target detection device can obtain historical energy data of the target detection region corresponding to each first historical detection time, and obtain energy data of the target detection region corresponding to the first time interval according to the historical energy data and the current energy data. That is, the energy data of the target detection region corresponding to the first time interval includes the historical energy data corresponding to each first historical detection time in the first time interval, and the current energy data corresponding to the current detection time.

[0079] It can be understood that the end time of the first time interval is the current detection time, and the fluctuation of the energy data of the target detection region corresponding to the first time interval can be used as the fluctuation of the energy data of the target detection region corresponding to the current detection time, so that the target detection result in real time can be obtained.

[0080] The technical scheme of the embodiment includes the following steps: the first time interval includes the current detection time and the first historical detection time before the current detection time; the detection signal of the target detection region corresponding to the current detection time is obtained; in the case that the current detection time is within the preset time range, the current energy data of the target detection region corresponding to the current detection time is obtained according to the detection signal of the target detection region corresponding to the current detection time; the historical energy data of the target detection region corresponding to each first historical detection time is obtained, and the energy data of the target detection region corresponding to the first time interval is obtained according to the historical energy data and the current energy data; the historical energy data corresponding to each first historical detection time is obtained according to the detection signal of the target detection region corresponding to each first historical detection time.

[0081] In this way, the end time of the first time interval is the current detection time, and the energy data of the target detection region corresponding to the first time interval is obtained by considering the detection signal received at the current detection time. The fluctuation of the energy data of the target detection region corresponding to the first time interval can be used to determine whether the target detection region has a target at the current detection time, and real-time target detection can be achieved.

[0082] In one embodiment, the number of detection signals corresponding to the current detection moment is multiple, corresponding to each sub-region in the target detection region; according to the detection signal of the target detection region corresponding to the current detection moment, the current energy data of the target detection region corresponding to the current detection moment is obtained, including: converting the detection signal of each sub-region corresponding to the current detection moment into the current energy data of each sub-region corresponding to the current detection moment; accumulating the current energy data of each sub-region corresponding to the current detection moment to obtain the current energy data of the target detection region corresponding to the current detection moment.

[0083] Wherein, the target detection region includes multiple sub-regions. By dividing the target detection region, multiple sub-regions can be obtained.

[0084] In some embodiments, in the process of obtaining the detection signal by preprocessing the electromagnetic wave signal, the signal at different distances and different angles can be obtained by ranging processing and angle processing of the electromagnetic wave signal. In this way, the region where a signal in the target detection region is located can be used as a sub-region (Bin).

[0085] Wherein, as described above, the target detection region includes multiple sub-regions, therefore, the detection signal of the target detection region corresponding to the current detection moment includes the detection signal of each sub-region corresponding to the current detection moment.

[0086] In this way, in the process of obtaining the current energy data of the target detection region corresponding to the current detection moment according to the detection signal of the target detection region corresponding to the current detection moment, the target detection device can extract the signal features of the detection signal of each sub-region corresponding to the current detection moment to convert to energy data, to obtain the current energy data of each sub-region corresponding to the current detection moment, and then accumulate the current energy data of each sub-region corresponding to the current detection moment to obtain the current energy data of the target detection region corresponding to the current detection moment.

[0087] It can be understood that the method of obtaining the historical energy data of the target detection region corresponding to the first historical detection moment according to the detection signal of the target detection region corresponding to the first historical detection moment is the same as the above method for the current detection moment, which will not be described here.

[0088] Exemplarily, the detection signal corresponding to each sub-region is a complex number of a+bi. Wherein, a is a real number, i is an imaginary unit, and bi is an imaginary number. Assuming that the target detection region contains m bins (m sub-regions), the detection signal of the target detection region corresponding to the current detection moment (taking the current detection moment as N for example) is expressed as: (a N1 +b N1 i、a N2 +bN2 i、…、a Nm +b Nm i) Wherein, the first subscript of a and b is a time unit, indicating the detection signal corresponding to the detection time; the second subscript of a and b is a space unit, representing the sub-region in the target detection area. At the current detection time, the detection signal corresponding to each sub-region is converted into energy data and added to obtain the current energy data E of the target detection area corresponding to the current detection time:

[0089]

[0090] The technical scheme of the embodiment, the number of detection signals corresponding to the current detection time is multiple, corresponding to each sub-region in the target detection area; by converting the detection signal corresponding to each sub-region at the current detection time into the current energy data corresponding to each sub-region at the current detection time; accumulate the current energy data corresponding to each sub-region at the current detection time to obtain the current energy data corresponding to the target detection area at the current detection time. In this way, the detection signal corresponding to each sub-region in the target detection area at the current detection time is converted into the corresponding energy data, and the current energy data corresponding to each sub-region at the current detection time is accumulated, and the current energy data corresponding to the target detection area at the current detection time can be accurately obtained.

[0091] In another embodiment, the detection signal corresponding to the target detection area at the current detection time includes the detection signal of the target detection area in the second time interval corresponding to the current detection time; the second time interval includes the current detection time and at least one second historical detection time before the current detection time; according to the detection signal of the target detection area corresponding to the current detection time, the current energy data of the target detection area corresponding to the current detection time is obtained, including: according to the detection signal of the target detection area in the second time interval, the current energy data of the target detection area corresponding to the current detection time is obtained.

[0092] Wherein, the energy data corresponding to the target detection area at a single detection time can be obtained by converting the detection signal corresponding to the target detection area at a single detection time, and can also be obtained by converting the detection signal corresponding to multiple detection times.

[0093] Exemplarily, for the calculation of the current energy data of the target detection area at the current detection time, the detection signal corresponding to the current detection time can include the detection signal of the target detection area in the second time interval corresponding to the current detection time.

[0094] The second time interval can be a time interval ending at the current detection moment and satisfying a second preset time length. The second preset time length can be set according to actual needs. In this way, the second time interval can include the current detection moment and at least one second historical detection moment before the current detection moment.

[0095] The second historical detection moment includes a detection moment in the second time interval and before the current detection moment. A time length between the first second historical detection moment in the second time interval and the current detection moment is the second preset time length.

[0096] In this way, the detection signal in the second time interval corresponding to the current detection moment not only includes the detection signal acquired for the target detection region at the current detection moment, but also includes the detection signal acquired for the target detection region at each second historical detection moment.

[0097] If the first preset time length corresponding to the first time interval includes time lengths corresponding to p detection moments (that is, the first time interval includes p detection moments), and if the second preset time length corresponding to the second time interval includes time lengths corresponding to n detection moments (that is, the second time interval includes n detection moments), then the start moment T1 in the preset time range is greater than or equal to (n+p-1). That is, in the process of calculating the energy data corresponding to a single detection moment by comprehensively combining the detection signals corresponding to multiple detection moments, only when the current detection moment N is greater than or equal to (n+p-1), the fluctuation of the energy data corresponding to the target detection region in the first time interval can be calculated.

[0098] For example, if p=5 and n=4, then T1 is greater than or equal to 8. In the target detection process, the target detection device collects data at a certain frequency, and one frame of detection signal can be obtained at each detection moment. The previous frame of detection signal is the detection signal collected at the previous detection moment, and the current frame of detection signal is the detection signal collected at the current detection moment.

[0099] Correspondingly, the preset time range can be a preset frame range, the first time interval can refer to a first frame interval, the second time interval can refer to a second frame interval, the current detection moment can refer to a current detection frame, and the historical detection moment can refer to a historical detection frame. For example, if the start frame of the preset frame range is the 8th frame after starting target detection, and if the current detection frame N is the 8th frame, that is, N=8, then the second time interval corresponding to the current detection frame can include the 8th frame, the 7th frame, the 6th frame, and the 5th frame. The first time interval corresponding to the current detection frame can include the 8th frame, the 7th frame, the 6th frame, the 5th frame, and the 4th frame.

[0100] If the starting frame of the preset frame range is the 8th frame after starting target detection, if the current detection frame N is the 9th frame, i.e. N = 9, the second time interval corresponding to the current detection frame can include the 9th frame, the 8th frame, the 7th frame and the 6th frame; the first time interval corresponding to the current detection frame can include the 9th frame, the 8th frame, the 7th frame, the 6th frame and the 5th frame.

[0101] It can be understood that, when the energy data corresponding to a single detection moment is calculated based on the detection signal corresponding to the single detection moment, the starting moment T1≥p in the preset time range and the current detection moment N≥p, i.e. the fluctuation of the energy data corresponding to the target detection region in the first time interval can be calculated. For example, if p = 5, T1≥5, if the starting frame of the preset frame range is the 5th frame after starting target detection, if the current detection frame N is the 5th frame, i.e. N = 5, the first time interval corresponding to the current detection frame can include the 5th frame, the 4th frame, the 3rd frame, the 2nd frame and the 1st frame; if the current detection frame N is the 6th frame, i.e. N = 6, the first time interval corresponding to the current detection frame can include the 6th frame, the 5th frame, the 4th frame, the 3rd frame and the 2nd frame.

[0102] In this way, in the process of obtaining the current energy data corresponding to the target detection region at the current detection moment according to the detection signal of the target detection region at the current detection moment, the target detection device can perform signal feature extraction according to the detection signal of the target detection region in the second time interval, and obtain the current energy data corresponding to the target detection region at the current detection moment.

[0103] The technical scheme of the embodiment, the detection signal of the target detection region at the current detection moment includes the detection signal of the target detection region in the second time interval corresponding to the current detection moment; the second time interval includes the current detection moment and at least one second historical detection moment before the current detection moment; the current energy data of the target detection region at the current detection moment is obtained according to the detection signal of the target detection region in the second time interval. In this way, the calculation of the current energy data corresponding to the current detection moment can be performed by comprehensively calculating the detection signals corresponding to multiple historical detection moments including the historical detection moment, so that the current energy data corresponding to the current detection moment can be more accurately calculated.

[0104] In one embodiment, the current energy data corresponding to the target detection region at the current detection moment is obtained according to the detection signal of the target detection region in the second time interval, including: extracting the breathing data matching the breathing feature from the detection signal of the target detection region in the second time interval to obtain the breathing data corresponding to the target detection region in the second time interval; and converting the breathing data corresponding to the target detection region in the second time interval into energy data to obtain the current energy data corresponding to the target detection region at the current detection moment.

[0105] The breathing feature can include a feature exhibited by the living target when breathing.

[0106] In the process of obtaining the current energy data corresponding to the target detection region at the current detection moment according to the detection signal of the target detection region in the second time interval, the target detection device can extract the breathing data matching the breathing feature from the detection signal of the target detection region in the second time interval to obtain the breathing data corresponding to the target detection region in the second time interval.

[0107] For example, the target detection device can perform frequency spectrum analysis on the detection signal in the second time interval, and extract the frequency component related to the breathing feature from the detection signal after the frequency spectrum analysis, so that the breathing data matching the breathing feature can be obtained according to the frequency component related to the breathing feature.

[0108] In this way, the target detection device can convert the breathing data corresponding to the target detection region in the second time interval into energy data to obtain the current energy data corresponding to the target detection region at the current detection moment. In actual application, the corresponding energy data can be obtained according to the energy value of the breathing data in the corresponding frequency domain in the process of converting the breathing data into energy data.

[0109] The technical scheme of the embodiment extracts the breathing data matching the breathing feature from the detection signal of the target detection region in the second time interval to obtain the breathing data corresponding to the target detection region in the second time interval, and converts the breathing data corresponding to the target detection region in the second time interval into energy data to obtain the current energy data corresponding to the target detection region at the current detection moment.

[0110] Therefore, by extracting the breathing data matching the breathing feature of the living body target from the detection signal of the target detection region and converting the breathing data into energy data, whether the living body target exists in the target detection region can be more accurately determined according to the fluctuation of the energy data corresponding to the target detection region in the first time interval, and for the living body target that is long-time static or micro-movement, whether the living body target exists in the target detection region can also be effectively determined. The problem that the target detection is prone to error due to the loss of tracking of the long-time static or lying state of the living body target in the related art is solved, and the accuracy of target detection is effectively improved.

[0111] In one embodiment, the detection signal of the target detection region in the second time interval includes the detection signal of each sub-region in the target detection region in the second time interval; and the breathing data matching the breathing feature is extracted from the detection signal of the target detection region in the second time interval to obtain the corresponding breathing data of the target detection region in the second time interval, including: converting the detection signal of the target detection region in the second time interval into the frequency domain data corresponding to the target detection region in the second time interval; the number of frequency domain data is multiple, and each sub-region corresponds to a frequency domain data; the target frequency domain data matching the breathing feature of each sub-region in the second time interval is screened from the frequency domain data corresponding to each sub-region in the second time interval; and the corresponding breathing data of the target detection region in the second time interval is obtained according to the target frequency domain data corresponding to each sub-region.

[0112] In a specific implementation, in the process of extracting the breathing data matching the breathing feature from the detection signal of the target detection region in the second time interval to obtain the corresponding breathing data of the target detection region in the second time interval, the detection signal of the target detection region in the second time interval is converted into the frequency domain data corresponding to the target detection region in the second time interval. Since the target detection region includes multiple sub-regions (bins), the detection signal of the target detection region in the second time interval includes the detection signal of each sub-region in the target detection region in the second time interval. Therefore, the number of frequency domain data corresponding to the target detection region in the second time interval is multiple, and each sub-region corresponds to a frequency domain data.

[0113] The target detection device can perform spectrum analysis on the detection signal of the target detection region in the second time interval to obtain the frequency domain data corresponding to the target detection region in the second time interval.

[0114] Exemplarily, in the process of performing the spectrum analysis, the target detection device can perform a fast Fourier transform on the detection signal of each sub-region in the second time interval to obtain the frequency domain data corresponding to each sub-region in the second time interval.

[0115] Thus, the target detection device can screen out the frequency domain data matching the breathing feature of each sub-region in the second time interval from the frequency domain data corresponding to each sub-region in the second time interval as the target frequency domain data corresponding to each sub-region in the second time interval, and further obtain the breathing data corresponding to the target detection region in the second time interval through the target frequency domain data corresponding to each sub-region.

[0116] In this way, the target detection device can extract the frequency component matching the breathing feature from the frequency domain data corresponding to each sub-region in the second time interval to obtain the target frequency domain data.

[0117] In some embodiments, the breathing feature includes a breathing frequency range. Heartbeat and breathing can cause slight vibrations of the living target, and the vibration frequency range corresponding to the breathing of different living targets is different, so the breathing frequency range can be used to more accurately detect whether there is a living target.

[0118] Specifically, the target detection device can screen out the frequency domain data matching the breathing frequency range from the frequency domain data corresponding to each sub-region in the second time interval to obtain the target frequency domain data.

[0119] The technical scheme of the embodiment, the detection signal of the target detection region in the second time interval includes the detection signal of each sub-region in the target detection region in the second time interval; the detection signal of the target detection region in the second time interval is converted into the frequency domain data corresponding to the target detection region in the second time interval; the number of frequency domain data is multiple, corresponding to each sub-region; the target frequency domain data matching the breathing feature of each sub-region in the second time interval is screened out from the frequency domain data corresponding to each sub-region in the second time interval; and the breathing data corresponding to the target detection region in the second time interval is obtained according to the target frequency domain data corresponding to each sub-region.

[0120] In this way, the detection signal of the target detection region in the second time interval containing multiple sub-regions is converted into the frequency domain, the detection signal corresponding to each sub-region can be converted from the time domain to the frequency domain, so that the frequency domain data matching the breathing feature can be efficiently and accurately screened out from the frequency domain data corresponding to each sub-region in the second time interval, and further, the breathing data obtained based on the frequency domain data matching the breathing feature can be used to more accurately determine whether there is a living target in the target detection region.

[0121] In one embodiment, the target detection region corresponds to multiple pieces of breathing data in the second time interval, each corresponding to a sub-region; and the target detection region corresponds to breathing data in the second time interval is obtained according to the target frequency domain data corresponding to each sub-region, including: in the target frequency domain data corresponding to each sub-region, the target frequency domain data corresponding to each sub-region with the strongest energy is screened out; and the target frequency domain data corresponding to each sub-region with the strongest energy is taken as the breathing data corresponding to each sub-region in the second time interval.

[0122] In the process of obtaining the target detection region corresponding to breathing data in the second time interval according to the target frequency domain data corresponding to each sub-region, the target detection device can screen out the target frequency domain data corresponding to each sub-region with the strongest energy in the target frequency domain data corresponding to each sub-region in the second time interval; in this way, the target frequency domain data corresponding to each sub-region with the strongest energy in the second time interval can be taken as the breathing data corresponding to each sub-region in the second time interval.

[0123] The technical solution of the embodiment screens out the target frequency domain data corresponding to each sub-region with the strongest energy in the target frequency domain data corresponding to each sub-region; and takes the target frequency domain data corresponding to each sub-region with the strongest energy as the breathing data corresponding to each sub-region in the second time interval. In this way, since the breathing characteristics of the living target will show energy concentration in a certain frequency range in the frequency domain, by selecting the target frequency domain data with the strongest energy in the target frequency domain data matching the breathing characteristics of the living target, the breathing characteristics can be more accurately captured, which helps to accurately obtain the breathing data. Moreover, the target frequency domain data with the strongest energy usually represents the main component of the signal in the breathing frequency range of the living target, has a high signal-to-noise ratio and good signal quality, and by selecting the target frequency domain data with the strongest energy to obtain the breathing data, the stability and accuracy of the breathing data can be improved.

[0124] In some embodiments, in addition to obtaining the target frequency domain data corresponding to each sub-region in the second time interval by performing spectral analysis on the detection signal of each sub-region in the second time interval, for example, by fast Fourier transform processing, to select the target frequency domain data with the strongest energy in the target frequency domain data matching the breathing characteristics and obtain the breathing data corresponding to each sub-region in the second time interval, the detection signal of each sub-region in the second time interval can also be processed by other methods such as phase difference to obtain the breathing data corresponding to each sub-region in the second time interval.

[0125] In one embodiment, the respiration data corresponding to the target detection region in the second time interval is converted into energy data to obtain current energy data corresponding to the target detection region at the current detection moment, including: converting the respiration data corresponding to each sub-region in the second time interval into energy data corresponding to each sub-region in the second time interval; accumulating the energy data corresponding to each sub-region in the second time interval to obtain energy data corresponding to the target detection region in the second time interval; and taking the energy data corresponding to the target detection region in the second time interval as the current energy data corresponding to the target detection region at the current detection moment.

[0126] In a specific implementation, in the process of converting the respiration data corresponding to the target detection region in the second time interval into energy data to obtain the current energy data corresponding to the target detection region at the current detection moment, the target detection device can convert the respiration data corresponding to each sub-region in the second time interval into corresponding energy data to obtain energy data corresponding to each sub-region in the second time interval. The corresponding energy data can be obtained according to the energy value of the respiration data in the corresponding frequency domain.

[0127] In this way, the energy data corresponding to the target detection region in the second time interval can be obtained by accumulating the energy data corresponding to each sub-region in the second time interval. As described in the above embodiment, the second time interval can include the current detection moment and at least one second historical detection moment before the current detection moment, and therefore, the right endpoint of the second time interval can be the current detection moment. Correspondingly, the energy data corresponding to the target detection region in the second time interval can be taken as the current energy data corresponding to the target detection region at the current detection moment, so as to realize comprehensive calculation of the detection signals corresponding to multiple detection moments in the second time interval corresponding to the current detection moment to obtain the current energy data corresponding to the current detection moment.

[0128] The technical scheme of the embodiment converts the respiration data corresponding to each sub-region in the second time interval into energy data corresponding to each sub-region in the second time interval, accumulates the energy data corresponding to each sub-region in the second time interval to obtain energy data corresponding to the target detection region in the second time interval, and takes the energy data corresponding to the target detection region in the second time interval as the current energy data corresponding to the target detection region at the current detection moment.

[0129] Therefore, the target detection region includes a plurality of sub-regions, the energy data corresponding to each sub-region in the second time interval corresponding to the current detection time is converted, and the energy data corresponding to each sub-region in the second time interval is accumulated, so that the energy data corresponding to the target detection region in the second time interval is accurately obtained as the current energy data corresponding to the target detection region at the current detection time. The detection signals corresponding to a plurality of detection times in the second time interval corresponding to the current detection time are comprehensively calculated to improve the detection reliability, enhance the anti-interference performance, and make the current energy data corresponding to the current detection time obtained by calculation more reliable.

[0130] In one embodiment, the right endpoint of the first time interval is the current detection time, and whether the target exists in the target detection region is determined according to the fluctuation of the energy data corresponding to the target detection region in the first time interval, including: determining the energy fluctuation value corresponding to the target detection region at the current detection time according to the energy data corresponding to the target detection region in the first time interval; the energy fluctuation value is used to represent the fluctuation of the energy data corresponding to the target detection region in the first time interval; and in the case that the energy fluctuation value corresponding to the current detection time is less than the preset energy fluctuation threshold, it is determined that the target does not exist in the target detection region at the current detection time.

[0131] Therefore, in the process of determining whether the target exists in the target detection region according to the fluctuation of the energy data corresponding to the target detection region in the first time interval, the target detection device can first determine the energy fluctuation value corresponding to the target detection region at the current detection time according to the fluctuation of the energy data corresponding to the target detection region in the first time interval. Specifically, the target detection device can obtain the dispersion degree of the energy data corresponding to the target detection region in the first time interval according to the energy data corresponding to the target detection region at the current detection time and each first historical detection time in the first time interval, so as to determine the energy fluctuation value of the target detection region in the first time interval according to the dispersion degree of the energy data corresponding to the target detection region in the first time interval. As described in the above embodiment, the first time interval can be a time interval with the right endpoint being the current detection time and satisfying the first preset time length, and the first time interval can include the current detection time and the first historical detection time before the current detection time. Therefore, the energy fluctuation value can be used as the energy fluctuation value corresponding to the target detection region at the current detection time, and the fluctuation of the energy data corresponding to the target detection region in the first time interval is represented by the energy fluctuation value.

[0132] In practical applications, the dispersion degree of the energy data can be determined by calculating the variance or standard deviation of the energy data corresponding to the target detection region at the current detection time and each first historical detection time.

[0133] The calculation of the energy data corresponding to each first historical detection moment in the first time interval of the target detection region is the same as the calculation method of the current energy data corresponding to the current detection moment. Each first historical detection moment can be regarded as the current detection moment, and the above-mentioned method of calculating the current energy data corresponding to the current detection moment can be repeated to obtain the energy data corresponding to each first historical detection moment. The specific process is not described here.

[0134] In this way, whether there is a target in the target detection region at the current detection moment can be determined in real time by the energy fluctuation value corresponding to the target detection region at the current detection moment and the preset energy fluctuation threshold. Specifically, in the case where the energy fluctuation value corresponding to the current detection moment is less than the preset energy fluctuation threshold, it is determined that there is no target in the target detection region at the current detection moment; in the case where the energy fluctuation value corresponding to the current detection moment is greater than or equal to the preset energy fluctuation threshold, it is determined that there is a target in the target detection region at the current detection moment.

[0135] The technical scheme of the embodiment is that the right end point of the first time interval is the current detection moment; the energy fluctuation value corresponding to the target detection region at the current detection moment is determined according to the energy data corresponding to the target detection region in the first time interval; the energy fluctuation value is used to represent the fluctuation of the energy data corresponding to the target detection region in the first time interval; and in the case where the energy fluctuation value corresponding to the current detection moment is less than the preset energy fluctuation threshold, it is determined that there is no target in the target detection region at the current detection moment. In this way, since the living target with breathing and heartbeat has different energy fluctuations during exhalation and inhalation, and the non-living target does not have this feature, by comparing the energy fluctuation value representing the fluctuation of the energy data corresponding to the target detection region in the first time interval with the preset energy fluctuation threshold, whether there is a target in the target detection region can be more accurately determined.

[0136] In some embodiments, for the calculation of the energy fluctuation value, as described above, one frame of detection signal can be obtained at each detection moment, the first time interval can refer to the first frame interval, the current detection moment can refer to the current detection frame, and the historical detection moment can refer to the historical detection frame. Assuming that the first preset time length corresponding to the first time interval includes the time lengths corresponding to p detection moments, i.e., taking the first frame interval corresponding to the current detection frame as an example, which includes p frames, if the current detection frame is N, the energy data corresponding to the target detection region in the first frame interval includes the energy data (E N-p+1 , E N-p+2 , …, E N), the energy fluctuation value of the p energy data in the first time interval can be obtained according to the ratio between the average value of the p energy data and the standard deviation of the p energy data, and the energy fluctuation value represents the fluctuation of the p energy data in the first time interval.

[0137] Specifically, the formula is as follows:

[0138]

[0139]

[0140] Wave=std(E N-p+1 、E N-p+2 、……、E N ) / mean(E N-p+1 、E N-p+2 、……、E N )

[0141] Wherein, mean(E N-p+1 、E N-p+2 、……、E N ) is the average value of the p energy data in the first frame interval corresponding to the current detection frame, std(E N-p+1 、E N-p+2 、……、E N ) is the standard deviation of the p energy data, and Wave is the energy fluctuation value in the first frame interval.

[0142] Wherein, for the calculation of the energy data corresponding to a single detection time based on the detection signal corresponding to the single detection time, as described in the above embodiment, if the first time interval includes p frames, when the current detection frame N is greater than or equal to p, the fluctuation of the energy data corresponding to the target detection region in the first time interval can be calculated; for the calculation of the energy data corresponding to a single detection time based on the detection signal corresponding to multiple detection times, as described in the above embodiment, if the first time interval corresponds to p frames and the second time interval corresponds to n frames, when the current detection frame N is greater than or equal to (n+p-1), the fluctuation of the energy data corresponding to the target detection region in the first time interval can be calculated.

[0143] In one embodiment, the method further comprises: when the duration of the absence of the target in the target detection region meets the preset duration, updating the energy fluctuation threshold according to the fluctuation stability in the preset duration.

[0144] Wherein, the fluctuation stability is used to represent the stability of the energy fluctuation value detected in the preset duration.

[0145] Wherein, the preset duration can be set according to actual needs, for example, it can be 30 minutes. The specific value is not limited here.

[0146] In a specific implementation, when the duration that the target detection area does not have a target meets a preset duration, for example, the target detection device does not detect a target in the target detection area for 30 minutes, it is considered that the target detection area has not detected a target for a long time, and the energy fluctuation threshold can be updated according to the fluctuation stability in the preset duration.

[0147] To make those skilled in the art understand, Figure 3 A flowchart for updating an energy fluctuation threshold is provided. As Figure 3 shown, taking a target as a person for example, after the target detection device starts to calculate the fluctuation of energy data, it can judge whether the current detection time corresponds to the energy fluctuation value and the preset energy fluctuation threshold b. If the energy fluctuation value corresponding to the current detection time is less than the preset energy fluctuation threshold, it is determined that there is no person in the target detection area at the current detection time. If the energy fluctuation value corresponding to the current detection time is greater than or equal to the preset energy fluctuation threshold, it is determined that there is a person in the target detection area at the current detection time. If no human body is detected for a preset duration, the energy fluctuation threshold b is updated according to the fluctuation stability in the preset duration.

[0148] The technical solution of the embodiment updates the energy fluctuation threshold according to the fluctuation stability in the preset duration when the duration that the target detection area does not have a target meets a preset duration. In this way, when no target is detected in the target detection area for a preset duration, the energy fluctuation threshold is updated according to the fluctuation stability in the preset duration, which can correct the energy fluctuation threshold according to the fluctuation stability of the current state, thereby improving the accuracy and stability of target detection. By adaptively updating the energy fluctuation threshold, the robustness and applicability of the target detection algorithm can be improved better to adapt to different environments and conditions.

[0149] In one embodiment, the method further comprises: obtaining an energy fluctuation value corresponding to each detection time; determining a maximum value and a minimum value in the energy fluctuation value corresponding to each detection time; determining a fluctuation change range of the target detection area in the preset duration according to the difference between the maximum value and the minimum value; and the fluctuation change range is used to represent the fluctuation stability.

[0150] The preset duration includes a plurality of detection times, and each detection time corresponds to a different time interval. Specifically, each detection time corresponds to a different time interval to calculate the energy fluctuation value corresponding to each detection time. Specifically, each detection time can be taken as a current detection time, and the above method of calculating the energy fluctuation value corresponding to the current detection time is repeated to obtain the energy fluctuation value corresponding to each detection time. The specific calculation process is not described here.

[0151] In a specific implementation, in the process of determining the fluctuation stability of the target detection region within the preset time length, the target detection device can obtain a maximum value and a minimum value in the energy fluctuation values corresponding to the respective detection time of the target detection region. That is, the maximum energy fluctuation value and the minimum energy fluctuation value are obtained. In this way, the fluctuation change range of the target detection region within the preset time length can be obtained according to the difference between the maximum energy fluctuation value and the minimum energy fluctuation value of the target detection region within the preset time length. The fluctuation change range of the target detection region within the preset time length can represent the fluctuation stability of the target detection region within the preset time length.

[0152] The technical scheme of the embodiment obtains the energy fluctuation values corresponding to the respective detection time, determines the maximum value and the minimum value in the energy fluctuation values corresponding to the respective detection time, and determines the fluctuation change range of the target detection region within the preset time length according to the difference between the maximum value and the minimum value. The fluctuation change range is used to represent the fluctuation stability. In this way, the fluctuation change range within the preset time length is determined according to the difference between the maximum value and the minimum value in the multiple energy fluctuation values of the target detection region within the preset time length, which can more accurately represent the energy data stability of the target detection region within the preset time length, so as to effectively reflect the fluctuation stability of the target detection region within the preset time length.

[0153] In one embodiment, the detection signal corresponding to the current detection time of the target detection region is obtained by: obtaining the target signal collected at the current detection time through a detection device arranged in an actual environment where the target detection region is located; performing ranging processing and angle measurement processing based on the target signal to obtain a distance-angle heat map; the distance-angle heat map is used to represent the processed target signal at different distances and different angles; and determining the processed target signal belonging to the target detection region in the distance-angle heat map as the detection signal corresponding to the current detection time of the target detection region.

[0154] The detection device can be the target detection device itself. The detection device can be a radar device.

[0155] The target signal can be a signal converted by an analog-to-digital converter. Specifically, the radar device sends an electromagnetic wave signal to the detection region corresponding to the radar device, and receives an electromagnetic wave signal reflected by the detection region. The electromagnetic wave signal reflected by the detection region is a return signal. By inputting the return signal into an analog-to-digital converter (ADC), a converted digital signal (i.e., an ADC signal) can be obtained, which can be used as the target signal.

[0156] Thus, the target detection device can obtain the target signal corresponding to the detection region at the current detection moment by performing the above processing on the electromagnetic wave signal reflected by the detection region at the current detection moment. By performing the ranging processing and the angle measurement processing on the target signal corresponding to the detection region at the current detection moment, the target detection device can obtain a distance-angle heat map corresponding to the detection region at the current detection moment. The distance-angle heat map is used to represent the processed target signal at different distances and different angles. In order to facilitate the understanding of those skilled in the art, Figure 4 A schematic diagram of a distance-angle heat map is provided. As shown in Figure 4 The horizontal axis and the vertical axis represent the distance and the angle respectively, and the height axis represents the signal strength. Different distances and angles can determine a signal region (bin).

[0157] In the process of performing the ranging processing and the angle measurement processing on the target signal, the fast Fourier transform method is generally used. In the process of performing the angle measurement processing, some super-resolution algorithms can be used, for example, the super-resolution algorithm CAPON.

[0158] The distance-angle heat map corresponding to the current detection moment contains the processed signals of all regions in the detection region corresponding to the detection device. Therefore, the target detection device can determine the processed target signal belonging to the target detection region in the distance-angle heat map as the detection signal corresponding to the target detection region at the current detection moment.

[0159] Specifically, the target detection device can determine the signals belonging to the target detection region in the heat map according to the coordinate positions of the signals (the processed target signal is referred to as a signal for short) in the distance-angle heat map and the region boundary corresponding to the target detection region in the heat map.

[0160] Each signal belonging to the target detection region in the heat map is in a region (bin), which is regarded as each sub-region contained in the target detection region. Thus, the detection signal corresponding to each sub-region in the target detection region can be obtained according to the signals belonging to the target detection region in the heat map.

[0161] The technical scheme of the embodiment is that the detection device arranged in the actual environment where the target detection region is located acquires the target signal collected at the current detection moment; distance-angle heat maps are obtained through distance measurement processing and angle measurement processing based on the target signal; the distance-angle heat maps are used to represent the processed target signals at different distances and different angles; and the processed target signals belonging to the target detection region are determined in the distance-angle heat maps as the detection signals corresponding to the current detection moment of the target detection region. In this way, the target signal collected by the detection device in the actual environment where the target detection region is located is converted into a distance-angle heat map, which can intuitively represent the signals at different distances and different angles in the detection region of the detection device, so that the signals belonging to the target detection region are determined in the distance-angle heat map, and the technical effect of quickly and accurately acquiring the signals belonging to the target detection region can be achieved.

[0162] In some embodiments, it is assumed that the regions where m signals in the heat map are located fall within the target detection region, that is, the target detection region contains m bins (m sub-regions). For the process of converting the detection signals corresponding to multiple detection moments to obtain the energy data corresponding to a single detection moment of the target detection region, for example, the second time interval includes n detection moments, that is, the detection signals in the second time interval corresponding to the current detection moment of the target detection region include n frames of detection signals, and each frame of detection signal contains the detection signals corresponding to m bins, so the detection signals corresponding to the second time interval of the target detection region containing m bins include m*n detection signals. That is, each sub-region in the target detection region corresponds to n detection signals in the second time interval.

[0163] wherein each signal in the heat map is a complex number of a+bi. Wherein a is a real number, i is an imaginary unit, and bi is an imaginary number. In this way, for example, taking the current detection moment N as an example, the detection signal collected at the current detection moment is (a N1 +b N1 i、a N2 + N2 i、……、a Nm + Nm i); then the n detection signals in the second time interval corresponding to each sub-region at the current detection moment can be expressed as: (a (-n+1) + (-n+1) i、a (-n+2) + (-n+2) i、……、a Nk + Nk i), wherein the first subscript of a and b represents the time unit, indicating the detection signal corresponding to the detection moment; k represents the sub-region in the m sub-regions. For example, the first sub-region (k=1), the corresponding n detection signals can be expressed as: (a(-n+1) +b (-n+1) i、a (-n+2) + (-n+2) i、……、a N1 + N1 i)。

[0164] Thus, taking the current detection time as N as an example, the detection signal of the target detection area in the second time interval corresponding to the current detection time includes:

[0165] (a (N-n+1)1 + (N-n+1)1 i、a (N-n+1)2 + (N-n+1)2 i、……、a (N-n+1)m + (N-n+1)m i;

[0166] a (N-n+2)1 + (N-n+2)1 i、a (N-n+2)2 + (N-n+2)2 i、……、a (N-n+2)m +b (N-n+2)m i;

[0167] …

[0168] a N1 + N1 i、a N2 + N2 i、……、a Nm + Nm i)

[0169] a total of m*n detection signals.

[0170] In one embodiment, as shown in Figure 5 , a target detection method is provided, and the embodiment takes the terminal device 500 in the method applied to Figure 1 as an example. In the embodiment, the method includes the following steps:

[0171] Step S510, a scene calibration interface is displayed.

[0172] The scene calibration interface includes a space layout diagram corresponding to an actual detection area, and the scene calibration interface is configured to allow a user to select a region for which target detection is required.

[0173] The actual detection area can refer to a detection device arranged in an actual environment in which target detection is performed, and a corresponding detection area in the actual environment. In actual applications, the actual detection area can also be referred to as a detection area.

[0174] The space layout diagram is configured to represent the distribution of the actual detection area.

[0175] In a specific implementation, when target detection is needed, a UI (User Interface) of the terminal device can display a scene calibration interface.

[0176] At step S520, in response to a region boundary calibration operation on the scene calibration interface, a calibrated target region is displayed in the scene calibration interface.

[0177] The target region corresponds to a target detection region in the actual detection region.

[0178] The target detection region is a region in the actual environment where target detection is needed.

[0179] The region boundary calibration operation is an operation for calibrating a region where target detection is needed.

[0180] In a specific implementation, the user can select a region where target detection is needed according to a spatial layout diagram displayed in the scene calibration interface. The user can input a region boundary calibration operation on the scene calibration interface to the terminal device. The terminal device can determine the region calibrated by the user as the target region in response to the region boundary calibration operation on the scene calibration interface, and display the calibrated target region in the scene calibration interface. The region corresponding to the calibrated target region in the actual detection region is the target detection region where target detection is actually needed.

[0181] For example, the user wants to perform target detection on a sofa in the actual detection region. The user can calibrate the region boundary of the location of the sofa in the scene calibration interface to input the region boundary calibration operation to the terminal device. In actual applications, the region boundary calibration operation can be a box selection operation.

[0182] To facilitate understanding by those skilled in the art, Figure 6 A schematic diagram of a scene calibration interface is provided. All grid regions in the scene calibration interface correspond to the actual detection region. The target region in the dark part is the region calibrated by the user to represent the target detection region.

[0183] At step S530, a target detection result corresponding to the target detection region is displayed in the target region.

[0184] The target detection result is used to represent whether the target detection region has a target. Whether the target detection region has a target is determined according to the fluctuation of the energy data corresponding to the target detection region in the first time interval. The energy data corresponding to the target detection region in the first time interval is determined according to the detection signal corresponding to the target detection region in the first time interval.

[0185] The target detection result corresponding to the target detection region can be obtained according to the above embodiments, and details are not described herein.

[0186] In this way, after the target detection result corresponding to the target detection region is obtained, the target detection result corresponding to the target detection region can be displayed in the target region. In actual application, different colors or other identifiers can be used to distinguish whether the target detection region has a target. For example, a first color is used to represent that there is a target, and a second color different from the first color is used to represent that there is no target.

[0187] The target detection method described above comprises the following steps: displaying a scene calibration interface; the scene calibration interface comprises a spatial layout diagram corresponding to an actual detection region; in response to a region boundary calibration operation on the scene calibration interface, displaying a calibrated target region in the scene calibration interface; the target region corresponds to a target detection region in the actual detection region; displaying a target detection result corresponding to the target detection region in the target region; the target detection result is used to represent whether the target detection region has a target; whether the target detection region has a target is determined according to fluctuation of energy data corresponding to the target detection region in a first time interval; the energy data corresponding to the target detection region in the first time interval is determined according to a detection signal corresponding to the target detection region in the first time interval. In this way, by displaying the scene calibration interface, the user can clearly understand the spatial layout of the actual environment, so as to efficiently select and calibrate the region that needs to be subjected to target detection, so that the target detection result of the target detection region corresponding to the target region calibrated by the user in the actual detection region can be obtained, and the target detection result can be displayed on the calibrated target region in the scene calibration interface, so that the user can quickly obtain the target detection result of the target detection region, and the intelligent nature of human-computer interaction in the target detection process is improved.

[0188] In some embodiments, as shown in Figure 7 , a flowchart of another target detection method is provided, which is described by taking the target detection device as an example. As shown in Figure 7 , the user can calibrate the target region through the display scene calibration interface displayed by the terminal device, and the region corresponding to the target region in the actual detection region is the target detection region that actually needs to be subjected to target detection, and the target detection device connected to the terminal device can determine the target detection region and perform target detection in the actual detection region.

[0189] Specifically, the target detection region can include m sub-regions, each frame of detection signal contains m bins corresponding detection signals, if energy data is calculated by using detection signals corresponding to multiple detection moments, it is assumed that the second frame interval corresponding to the current frame includes n frames, when the current frame N is greater than or equal to n, n*m detection signals from the (N+n-1)th frame to the Nth frame are converted into frequency domain data, in the frequency domain data corresponding to each sub-region in the second frame interval, target frequency domain data corresponding to each sub-region in the second frame interval which matches the breathing feature is screened out, and in the target frequency domain data corresponding to each sub-region, target frequency domain data corresponding to each sub-region with the strongest energy is screened out, so as to obtain energy data corresponding to each sub-region in the second frame interval, and the energy data corresponding to each sub-region in the second frame interval is accumulated to obtain energy data corresponding to the target detection region in the second frame interval.

[0190] If the first frame interval corresponding to the energy fluctuation calculation includes p frames, it is judged whether the current frame N is greater than or equal to (n+p-1), if N≥(n+p-1), the energy fluctuation value of the energy data corresponding to each frame between the (N-p+1)th frame and the Nth frame is calculated, that is, the energy fluctuation value of (E N-p+1 , E N-p+2 , …, E N ) is calculated to obtain the energy fluctuation value corresponding to the current frame, in the case that the energy fluctuation value corresponding to the current detection moment is less than the preset energy fluctuation threshold, it is determined that there is no target in the target detection region at the current detection moment, in the case that the energy fluctuation value corresponding to the current detection moment is greater than or equal to the preset energy fluctuation threshold, it is determined that there is a target in the target detection region at the current detection moment.

[0191] In this way, the target detection device can send the target detection result indicating whether there is a target in the target detection region to the gateway device, so that the gateway device performs corresponding control or other processing, such as controlling the working state of the intelligent device in the scene where the target detection region is located. For example, when it is detected that there is a person in the target detection region, the gateway device controls the light in the scene where the target detection region is located to be in an open state; when it is detected that there is no person in the target detection region, the gateway device controls the light in the scene where the target detection region is located to be in a closed state.

[0192] Wherein, in the case that the duration when it is detected that there is no target in the target detection region satisfies the preset duration, the target detection device can update the energy fluctuation threshold according to the fluctuation stability in the preset duration.

[0193] It should be understood that, although the steps in the flowcharts involved in the embodiments described above are shown in sequence according to the arrows, the steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, the execution of the steps is not strictly limited in sequence, and the steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the embodiments described above can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution of the steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least some of the other steps or the steps or stages in the other steps.

[0194] Based on the same inventive concept, the embodiments of the present application also provide a target detection device for implementing the target detection method described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more target detection device embodiments provided below can refer to the limitations of the target detection method described above, and will not be repeated here.

[0195] In one exemplary embodiment, as shown in Figure 8 a target detection device is provided, comprising: an acquisition module 810 and a determination module 820, wherein:

[0196] The acquisition module 810 is configured to acquire energy data of a target detection area in a first time interval according to a detection signal corresponding to the target detection area in the first time interval.

[0197] The determination module 820 is configured to determine whether a target exists in the target detection area according to a fluctuation of the energy data of the target detection area in the first time interval.

[0198] In one of the embodiments, the first time interval includes a current detection time and a first historical detection time before the current detection time; the obtaining module 810 is specifically configured to obtain a detection signal corresponding to the target detection area at the current detection time; in the case that the current detection time is within a preset time range, obtain current energy data of the target detection area at the current detection time according to the detection signal corresponding to the target detection area at the current detection time; obtain historical energy data of the target detection area at each of the first historical detection times, and obtain energy data of the target detection area within the first time interval according to each of the historical energy data and the current energy data; the historical energy data corresponding to each of the first historical detection times is obtained according to the detection signal corresponding to the target detection area at each of the first historical detection times.

[0199] In one of the embodiments, the number of detection signals corresponding to the current detection time is multiple, which respectively correspond to each sub-area in the target detection area; the obtaining module 810 is specifically configured to convert the detection signal corresponding to each of the sub-areas at the current detection time into current energy data of each of the sub-areas at the current detection time; accumulate the current energy data of each of the sub-areas at the current detection time to obtain the current energy data of the target detection area at the current detection time.

[0200] In one of the embodiments, the detection signal of the target detection area at the current detection time includes a detection signal of the target detection area within a second time interval corresponding to the current detection time; the second time interval includes the current detection time and at least one second historical detection time before the current detection time; the obtaining module 810 is specifically configured to obtain the current energy data of the target detection area at the current detection time according to the detection signal of the target detection area within the second time interval.

[0201] In one of the embodiments, the obtaining module 810 is specifically configured to extract breathing data matching the breathing feature from the detection signal of the target detection area within the second time interval to obtain breathing data corresponding to the target detection area within the second time interval; convert the breathing data corresponding to the target detection area within the second time interval into energy data to obtain the current energy data of the target detection area at the current detection time.

[0202] In one of the embodiments, the detection signal of the target detection region in the second time interval includes detection signals of each sub-region in the target detection region in the second time interval; the obtaining module 810 is specifically configured to convert the detection signal of the target detection region in the second time interval into corresponding frequency domain data of the target detection region in the second time interval; the number of the frequency domain data is multiple, and each of the frequency domain data corresponds to a sub-region; target frequency domain data of each sub-region in the second time interval is filtered out from the corresponding frequency domain data of each sub-region in the second time interval; and the breathing data corresponding to the target detection region in the second time interval is obtained according to the target frequency domain data corresponding to each sub-region.

[0203] In one of the embodiments, the breathing data corresponding to the target detection region in the second time interval is multiple, and each of the breathing data corresponds to a sub-region; the obtaining module 810 is specifically configured to filter out the target frequency domain data with the strongest energy corresponding to each sub-region from the target frequency domain data corresponding to each sub-region; and the target frequency domain data with the strongest energy corresponding to each sub-region is taken as the breathing data corresponding to each sub-region in the second time interval.

[0204] In one of the embodiments, the obtaining module 810 is specifically configured to convert the breathing data corresponding to each sub-region in the second time interval into energy data corresponding to each sub-region in the second time interval; accumulate the energy data corresponding to each sub-region in the second time interval to obtain energy data corresponding to the target detection region in the second time interval; and take the energy data corresponding to the target detection region in the second time interval as the current energy data corresponding to the target detection region at the current detection moment.

[0205] In one of the embodiments, the right end point of the first time interval is the current detection moment; the determining module 820 is specifically configured to determine the energy fluctuation value corresponding to the target detection region at the current detection moment according to the energy data corresponding to the target detection region in the first time interval; the energy fluctuation value is used to represent the fluctuation of the energy data corresponding to the target detection region in the first time interval; and in the case that the energy fluctuation value corresponding to the current detection moment is less than a preset energy fluctuation threshold, it is determined that there is no target in the target detection region at the current detection moment.

[0206] In one of the embodiments, the device further includes a threshold updating module configured to update the energy fluctuation threshold according to the fluctuation stability in the preset time length in the case that the length of time during which it is detected that there is no target in the target detection region satisfies the preset time length.

[0207] In one of the embodiments, the preset time length comprises a plurality of detection time points, and each detection time point corresponds to a different time interval; the device further comprises a range determination module, configured to: acquire the energy fluctuation value corresponding to each detection time point; determine the maximum value and the minimum value in the energy fluctuation value corresponding to each detection time point; and determine the fluctuation change range of the target detection region in the preset time length according to the difference between the maximum value and the minimum value; the fluctuation change range is used to represent the fluctuation stability.

[0208] In one of the embodiments, the acquisition module 810 is specifically configured to: acquire the target signal collected at the current detection time point through a detection device arranged in an actual environment where the target detection region is located; perform ranging processing and angle measurement processing based on the target signal to obtain a distance-angle heat map; the distance-angle heat map is used to represent the processed target signal at different distances and different angles; and determine the processed target signal belonging to the target detection region in the distance-angle heat map as the detection signal corresponding to the target detection region at the current detection time point.

[0209] The above-mentioned modules in the target detection device can be all or partially implemented by software, hardware, and combinations thereof. The above-mentioned modules can be embedded in or independent of a processor in an electronic device in hardware form, or can be stored in a memory in the electronic device in software form, so as to be called and executed by a processor to perform the operations corresponding to the above-mentioned modules.

[0210] Based on the same inventive concept, the embodiments of the present application also provide a target detection device for implementing the target detection method described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more target detection device embodiments provided below can be referred to the limitations of the target detection method in the above text, which will not be described here again.

[0211] In one exemplary embodiment, as shown in Figure 9 a target detection device is provided, comprising: an interface display module 910, a region display module 920, and a result display module 930, wherein:

[0212] The interface display module 910 is configured to display a scene calibration interface; the scene calibration interface comprises a space layout diagram corresponding to an actual detection region.

[0213] The region display module 920 is configured to display a calibrated target region in the scene calibration interface in response to a region boundary calibration operation on the scene calibration interface; wherein the region corresponding to the target region in the actual detection region is a target detection region.

[0214] The result display module 930 is configured to display a target detection result corresponding to the target detection region in the target region, the target detection result being used to represent whether the target detection region has a target, and whether the target detection region has a target being determined according to fluctuation of energy data corresponding to the target detection region in a first time interval, and the energy data corresponding to the target detection region in the first time interval being determined according to a detection signal corresponding to the target detection region in the first time interval.

[0215] The above modules in the target detection device can be implemented by software, hardware, or a combination thereof, in whole or in part. The above modules can be embedded in or independent of a processor in an electronic device in hardware form, or can be stored in a memory in the electronic device in software form, so as to be called and executed by the processor to perform the operations corresponding to the above modules.

[0216] In an exemplary embodiment, an electronic device, which can be a server, has an internal structure diagram as shown in Figure 10 The electronic device includes a processor, a memory, an input / output interface (I / O), and a communication interface. The processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the electronic device is configured to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The database of the electronic device is configured to store energy fluctuation threshold data. The input / output interface of the electronic device is configured to exchange information between the processor and external devices. The communication interface of the electronic device is configured to communicate with external terminals through network connection. The computer program is executed by the processor to implement a target detection method.

[0217] Those skilled in the art can understand that Figure 10 The structure shown in the above embodiment is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the electronic device to which the scheme of the present application is applied. Specifically, the electronic device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0218] In one embodiment, an electronic device is also provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps in the above method embodiments.

[0219] In an embodiment, a computer readable storage medium is provided, and a computer program is stored on the computer readable storage medium, and the computer program is executed by a processor to implement the steps in the above method embodiments.

[0220] In an embodiment, a computer program product is provided, and the computer program product comprises a computer program, and the computer program is executed by a processor to implement the steps in the above method embodiments.

[0221] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of the related data need to comply with relevant regulations.

[0222] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0223] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0224] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A target detection method characterized by, The method comprises: According to the detection signal corresponding to the target detection area in the first time interval, the energy data corresponding to the target detection area in the first time interval is obtained; According to the fluctuation of the energy data corresponding to the target detection area in the first time interval, it is determined whether there is a target in the target detection area.

2. The method of claim 1, wherein, The first time interval includes the current detection time and the first historical detection time before the current detection time; the energy data corresponding to the target detection area in the first time interval is obtained according to the detection signal corresponding to the target detection area in the first time interval, comprising: Obtain the detection signal corresponding to the target detection area at the current detection time; In the case that the current detection time is within a predetermined time range, the current energy data corresponding to the target detection area at the current detection time is obtained according to the detection signal corresponding to the target detection area at the current detection time; Obtain the historical energy data corresponding to each of the first historical detection time of the target detection area, and obtain the energy data corresponding to the target detection area in the first time interval according to each of the historical energy data and the current energy data; the historical energy data corresponding to each of the first historical detection time is obtained according to the detection signal corresponding to each of the first historical detection time of the target detection area.

3. The method of claim 2, wherein, The number of detection signals corresponding to the current detection time is multiple, corresponding to each sub area in the target detection area; the current energy data corresponding to the target detection area at the current detection time is obtained according to the detection signal corresponding to the target detection area at the current detection time, comprising: Convert the detection signal corresponding to each of the sub area at the current detection time into the current energy data corresponding to each of the sub area at the current detection time; Accumulate the current energy data corresponding to each of the sub area at the current detection time to obtain the current energy data corresponding to the target detection area at the current detection time.

4. The method of claim 2, wherein, The detection signal corresponding to the target detection area at the current detection time includes the detection signal of the target detection area in the second time interval corresponding to the current detection time; the second time interval includes the current detection time and at least one second historical detection time before the current detection time; The current energy data corresponding to the target detection area at the current detection time is obtained according to the detection signal corresponding to the target detection area in the second time interval, comprising: According to the detection signal of the target detection area in the second time interval, the current energy data corresponding to the target detection area at the current detection time is obtained.

5. The method of claim 4, wherein, The current energy data corresponding to the target detection area at the current detection time is obtained according to the detection signal of the target detection area in the second time interval, comprising: extracting, from the detection signal of the target detection region in the second time interval, breathing data matching the breathing feature, to obtain corresponding breathing data of the target detection region in the second time interval; convert the corresponding breathing data of the target detection region in the second time interval into energy data, to obtain current energy data corresponding to the target detection region at the current detection moment.

6. The method of claim 5, wherein, The detection signal of the target detection region in the second time interval includes detection signals of each sub-region in the target detection region in the second time interval; the extracting, from the detection signal of the target detection region in the second time interval, breathing data matching the breathing feature, to obtain corresponding breathing data of the target detection region in the second time interval, includes: convert the detection signal of the target detection region in the second time interval into corresponding frequency domain data of the target detection region in the second time interval; the frequency domain data are multiple and correspond to each sub-region respectively; screen, from the corresponding frequency domain data of each sub-region in the second time interval, target frequency domain data of each sub-region in the second time interval matching the breathing feature; obtain, according to the corresponding target frequency domain data of each sub-region, corresponding breathing data of the target detection region in the second time interval.

7. The method of claim 6, wherein, The corresponding breathing data of the target detection region in the second time interval are multiple and correspond to each sub-region respectively; the obtaining, according to the corresponding target frequency domain data of each sub-region, of the corresponding breathing data of the target detection region in the second time interval includes: screen, from the corresponding target frequency domain data of each sub-region, target frequency domain data of each sub-region corresponding to the strongest energy; take the target frequency domain data of each sub-region corresponding to the strongest energy as the corresponding breathing data of each sub-region in the second time interval.

8. The method of claim 7, wherein, The converting the corresponding breathing data of the target detection region in the second time interval into energy data, to obtain current energy data corresponding to the target detection region at the current detection moment, includes: convert the corresponding breathing data of each sub-region in the second time interval into corresponding energy data of each sub-region in the second time interval; accumulate the corresponding energy data of each sub-region in the second time interval, to obtain energy data of the target detection region corresponding to the second time interval; take the energy data of the target detection region corresponding to the second time interval as current energy data corresponding to the target detection region at the current detection moment.

9. The method according to any one of claims 2-8, characterized in that, The right end point of the first time interval is the current detection moment; the determining, according to the fluctuation of the energy data of the target detection region in the first time interval, whether the target detection region has a target, includes: determine an energy fluctuation value corresponding to the target detection region at the current detection moment according to energy data corresponding to the target detection region in the first time interval; the energy fluctuation value is used to represent fluctuation of the energy data corresponding to the target detection region in the first time interval; in a case where the energy fluctuation value corresponding to the current detection moment is less than a preset energy fluctuation threshold, it is determined that the target detection region does not have a target at the current detection moment.

10. The method of claim 9, wherein, The method further comprises: in a case where a length of time during which it is detected that the target detection region does not have a target satisfies a preset length of time, updating the energy fluctuation threshold according to fluctuation stability in the preset length of time.

11. The method of claim 10, wherein, The preset length of time includes a plurality of detection moments, and each detection moment corresponds to a different time interval; the method further comprises: obtaining an energy fluctuation value corresponding to each detection moment; determining a maximum value and a minimum value in the energy fluctuation value corresponding to each detection moment; determining a fluctuation change range of the target detection region in the preset length of time according to a difference between the maximum value and the minimum value; the fluctuation change range is used to represent the fluctuation stability.

12. The method according to any one of claims 2-8, characterized in that, The method comprises: obtaining a target signal collected at the current detection moment through a detection device arranged in an actual environment in which the target detection region is located; performing ranging processing and angle measurement processing based on the target signal to obtain a distance-angle heat map; the distance-angle heat map is used to represent the processed target signal at different distances and different angles; determining the processed target signal belonging to the target detection region in the distance-angle heat map as the detection signal corresponding to the target detection region at the current detection moment.

13. A target detection method characterized by, The method comprises: displaying a scene calibration interface; the scene calibration interface includes a space layout diagram corresponding to an actual detection region; in response to a region boundary calibration operation on the scene calibration interface, displaying a calibrated target region in the scene calibration interface; wherein a region corresponding to the target region in the actual detection region is a target detection region; displaying a target detection result corresponding to the target detection region in the target region; the target detection result is used to represent whether the target detection region has a target; whether the target detection region has a target is determined according to fluctuation of energy data corresponding to the target detection region in a first time interval; the energy data corresponding to the target detection region in the first time interval is determined according to a detection signal corresponding to the target detection region in the first time interval.

14. A target detection apparatus characterized by comprising: The device comprises: an obtaining module configured to obtain energy data corresponding to a target detection region in a first time interval according to a detection signal corresponding to the target detection region in the first time interval; a determining module configured to determine whether the target detection region has a target according to fluctuation of the energy data corresponding to the target detection region in the first time interval.

15. A target detection apparatus characterized by comprising: The device comprises: An interface display module is configured to display a scene calibration interface; the scene calibration interface comprises a space layout diagram corresponding to an actual detection area; A region display module is configured to display a calibrated target region in the scene calibration interface in response to a region boundary calibration operation on the scene calibration interface; a region in the actual detection area corresponding to the target region is a target detection region; A result display module is configured to display a target detection result corresponding to the target detection region in the target region; the target detection result is used to represent whether the target detection region has a target; whether the target detection region has a target is determined according to fluctuation of energy data corresponding to the target detection region in a first time interval; the energy data corresponding to the target detection region in the first time interval is determined according to a detection signal corresponding to the target detection region in the first time interval.

16. An electronic device, comprising a memory and a processor, the memory storing a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 13.

17. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 13.

18. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 13.

Images