Living body detection method and device, storage medium and electronic equipment

Abstract

The invention discloses a living body detection method and device, a storage medium and electronic equipment, and the method comprises the steps: tracking each target in a to-be-detected environment through a millimeter wave radar, and generating the track information of each target; at each detection time point of the millimeter wave radar, synchronously utilizing the PIR sensor to carry out living body detection on the environment to be detected, and generating a living body detection result; according to the detection time point, fusing the track information with a corresponding living body detection result to generate a perception information time sequence of the target; obtaining cross validation intervals of the corresponding targets according to the perception information time sequence, and performing self-consistency verification on each cross validation interval; and when all the cross validation intervals of the target are self-consistent intervals, determining that the target is a living body. According to the invention, the accuracy of living body detection can be improved.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of living body detection, and particularly relate to a living body detection method and device, a storage medium and an electronic device. BACKGROUND

[0002] With the continuous development of smart home technology, target detection systems based on sensors have been widely applied in the fields of home security, environmental monitoring, automation control, etc. Living body detection, as a core technology in smart home systems, its main purpose is to identify and distinguish human bodies from other non-living body targets, so as to realize accurate environmental monitoring and intelligent response.

[0003] In traditional living body detection methods, a single sensor is often relied on for living body detection. However, a single sensor often has difficulty in providing reliable judgment in the presence of multiple interference factors and complex dynamic scenes. In particular, for living body detection of stationary or micro-movement targets, misjudgment is often prone to occur, and the accuracy of living body detection is relatively low. SUMMARY

[0004] Embodiments of the present application provide a living body detection method, device, storage medium and electronic device, which can improve the accuracy of living body detection.

[0005] In a first aspect, embodiments of the present application provide a living body detection method, comprising: tracking each target in a to-be-detected environment using a millimeter wave radar to generate trajectory information of each target; synchronously detecting living bodies in the to-be-detected environment using a PIR sensor at each detection time point of the millimeter wave radar to generate a living body detection result; fusing the trajectory information and the corresponding living body detection result according to the detection time point to generate a perception information time sequence of the target; obtaining a cross-validation interval of the target according to the perception information time sequence, and performing self-consistency verification on each cross-validation interval; when all the cross-validation intervals of the target are self-consistent intervals, determining that the target is a living body.

[0006] In the living body detection method provided in embodiments of the present application, the trajectory information includes a plurality of trajectory elements, and the fusion of the trajectory information and the corresponding living body detection result according to the detection time point to generate the perception information time sequence of the target comprises: pairing the living body detection result at the same time with the trajectory element based on the detection time point to form a perception element; arranging a plurality of perception elements in time sequence to generate the perception information time sequence of the target.

[0007] In the living body detection method provided in the embodiments of the present application, the cross-validation interval corresponding to the target is obtained according to the time sequence of the sensing information, and each cross-validation interval is verified for self-consistency, which comprises: filtering a continuous time period meeting a preset motion criterion from the time sequence of the sensing information as a cross-validation interval; verifying each cross-validation interval for self-consistency.

[0008] In the living body detection method provided in the embodiments of the present application, the verifying each cross-validation interval for self-consistency comprises: verifying the living body detection result contained in each cross-validation interval; when at least one living body detection result in a cross-validation interval is represented as a living body, determining that the cross-validation interval is a self-consistent interval; when all the living body detection results in a cross-validation interval are represented as non-living bodies, determining that the cross-validation interval is a non-self-consistent interval.

[0009] In the living body detection method provided in the embodiments of the present application, the filtering a continuous time period meeting a preset motion criterion from the time sequence of the sensing information as a cross-validation interval comprises: filtering a continuous time period meeting a condition from the time sequence of the sensing information based on a preset displacement criterion and / or a speed criterion; taking the continuous time period meeting the condition as a cross-validation interval.

[0010] In the living body detection method provided in the embodiments of the present application, the filtering a continuous time period meeting a preset motion criterion from the time sequence of the sensing information as a cross-validation interval comprises: traversing the time sequence of the sensing information based on a preset speed threshold and / or a preset displacement threshold; when there is a continuous time period in which the absolute values of the instantaneous speeds of a plurality of continuous sensing elements in the time sequence of the sensing information exceed the preset speed threshold, determining that the corresponding continuous time period meets the condition; and / or when there is a continuous time period in which the displacement change exceeds the preset displacement threshold, determining that the corresponding continuous time period meets the condition.

[0011] In the living body detection method provided in the embodiments of the present application, the tracking each target in the environment to be detected by using the millimeter wave radar to generate the trajectory information of each target comprises: receiving and processing echo signals of the millimeter wave radar to obtain point cloud data of one or more targets in a to-be-detected environment; performing clustering processing on the point cloud data to distinguish different targets; continuously tracking each target after clustering by using a multi-target tracking algorithm to generate trajectory information of each target.

[0012] In a second aspect, an embodiment of the present application provides a living body detection device, comprising: a tracking unit configured to track each target in a to-be-detected environment by using a millimeter wave radar to generate trajectory information of each target; a detection unit configured to synchronously detect a living body in the to-be-detected environment by using a PIR sensor at each detection time point of the millimeter wave radar to generate a living body detection result; a fusion unit configured to fuse the trajectory information and the corresponding living body detection result according to the detection time point to generate a perception information time sequence of the target; a verification unit configured to obtain a cross-validation interval of the target according to the perception information time sequence and perform self-consistency verification on each cross-validation interval; a determination unit configured to determine that the target is a living body when all the cross-validation intervals of the target are self-consistent intervals.

[0013] In a third aspect, the present application provides a storage medium, which stores a plurality of instructions, and the instructions are adapted to be loaded by a processor to execute the living body detection method of any one of the above aspects.

[0014] In a fourth aspect, the present application provides an electronic device, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the living body detection method of any one of the above aspects when executing the computer program.

[0015] In summary, the living body detection method provided in the embodiments of the present application comprises tracking each target in a to-be-detected environment by using a millimeter wave radar to generate trajectory information of each target; at each detection time point of the millimeter wave radar, a PIR sensor is used to detect the living body of the to-be-detected environment synchronously to generate a living body detection result; according to the detection time point, the trajectory information and the corresponding living body detection result are fused to generate a perception information time sequence of the target; a cross-validation interval corresponding to the target is obtained according to the perception information time sequence, and each cross-validation interval is verified for self-consistency; when all the cross-validation intervals of the target are self-consistent intervals, the target is determined to be a living body. The embodiments of the present application improve the accuracy of living body detection by synchronous detection and data fusion of the millimeter wave radar and the PIR sensor, and introduce a cross-validation interval decision mechanism based on time sequence. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment 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 effort.

[0017] Figure 1 is an application scenario diagram of the living body detection method provided in the embodiments of the present application.

[0018] Figure 2 is a flowchart of the living body detection method provided in the embodiments of the present application.

[0019] Figure 3 is a structural diagram of the living body detection device provided in the embodiments of the present application.

[0020] Figure 4 is a structural diagram of the electronic device provided in the embodiments of the present application. DETAILED DESCRIPTION

[0021] The exemplary embodiments will be described in detail herein with reference to the drawings. Unless otherwise indicated, the same numbers on the different drawings represent the same or similar elements. The following exemplary embodiments described in the following description are not meant to be exhaustive or to be limiting in scope to the precise embodiments set forth. They are presented for illustrative purposes only. They are not meant to be limiting as to the scope of the application, which is defined by the appended claims as interpreted in the light of this disclosure.

[0022] It should be noted that, in this document, the terms "comprise", "contain" or any other variant thereof are intended to cover a non-exclusive inclusion, so that a process, method, article or device that includes a list of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent in such a process, method, article or device. Without more limitations, the element defined by the statement "comprises a" does not exclude the presence of additional identical elements in the process, method, article or device that includes the element, in addition, components, features, elements with the same name in different embodiments of the present application can have the same meaning or different meanings, and the specific meaning thereof should be determined in combination with the explanation in the specific embodiment or the context in the specific embodiment.

[0023] It should be understood that the specific embodiments described herein are merely intended to explain the present application, and are not intended to limit the present application.

[0024] In the subsequent description, the suffix such as "module", "component" or "unit" used to represent elements is only for the convenience of the description of the present application, and has no specific meaning. Therefore, "module", "component" or "unit" can be used mixedly.

[0025] In the description of the present application, it should be noted that the terms "upper", "lower", "left", "right", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the indicated device or element must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first", "second" and the like are only for the purpose of description, and cannot be understood as indicating or implying relative importance.

[0026] In the traditional living body detection method, a single sensor is often used for living body detection, however, the single sensor often has difficulty in providing reliable judgment in the presence of multiple interference factors and complex dynamic scenes. In particular, for the living body detection of a stationary or micro-motion target, false judgments are often generated, and the accuracy of living body detection is low.

[0027] Based on this, the embodiments of the present application provide a living body detection method, device, storage medium and electronic equipment. Specifically, the living body detection device can be integrated in an electronic equipment, which can be a server or a terminal and the like. The terminal can include a mobile phone, a wearable smart device, a tablet computer, a notebook computer, a personal computer (PC) and the like. The server can be a single server or a server cluster composed of multiple servers, and can be a physical server or a virtual server.

[0028] For example, as shown in Figure 1 , the electronic device can track each target in the to-be-detected environment by using the millimeter wave radar to generate trajectory information of each target; at each detection time point of the millimeter wave radar, the to-be-detected environment is synchronously detected by using the PIR sensor to generate a living body detection result; according to the detection time point, the trajectory information is fused with the corresponding living body detection result to generate a time sequence of perception information of the target; a cross-validation interval of the corresponding target is obtained according to the time sequence of perception information, and each cross-validation interval is verified for self-consistency; when all the cross-validation intervals of the target are self-consistent intervals, it is determined that the target is a living body.

[0029] The technical solutions shown in the present application will be described in detail below through specific embodiments. It should be noted that the order of the following embodiments is not limited as the priority order of the embodiments.

[0030] Please refer to Figure 2 , Figure 2 is a flowchart of a living body detection method provided by an embodiment of the present application. The specific process of the living body detection method can be as follows: 101. Track each target in the to-be-detected environment by using the millimeter wave radar to generate trajectory information of each target.

[0031] The millimeter wave radar can emit a frequency-modulated continuous wave (FMCW) signal and receive a return signal thereof, thereby realizing active perception of the to-be-detected environment and generating trajectory information of each target.

[0032] Specifically, the return signal of the millimeter wave radar can be received and processed to obtain point cloud data of one or more targets in the to-be-detected environment; the point cloud data is processed by clustering to distinguish different targets; each target after clustering is continuously tracked by a multi-target tracking algorithm to generate trajectory information of each target.

[0033] In some embodiments, the return signal received by the millimeter wave radar can be processed by mixing, amplification, and analog-to-digital conversion, and then processed by Fast Fourier Transform (FFT) to analyze the distance, azimuth angle information of each scattering point in the to-be-detected environment relative to the millimeter wave radar, and directly obtain its radial velocity through Doppler shift analysis, and finally form a point cloud data frame containing distance, angle, and velocity information.

[0034] Since a single target is usually composed of multiple scattering points, clustering algorithms (such as DBSCAN, K-Means) can be used to process single-frame point cloud data, aggregate scattering points belonging to the same physical target together, and form individual target clusters, thereby distinguishing different targets.

[0035] To achieve continuous tracking of multiple targets, multi-target tracking algorithms (such as multi-hypothesis tracking (MHT) or joint probabilistic data association (JPDA) based on Kalman filtering) can be used to track each target.

[0036] In some embodiments, when new targets are generated in a new frame, multi-target tracking algorithms can be used to data associate these new targets with existing targets in the previous frame (such as using the nearest neighbor algorithm) to determine whether they are the same target. For successfully associated targets, Kalman filters can be used to predict their position coordinates and speed information at the next time, and then use the actual measurement values of the current frame to update and correct them, thereby outputting smooth and continuous trajectories. In addition, a unique identity identifier (ID) can be assigned to each newly appearing target, and the target can be tracked from its appearance, residence or movement in the environment, to its disappearance.

[0037] Finally, a trajectory information can be output for each target ID. The trajectory information is a time series, and the trajectory information includes several trajectory elements, each of which includes but is not limited to a detection time point, a position coordinate, and an instantaneous speed.

[0038] In some embodiments, the position coordinate can be the coordinate (x, y) of the target in the Cartesian coordinate system. The instantaneous speed is the speed vector of the target at the detection time point, which can be further decomposed into two key components: radial speed and tangential speed.

[0039] The radial speed can be directly measured by the millimeter wave radar through the Doppler effect, representing the speed component of the target approaching or moving away from the millimeter wave radar. The tangential speed can be calculated by comparing the change (i.e., displacement) of the position coordinate between consecutive frames and combining the time difference, representing the transverse motion speed component of the target perpendicular to the radial direction of the millimeter wave radar.

[0040] 102、At each detection time point of the millimeter wave radar, a PIR sensor is used to detect the living body in the environment to be detected, and a living body detection result is generated.

[0041] In some embodiments, the host chip of the millimeter wave radar can generate a high-level pulse signal as a synchronization trigger signal through a general input / output (GPIO) pin at each time of environmental detection. The synchronization trigger signal is directly transmitted to the signal processing circuit of the passive infrared (PIR) sensor. The PIR sensor is configured to trigger the working mode, and once the synchronization trigger signal is received, the living body detection of the to-be-detected environment is immediately started.

[0042] Through this "millimeter wave radar leading and PIR sensor following" hardware synchronization mode, it can be ensured that there is a living body detection result completely aligned in time at each detection time point of the millimeter wave radar, and the time error between the millimeter wave radar and the PIR sensor is controlled at the level of milliseconds or even microseconds.

[0043] In another embodiment, the power-on initialization can be synchronized by the host microprocessor (MCU) to start the power supply and working program of the millimeter wave radar and the PIR sensor, so that the millimeter wave radar and the PIR sensor start to run. A fixed sampling period T (for example, T=100 milliseconds, that is, 10 samples per second) can be set in the host MCU. The sampling period serves as a global synchronization clock reference.

[0044] At the starting time of each sampling period, the host MCU can read the data collected by the millimeter wave radar and the PIR sensor in the current period in parallel or in sequence extremely fast through software instructions. Since the reading action is controlled by the same clock source and the time interval is extremely short, it can be considered that the two groups of data are collected in the same time window, thereby realizing the synchronization at the software level.

[0045] After reading the two groups of data, the host MCU can mark the two groups of data with the same time stamp (detection time point). The time stamp is usually the starting time of the current sampling period or the time when the data reading is completed. Through the time stamp alignment method, even if there is a slight phase difference between the sampling clocks of the millimeter wave radar and the PIR sensor, the system level can also regard them as data of the same detection time point.

[0046] 103、According to the detection time point, the trajectory information and the corresponding living body detection result are fused to generate the perception information time sequence of the target.

[0047] In some embodiments, the living body detection result and the trajectory element at the same time can be paired to form a perception element based on the detection time point, and then a plurality of perception elements are arranged in time sequence to generate the perception information time sequence of the target.

[0048] For example, for each target tracked by the millimeter wave radar, a track element generated at a certain detection time point can be obtained, which contains the position coordinates and instantaneous speed of the target at the detection time point. At the same time, the living body detection result corresponding to the detection time point is retrieved from the output cache of the PIR sensor. The track element and the living body detection result are combined to form a perception element.

[0049] For each target, when a new perception element is generated, it can be arranged in the perception information time sequence of the corresponding target in chronological order.

[0050] 104. Obtain the cross-validation interval of the corresponding target according to the perception information time sequence, and perform self-consistency verification on each cross-validation interval.

[0051] Specifically, a continuous time period that meets the preset motion criterion can be selected from the perception information time sequence as a cross-validation interval, and then each cross-validation interval is subjected to self-consistency verification.

[0052] The preset motion criterion can include a speed criterion and / or a displacement criterion. Therefore, the step of "selecting a continuous time period that meets the preset motion criterion from the perception information time sequence as a cross-validation interval" can specifically be: based on the preset displacement criterion and / or speed criterion, selecting a continuous time period that meets the condition from the perception information time sequence; and taking the continuous time period that meets the condition as a cross-validation interval.

[0053] In some embodiments, a preset speed threshold (for example, 0.15 m / s) can be set, and when the absolute value of the instantaneous speed of a continuous time period in the perception information time sequence exceeds the preset speed threshold for N consecutive perception elements (N≥1, usually set to 3-5 according to the sampling rate), the continuous time period is identified as a cross-validation interval.

[0054] In some embodiments, a preset displacement threshold (for example, 0.5 m) can be set, and when the displacement change in a continuous time period in the perception information time sequence exceeds the preset displacement threshold, the continuous time period is identified as a cross-validation interval. The displacement change refers to the displacement value between the starting position and the ending position of the target in the continuous time period (i.e., the straight-line distance between the position coordinates in the starting perception element and the position coordinates in the ending perception element in the continuous time period).

[0055] In some embodiments, only the tangential displacement (i.e., the displacement component perpendicular to the radial direction of the millimeter wave radar) can be used as the displacement change, because it is a typical feature of human lateral movement and can effectively distinguish from many non-living body targets that mainly move radially.

[0056] That is, the step of "filtering out continuous time periods satisfying the condition from the time sequence of perception information based on the preset displacement criterion and / or speed criterion" can be: traversing the time sequence of perception information based on a preset speed threshold and / or a preset displacement threshold; when there are continuous time periods in the time sequence of perception information in which the absolute values of the instantaneous speeds of the continuous perception elements exceed the preset speed threshold, determining that the corresponding continuous time periods satisfy the condition; and / or when there are continuous time periods in the time sequence of perception information in which the displacement changes exceed the preset displacement threshold, determining that the corresponding continuous time periods satisfy the condition.

[0057] Wherein, the self-consistency verification of each cross-verification interval refers to judging whether the living body detection result in the cross-verification interval represents a living body.

[0058] When at least one living body detection result represents a living body, the cross-verification interval is determined to be a self-consistent interval. This indicates that when the target moves significantly, the PIR sensor also confirms its living body property, and the perceptions of the millimeter wave radar and the PIR sensor are consistent.

[0059] When all living body detection results in the cross-verification interval represent non-living bodies, the cross-verification interval is determined to be a non-self-consistent interval. This indicates that the target moving significantly is not identified as a living body by the PIR sensor, which exhibits the characteristics of "moving but not heating" and is most likely a non-living body interference.

[0060] That is, the step of "verifying the self-consistency of each cross-verification interval" can be: verifying the living body detection results contained in each cross-verification interval; when at least one living body detection result in a cross-verification interval represents a living body, determining that the cross-verification interval is a self-consistent interval; and when all living body detection results in a cross-verification interval represent non-living bodies, determining that the cross-verification interval is a non-self-consistent interval.

[0061] The embodiment introduces the concept of "cross-verification interval" to deeply correlate the originally independent trajectory information and discrete living body detection in a time window with discriminative significance. Not only can the instantaneous state of the target be determined, but also a comprehensive judgment can be made by analyzing the historical behavior segment (cross-verification interval), which can effectively deal with complex multi-target scenarios (such as the coexistence of a person and a sweeping machine) and maintain a very low false alarm rate.

[0062] 105、When all cross-verification intervals of the target are self-consistent intervals, the target is determined to be a living body.

[0063] Through the above embodiments, a living body state identifier can be labeled for each tracked target. When the final identity of the target needs to be output (for example, reported to a smart home system), the target can be checked in all historical cross-verification intervals that have been identified and verified, and the self-consistency verification result in the whole tracking period of the target. Only when all historical cross-verification intervals of the target are self-consistent intervals, the target is determined to be a living body. That is, at each time when the target shows significant motion (thus triggering cross-verification) in history, the behavior of the target is confirmed by the PIR sensor (at least once the living body detection result represents a living body). Such high behavior consistency is a typical feature of a living body target (such as a human).

[0064] In the embodiments of the present application, once a target is determined to be a living body, the living body state of the target will be continuously maintained. Even if the target subsequently enters a stationary state (no new cross-verification interval is generated), the target will still be reported as a living body until the target disappears or the state is reversed. The embodiments can ensure the continuity of human presence perception. Users will not experience frequent switching of living body states due to temporary stillness (such as sitting still), thereby achieving smooth and natural smart home control.

[0065] Wherein, the state reversal refers to that in subsequent tracking, a new cross-verification interval of the target is verified as inconsistent. At this time, the living body state of the target should be immediately reversed to "non-living body". The target disappearance refers to that the target leaves the environment to be detected and is determined to disappear by the millimeter wave radar, and the target ID is removed.

[0066] In the embodiments of the present application, if a target is determined to be inconsistent in any historical cross-verification interval, the target will be immediately and permanently determined to be a non-living body target. This state is irreversible in the whole tracking period of the target. The embodiments adopt a strict standard that "all cross-verification intervals need to be self-consistent", and give the veto right of "once inconsistent, forever determined to be a non-living body". The probability of misreporting a non-living body as a living body is greatly reduced from the algorithm level. The misjudgment problem in a multi-target scene (such as a human and a sweeping machine running in parallel) is effectively solved. Even if a non-living body target accidentally approaches a living body target, the "inconsistency" record in the history of the non-living body target can ensure that the non-living body target is correctly distinguished.

[0067] In summary, the living body detection method provided in the embodiments of the present application comprises tracking each target in a to-be-detected environment by using a millimeter wave radar to generate trajectory information of each target; at each detection time point of the millimeter wave radar, synchronously detecting the living body of the to-be-detected environment by using a PIR sensor to generate a living body detection result; fusing the trajectory information and the corresponding living body detection result according to the detection time point to generate a perception information time sequence of the target; obtaining a cross-validation interval of the corresponding target according to the perception information time sequence, and performing self-consistency verification on each cross-validation interval; and when all the cross-validation intervals of the target are self-consistent intervals, determining that the target is a living body. The embodiments of the present application fundamentally improve the accuracy of living body detection by synchronous detection and data fusion of the millimeter wave radar and the PIR sensor, and by introducing a cross-validation interval decision mechanism based on a time sequence.

[0068] To better implement the living body detection method provided in the embodiments of the present application, the embodiments of the present application further provide a living body detection device. The meanings of the terms are the same as those in the above living body detection method, and the specific implementation details can be referred to the description in the method embodiments.

[0069] Please refer to Figure 3 , Figure 3 is a structural schematic diagram of the living body detection device provided in the embodiments of the present application. The living body detection device can comprise a tracking unit 201, a detection unit 202, a fusion unit 203, a verification unit 204 and a determination unit 205. Among them, The tracking unit 201 is configured to track each target in a to-be-detected environment by using a millimeter wave radar to generate trajectory information of each target; The detection unit 202 is configured to, at each detection time point of the millimeter wave radar, synchronously detect the living body of the to-be-detected environment by using a PIR sensor to generate a living body detection result; The fusion unit 203 is configured to fuse the trajectory information and the corresponding living body detection result according to the detection time point to generate a perception information time sequence of the target; The verification unit 204 is configured to obtain a cross-validation interval of the corresponding target according to the perception information time sequence, and perform self-consistency verification on each cross-validation interval; The determination unit 205 is configured to, when all the cross-validation intervals of the target are self-consistent intervals, determine that the target is a living body.

[0070] The specific implementation of each unit can be referred to the above embodiments of the living body detection method, which will not be repeated here.

[0071] In summary, the living body detection device provided by the embodiment of the present application can track each target in the to-be-detected environment by the tracking unit 201 using the millimeter wave radar to generate trajectory information of each target; the detection unit 202 synchronously detects the living body of the to-be-detected environment by using the PIR sensor at each detection time point of the millimeter wave radar to generate a living body detection result; the fusion unit 203 fuses the trajectory information and the corresponding living body detection result according to the detection time point to generate a perception information time sequence of the target; the verification unit 204 obtains a cross-validation interval of the corresponding target according to the perception information time sequence, and performs self-consistency verification on each cross-validation interval; and the determination unit 205 determines that the target is a living body when all the cross-validation intervals of the target are self-consistent intervals. The embodiment of the present application improves the accuracy of living body detection by synchronous detection and data fusion of the millimeter wave radar and the PIR sensor, and introduces a cross-validation interval decision mechanism based on a time sequence.

[0072] The embodiment of the present application also provides an electronic device, which can integrate the living body detection device of the embodiment of the present application, as shown in Figure 4 The electronic device structure involved in the embodiment of the present application is shown, which shows a structural schematic diagram of the electronic device involved in the embodiment of the present application, in particular: The electronic device can include a processor 301 with one or more processing cores and a memory 302 with one or more computer readable storage media, and the like. Those skilled in the art can understand that the electronic device structure shown in Figure 4 The electronic device structure shown in the embodiment of the present application does not constitute a limitation on the electronic device, and can include more or fewer components than the diagram, or combine certain components, or different component arrangements. Among them: The processor 301 is the control center of the electronic device, which connects all parts of the electronic device through various interfaces and lines, executes the software programs and / or the present application stored in the memory 302 and the data stored in the memory 302, and processes various functions and data of the electronic device, thereby overall monitoring the electronic device. Optionally, the processor 301 can include one or more processing cores; preferably, the processor 301 can integrate an application processor and a modem processor, wherein the application processor mainly processes operation storage media, user interfaces and application programs, and the modem processor mainly processes wireless communication. It can be understood that the above-mentioned modem processor can also not be integrated into the processor 301.

[0073] The memory 302 can be used to store software programs and the present application, and the processor 301 executes various functional applications and data processing by running the software programs and the present application stored in the memory 302. The memory 302 can mainly include a program storage area and a data storage area, wherein the program storage area can store application programs required by at least one function of operating a storage medium, and the like; and the data storage area can store data created according to the use of the electronic device, and the like. In addition, the memory 302 can include a high-speed random access memory, and can also include a non-volatile memory such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state memory device. Accordingly, the memory 302 can also include a memory controller to provide access for the processor 301 to the memory 302.

[0074] Although not shown, the electronic device can also include a display unit, an input unit, a power supply, and the like, which will not be described here. In particular, in the present embodiment, the processor 301 in the electronic device will load the executable file corresponding to the process of one or more application programs into the memory 302 according to the following instructions, and run the application programs stored in the memory 302 by the processor 301, thereby realizing various functions, as follows: tracking each target in the to-be-detected environment by using the millimeter wave radar to generate trajectory information of each target; synchronously detecting living bodies in the to-be-detected environment by using the PIR sensor at each detection time point of the millimeter wave radar to generate a living body detection result; fusing the trajectory information and the corresponding living body detection result according to the detection time point to generate a time sequence of perception information of the target; obtaining a cross-validation interval of the corresponding target according to the time sequence of perception information, and performing self-consistency verification on each cross-validation interval; determining that the target is a living body when all cross-validation intervals of the target are self-consistent intervals.

[0075] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructions, or controlled by instructions related to hardware, which can be stored in a computer readable storage medium and loaded and executed by a processor.

[0076] To this end, the present application provides a storage medium having a plurality of instructions stored therein, which can be loaded by a processor to execute the steps in any method provided by the embodiments of the present application. For example, the instructions can execute the following steps: tracking each target in the to-be-detected environment by using the millimeter wave radar to generate trajectory information of each target; At each detection time point of the millimeter wave radar, a living body detection result is generated by synchronously detecting a living body in a to-be-detected environment by using the PIR sensor; According to the detection time point, the trajectory information is fused with the corresponding living body detection result to generate a perception information time sequence of the target; According to the perception information time sequence, a cross-validation interval of the corresponding target is obtained, and each cross-validation interval is verified for self-consistency; When all cross-validation intervals of the target are self-consistent intervals, the target is determined as a living body.

[0077] The specific implementation of each operation can refer to the foregoing embodiments, and will not be described here.

[0078] The storage medium can include a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0079] Since the instructions stored in the storage medium can execute the steps in any method provided in the embodiments of the present application, the beneficial effects that can be achieved by any method provided in the embodiments of the present application can be achieved, which are described in detail in the foregoing embodiments and will not be described here.

[0080] The living body detection method, device, storage medium, and electronic equipment provided in the present application are described in detail above, and the principles and implementation manners of the present application are described by applying specific examples in this paper. The foregoing example is only used to help understand the core idea of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation manner and application range will be changed, and in summary, the content of the specification should not be understood as a limitation of the present application.

Claims

1. A method for detecting liveness, characterized in that, include: Millimeter-wave radar is used to track each target in the environment to be detected, and trajectory information of each target is generated; At each detection time point of the millimeter-wave radar, a PIR sensor is used simultaneously to perform liveness detection on the environment to be detected, and a liveness detection result is generated. Based on the detection time point, the trajectory information is fused with the corresponding liveness detection result to generate a time series of perception information of the target; Based on the time series of the perceived information, obtain the cross-validation intervals corresponding to the target, and perform self-consistency verification on each cross-validation interval; The target is determined to be a live object when all of the cross-validation intervals of the target are self-consistent intervals.

2. The live detection method as described in claim 1, characterized in that, The trajectory information includes several trajectory elements. The step of fusing the trajectory information with the corresponding liveness detection result based on the detection time point to generate a time series of perception information for the target includes: Based on the detection time point, the liveness detection result at the same moment is paired with the trajectory element to form a sensing element; Arrange the aforementioned sensing elements in chronological order to generate a time sequence of sensing information for the target.

3. The live detection method as described in claim 1, characterized in that, The step of obtaining the cross-validation intervals corresponding to the target based on the time series of the perceived information, and performing self-consistency verification on each cross-validation interval, includes: Filter out continuous time periods that meet preset motion criteria from the time series of the perceived information as cross-validation intervals; Self-consistency verification is performed on each of the cross-validation intervals.

4. The live detection method as described in claim 3, characterized in that, The self-consistency verification of each of the cross-validation intervals includes: For each of the aforementioned cross-validation intervals, the liveness detection results contained therein are verified; When at least one of the liveness detection results in a cross-validation interval is characterized as a liveness, the cross-validation interval is determined to be a self-consistent interval. When all the liveness detection results in a cross-validation interval are characterized as non-liveness, the cross-validation interval is determined to be a non-consistent interval.

5. The live detection method as described in claim 3, characterized in that, The step of selecting continuous time periods that satisfy preset motion criteria from the time series of the perceived information as cross-validation intervals includes: Based on preset displacement criteria and / or velocity criteria, continuous time periods that meet the conditions are selected from the time series of the sensed information. The consecutive time periods that meet the conditions are used as cross-validation intervals.

6. The liveness detection method as described in claim 5, characterized in that, The step of filtering continuous time periods that meet the conditions from the time series of the sensed information based on preset displacement and / or velocity criteria includes: The time series of the sensed information is traversed based on a preset speed threshold and / or a preset displacement threshold. When there is a consecutive time period in the time series of the sensed information where the absolute value of the instantaneous velocity of multiple sensed elements exceeds a preset velocity threshold, the corresponding consecutive time period is determined to meet the condition; and / or When there is a continuous time period in the time series of the sensed information where the displacement change exceeds a preset displacement threshold, the corresponding continuous time period is determined to meet the condition.

7. The live detection method as described in claim 1, characterized in that, The process of using millimeter-wave radar to track targets in the environment to be detected and generating trajectory information for each target includes: It receives and processes the echo signals from millimeter-wave radar to obtain point cloud data of one or more targets in the environment to be detected. The point cloud data is clustered to distinguish different targets; A multi-target tracking algorithm is used to continuously track each of the clustered targets and generate trajectory information for each target.

8. A liveness detection device, characterized in that, include: The tracking unit is used to track each target in the environment to be detected using millimeter-wave radar and generate trajectory information for each target. The detection unit is used to synchronously perform liveness detection on the environment to be detected using a PIR sensor at each detection time point of the millimeter-wave radar, and generate liveness detection results. The fusion unit is used to fuse the trajectory information with the corresponding liveness detection result according to the detection time point to generate a time series of perception information of the target; The verification unit is used to obtain the cross-validation interval corresponding to the target based on the time series of the perceived information, and to perform self-consistency verification on each cross-validation interval. A determining unit is configured to determine that the target is a living entity when all of the cross-validation intervals of the target are self-consistent intervals.

9. A storage medium, characterized in that, The storage medium stores multiple instructions, which are adapted for loading by a processor to execute the liveness detection method according to any one of claims 1-7.

10. An electronic device, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the liveness detection method as described in any one of claims 1-7.

Images