Personnel detection method, device, storage medium and electronic equipment

By clustering and matching the millimeter-wave radar point cloud data, the problem of insufficient radar detection capabilities for stationary personnel is solved, and the accuracy and sensitivity of personnel tracking and detection are improved.

CN114442081BActive Publication Date: 2024-11-15GREE ELECTRIC APPLIANCE INC OF ZHUHAI +1
View PDF 9 Cites 0 Cited by

Patent Information

Application Number
CN202111571158.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-12-21
Publication Date
2024-11-15
Estimated Expiration
2041-12-21

AI Technical Summary

Technical Problem

The existing personnel detection based on millimeter-wave radars is weak in detection capabilities of people who are stationary or perform tiny movements, resulting in the problem of personnel targets and loss.

Method used

By obtaining point cloud data of the target area, clustering to obtain candidate targets, confirming whether the position information in the lost person list matches the candidate target, and reducing the formation conditions of the candidate target when matching. If the target can still be formed, it is determined as Real target, marked as a person and continue tracking and detection, deleting information from the missing person list.

Benefits of technology

It improves the accuracy and sensitivity of personnel tracking and detection, and realizes effective detection and tracking of static personnel.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114442081B_ABST
    Figure CN114442081B_ABST
Patent Text Reader

Abstract

The present application relates to the field of target detection technology, and specifically to a personnel detection method, device, storage medium and electronic device, including: clustering according to point cloud data to obtain candidate targets; confirming whether there is target location information in the location information of all lost persons in the lost person list; the target location information is the location information of the lost person whose deviation from the location information of the candidate target is less than or equal to a preset deviation; when the target location information exists, reducing the formation conditions of the candidate target; if the candidate target can still be formed after reducing the formation conditions of the candidate target, it is determined that the candidate target and the lost person obtained by comparison are the same target; and continuing tracking and detection after marking the candidate target as a person. The present application realizes the recovery of persons lost due to the stationary target person by establishing a lost person list, realizes the re-tracking and detection of lost targets, and improves the accuracy and sensitivity of personnel tracking detection.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of target detection technology, and in particular to a method, device, storage medium and electronic device for detecting a person. Background Art

[0002] Millimeter-wave radars are widely used in various fields due to their high sensitivity, strong penetration, and no need for contact. Currently, millimeter-wave radar technology is widely used in the automotive field. However, it is still relatively lacking in home use and human recognition. This will be the next stage of radar development, truly using technology to benefit human life.

[0003] In the prior art, the detection of people based on millimeter wave radar is sometimes unable to detect people who are stationary or making small movements, which leads to the loss of human targets. Millimeter wave radar is less sensitive to the detection of stationary targets and cannot accurately detect real stationary targets. Summary of the invention

[0004] In response to the above problems, the present application provides a personnel detection method, device, storage medium and electronic device, which solves the technical problem in the related art that the millimeter wave radar's personnel detection ability is relatively weak due to the radar's own ability to detect people who are stationary or making small movements.

[0005] In a first aspect, the present application provides a method for detecting a person, the method comprising:

[0006] Obtain point cloud data of the target area;

[0007] Clustering is performed according to the point cloud data to obtain candidate targets;

[0008] Confirm whether there is target location information in the location information of all lost persons in the lost person list; the target location information is the location information of the lost person whose difference from the location information of the candidate target is less than or equal to a preset deviation;

[0009] When the target location information exists, lowering the formation conditions of the candidate target;

[0010] If a candidate target can still be formed after the formation conditions of the candidate target are lowered, it is determined that the candidate target and the lost person obtained by comparison are the same target;

[0011] After marking the candidate target as a person, continue tracking and detecting, and delete the information of the missing person obtained by the comparison from the missing person list.

[0012] In some embodiments, the point cloud data includes:

[0013] The distance between each target point and the detection radar in the target area;

[0014] The azimuth of each target point in the target area relative to the detection radar;

[0015] The speed of each target point in the target area relative to the detection radar;

[0016] The signal-to-noise ratio of each target point in the target area.

[0017] In some embodiments, the step of marking the candidate target as a person and continuing to track and detect the target includes:

[0018] After the candidate target is marked as a person, the extended Kalman filter tracking algorithm is used to continue tracking and detecting.

[0019] In some embodiments, the process of generating the missing persons list includes:

[0020] When the millimeter wave radar detects that the target is lost, determining whether the target is stationary and released;

[0021] If it is determined that the target is stationary and released, confirming whether the target is a person according to the classification label of the target;

[0022] If the target is confirmed to be a person, the location information of the target when it is lost is written into a pre-established lost person list.

[0023] In some embodiments, after confirming that the target is a person, the method further includes:

[0024] Detecting whether the missing persons list is full;

[0025] If it is detected that the missing person list is full, the location information of the missing person stored in the list for the longest time is deleted; then the step of writing the location information of the target at the time of loss into the pre-established missing person list is executed;

[0026] If it is detected that the missing person list is not full, a step is executed to write the location information of the target when it is lost into the pre-established missing person list.

[0027] In some embodiments, the method further comprises:

[0028] Real-time detection of whether the storage time of the location information of all the missing persons in the missing persons list reaches a preset time;

[0029] The location information of the lost person whose storage time reaches the preset time is deleted from the lost person list.

[0030] In some embodiments, clustering the point cloud data to obtain candidate targets includes:

[0031] A point is randomly selected in the point cloud data as a first point, and the first point is used as a center point, and a point is selected in turn from all other points to calculate the distance between the two selected points;

[0032] If the distance is greater than a preset distance threshold, the first point is discarded; if the distance is less than or equal to a preset deviation threshold, the first point is saved;

[0033] A point is randomly selected from all the remaining points as the next point, and a point is selected from all the remaining points in turn to calculate the distance between the two selected points. If the distance is greater than a preset distance threshold, the current point is discarded; if the distance is less than or equal to a preset deviation threshold, the current point is saved;

[0034] The distance between the current point and the first point previously saved is used to calculate the middle position, and one point is selected from the remaining points in turn to calculate the distance to the middle position;

[0035] Repeat the above steps until all points in the point cloud data are traversed, and each cluster obtained is a candidate target;

[0036] Determine whether the points of the candidate target are greater than a preset number of points, and whether the sum of the signal-to-noise ratios of the candidate target is greater than a preset signal-to-noise ratio;

[0037] If it is determined that the number of points of the candidate target is greater than or equal to the preset number of points, and the sum of the signal-to-noise ratios of the candidate targets is greater than or equal to the preset signal-to-noise ratio, then the candidate target is determined to be a real target;

[0038] If it is determined that the number of points of the candidate target is less than the preset number of points, and the sum of the signal-to-noise ratios of the candidate targets is less than the preset signal-to-noise ratio, it is determined that the candidate target is not a real target.

[0039] In a second aspect, a personnel detection device is provided, the device comprising:

[0040] A detection unit, used to obtain point cloud data of a target area;

[0041] A clustering unit, used for clustering the point cloud data to obtain candidate targets;

[0042] A confirmation unit, used to confirm whether there is target location information in the location information of all lost persons in the lost person list; the target location information is the location information of the lost person whose difference from the location information of the candidate target is less than or equal to a preset deviation;

[0043] a reducing unit, configured to reduce a formation condition of the candidate target when the target position information exists;

[0044] a determination unit, configured to determine that the candidate target and the lost person obtained by comparison are the same target if the candidate target can still be formed after the formation conditions of the candidate target are reduced;

[0045] The detection unit is used to continue tracking and detecting after marking the candidate target as a person, and delete the information of the missing person obtained by the comparison from the missing person list.

[0046] In a third aspect, a storage medium stores a computer program that can be executed by one or more processors and can be used to implement the personnel detection method as described in the first aspect.

[0047] In a fourth aspect, an electronic device includes a memory and a processor, wherein a computer program is stored in the memory, and the memory and the processor are communicatively connected to each other. When the computer program is executed by the processor, the personnel detection method described in the first aspect above is executed.

[0048] The present application provides a personnel detection method, device, storage medium and electronic device, including: acquiring point cloud data of a target area; clustering according to the point cloud data to obtain candidate targets; confirming whether there is target location information in the location information of all lost persons in the lost person list; the target location information is the location information of the lost person whose deviation from the location information of the candidate target is less than or equal to a preset deviation; when the target location information exists, reducing the formation conditions of the candidate target; if the candidate target can still be formed after reducing the formation conditions of the candidate target, it is determined that the candidate target and the lost person obtained by comparison are the same target; after marking the candidate target as a person, continue tracking and detecting, and delete the information of the lost person obtained by comparison from the lost person list. The present application realizes the recovery of persons lost due to the stationary target person by establishing a lost person list, realizes the re-tracking and detection of lost targets, and improves the accuracy and sensitivity of personnel tracking detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0050] Figure 1 A flow chart of a method for detecting a person provided in an embodiment of the present application;

[0051] Figure 2 A schematic diagram of the structure of a personnel detection device provided in an embodiment of the present application;

[0052] Figure 3 A connection block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0053] The following will describe the implementation methods of the present application in detail with reference to the accompanying drawings and embodiments, so that the implementation process of how the present application applies technical means to solve technical problems and achieve corresponding technical effects can be fully understood and implemented accordingly. The embodiments of the present application and the various features in the embodiments can be combined with each other without conflict, and the technical solutions formed are all within the scope of protection of the present application.

[0054] As can be seen from the background technology, in the prior art, the detection of people based on millimeter wave radar is sometimes unable to detect people who are stationary or making small movements, resulting in the loss of human targets. Millimeter wave radar has the problem of being less sensitive to the detection of stationary targets and unable to accurately detect real stationary targets.

[0055] In view of this, the present application provides a personnel detection method, device, storage medium and electronic device, which solve the technical problem of personnel detection by millimeter wave radar in the related art due to the radar's own weak ability to detect people who are stationary or making small movements.

[0056] Embodiment 1

[0057] Figure 1 A flow chart of a method for detecting a person provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the method includes:

[0058] S101, obtaining point cloud data of the target area;

[0059] Specifically, the point cloud data of the target area can be obtained by radar detection, and millimeter wave radar is preferably used.

[0060] S102, clustering the point cloud data to obtain candidate targets;

[0061] S103, confirming whether there is target location information in the location information of all lost persons in the lost person list; the target location information is the location information of the lost person whose difference from the location information of the candidate target is less than or equal to a preset deviation;

[0062] S104, when the target location information exists, lowering the formation conditions of the candidate target;

[0063] S105, if a candidate target can still be formed after the formation conditions of the candidate target are lowered, determining that the candidate target and the lost person obtained by comparison are the same target;

[0064] S106, continue tracking and detecting after marking the candidate target as a person, and delete the information of the missing person obtained by comparison from the missing person list.

[0065] Among them, the preset deviation includes a preset distance deviation and a preset angle deviation; the position information includes the current position and the relative position to the millimeter-wave radar, and the angle deviation between the candidate target and the lost person can be calculated through the relative position; the distance deviation between the candidate target and the lost target can be calculated through the current position; when the distance deviation and the angle deviation are both less than the corresponding preset deviations, the formation conditions of the candidate target are reduced, and the reduced target formation conditions include reducing the point value and signal-to-noise ratio value required for forming the target. If the candidate target can still form a target, it is the same target as the lost target obtained by comparison. If the target cannot be formed, it means that the candidate target is a false target caused by the clutter generated by the tracked target, and if it is a false target, it is discarded.

[0066] It should be noted that this patent is an upper-level application based on the point cloud data detected by millimeter-wave radar. Millimeter-wave radar obtains point cloud data by processing the received echo signal, and the point cloud data is the original data to be calculated and processed by this patent.

[0067] In some embodiments, the point cloud data includes:

[0068] The distance between each target point and the detection radar in the target area;

[0069] The azimuth of each target point in the target area relative to the detection radar;

[0070] The speed of each target point in the target area relative to the detection radar;

[0071] The signal-to-noise ratio of each target point in the target area.

[0072] Four things that need to be explained are that each target point is a moving object detected by the detection radar that may be a tracking target. The detection radar collects the straight-line distance between the target point and the detection radar, and establishes a coordinate system with the detection radar as the center. The azimuth of the target point relative to the detection radar can be obtained, as well as the speed and signal-to-noise ratio of the target point detected by the detection radar. Since the detection radar is stationary, the speed of the target point relative to the detection radar is the speed of the target point itself.

[0073] In some embodiments, the step of marking the candidate target as a person and continuing to track and detect the target includes:

[0074] After the candidate target is marked as a person, the extended Kalman filter tracking algorithm is used to continue tracking and detecting.

[0075] In some embodiments, the process of generating the missing persons list includes:

[0076] When the millimeter wave radar detects that the target is lost, determining whether the target is stationary and released;

[0077] If it is determined that the target is stationary and released, confirming whether the target is a person according to the classification label of the target;

[0078] If the target is confirmed to be a person, the location information of the target when it is lost is written into a pre-established lost person list.

[0079] It should be noted that there are two main forms of target loss by millimeter-wave radar. One is that the tracked target is stationary or moves too little, resulting in target loss. This type of target loss is called stationary release. The other is that the tracked target moves out of the radar detection range and is therefore lost.

[0080] It should be further explained that the millimeter wave feedback of the detected target can determine the shape of the target, thereby determining whether the target is a human or a non-human, and adding a corresponding label to the target, where non-humans can include other moving objects besides humans, such as electric fans, wind-blown curtains, sweepers, etc.

[0081] In some embodiments, after confirming that the target is a person, the method further includes:

[0082] Detecting whether the missing persons list is full;

[0083] If it is detected that the missing person list is full, the location information of the missing person stored in the list for the longest time is deleted; then the step of writing the location information of the target at the time of loss into the pre-established missing person list is executed;

[0084] If it is detected that the missing person list is not full, a step is executed to write the location information of the target when it is lost into the pre-established missing person list.

[0085] It should be noted that in order to prevent the missing persons list from being too large and occupying too many storage resources and data processing resources, the number of missing persons location information stored in the list is limited.

[0086] In some embodiments, the method further comprises:

[0087] Real-time detection of whether the storage time of the location information of all the missing persons in the missing persons list reaches a preset time;

[0088] The location information of the lost person whose storage time reaches the preset time is deleted from the lost person list.

[0089] It should be noted that the target that is lost or goes out of the detection range will be released. Regardless of whether the target is lost or goes out of the detection range, the phenomenon is the same, that is, no relevant data (point cloud data) can be detected at the location of the tracked target. The duration of the target data not being detected is recorded, and a time threshold is set. If the target data not being detected continues for more than the time threshold, the corresponding target will be released. The set time is generally 10 minutes, and you can also adjust the setting according to the specific situation or needs.

[0090] In some embodiments, clustering the point cloud data to obtain candidate targets includes:

[0091] A point is randomly selected in the point cloud data as a first point, and the first point is used as a center point, and a point is selected in turn from all other points to calculate the distance between the two selected points;

[0092] If the distance is greater than a preset distance threshold, the first point is discarded; if the distance is less than or equal to a preset deviation threshold, the first point is saved;

[0093] A point is randomly selected from all the remaining points as the next point, and a point is selected from all the remaining points in turn to calculate the distance between the two selected points. If the distance is greater than a preset distance threshold, the current point is discarded; if the distance is less than or equal to a preset deviation threshold, the current point is saved;

[0094] The distance between the current point and the first point previously saved is used to calculate the middle position, and one point is selected from the remaining points in turn to calculate the distance to the middle position;

[0095] Repeat the above steps until all points in the point cloud data are traversed, and each cluster obtained is a candidate target;

[0096] Determine whether the points of the candidate target are greater than a preset number of points, and whether the sum of the signal-to-noise ratios of the candidate target is greater than a preset signal-to-noise ratio;

[0097] If it is determined that the number of points of the candidate target is greater than or equal to the preset number of points, and the sum of the signal-to-noise ratios of the candidate targets is greater than or equal to the preset signal-to-noise ratio, then the candidate target is determined to be a real target;

[0098] If it is determined that the number of points of the candidate target is less than the preset number of points, and the sum of the signal-to-noise ratios of the candidate targets is less than the preset signal-to-noise ratio, it is determined that the candidate target is not a real target.

[0099] It should be noted that by comparing with the preset number of points and the preset signal-to-noise ratio, it can be determined whether the candidate target is a real target or a false target caused by clutter generated by the tracked target. If it is a false target, it will be discarded.

[0100] In summary, the embodiment of the present application provides a method for detecting personnel, including: acquiring point cloud data of a target area; clustering according to the point cloud data to obtain candidate targets; confirming whether there is target location information in the location information of all lost persons in the lost person list; the target location information is the location information of the lost person whose deviation from the location information of the candidate target is less than or equal to a preset deviation; when the target location information exists, reducing the formation conditions of the candidate target; if the candidate target can still be formed after reducing the formation conditions of the candidate target, then determining that the candidate target and the lost person obtained by comparison are the same target; marking the candidate target as a person and continuing to track and detect, and deleting the information of the lost person obtained by comparison from the lost person list. The present application realizes the recovery of persons lost due to the stationary target person by establishing a lost person list, realizes the re-tracking and detection of lost targets, and improves the accuracy and sensitivity of personnel tracking detection.

[0101] Embodiment 2

[0102] Based on the personnel detection method disclosed in the above embodiment of the present invention, Figure 2 Specifically disclosed is a personnel detection device applying the personnel detection method.

[0103] like Figure 2 As shown, an embodiment of the present invention discloses a personnel detection device, the device comprising:

[0104] A detection unit 201 is used to obtain point cloud data of a target area;

[0105] A clustering unit 202, configured to perform clustering based on the point cloud data to obtain candidate targets;

[0106] A confirmation unit 203 is used to confirm whether there is target location information in the location information of all lost persons in the lost person list; the target location information is the location information of the lost person whose difference from the location information of the candidate target is less than or equal to a preset deviation;

[0107] a reducing unit, configured to reduce a formation condition of the candidate target when the target position information exists;

[0108] A determination unit 205, configured to determine that the candidate target and the lost person obtained by comparison are the same target if a candidate target can still be formed after the formation conditions of the candidate target are reduced;

[0109] The detection unit 206 is used to continue tracking and detecting after marking the candidate target as a person, and delete the information of the missing person obtained by the comparison from the missing person list.

[0110] In some embodiments, the point cloud data includes:

[0111] The distance between each target point and the detection radar in the target area;

[0112] The azimuth of each target point in the target area relative to the detection radar;

[0113] The speed of each target point in the target area relative to the detection radar;

[0114] The signal-to-noise ratio of each target point in the target area.

[0115] In some embodiments, the detection unit 206, after marking the candidate target as a person, continues tracking and detecting, including:

[0116] After the candidate target is marked as a person, the extended Kalman filter tracking algorithm is used to continue tracking and detecting.

[0117] In some embodiments, the apparatus further comprises:

[0118] The list generation unit is used to determine whether the target is released in a stationary state when the millimeter-wave radar detects that the target is lost; if the target is determined to be released in a stationary state, confirm whether the target is a person according to the classification label of the target; if the target is confirmed to be a person, write the location information of the target at the time of loss into a pre-established missing person list.

[0119] In some embodiments, the list generation unit is further used to detect whether the missing person list is full after the target is confirmed to be a person;

[0120] If it is detected that the missing person list is full, the location information of the missing person stored in the list for the longest time is deleted; then the step of writing the location information of the target at the time of loss into the pre-established missing person list is executed;

[0121] If it is detected that the missing person list is not full, a step is executed to write the location information of the target when it is lost into the pre-established missing person list.

[0122] In some embodiments, the apparatus further comprises:

[0123] The deleting unit is used to detect in real time whether the storage time of the location information of all the missing persons in the missing persons list reaches a preset time; and delete the location information of the missing persons whose storage time reaches the preset time from the missing persons list.

[0124] In some embodiments, the clustering unit clusters the point cloud data to obtain candidate targets, including:

[0125] A point is randomly selected in the point cloud data as a first point, and the first point is used as a center point, and a point is selected in turn from all other points to calculate the distance between the two selected points;

[0126] If the distance is greater than a preset distance threshold, the first point is discarded; if the distance is less than or equal to a preset deviation threshold, the first point is saved;

[0127] A point is randomly selected from all the remaining points as the next point, and a point is selected from all the remaining points in turn to calculate the distance between the two selected points. If the distance is greater than a preset distance threshold, the current point is discarded; if the distance is less than or equal to a preset deviation threshold, the current point is saved;

[0128] The distance between the current point and the first point previously saved is used to calculate the middle position, and one point is selected from the remaining points in turn to calculate the distance to the middle position;

[0129] Repeat the above steps until all points in the point cloud data are traversed, and each cluster obtained is a candidate target;

[0130] Determine whether the points of the candidate target are greater than a preset number of points, and whether the sum of the signal-to-noise ratios of the candidate target is greater than a preset signal-to-noise ratio;

[0131] If it is determined that the number of points of the candidate target is greater than or equal to the preset number of points, and the sum of the signal-to-noise ratios of the candidate targets is greater than or equal to the preset signal-to-noise ratio, then the candidate target is determined to be a real target;

[0132] If it is determined that the number of points of the candidate target is less than the preset number of points, and the sum of the signal-to-noise ratios of the candidate targets is less than the preset signal-to-noise ratio, it is determined that the candidate target is not a real target.

[0133] For the specific working process of each unit in the personnel detection device disclosed in the above embodiment of the present invention, reference may be made to the corresponding content in the personnel detection method disclosed in the above embodiment of the present invention, and will not be described in detail here.

[0134] In summary, the embodiment of the present application provides a personnel detection device, including: acquiring point cloud data of a target area; clustering according to the point cloud data to obtain candidate targets; confirming whether there is target location information in the location information of all lost persons in the lost person list; the target location information is the location information of the lost person whose deviation from the location information of the candidate target is less than or equal to a preset deviation; when the target location information exists, reducing the formation conditions of the candidate target; if the candidate target can still be formed after reducing the formation conditions of the candidate target, then determining that the candidate target and the lost person obtained by comparison are the same target; marking the candidate target as a person and continuing to track and detect, and deleting the information of the lost person obtained by comparison from the lost person list. The present application realizes the recovery of persons who are lost due to the stationary target person by establishing a lost person list, realizes the re-tracking and detection of lost targets, and improves the accuracy and sensitivity of personnel tracking detection.

[0135] Embodiment 3

[0136] This embodiment also provides a computer-readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a disk, an optical disk, a server, an App application store, etc., on which a computer program is stored. When the computer program is executed by a processor, the method steps of the first embodiment can be implemented, and this embodiment will not be repeated here.

[0137] Embodiment 4

[0138] Figure 3 A connection block diagram of an electronic device 500 provided in an embodiment of the present application, such as Figure 3 As shown, the electronic device 500 may include: a processor 501 , a memory 502 , a multimedia component 503 , an input / output (I / O) interface 504 , and a communication component 505 .

[0139] The processor 501 is used to execute all or part of the steps in the personnel detection method in Embodiment 1. The memory 502 is used to store various types of data, which may include instructions of any application or method in the electronic device, and data related to the application.

[0140] The processor 501 can be an application specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a controller, a microcontroller, a microprocessor or other electronic components, and is used to execute the personnel detection method in the above-mentioned embodiment 1.

[0141] The memory 502 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0142] The multimedia component 503 may include a screen and an audio component, the screen may be a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone, and the microphone is used to receive external audio signals. The received audio signal may be further stored in a memory or sent via a communication component. The audio component also includes at least one speaker for outputting audio signals.

[0143] The I / O interface 504 provides an interface between the processor 501 and other interface modules, which may be a keyboard, a mouse, buttons, etc. These buttons may be virtual buttons or physical buttons.

[0144] The communication component 505 is used for wired or wireless communication between the electronic device 500 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 505 can include: Wi-Fi module, Bluetooth module, NFC module.

[0145] In summary, the present application provides a method, device, storage medium and electronic device for detecting personnel, the method comprising: acquiring point cloud data of a target area; clustering according to the point cloud data to obtain candidate targets; confirming whether there is target location information in the location information of all lost persons in the lost person list; the target location information is the location information of the lost person whose deviation from the location information of the candidate target is less than or equal to a preset deviation; when the target location information exists, reducing the formation conditions of the candidate target; if the candidate target can still be formed after reducing the formation conditions of the candidate target, it is determined that the candidate target and the lost person obtained by comparison are the same target; after marking the candidate target as a person, continue tracking and detecting, and delete the information of the lost person obtained by comparison from the lost person list. The present application realizes the recovery of persons lost due to the stationary target person by establishing a lost person list, realizes the re-tracking and detection of lost targets, and improves the accuracy and sensitivity of personnel tracking detection.

[0146] In the several embodiments provided in the present application, it should be understood that the disclosed method can also be implemented in other ways. The method embodiments described above are merely illustrative.

[0147] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0148] Although the implementation methods disclosed in this application are as above, the above contents are only the implementation methods adopted for facilitating the understanding of this application, and are not intended to limit this application. Any technician in the technical field to which this application belongs can make any modifications and changes in the form and details of the implementation without departing from the spirit and scope disclosed in this application, but the scope of patent protection of this application shall still be based on the scope defined in the attached claims.

Claims

1. A method for detecting a person, It is characterized in that The method comprises: Obtain point cloud data of the target area; Clustering is performed according to the point cloud data to obtain candidate targets; Confirm whether there is target location information in the location information of all lost persons in the lost person list; the target location information is the location information of the lost person whose difference from the location information of the candidate target is less than or equal to a preset deviation; When the target position information exists, lowering the formation conditions of the candidate target; lowering the formation conditions of the candidate target includes lowering the point value and signal-to-noise ratio value required for forming the target; If a candidate target can still be formed after the formation conditions of the candidate target are lowered, it is determined that the candidate target and the lost person obtained by comparison are the same target; After marking the candidate target as a person, continue tracking and detecting, and delete the information of the missing person obtained by the comparison from the missing person list.

2. The method according to claim 1, It is characterized in that The point cloud data includes: The distance between each target point and the detection radar in the target area; The azimuth of each target point in the target area relative to the detection radar; The speed of each target point in the target area relative to the detection radar; The signal-to-noise ratio of each target point in the target area.

3. The method according to claim 1, It is characterized in that The step of marking the candidate target as a person and continuing to track and detect the candidate target includes: After the candidate target is marked as a person, the extended Kalman filter tracking algorithm is used to continue tracking and detecting.

4. The method according to claim 1, It is characterized in that The process of generating the missing persons list includes: When the millimeter wave radar detects that the target is lost, determining whether the target is stationary and released; If it is determined that the target is stationary and released, confirming whether the target is a person according to the classification label of the target; If the target is confirmed to be a person, the location information of the target when it is lost is written into a pre-established lost person list.

5. The method according to claim 4, It is characterized in that After confirming that the target is a person, the method further includes: Detecting whether the missing persons list is full; If it is detected that the missing person list is full, the location information of the missing person stored in the list for the longest time is deleted; then the step of writing the location information of the target at the time of loss into the pre-established missing person list is executed; If it is detected that the missing person list is not full, a step is executed to write the location information of the target when it is lost into the pre-established missing person list.

6. The method according to claim 1, It is characterized in that Also includes: Real-time detection of whether the storage time of the location information of all the missing persons in the missing persons list reaches a preset time; The location information of the lost person whose storage time reaches the preset time is deleted from the lost person list.

7. The method according to claim 1, It is characterized in that The step of clustering the point cloud data to obtain candidate targets includes: A point is randomly selected in the point cloud data as a first point, and the first point is used as a center point, and a point is selected in turn from all other points to calculate the distance between the two selected points; If the distance is greater than a preset distance threshold, the first point is discarded; if the distance is less than or equal to a preset deviation threshold, the first point is saved; A point is randomly selected from all the remaining points as the next point, and a point is selected from all the remaining points in turn to calculate the distance between the two selected points. If the distance is greater than a preset distance threshold, the current point is discarded; if the distance is less than or equal to a preset deviation threshold, the current point is saved; The distance between the current point and the first point previously saved is used to calculate the middle position, and one point is selected from the remaining points in turn to calculate the distance to the middle position; Repeat the above steps until all points in the point cloud data are traversed, and each cluster obtained is a candidate target; Determine whether the points of the candidate target are greater than a preset number of points, and whether the sum of the signal-to-noise ratios of the candidate target is greater than a preset signal-to-noise ratio; If it is determined that the number of points of the candidate target is greater than or equal to the preset number of points, and the sum of the signal-to-noise ratios of the candidate targets is greater than or equal to the preset signal-to-noise ratio, then the candidate target is determined to be a real target; If it is determined that the number of points of the candidate target is less than the preset number of points, and the sum of the signal-to-noise ratios of the candidate targets is less than the preset signal-to-noise ratio, it is determined that the candidate target is not a real target.

8. A person detection device, It is characterized in that The device comprises: A detection unit, used to obtain point cloud data of a target area; A clustering unit, used for clustering the point cloud data to obtain candidate targets; A confirmation unit, used to confirm whether there is target location information in the location information of all lost persons in the lost person list; the target location information is the location information of the lost person whose difference from the location information of the candidate target is less than or equal to a preset deviation; A reducing unit, used for reducing the formation condition of the candidate target when the target position information exists; the reducing the formation condition of the candidate target includes reducing the point value and signal-to-noise ratio value required for forming the target; a determination unit, configured to determine that the candidate target and the lost person obtained by comparison are the same target if the candidate target can still be formed after the formation conditions of the candidate target are reduced; The detection unit is used to continue tracking and detecting after marking the candidate target as a person, and delete the information of the missing person obtained by the comparison from the missing person list.

9. A storage medium, It is characterized in that The computer program stored in the storage medium can be executed by one or more processors and can be used to implement the personnel detection method as described in any one of claims 1 to 7.

10. An electronic device, It is characterized in that The method comprises a memory and a processor, wherein a computer program is stored in the memory, and the memory and the processor are communicatively connected with each other. When the computer program is executed by the processor, the personnel detection method according to any one of claims 1 to 7 is executed.

Citation Information

Patent Citations

  • Method and device for human tracking

    CN106355603A

  • Improved multi-extended target tracking method

    CN108427112A

  • Multi-target detection and positioning method based on constant false alarm rate detection

    CN108919247A

  • Multi-target clustering method for high resolution millimeter wave radar

    CN109581312A

  • Region detection method and device

    CN110609281A