Security and protection auxiliary method and system for spontoon

Abstract

The invention provides a security auxiliary method and system for a spontoon, and the method comprises the steps: carrying out the sensing of a surrounding environment based on a millimeter-wave radar sensor disposed on the spontoon, and obtaining first sensing data; sensing the surrounding environment based on a visual sensor arranged on the spontoon to obtain second sensing data; judging whether sneak attacks exist or not according to the first sensing data and the second sensing data; and when the existence of the sneak attacks is determined, an alarm module arranged on the baton gives an alarm for reminding. The technical effects that security assistance is carried out based on the spontoon in the law enforcement process, the safety of security law enforcement personnel is guaranteed, and the law enforcement efficiency is improved are achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the security detection technical field, in particular to a security auxiliary method and system for baton. BACKGROUND

[0002] In today's society, security law enforcement personnel often deal with some illegal events, and security law enforcement personnel may be attacked by illegal personnel during law enforcement. Therefore, how to avoid attacks during law enforcement is a very important problem, and security assistance is one of the effective means to avoid attacks, and security assistance has the following advantages: (1) security assistance can master the surrounding environment in advance, and can discover suspicious behavior or abnormal situation in time, so as to avoid the occurrence of criminal events; (2) security assistance can effectively protect the personal safety of law enforcement personnel and avoid personnel injury accidents; (3) security assistance can automatically monitor and alarm, reduce manual patrol and management cost, and improve law enforcement efficiency.

[0003] The baton is one of the most important and commonly used tools in law enforcement, and can become an important carrier for security assistance during law enforcement.

[0004] However, there is a lack of security assistance technology using the baton in the prior art. Therefore, how to realize security assistance based on the baton during law enforcement, and further ensure the safety of security law enforcement personnel and improve the law enforcement efficiency, is one of the problems to be solved in the security detection technical field. SUMMARY

[0005] The present application aims to at least partly solve the above technical problems in the art. To this end, the present application aims to provide a security auxiliary method and system for baton, which obtains sensing data through the sensor arranged on the baton, analyzes the sensing data to determine whether there is an attacking personnel, and issues an alarm information to remind if there is an attacking personnel. The technical effect of security assistance based on the baton during law enforcement is achieved, and the safety of security law enforcement personnel is ensured and the law enforcement efficiency is improved.

[0006] The present application provides a security auxiliary method for baton, comprising:

[0007] The surrounding environment is sensed based on the millimeter wave radar sensor arranged on the baton to obtain first sensing data;

[0008] The surrounding environment is sensed based on the visual sensor arranged on the baton to obtain second sensing data;

[0009] It is determined whether there is an attacking personnel according to the first sensing data and the second sensing data;

[0010] When it is determined that there is a sneak attack personnel, an alarm is issued based on the alarm module arranged on the baton to remind.

[0011] Preferably, the baton uses a security auxiliary method to perceive the surrounding environment based on the millimeter wave radar sensor arranged on the baton to obtain first perception data, including:

[0012] The millimeter wave radar sensor arranged on the baton emits an electromagnetic wave signal;

[0013] When the electromagnetic wave signal encounters the personnel to be analyzed in the surrounding environment, the electromagnetic wave signal is reflected back to the millimeter wave radar sensor;

[0014] The round-trip propagation time of the electromagnetic wave signal is determined based on the time delay of the electromagnetic wave signal reflected back to the millimeter wave radar sensor, and the one-way propagation time of the electromagnetic wave signal is determined according to the round-trip time;

[0015] The target propagation speed of the electromagnetic wave signal is determined based on the frequency change of the electromagnetic wave signal reflected back to the millimeter wave radar sensor;

[0016] The propagation distance of the electromagnetic wave signal is determined according to the one-way propagation time and the target propagation speed, the propagation distance is taken as the distance between the personnel to be analyzed and the millimeter wave radar sensor, and the distance between the personnel to be analyzed and the millimeter wave radar sensor is taken as the first perception data.

[0017] Preferably, the baton uses a security auxiliary method to perceive the surrounding environment based on the visual sensor arranged on the baton to obtain second perception data, including:

[0018] The personnel image corresponding to the personnel to be analyzed in the surrounding environment is collected based on the visual sensor arranged on the baton, and the personnel image is taken as the second perception data.

[0019] Preferably, the baton uses a security auxiliary method to determine whether there is a sneak attack personnel according to the first perception data and the second perception data, including:

[0020] It is determined whether the distance between the personnel to be analyzed and the millimeter wave radar sensor is less than a preset threshold value, and a first analysis result is determined according to the determination result;

[0021] The personnel to be analyzed is subjected to personnel analysis based on the personnel image to obtain a second analysis result;

[0022] It is determined whether the personnel to be analyzed is a sneak attack personnel based on the first analysis result and the second analysis result.

[0023] Preferably, the baton uses a security auxiliary method to determine whether there is a sneak attack personnel according to the first perception data and the second perception data, including:

[0024] The action analysis result is obtained by performing action analysis on the personnel to be analyzed based on the personnel image;

[0025] The line-of-sight analysis result is obtained by performing line-of-sight analysis on the personnel to be analyzed based on the personnel image;

[0026] The expression analysis result is obtained by performing expression analysis on the personnel to be analyzed based on the personnel image;

[0027] The action analysis result, the line-of-sight analysis result, and the expression analysis result constitute a second analysis result.

[0028] Preferably, the baton security auxiliary method comprises the following steps:

[0029] The posture of the personnel image is estimated based on an OpenPose model to identify the key points of the human body.

[0030] The angles and distances between the key points of the human body are calculated to form an action feature vector.

[0031] The action feature vector is input into an LSTM model to output the action analysis result.

[0032] Preferably, the baton security auxiliary method comprises the following steps:

[0033] The eye region in the personnel image is determined; the eye region comprises a left eye region and a right eye region.

[0034] A first key point extraction operation is performed on the left eye region by using a first preset eye key point detection model to obtain first eye key points of the left eye region.

[0035] A second key point extraction operation is performed on the left eye region by using a second preset eye key point detection model to obtain second eye key points of the left eye region.

[0036] The first eye key points and the second eye key points constitute initial left eye key points, and the key point positions of the initial left eye key points are obtained.

[0037] The pupil center point position of the left eye is obtained.

[0038] The distance between each initial left eye key point and the pupil center point is calculated based on the key point positions of the initial left eye key points and the pupil center point position.

[0039] When the distance between the initial left eye key point and the pupil center point is less than a preset distance threshold, the initial left eye key point is determined as a target left eye key point.

[0040] Based on the target left eye key points, the left eye contour curve is obtained by least square fitting;

[0041] Determine the major axis and minor axis of the left eye contour curve, and determine the intersection position of the major axis and the minor axis;

[0042] Determine the left eye's sight direction based on the intersection of the major axis and the minor axis and the pupil center of the left eye;

[0043] Perform the above operations on the right eye area to determine the right eye's sight direction;

[0044] The gaze analysis result is determined based on the left eye gaze direction and the right eye gaze direction.

[0045] Preferably, the baton security auxiliary method performs facial expression analysis on the person to be analyzed based on the person image, and obtains the facial expression analysis result, including:

[0046] Obtaining sample person images and corresponding sample person expression analysis results, performing model training based on the sample person images and corresponding sample person expression analysis results, and obtaining an expression analysis model;

[0047] Input the person image into the expression analysis model to obtain the expression analysis result.

[0048] Preferably, the baton uses a security auxiliary method. When it is determined that there is a sneak attacker, an alarm module set on the baton issues an alarm to remind. The method includes: when it is determined that there is a sneak attacker, the alarm module issues a voice alarm and the alarm module indicator light turns red to remind the sneak attack.

[0049] A security auxiliary system for a baton, comprising:

[0050] a first perception module, configured to perceive the surrounding environment based on a millimeter-wave radar sensor provided on the baton, and obtain first perception data;

[0051] A second perception module is used to perceive the surrounding environment based on a visual sensor provided on the baton to obtain second perception data;

[0052] A judgment module, configured to judge whether there is a sneak attacker based on the first perception data and the second perception data;

[0053] The alarm module is used to sound an alarm to remind people when it is determined that there is a sneak attack.

[0054] The application provides a security auxiliary method and system for a baton, which comprises the following steps: acquiring first sensing data by sensing a surrounding environment based on a millimeter wave radar sensor arranged on the baton; acquiring second sensing data by sensing the surrounding environment based on a visual sensor arranged on the baton; determining whether there is a sneak attacker according to the first sensing data and the second sensing data; and issuing an alarm by an alarm module arranged on the baton to remind when it is determined that there is a sneak attacker. The security auxiliary method and system for the baton are achieved in the law enforcement process, and the safety of the security law enforcement personnel is ensured and the law enforcement efficiency is improved.

[0055] Other features and advantages of the present application will be set forth in the following description, and in part will be apparent from the description, or can be learned by practice of the present application. The objects and other advantages of the present application will be realized and attained by the structure particularly pointed out in the written description and claims hereof.

[0056] The technical solutions of the present application will be further described in detail below with the drawings and examples. BRIEF DESCRIPTION OF DRAWINGS

[0057] The accompanying drawings are included to provide a further understanding of the present application, and constitute a part of the specification, illustrate the present application and explain the technical solutions of the present application, and do not constitute a limitation on the present application. In the drawings:

[0058] Figure 1 A flowchart of a security auxiliary method for a baton in an embodiment of the present application is shown in FIG. 1.

[0059] Figure 2 A flowchart of an optional method for acquiring first sensing data in an embodiment of the present application is shown in FIG. 2.

[0060] Figure 3 A block diagram of a security auxiliary system for a baton in an embodiment of the present application is shown in FIG. 3. DETAILED DESCRIPTION

[0061] The preferred embodiments of the present application will be described below with reference to the accompanying drawings, and it should be understood that the preferred embodiments described herein are only used to explain and illustrate the present application, and do not constitute a limitation on the present application.

[0062] Reference Figure 1 The embodiment of the present application provides a security auxiliary method for a baton, which comprises the following steps:

[0063] Step S1: acquiring first sensing data by sensing a surrounding environment based on a millimeter wave radar sensor arranged on the baton;

[0064] Step S2: acquiring second sensing data by sensing the surrounding environment based on a visual sensor arranged on the baton;

[0065] Step S3, determining whether there is a sneak personnel according to the first sensing data and the second sensing data;

[0066] Step S4, when it is determined that there is a sneak personnel, issuing a warning alarm based on the alarm module arranged on the baton to remind.

[0067] The technical principle and technical effect of the above technical solution are: based on the millimeter wave radar sensor arranged on the baton to sense the surrounding environment and obtain the first sensing data; based on the visual sensor arranged on the baton to sense the surrounding environment and obtain the second sensing data; according to the first sensing data and the second sensing data, it is determined whether there is a sneak personnel; when it is determined that there is a sneak personnel, a warning alarm is issued based on the alarm module arranged on the baton to remind. The technical effect of achieving security assistance based on the baton in the law enforcement process, thereby ensuring the safety of the security law enforcement personnel and improving the law enforcement efficiency is achieved.

[0068] Reference Figure 2 The embodiment of the present application provides a security assistance method for a baton, based on the millimeter wave radar sensor arranged on the baton to sense the surrounding environment and obtain the first sensing data, comprising:

[0069] Step S11, issuing an electromagnetic wave signal based on the millimeter wave radar sensor arranged on the baton;

[0070] Step S12, when the electromagnetic wave signal meets the personnel to be analyzed in the surrounding environment, the electromagnetic wave signal is reflected back to the millimeter wave radar sensor;

[0071] Step S13, determining the round-trip propagation time of the electromagnetic wave signal based on the time delay of the electromagnetic wave signal reflected back to the millimeter wave radar sensor, and determining the one-way propagation time of the electromagnetic wave signal according to the round-trip time;

[0072] Step S14, determining the target propagation speed of the electromagnetic wave signal based on the frequency change of the electromagnetic wave signal reflected back to the millimeter wave radar sensor;

[0073] Step S15, determining the propagation distance of the electromagnetic wave signal according to the one-way propagation time and the target propagation speed, taking the propagation distance as the distance between the personnel to be analyzed and the millimeter wave radar sensor, and taking the distance between the personnel to be analyzed and the millimeter wave radar sensor as the first sensing data.

[0074] In this embodiment, the round-trip propagation time of the electromagnetic wave signal is T1, and the one-way propagation time of the electromagnetic wave signal is T1 / 2.

[0075] In this embodiment, the specific implementation of determining the target propagation speed of the electromagnetic wave signal based on the frequency change of the electromagnetic wave signal reflected back to the millimeter wave radar sensor can be: determining the target propagation speed of the electromagnetic wave signal according to a modified Doppler shift formula, specifically: determining the target propagation speed of the electromagnetic wave signal as v, then wherein f1 is the frequency of the electromagnetic wave signal emitted by the millimeter wave radar sensor, f2 is the frequency of the electromagnetic wave signal reflected back to the millimeter wave radar sensor, and c is the propagation speed of the electromagnetic wave in air medium.

[0076] In this embodiment, the propagation distance of the electromagnetic wave signal is v x T1 / 2.

[0077] The technical principle and technical effect of the above technical solution are: the millimeter wave radar sensor arranged on the baton emits an electromagnetic wave signal; when the electromagnetic wave signal encounters a to-be-analyzed person in the surrounding environment, the electromagnetic wave signal is reflected back to the millimeter wave radar sensor; the round-trip propagation time of the electromagnetic wave signal is determined based on the time delay of the electromagnetic wave signal reflected back to the millimeter wave radar sensor, and the one-way propagation time of the electromagnetic wave signal is determined according to the round-trip time; the target propagation speed of the electromagnetic wave signal is determined based on the frequency change of the electromagnetic wave signal reflected back to the millimeter wave radar sensor; the propagation distance of the electromagnetic wave signal is determined according to the one-way propagation time and the target propagation speed, the propagation distance is taken as the distance between the to-be-analyzed person and the millimeter wave radar sensor, and the distance between the to-be-analyzed person and the millimeter wave radar sensor is taken as the first perception data. The distance between the to-be-analyzed person and the baton is obtained, distance analysis is performed according to the distance therebetween, the distance analysis result is taken as one of the determination bases of the sneak attack person, and the technical effect of improving the determination accuracy of the sneak attack person is achieved.

[0078] The security auxiliary method for the baton provided in the embodiment of the application perceives the surrounding environment based on the visual sensor arranged on the baton, and obtains second perception data, which includes:

[0079] The visual sensor arranged on the baton collects a personnel image corresponding to a to-be-analyzed person in the surrounding environment, and takes the personnel image as the second perception data.

[0080] The technical principle and technical effect of the above technical solution are: the visual sensor arranged on the baton collects a personnel image corresponding to a to-be-analyzed person in the surrounding environment, and takes the personnel image as the second perception data. The personnel image is obtained, so as to provide an analysis basis for the personnel analysis process, ensure the accuracy of the personnel analysis result, and improve the determination accuracy of the sneak attack person.

[0081] The security auxiliary method for the baton provided in the embodiment of the application judges whether there is a sneak attack person according to the first perception data and the second perception data, which includes:

[0082] determine whether the distance between the to-be-analyzed person and the millimeter wave radar sensor is less than a preset threshold value, and determine a first analysis result according to a result of the determination;

[0083] perform personnel analysis on the to-be-analyzed person based on the personnel image, and obtain a second analysis result;

[0084] determine whether the to-be-analyzed person is a sneak attacker based on the first analysis result and the second analysis result.

[0085] In this embodiment, the preset threshold value can be determined according to actual application conditions, for example, the preset threshold value can be an average value of a sum of a maximum distance between the to-be-analyzed person and the millimeter wave radar sensor and a minimum distance between the to-be-analyzed person and the millimeter wave radar sensor.

[0086] In this embodiment, when the distance between the to-be-analyzed person and the millimeter wave radar sensor is less than the preset threshold value and the second analysis result determines that the to-be-analyzed person meets a condition of a sneak attacker, the to-be-analyzed person is determined to be a sneak attacker.

[0087] The technical principle and technical effects of the above technical solution are as follows: determining whether the distance between the to-be-analyzed person and the millimeter wave radar sensor is less than a preset threshold value, and determining a first analysis result according to a result of the determination; performing personnel analysis on the to-be-analyzed person based on the personnel image, and obtaining a second analysis result; and determining whether the to-be-analyzed person is a sneak attacker based on the first analysis result and the second analysis result. The technical effects of accurately determining a sneak attacker, assisting security based on a baton in a law enforcement process, ensuring the safety of security law enforcement personnel, and improving law enforcement efficiency are achieved.

[0088] The embodiment of the present application provides a security assistance method for a baton, performs personnel analysis on a to-be-analyzed person based on a personnel image, and obtains a second analysis result, including:

[0089] performing action analysis on the to-be-analyzed person based on the personnel image, and obtaining an action analysis result;

[0090] performing line-of-sight analysis on the to-be-analyzed person based on the personnel image, and obtaining a line-of-sight analysis result;

[0091] performing expression analysis on the to-be-analyzed person based on the personnel image, and obtaining an expression analysis result;

[0092] The action analysis result, the line-of-sight analysis result, and the expression analysis result constitute the second analysis result.

[0093] The technical principles and effects of the above technical solutions are as follows: based on the personnel image, action analysis is performed on the to-be-analyzed personnel to obtain an action analysis result; based on the personnel image, gaze analysis is performed on the to-be-analyzed personnel to obtain a gaze analysis result; based on the personnel image, expression analysis is performed on the to-be-analyzed personnel to obtain an expression analysis result; the action analysis result, the gaze analysis result, and the expression analysis result constitute a second analysis result. The action, the gaze, and the expression of the to-be-analyzed personnel are determined, whether the to-be-analyzed personnel is a sneak attack personnel is determined according to the three aspects of the action, the gaze, and the expression, and the technical effect of accurately determining the sneak attack personnel is achieved.

[0094] The security auxiliary method for batons provided in the embodiment of the application comprises the following steps:

[0095] The posture of the personnel image is estimated based on an OpenPose model, and human body key points are recognized.

[0096] The angle and distance between the human body key points are calculated to form an action feature vector.

[0097] The action feature vector is input into an LSTM model, and an action analysis result is output.

[0098] The working principle and beneficial effects of the above technical solutions are as follows: the OpenPose model is used to process the personnel image, and the coordinates of the human body key points are output. The key points include the head, the left shoulder, the right shoulder, the left elbow, the right elbow, the left wrist, the right wrist, the left hip, the right hip, the left knee, the right knee, the left ankle, and the right ankle. The included angle between the key points (such as the included angle between the shoulder and the elbow and the included angle between the hip and the knee) is calculated. The Euclidean distance between the key points (such as the distance from the head to the left shoulder and the distance from the left shoulder to the left elbow) is calculated. The angle and the distance are combined into a feature vector. The feature vector is input into the LSTM model, and an action classification result (sneak attack or non-sneak attack) and a confidence degree are output. By combining the OpenPose and the LSTM model, the sneak attack action analysis on the personnel image can be achieved. The accuracy of determining whether there is a sneak attack is improved.

[0099] The security auxiliary method for batons provided in the embodiment of the application comprises the following steps:

[0100] The eye region in the personnel image is determined; wherein the eye region comprises a left eye region and a right eye region;

[0101] A first key point extraction operation is performed on the left eye region by using a first preset eye key point detection model to obtain a first eye key point of the left eye region;

[0102] The second key point extraction operation is performed on the left eye region by using a second preset eye key point detection model to obtain second eye key points of the left eye region.

[0103] The first eye key points and the second eye key points form initial left eye key points, and a key point position of the initial left eye key points is obtained.

[0104] A pupil center position of the left eye is obtained.

[0105] Based on the key point position of the initial left eye key points and the pupil center position, a distance between each initial left eye key point and the pupil center is calculated.

[0106] When the distance between the initial left eye key point and the pupil center is less than a preset distance threshold, the initial left eye key point is determined as a target left eye key point.

[0107] Based on the target left eye key point, a left eye contour curve is fitted by using a least square method.

[0108] A long axis and a short axis of the left eye contour curve are determined, and a position of an intersection of the long axis and the short axis is determined.

[0109] A left eye gaze direction is determined based on the position of the intersection of the long axis and the short axis and the pupil center position of the left eye.

[0110] The above operations are performed on the right eye region to determine a right eye gaze direction.

[0111] A gaze analysis result is determined based on the left eye gaze direction and the right eye gaze direction.

[0112] In this embodiment, the training process of the first preset eye key point detection model is as follows: historical eye regions and corresponding historical eye region key points are obtained, and model training is performed based on the historical eye regions and the corresponding historical eye region key points to obtain the first preset eye key point detection model.

[0113] In this embodiment, the second preset eye key point detection model is an ORB key point detection model in an OpenCV library.

[0114] In this embodiment, the preset distance threshold can be an average value of distances between all initial left eye key points and the pupil center.

[0115] In this embodiment, the specific implementation of determining the left eye gaze direction based on the position of the intersection of the long axis and the short axis and the pupil center position of the left eye is as follows: the left eye gaze direction is a direction of a left eye gaze vector, the coordinates of the position of the intersection of the long axis and the short axis and the pupil center position of the left eye are determined, and a difference between the coordinates of the position of the intersection of the long axis and the short axis and the coordinates of the pupil center position of the left eye is taken as the left eye gaze vector.

[0116] In this embodiment, the specific implementation of determining the gaze analysis result based on the left eye gaze direction and the right eye gaze direction is: when the left eye gaze direction and the right eye gaze direction are both directed to the baton holder, the gaze analysis result is determined as a gaze direction conforming to the sneak attack behavior, otherwise, the gaze analysis result is determined as a normal direction.

[0117] The technical principles and effects of the above technical solutions are: determining an eye region in a personnel image; wherein the eye region includes a left eye region and a right eye region; performing a first key point extraction operation on the left eye region by using a first preset eye key point detection model to obtain first eye key points of the left eye region; performing a second key point extraction operation on the left eye region by using a second preset eye key point detection model to obtain second eye key points of the left eye region; the first eye key points and the second eye key points form initial left eye key points, and a key point position of the initial left eye key points is obtained; a pupil center point position of the left eye is obtained; based on the key point position of the initial left eye key points and the pupil center point position, a distance between each initial left eye key point and the pupil center point is calculated; when the distance between the initial left eye key point and the pupil center point is less than a preset distance threshold, the initial left eye key point is determined as a target left eye key point; based on the target left eye key point, a left eye contour curve is fitted by using a least square method; a long axis and a short axis of the left eye contour curve are determined, and a position of an intersection of the long axis and the short axis is determined; based on the position of the intersection of the long axis and the short axis and the pupil center point position of the left eye, a left eye gaze direction is determined; the above operations are performed on the right eye region to determine a right eye gaze direction; and a gaze analysis result is determined based on the left eye gaze direction and the right eye gaze direction. The technical effect of accurately obtaining a gaze analysis result of a to-be-analyzed personnel is achieved, and then whether the to-be-analyzed personnel is a sneak attack personnel is accurately determined.

[0118] The security auxiliary method for a baton provided in the embodiment of the application includes the following steps:

[0119] A sample personnel image and a corresponding sample personnel expression analysis result are obtained, a model training is performed based on the sample personnel image and the corresponding sample personnel expression analysis result, and an expression analysis model is obtained.

[0120] The personnel image is input into the expression analysis model, and an expression analysis result is obtained.

[0121] In this embodiment, the expression analysis result is a sneak attack behavior expression (for example, frowning, etc.) and a normal expression (for example, smiling, etc.).

[0122] The technical principle and technical effect of the above technical solution are: obtaining sample personnel images and corresponding sample personnel expression analysis results, performing model training based on the sample personnel images and the corresponding sample personnel expression analysis results to obtain an expression analysis model, inputting a personnel image into the expression analysis model to obtain an expression analysis result. The technical effect of accurately obtaining the expression analysis result of the personnel to be analyzed is achieved, and it is further determined whether the personnel to be analyzed is a sneak attack personnel.

[0123] The security auxiliary method for a baton provided by the embodiment of the application includes the following steps: when it is determined that there is a sneak attack personnel, the alarm module emits a voice alarm and the alarm module indicator light is red to remind the sneak attack.

[0124] The technical principle and technical effect of the above technical solution are: when it is determined that there is a sneak attack personnel, the alarm module emits a voice alarm and the alarm module indicator light is red to remind the sneak attack. The technical effect of timely warning the holder of the baton is achieved, and the safety of the security law enforcement personnel is ensured and the law enforcement efficiency is improved.

[0125] Reference Figure 3 The security auxiliary system for a baton provided by the embodiment of the application includes the following components:

[0126] The first sensing module 10 is configured to sense the surrounding environment based on the millimeter wave radar sensor arranged on the baton to obtain first sensing data.

[0127] The second sensing module 20 is configured to sense the surrounding environment based on the visual sensor arranged on the baton to obtain second sensing data.

[0128] The judgment module 30 is configured to determine whether there is a sneak attack personnel according to the first sensing data and the second sensing data.

[0129] The alarm module 40 is configured to emit an alarm to remind when it is determined that there is a sneak attack personnel.

[0130] The technical principle and technical effect of the above technical solution are: based on the millimeter wave radar sensor arranged on the baton, the surrounding environment is sensed to obtain first sensing data; based on the visual sensor arranged on the baton, the surrounding environment is sensed to obtain second sensing data; whether there is a sneak attack personnel is determined according to the first sensing data and the second sensing data; when it is determined that there is a sneak attack personnel, an alarm is emitted to remind. The technical effect of security auxiliary based on the baton in the law enforcement process is achieved, and the safety of the security law enforcement personnel is ensured and the law enforcement efficiency is improved.

[0131] Obviously, many modifications and variations of the present application are possible in light of the above teachings. It is, therefore, to be understood that within the scope of the appended claims and their equivalents, the application can be practiced otherwise than as specifically described.

Claims

1. A security auxiliary method for a baton, characterized in that: include: The millimeter-wave radar sensor provided on the baton senses the surrounding environment and obtains first sensing data; The visual sensor provided on the baton senses the surrounding environment to obtain second sensing data; Determine whether there is a sneak attacker based on the first perception data and the second perception data; When it is determined that there is a sneak attacker, an alarm module set on the baton will sound an alarm to remind.

2. The security auxiliary method for batons according to claim 1, characterized in that: The millimeter-wave radar sensor provided on the baton senses the surrounding environment to obtain first sensing data, including: The millimeter-wave radar sensor provided on the baton emits an electromagnetic wave signal; When the electromagnetic wave signal encounters the person to be analyzed in the surrounding environment, the electromagnetic wave signal is reflected back to the millimeter wave radar sensor; determining a round-trip propagation time of the electromagnetic wave signal based on a time delay of the electromagnetic wave signal reflected back to the millimeter-wave radar sensor, and determining a one-way propagation time of the electromagnetic wave signal based on the round-trip time; determining the target propagation speed of the electromagnetic wave signal based on the frequency change of the electromagnetic wave signal reflected back to the millimeter wave radar sensor; The propagation distance of the electromagnetic wave signal is determined according to the one-way propagation time and the target propagation speed, the propagation distance is used as the distance between the person to be analyzed and the millimeter-wave radar sensor, and the distance between the person to be analyzed and the millimeter-wave radar sensor is used as the first perception data.

3. The security auxiliary method for batons according to claim 2, characterized in that: The visual sensor provided on the baton senses the surrounding environment and obtains second perception data, including: Based on the visual sensor arranged on the baton, a person image corresponding to the person to be analyzed in the surrounding environment is collected, and the person image is used as the second perception data.

4. The security auxiliary method for batons according to claim 3, characterized in that: Judging whether there is a sneak attacker based on the first and second perception data includes: Determine whether the distance between the person to be analyzed and the millimeter-wave radar sensor is less than a preset threshold, and determine a first analysis result based on the determination result; Based on the personnel image, personnel analysis is performed on the personnel to be analyzed to obtain a second analysis result; Based on the first analysis result and the second analysis result, it is determined whether the person to be analyzed is a sneak attacker.

5. The security auxiliary method for batons according to claim 4, characterized in that: Based on the personnel image, personnel analysis is performed on the personnel to be analyzed to obtain a second analysis result, including: Based on the personnel image, performing motion analysis on the personnel to be analyzed to obtain a motion analysis result; Based on the personnel image, performing a sight line analysis on the person to be analyzed to obtain a sight line analysis result; Based on the personnel image, performing expression analysis on the person to be analyzed to obtain an expression analysis result; The action analysis result, the sight line analysis result and the expression analysis result constitute the second analysis result.

6. The security auxiliary method for batons according to claim 5, characterized in that: Based on the personnel image, the motion analysis of the personnel to be analyzed is performed to obtain the motion analysis results, including: Perform pose estimation on person images based on the OpenPose model and identify key points of the human body; Calculate the angles and distances between key points of the human body to form motion feature vectors; Input the action feature vector into the LSTM model and output the action analysis results.

7. The security auxiliary method for batons according to claim 5, characterized in that: Based on the personnel image, a line of sight analysis is performed on the personnel to be analyzed to obtain a line of sight analysis result, including: Determine an eye region in the person image; wherein the eye region includes a left eye region and a right eye region; Performing a first key point extraction operation on the left eye region using a first preset eye key point detection model to obtain a first eye key point of the left eye region; Performing a second key point extraction operation on the left eye region using a second preset eye key point detection model to obtain a second eye key point of the left eye region; The first eye key point and the second eye key point form an initial left eye key point, and the key point position of the initial left eye key point is obtained; Get the pupil center position of the left eye; Based on the key point position of the initial left eye key point and the pupil center point position, calculating the distance between each initial left eye key point and the pupil center point; When the distance between the initial left eye key point and the pupil center point is less than a preset distance threshold, determining the initial left eye key point as the target left eye key point; Based on the target left eye key points, obtaining a left eye contour curve by least squares fitting; Determining the major axis and minor axis of the left eye contour curve, and determining the intersection position of the major axis and minor axis; Determining the left eye's sight direction based on the intersection of the major axis and the minor axis and the pupil center of the left eye; Perform the above operations on the right eye area to determine the right eye's sight direction; A sight line analysis result is determined based on the left eye sight line direction and the right eye sight line direction.

8. The security auxiliary method for batons according to claim 5, characterized in that: Perform facial expression analysis on the person to be analyzed based on the person image to obtain facial expression analysis results, including: Obtaining sample person images and corresponding sample person expression analysis results, and performing model training based on the sample person images and corresponding sample person expression analysis results to obtain an expression analysis model; The person image is input into an expression analysis model to obtain an expression analysis result.

9. The security auxiliary method for batons according to claim 1, characterized in that: When it is determined that there is a sneak attacker, an alarm module set on the baton will issue an alarm to remind you, including: when it is determined that there is a sneak attacker, the alarm module will issue a voice alarm and the alarm module indicator light will turn red to remind you of the sneak attack.

10. A security auxiliary system for a baton, characterized in that: include: a first perception module, configured to perceive the surrounding environment based on a millimeter-wave radar sensor provided on the baton, and obtain first perception data; A second perception module is used to perceive the surrounding environment based on a visual sensor provided on the baton to obtain second perception data; A judgment module, configured to judge whether there is a sneak attacker based on the first perception data and the second perception data; The alarm module is used to sound an alarm to remind people when it is determined that there is a sneak attack.

Images