Vehicle alarm method and device, vehicle, storage medium and program product

Abstract

The invention relates to the technical field of vehicle safety, and discloses a vehicle alarm method and device, a vehicle, a storage medium and a program product, and the vehicle alarm method comprises the steps: carrying out the personnel detection of a current image collected by a vehicle-mounted camera, and determining the current position information of the personnel; the target person is tracked according to the current position information of the person, a tracking result is obtained, the tracking result comprises the current position information of the target person, and the target person is the person in the alarm range of the vehicle; according to the tracking result, a target sequence is updated, and the target sequence comprises position information of the target person at at least one moment; and determining whether to trigger an alarm according to the updated target sequence. According to the invention, the position information of the target person is maintained and tracked through the target sequence, so that confusion of state information of multiple persons can be avoided, and the alarm accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle safety technology, and in particular to a vehicle alarm method, device, vehicle, storage medium and program product. Background Art

[0002] Sentry mode is an intelligent safety feature of the vehicle. Once activated, the vehicle's existing sensors, cameras, and other hardware will be used to monitor the surrounding area. If suspicious activity is detected around the vehicle, the vehicle will be controlled to sound an alarm to serve as a warning.

[0003] Currently, vehicle sentry modes can be categorized as sensor fusion-based, millimeter-wave radar-based, and deep learning-based. Compared to sensor fusion-based and millimeter-wave radar-based sentry modes, deep learning-based sentry modes can better determine whether a person is approaching the vehicle, reducing false alarms.

[0004] However, in related technologies, when determining whether a person is engaging in suspicious activities based on a deep learning algorithm, if there are multiple people within the vehicle's alarm range, it is easy for errors in the person identification results to be large, resulting in a problem of low vehicle alarm accuracy. Summary of the Invention

[0005] In view of this, the present invention provides a vehicle alarm method, device, vehicle, storage medium and program product to improve the problem of low alarm accuracy caused by large errors in personnel recognition results.

[0006] In a first aspect, the present invention provides a vehicle alarm method, comprising: performing personnel detection on a current image captured by a vehicle-mounted camera to determine the current position information of the person; tracking a target person based on the current position information of the person to obtain a tracking result, wherein the tracking result includes the current position information of the target person, and the target person is a person within the alarm range of the vehicle; updating a target sequence based on the tracking result, wherein the target sequence includes the position information of the target person at at least one moment; and determining whether to trigger an alarm based on the updated target sequence.

[0007] The vehicle alarm method provided in this embodiment first detects a person in the current image captured by the vehicle's camera to determine the person's current location information. It then tracks the target person based on the person's current location information to obtain a tracking result, updates the target sequence based on the tracking result, and finally determines whether to trigger an alarm based on the updated target sequence. In this embodiment, updating the tracking result of the target person to the corresponding target sequence and maintaining the corresponding target person through the target sequence can avoid confusion between the status information of multiple people, effectively preventing the situation where the dwell time of multiple people passing through the alarm range is accumulated and an alarm is triggered, thereby improving the accuracy of the alarm.

[0008] In an optional embodiment, the number of target persons and the number of target sequences are both plural, and the number of target sequences is less than or equal to the number of target persons.

[0009] In an optional embodiment, determining whether to trigger an alarm based on the updated target sequence includes: determining status information of the target person based on the updated target sequence, wherein the status information includes time information reflecting that the target person is within the alarm range; and determining whether to trigger an alarm based on the status information of the target person.

[0010] In an optional implementation, determining whether to trigger an alarm based on the status information of the target person includes: triggering an alarm when the time information corresponding to the target person is greater than or equal to a preset alarm duration.

[0011] In this embodiment, an alarm is triggered when the duration and / or continuous duration of a person within the alarm range from any perspective is greater than or equal to the preset alarm duration, so that an abnormal situation can be responded to quickly and problems can be discovered in time.

[0012] In an optional embodiment, there are multiple vehicle-mounted cameras, target persons, and target sequences, and at least one vehicle-mounted camera corresponds to at least one target sequence; determining whether to trigger an alarm based on the status information of the target person includes: determining a first duration based on the status information of multiple target persons, wherein the first duration is the sum of the maximum values in the time information corresponding to at least one target person under each vehicle-mounted camera; and triggering an alarm when the first duration is greater than a preset alarm duration.

[0013] In this embodiment, the comprehensive judgment of whether to trigger an alarm based on multiple perspectives can more comprehensively grasp the activities of people within the entire alarm range, more accurately reflect the overall activity status of people from different perspectives, and reduce the possibility of missed reports.

[0014] In an optional embodiment, the status information also includes indication information of whether a person is missing, and the multiple vehicle-mounted cameras include at least a front camera, a rear camera, a left camera, and a right camera; determining whether to trigger an alarm based on the status information of the target person also includes: triggering an alarm when the status information of the target person corresponding to the front camera or the rear camera indicates lost, and the current images corresponding to the left camera and the right camera do not detect the person; or, triggering an alarm when the status information of the target person corresponding to the left camera and the right camera both indicate lost, and the current images corresponding to the front camera or the rear camera do not detect the person.

[0015] In this embodiment, monitoring the blind spots between different perspectives can effectively make up for the shortcomings of single-perspective alarms and multi-perspective alarms in monitoring blind spots, reduce the possibility of people using blind spots to hide or conduct suspicious activities, and further improve the safety of the vehicle.

[0016] In an optional embodiment, the alarm range includes a first alarm zone set around the vehicle body and a second alarm zone set around the first alarm zone, and the time information includes the duration and / or continuous duration of the target person in the first alarm zone, the duration and / or continuous duration of the target person in the second alarm zone, the timestamp of the target person's first entry into the first alarm zone, and the timestamp of the target person's first entry into the second alarm zone.

[0017] In this embodiment, the alarm range is divided into two areas, and computing resources can be reasonably allocated according to the importance and activity frequency of different areas.

[0018] In an optional embodiment, before determining whether to trigger an alarm based on the status information of the target person, the method also includes: determining a level of alarm sensitivity, wherein the alarm sensitivity is divided into multiple levels, and each level corresponds to different alarm information; determining whether to trigger an alarm based on the status information of the target person, including: determining whether to trigger an alarm based on the status information of the target person and the alarm information corresponding to the level of alarm sensitivity.

[0019] In an optional embodiment, the target person is tracked based on the person's current location information to obtain a tracking result, including: determining the predicted location information based on the target person's previous location information and a Kalman filtering method, wherein the predicted location information is the current location information of the target person predicted using the Kalman filtering method; matching the predicted location information and the person's current location information to obtain a tracking result.

[0020] In this embodiment, after extracting the current location information of the person, Kalman filtering is used to track the target person. The amount of calculation is small, which can reduce the operating load of the controller. Moreover, tracking can be performed only using location information. Compared with the tracking algorithm based on deep learning, the tracking effect is better, which can further improve the accuracy of the alarm.

[0021] In an optional embodiment, there are multiple people, and the predicted location information and the current location information of the people are matched to obtain tracking results, including: determining the distance score between the predicted location information and the current location information of the people to obtain multiple distance scores, wherein the multiple distance scores correspond one-to-one to the multiple people; determining the current location information of the person corresponding to the target distance score as the current location information of the target person, wherein the target distance score is the maximum value of at least one distance score among the multiple distance scores that is greater than the preset distance score.

[0022] In a second aspect, the present invention provides a vehicle alarm device, comprising: a detection module, used to perform personnel detection on a current image captured by a vehicle-mounted camera, and determine the current position information of the person; a tracking module, used to track a target person based on the current position information of the person, and obtain a tracking result, wherein the tracking result includes the current position information of the target person, and the target person is a person within the alarm range of the vehicle; an updating module, used to update a target sequence based on the tracking result, wherein the target sequence includes the position information of the target person at at least one moment; and an alarm module, used to determine whether to trigger an alarm based on the updated target sequence.

[0023] In an optional embodiment, the number of target persons and the number of target sequences are both plural, and the number of target sequences is less than or equal to the number of target persons.

[0024] In an optional embodiment, the alarm module includes: a first determination unit, used to determine the status information of the target person based on the updated target sequence, wherein the status information includes time information reflecting that the target person is within the alarm range; an alarm unit, used to determine whether to trigger an alarm based on the status information of the target person.

[0025] In an optional embodiment, the alarm unit includes: a first triggering unit, configured to trigger an alarm when the time information corresponding to the target person is greater than or equal to a preset alarm duration.

[0026] In an optional embodiment, there are multiple vehicle-mounted cameras, target persons, and target sequences, and at least one vehicle-mounted camera corresponds to at least one target sequence; the alarm unit includes: a first determination subunit, used to determine a first duration based on status information of multiple target persons, wherein the first duration is the sum of the maximum values in the time information corresponding to at least one target person under each vehicle-mounted camera; and a second triggering unit, used to trigger an alarm when the first duration is greater than a preset alarm duration.

[0027] In an optional embodiment, the status information also includes indication information of whether a person is missing, and the multiple vehicle-mounted cameras include at least a front camera, a rear camera, a left camera, and a right camera; the alarm unit also includes: a third trigger unit, which is used to trigger an alarm when the status information of the target person corresponding to the front camera or the rear camera indicates that the person is lost, and the current images corresponding to the left camera and the right camera do not detect the person; or, a fourth trigger unit, which is used to trigger an alarm when the status information of the target person corresponding to the left camera and the right camera both indicate that the person is lost, and the current image corresponding to the front camera or the rear camera does not detect the person.

[0028] In an optional embodiment, the alarm range includes a first alarm zone set around the vehicle body and a second alarm zone set around the first alarm zone, and the time information includes the duration and / or continuous duration of the target person in the first alarm zone, the duration and / or continuous duration of the target person in the second alarm zone, the timestamp of the target person's first entry into the first alarm zone, and the timestamp of the target person's first entry into the second alarm zone.

[0029] In an optional embodiment, the device further comprises: a determination module for determining a level of alarm sensitivity, wherein the alarm sensitivity is divided into multiple levels, each level corresponding to different alarm information;

[0030] The alarm unit includes: a fifth triggering unit, which is used to determine whether to trigger an alarm according to the state information of the target person and the alarm information corresponding to the level of alarm sensitivity.

[0031] In an optional embodiment, the tracking module includes: a second determination unit, used to determine the predicted location information based on the target person's previous location information and the Kalman filtering method, wherein the predicted location information is the current location information of the target person predicted using the Kalman filtering method; a matching unit, used to match the predicted location information and the person's current location information to obtain a tracking result.

[0032] In an optional embodiment, there are multiple people, and the matching unit includes: a second determination subunit, used to determine the distance score between the predicted location information and the current location information of the person, and obtain multiple distance scores, wherein the multiple distance scores correspond one-to-one to the multiple people; a third determination subunit, used to determine the current location information of the person corresponding to the target distance score as the current location information of the target person, wherein the target distance score is the maximum value of at least one distance score among the multiple distance scores that is greater than the preset distance score.

[0033] In a third aspect, the present invention provides a vehicle comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the vehicle alarm method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0034] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a vehicle to execute the vehicle alarm method of the first aspect or any corresponding embodiment thereof.

[0035] In a fifth aspect, the present invention provides a computer program product comprising computer instructions for causing a vehicle to execute the vehicle alarm method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in related technologies, the following briefly introduces the drawings required for use in the specific embodiments or related technical descriptions. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0037] Figure 1 is a flow chart of a vehicle alarm method according to an embodiment of the present invention;

[0038] Figure 2 is a schematic diagram of a process flow of key points of a human body according to an embodiment of the present invention;

[0039] Figure 3 is a flow chart of another vehicle alarm method according to an embodiment of the present invention;

[0040] Figure 4 is a schematic diagram of an alarm range according to an embodiment of the present invention;

[0041] Figure 5 is a flow chart of another vehicle alarm method according to an embodiment of the present invention;

[0042] Figure 6 This is a schematic diagram of a specific flow chart of a vehicle alarm method according to an embodiment of the present invention;

[0043] Figure 7 is a structural block diagram of a vehicle alarm device according to an embodiment of the present invention;

[0044] Figure 8 4 is a schematic diagram of the hardware structure of a vehicle according to an embodiment of the present invention. DETAILED DESCRIPTION

[0045] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. According to the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of the present invention.

[0046] When determining whether a person is engaging in suspicious activities based on a deep learning algorithm, if there are multiple people within the vehicle's alarm range, the deep learning algorithm is prone to large errors in person recognition results due to factors such as changes in natural environment such as lighting conditions, people's postures, and partial occlusion of their bodies. This can lead to confusion among multiple people, and the cumulative length of stay of multiple people may cause an alarm, thereby affecting the accuracy of the alarm.

[0047] In view of this, the present invention provides a vehicle alarm method, which can avoid confusion of status information (location and time, etc.) of multiple persons by tracking the location information of the target person through target sequence maintenance, thereby improving the accuracy of the alarm.

[0048] The vehicle alarm method provided by the present invention is applied to a vehicle equipped with an on-board camera, which may be a surround-view camera or a panoramic camera, etc.

[0049] The vehicle alarm method provided by the present invention is described in detail below with reference to the accompanying drawings.

[0050] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a vehicle controller such as a set of computer-executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0051] In this embodiment, a vehicle alarm method is provided, which can be used in a vehicle controller. Figure 1 FIG. 1 is a flow chart of a vehicle alarm method according to an embodiment of the present invention. Figure 1As shown, the method includes the following steps:

[0052] Step S101 : performing personnel detection on the current image captured by the vehicle-mounted camera to determine the current position information of the person.

[0053] The current image is the image captured by the vehicle-mounted camera at the current moment, and the current image changes dynamically over time.

[0054] Exemplarily, a posture estimation model (target detection algorithm and posture estimation algorithm) may be used to perform person detection on the current image to determine the current position information of the person.

[0055] Specifically, the target detection algorithm is used to identify whether there are people in the current image. If a person is present, a detection box (bounding box) can be used to identify the person's position. The posture estimation algorithm is used to estimate the coordinate information of the key points of the person's body within the detection box and determine the person's current coordinates (i.e., current position information) based on the coordinate information of the key points of the body. The target detection algorithm can be a conventional target detection algorithm in the field, and the posture estimation algorithm can also be a conventional posture estimation algorithm in the field, and will not be described in detail here.

[0056] For example, the key points of the human body can be Figure 2 As shown, the estimated human key points can be 17, namely nose 0, right eye 1, left eye 2, right ear 3, left ear 4, right shoulder 5, left shoulder 6, right elbow 7, left elbow 8, right wrist 9, left wrist 10, right hip 11, left hip 12, right knee 13, left knee 14, right ankle 15 and left ankle 16. The coordinate information of the human key points can be Keypoints{[X0,Y0],[X1,Y1],…,[X 16 ,Y 16 ]}.

[0057] After obtaining the coordinate information of the key points of the human body, the center coordinates of the two ankles (right ankle 15 and left ankle 16) can be used as the current position information K{K x ,K y}.

[0058] Optionally, the posture estimation model can be a deep learning model trained on a database, the database includes multiple annotated images, the annotated images contain the coordinate information of the detection box and the current coordinates of the person, the coordinate information of the detection box can be Box{X min ,Y min ,X max ,Y max},(X min ,Y min ) represents the coordinates of the boundary point located at the upper left corner, (X max ,Y max) represents the coordinates of the boundary point located in the lower right corner. During training, the input of the deep learning model is the image, and the output of the deep learning model is the current location information of the person and the coordinate information of the detection box.

[0059] Specifically, after acquiring the current image, the current image may be input into a posture estimation model, and the position information of the person may be determined according to the output of the posture estimation model.

[0060] The deep learning model is an end-to-end algorithm model. Compared with the traditional detection algorithm model, the end-to-end algorithm model directly outputs the bounding box and human posture key points, which not only improves the running speed but also outputs the detection box and human posture key points.

[0061] It should be understood that the above step S101 is explained based on the existence of people in the current image. The number of people can be at least one. If there is no person in the current image, the current location information of the person is empty. Then the current image is reacquired and people detection is continued in the current image.

[0062] Step S102: Track the target person according to the current location information of the person to obtain a tracking result.

[0063] The tracking result includes the current location information of the target person, and the target person is the person within the alarm range of the vehicle.

[0064] The target person can be someone who has entered the vehicle's alarm range before the current image was captured. For example, if person A enters the vehicle's alarm range in the image captured at the 1st second, person A is the target person. The image captured at the 1st second is recorded as the previous image, and the image captured at the 2nd second is recorded as the current image. Person A is tracked based on the person's current location information obtained through person detection in the current image. The 1st second image and the 2nd second image can be two consecutive frames, and there can be one or more target persons.

[0065] The alarm range can be a preset area centered on the vehicle. The preset area can be circular, elliptical or rectangular, etc. The alarm range can be configured by the designer according to needs. For example, the alarm range can be a circle center area centered on the centroid of the vehicle body with a radius of 2m.

[0066] Specifically, the target person is tracked based on the current position information of the person and a tracking algorithm to obtain a tracking result. For example, the tracking algorithm may be a Kalman filter, a particle filter, or an optical flow method.

[0067] It should be understood that the above step S102 is explained based on the existence of the target person in the current image. If the target person does not exist in the current image, the tracking result also includes indication information that the target person is missing and time information of the target person being missing.

[0068] Step S103: Update the target sequence according to the tracking result.

[0069] The target sequence is pre-configured in the controller of the vehicle, and the target sequence includes the location information of the target person at at least one moment.

[0070] Specifically, the target sequence corresponds to the target person. Each time the tracking result is processed, it is saved in the corresponding target sequence, resulting in an updated target sequence. If the tracking result includes an indication of the target person's loss and the time at which the target person was lost, the updated target sequence also includes the time at which the target person was lost.

[0071] For example, there are multiple target persons and multiple target sequences, and the number of target sequences is less than or equal to the number of target persons. That is, when there are a large number of target persons, it is not necessary to create a target sequence for each target person. Only some of the target persons can be tracked, thereby reducing the computational complexity of the vehicle controller.

[0072] Step S104: Determine whether to trigger an alarm based on the updated target sequence.

[0073] Specifically, after determining the updated target sequence, the time information of the target person within the alarm range can be determined. This time information can then be used to determine whether the target person is abnormal, thereby triggering an alarm. For example, if the target person's time information exceeds a preset duration, it indicates that the target person's activity is abnormal, triggering an alarm. The preset duration can be configured by the designer according to actual needs, for example, the preset duration can be 2 minutes (min) or 3 minutes, etc.

[0074] For example, triggering an alarm can specifically involve the vehicle controller controlling a sound device (such as a horn) on the vehicle to emit a continuous or intermittent honking sound to attract attention within a certain range and alert suspicious individuals. Triggering an alarm can also involve the vehicle controller controlling a lighting device such as the vehicle's headlights or hazard lights to flash, attracting attention from nearby personnel and alerting suspicious individuals. Triggering an alarm can also involve the vehicle controller pushing an alarm notification message to the owner's smart terminal (such as a mobile phone or smartwatch), which can include the alarm time and a description of the abnormal situation (such as "It is detected that a person has stayed around the vehicle for too long, which may be an abnormality"). Triggering an alarm can also be a combination of at least two of the above methods, and is not limited to this.

[0075] The vehicle alarm method provided in this embodiment first detects a person in the current image captured by the vehicle's camera to determine the person's current location information. It then tracks the target person based on the person's current location information to obtain a tracking result, updates the target sequence based on the tracking result, and finally determines whether to trigger an alarm based on the updated target sequence. In this embodiment, updating the tracking result of the target person to the corresponding target sequence and maintaining the corresponding target person through the target sequence can avoid confusion between the status information of multiple people, effectively preventing the situation where the dwell time of multiple people passing through the alarm range is accumulated and an alarm is triggered, thereby improving the accuracy of the alarm.

[0076] In this embodiment, another vehicle alarm method is provided, which can be used in a vehicle controller. Figure 3 FIG. 1 is a flow chart of another vehicle alarm method according to an embodiment of the present invention. Figure 3 As shown, the method includes the following steps:

[0077] Step S301 : performing personnel detection on the current image captured by the vehicle-mounted camera to determine the current position information of the person.

[0078] For details, please see Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0079] Step S302: Track the target person according to the current location information of the person to obtain a tracking result.

[0080] For details, please see Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0081] Step S303: Update the target sequence according to the tracking result.

[0082] For details, please see Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0083] Step S304: Determine whether to trigger an alarm based on the updated target sequence.

[0084] Specifically, the above step S304 includes:

[0085] Step S3041: Determine the status information of the target person according to the updated target sequence.

[0086] The status information includes time information reflecting that the target person is within the alarm range, and the status information changes in real time based on the updated target sequence.

[0087] Exemplarily, the status information may include the duration and / or continuous duration that the target person is within the alarm range of the vehicle. The duration may refer to the accumulated value of the duration that the target person is within the alarm range of the vehicle, and the continuous duration may refer to the duration that the target person is within the alarm range of the vehicle at one time.

[0088] For example, if the target person enters the alarm range of the vehicle from the 30th second of detection, the target person can be detected in the current image until the 60th second, and then the target person is detected again in the current image at the 80th second as entering the alarm range of the vehicle, and the target person can be detected in the current image until the 120th second. At this time, the duration of the target person being in the alarm range is 70s = (60s - 30s) + (120s - 80s), and the continuous duration of the person being in the alarm range can be 30s (the duration between the 30th and 60th seconds) and 40s (the duration between the 80th and 120th seconds).

[0089] Specifically, the updated target sequence includes the current location information of the target person, and whether the target person is within the alarm range of the vehicle can be determined based on the current location information of the target person, and the status information of the target person can be updated based on the information of whether the target person is within the alarm range of the vehicle and the acquisition time of the current image.

[0090] In some examples, the status information may also include information indicating that the target person is missing and the time when the target person is missing.

[0091] Step S3042: Determine whether to trigger an alarm based on the status information of the target person.

[0092] Specifically, after determining the status information of the target person, if the status information of the target person meets the alarm conditions, it indicates that there is an abnormality in the target person and an alarm is triggered; if the status information of the target person does not meet the alarm conditions, it indicates that there is no abnormality in the target person, and the current image is reacquired, and steps S301 to S304 are executed.

[0093] In some embodiments, the alarm condition can be a single-view alarm, that is, the alarm is triggered when the time information (such as duration and / or continuous duration) corresponding to any target person is greater than or equal to the preset alarm duration. The preset alarm duration can be determined by the designer based on actual needs, for example, the preset alarm duration can be 2 minutes or 3 minutes.

[0094] In this embodiment, an alarm is triggered when the duration and / or continuous duration of the target person within the alarm range from any perspective is greater than the preset alarm duration, so that an abnormal situation can be responded to quickly and problems can be discovered in time.

[0095] In other embodiments, there are multiple vehicle-mounted cameras, multiple target persons, and multiple target sequences, and at least one vehicle-mounted camera corresponds to at least one target sequence. That is, not every vehicle-mounted camera has a target sequence. Each vehicle-mounted camera may contain one target sequence or multiple target sequences (e.g., three). The alarm condition may be a multi-view alarm. In this case, step S3042 may include steps a1 and a2:

[0096] Step a1: Determine a first duration based on status information of multiple target persons.

[0097] The first duration is the sum of the maximum values in the time information corresponding to at least one target person under each vehicle-mounted camera.

[0098] Take the example of 4 onboard cameras and 3 target sequences for each camera. If 2 of the 3 target sequences corresponding to the first onboard camera are not empty, the empty sequences are ignored. From the 2 non-empty target sequences, we can get the duration (i.e., time information) corresponding to one target person as 2 minutes and the duration corresponding to another target person as 1 minute. If 1 of the 3 target sequences corresponding to the second onboard camera is not empty, from this target sequence we can get the duration corresponding to one target person as 1 minute. The 3 target sequences corresponding to the third onboard camera are all non-empty. Empty, from the three non-empty target sequences, it can be obtained that the duration corresponding to the first target person is 0.5min, the duration corresponding to the second target person is 1min, and the duration corresponding to the third target person is 0.5min. One of the three target sequences corresponding to the fourth vehicle-mounted camera is not empty, and from this target sequence, it can be obtained that the duration corresponding to a target person is 1min. Then the first duration can be 5min=max{2min, 1min}+1min+max{0.5min, 1min, 0.5min}+1min.

[0099] Step a2: triggering an alarm when the first duration is greater than or equal to a preset alarm duration.

[0100] Specifically, the maximum value of the time information (such as duration or continuous duration) corresponding to at least one target person in each viewing angle (on-board camera) is accumulated, and an alarm is triggered when the accumulated duration exceeds the preset alarm duration. Wherein, at least one viewing angle can detect the target person.

[0101] In this embodiment, whether to trigger an alarm is determined comprehensively based on multiple perspectives, which can more comprehensively grasp the activities of the target person within the entire alarm range, more accurately reflect the overall activity status of the target person at different perspectives, identify abnormal situations in which the target person stays for a short time at each perspective but wanders around the vehicle body, and reduce the possibility of missed reports.

[0102] In some other embodiments, there are multiple onboard cameras, including at least a front camera, a rear camera, a left camera, and a right camera. The front camera refers to the onboard camera located at the front of the vehicle, the rear camera refers to the onboard camera located at the rear of the vehicle, the left camera refers to the onboard camera located on the left side of the vehicle, and the right camera refers to the onboard camera located on the right side of the vehicle. The status information also includes information indicating whether a person is missing. The indication information may be a string or a symbol. If a string is present, it indicates that the person is missing.

[0103] The alarm condition of this embodiment may be a blind spot alarm. In this case, the above step S3042 may further include step b1 or step b2:

[0104] Step b1: When the status information of the target person corresponding to the front camera or the rear camera indicates that the person is lost, and no person is detected in the current images corresponding to the left camera and the right camera, an alarm is triggered.

[0105] Step b2: When the status information of the target person corresponding to the left camera and the right camera both indicate that the person is lost, and the current image corresponding to the front camera or the rear camera does not detect the person, an alarm is triggered.

[0106] In this embodiment, monitoring the blind spots between different perspectives can effectively make up for the shortcomings of single-perspective alarm and multi-perspective alarm in monitoring blind spots, reduce the possibility of target personnel using blind spots to hide or conduct suspicious activities, and further improve the safety of the vehicle.

[0107] It should be understood that the left camera is generally located on the left rearview mirror, and the right camera is generally located on the right rearview mirror. When the vehicle is parked (in a parking space or has been parked for longer than a preset time), the left and right rearview mirrors are retracted, and blind spots may exist at corresponding locations in the left and right front of the vehicle. Accordingly, when the left and right cameras are located in other locations, blind spots may also exist at corresponding locations in the left and right rear of the vehicle.

[0108] In this embodiment, each viewpoint can maintain three target sequences, and the vehicle can maintain 12 target sequences, determining the status information of 12 target personnel. The number of target sequences per viewpoint is limited by the operating speed. If the vehicle controller has sufficient computing power, the number of target sequences per viewpoint can be increased.

[0109] In some embodiments, as Figure 4As shown, the alarm range includes a first alarm zone 401 set around the vehicle body and a second alarm zone 402 set around the first alarm zone 401, and the time information includes the duration and / or continuous duration of the target person in the first alarm zone, the duration and / or continuous duration of the target person in the second alarm zone, the timestamp of the target person's first entry into the first alarm zone, and the timestamp of the target person's first entry into the second alarm zone.

[0110] Specifically, the range of the first alarm zone 401 and the second alarm zone 402 can be configured by the designer according to needs. For example, the first alarm zone 401 can be within 1 meter from the vehicle body, and the first alarm zone is a high-risk area; the second alarm zone 402 can be within 3 meters from the vehicle body, and the second alarm zone can be a low-risk area.

[0111] Optionally, before the above step S3042, the vehicle alarm method further includes:

[0112] Step c1, determining the level of alarm sensitivity.

[0113] Among them, the alarm sensitivity is divided into multiple levels, and each level corresponds to different alarm information.

[0114] In one example, the alarm sensitivity can be divided into three levels: 0, 1 and 2. When the alarm sensitivity level is 0, the alarm information may include that the continuous time that any target person is in the first alarm zone reaches the preset alarm time; when the alarm sensitivity level is 1, the alarm information may include that the continuous time and continuous time that any target person is in the first alarm zone reaches the preset alarm time, and the continuous time that the target person is in the second alarm zone also reaches the preset alarm time; when the alarm sensitivity level is 2, the alarm information may include that the continuous time and continuous time that any target person is in the first alarm zone reaches the preset alarm time, and the continuous time and continuous time that the target person is in the second alarm zone also reaches the preset alarm time.

[0115] At this time, the above step S3042 can specifically be: determining whether to trigger an alarm based on the target person's status information and the alarm information corresponding to the alarm sensitivity level. Specifically, when the target person's status information meets the alarm information corresponding to the alarm sensitivity level, it indicates that the target person's activity is abnormal, and the alarm is triggered.

[0116] In this embodiment, the alarm range is divided into two areas, and computing resources can be reasonably allocated according to the importance and activity frequency of different areas.

[0117] In this embodiment, another vehicle alarm method is provided, which can be used in a vehicle controller. Figure 5 FIG. 1 is a flow chart of another vehicle alarm method according to an embodiment of the present invention. Figure 5 As shown, the method includes the following steps:

[0118] Step S501 : performing personnel detection on the current image captured by the vehicle-mounted camera to determine the current position information of the person.

[0119] For details, please see Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0120] Step S502: Track the target person according to the current location information of the person to obtain a tracking result.

[0121] Specifically, the above step S502 includes:

[0122] Step S5021: Determine the predicted location information based on the target person's previous location information and the Kalman filter method.

[0123] The predicted location information is the current location information of the target person predicted by using the Kalman filter method.

[0124] Specifically, after obtaining the previous location information of the target person, a predicted location information can be obtained based on Kalman filtering.

[0125] Exemplarily, the update formula of the Kalman filter can be shown as formula (1):

[0126]

[0127] In formula (1), represents the prior estimate (predicted value) of the state at the current time t, It is the posterior estimate of the state at the previous moment t-1 And the current state predicted by the external control signal u(t) at the current moment; A t Represents the state transfer matrix, which describes the transition relationship of the system state from the previous time t-1 to the current time t; B t Represents the control input matrix, which maps the system input u(t) to the system state space and is used to reflect the impact of external input on the system state.

[0128] Represents the covariance matrix of the prior estimate of the state at the current time t, reflecting the uncertainty of the prior estimate; Represents the covariance matrix of the posterior estimate of the state at the previous moment t-1; Indicates A t The transposed matrix of t represents the process noise covariance matrix and is the system fixed error.

[0129] Represents the posterior estimate of the state at the current time t, which is combined with the observation value z t Prior estimates The result after correction; t Represents the observation value at the current time t; K t Represents the Kalman gain, which determines the weight between the observed value and the predicted value when updating the state estimate; H t Represents the observation matrix, which is used to map the system state space to the observation space and describe the relationship between the system state and the observation value.

[0130] Indicates H t The transposed matrix, R T Represents the observation noise covariance matrix, reflecting the statistical characteristics of the noise during the observation process, Represents the covariance matrix of the posterior estimate of the state at the current time t, reflecting the uncertainty of the updated state estimate.

[0131] The Kalman filter is a recursive algorithm with relatively low computational complexity at each time step. It requires only basic operations such as matrix multiplication, addition, and inversion, and does not require the storage of large amounts of historical data, resulting in high computational efficiency. The Kalman filter uses location information to track individuals, addressing the ineffectiveness of deep learning-based tracking algorithms when incomplete individual information is present.

[0132] Step S5022: Match the predicted location information with the person's current location information to obtain a tracking result.

[0133] Specifically, after obtaining the current location information of at least one person, the distance between the predicted position of the target person and the current position of each person can be determined. Based on the size of the distance, it can be determined whether the target person exists among at least one person and the current location information of the target person can be determined.

[0134] For example, if the distance between a person's current location and the predicted location of the target person is very close (less than the preset distance), the person is considered to match the target person, and the current location information of the person is the current location information of the target person. If there are multiple people whose distance to the predicted location of the target person is very close, the person with the closest distance can be considered to match the target person.

[0135] In some optional implementations, there are multiple personnel, and the above step S5022 may include:

[0136] Step d1, determining a distance score between the predicted location information and the current location information of the person, and obtaining a plurality of distance scores.

[0137] Among them, multiple distance scores correspond to multiple people one by one.

[0138] For example, the distance score between the predicted location information and the current location information of each person can be represented by the Euclidean distance. The larger the distance score, the closer the distance between the predicted location information and the current location information.

[0139] Step d2: determining the current location information of the person corresponding to the target distance score as the current location information of the target person.

[0140] The target distance score is the maximum value of at least one distance score among the multiple distance scores that is greater than the preset distance score.

[0141] Specifically, if there are multiple distance scores greater than the preset distance score among the multiple distance scores, the maximum value among the multiple distance scores greater than the preset distance score is determined as the target distance score.

[0142] In other embodiments, the predicted location information and the person's current location information may be matched based on a Hungarian matching algorithm to obtain a tracking result. The Hungarian matching algorithm may be a conventional Hungarian matching algorithm in the art and will not be described in detail here.

[0143] Step S503: Update the target sequence according to the tracking result.

[0144] For details, please see Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0145] Step S504: Determine whether to trigger an alarm based on the updated target sequence.

[0146] For details, please see Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0147] In this embodiment, after extracting the current location information of the person, Kalman filtering is used to track the target person. The amount of calculation is small, which can reduce the operating load of the controller. Moreover, tracking can be performed only using location information. Compared with the tracking algorithm based on deep learning, the tracking effect is better, which can further improve the accuracy of the alarm.

[0148] The following combination Figure 6 , the vehicle alarm method provided by the present invention is described in detail with specific examples.

[0149] like Figure 6As shown in the figure, when the vehicle is in sentry mode, it can first obtain a video stream from the on-board camera, then obtain a picture stream from the video stream to obtain the current image, and then input the current image into the posture estimation model to determine the current position information of the person based on the input of the posture estimation model.

[0150] After obtaining the person's current location information, the target person is tracked using a Kalman filter to obtain a tracking result. The target sequence is then updated based on the tracking result. The updated target sequence is used to determine whether the target person is abnormal. If so, an alarm is triggered; otherwise, the current image is reacquired.

[0151] In this embodiment, a vehicle alarm device is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments. Details already described will not be repeated here. As used below, the term "module" may refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0152] This embodiment provides a vehicle alarm device, such as Figure 7 As shown, including:

[0153] The detection module 701 is used to detect people in the current image captured by the vehicle-mounted camera and determine the current location information of the people;

[0154] A tracking module 702 is configured to track a target person according to the current location information of the person and obtain a tracking result, wherein the tracking result includes the current location information of the target person, and the target person is a person within the alarm range of the vehicle;

[0155] An updating module 703 is configured to update a target sequence according to the tracking result, wherein the target sequence includes location information of the target person at at least one moment;

[0156] The alarm module 704 is configured to determine whether to trigger an alarm based on the updated target sequence.

[0157] In some optional implementations, the number of target persons and the number of target sequences are both plural, and the number of target sequences is less than or equal to the number of target persons.

[0158] In some optional implementations, the alarm module 704 includes:

[0159] A first determining unit is configured to determine status information of a target person according to the updated target sequence, wherein the status information includes time information reflecting that the target person is within the alarm range;

[0160] The alarm unit is used to determine whether to trigger an alarm based on the status information of the target person.

[0161] In some optional embodiments, the alarm unit includes:

[0162] The first triggering unit is used to trigger an alarm when the time information corresponding to the target person is greater than or equal to a preset alarm duration.

[0163] In some optional embodiments, there are multiple vehicle-mounted cameras, multiple target persons, and multiple target sequences, and at least one vehicle-mounted camera corresponds to at least one target sequence; the alarm unit includes:

[0164] A first determining subunit is configured to determine a first duration based on status information of multiple target persons, wherein the first duration is the sum of the maximum values of time information corresponding to at least one target person under each vehicle-mounted camera;

[0165] The second triggering unit is used to trigger an alarm when the first duration is greater than a preset alarm duration.

[0166] In some optional embodiments, the status information further includes information indicating whether a person is missing, the multiple vehicle-mounted cameras include at least a front camera, a rear camera, a left camera, and a right camera; and the alarm unit further includes:

[0167] A third triggering unit is configured to trigger an alarm when the status information of the target person corresponding to the front camera or the rear camera indicates that the target person is lost and no person is detected in the current images corresponding to the left camera and the right camera; or

[0168] The fourth trigger unit is used to trigger an alarm when the status information of the target person corresponding to the left camera and the right camera both indicate that the person is lost, and the current image corresponding to the front camera or the rear camera does not detect the person.

[0169] In some optional embodiments, the alarm range includes a first alarm zone set around the vehicle body and a second alarm zone set around the first alarm zone, and the time information includes the duration and / or continuous duration of the target person in the first alarm zone, the duration and / or continuous duration of the target person in the second alarm zone, the timestamp of the target person's first entry into the first alarm zone, and the timestamp of the target person's first entry into the second alarm zone.

[0170] In some optional embodiments, the device further comprises:

[0171] A determination module, used to determine the level of alarm sensitivity, wherein the alarm sensitivity is divided into multiple levels, each level corresponding to different alarm information;

[0172] The alarm unit includes: a fifth triggering unit, which is used to determine whether to trigger an alarm according to the state information of the target person and the alarm information corresponding to the level of alarm sensitivity.

[0173] In some optional implementations, the tracking module 702 includes:

[0174] A second determining unit is configured to determine predicted location information based on the previous location information of the target person and a Kalman filter method, wherein the predicted location information is the current location information of the target person predicted by the Kalman filter method;

[0175] The matching unit is used to match the predicted location information with the current location information of the person to obtain the tracking result.

[0176] In some optional implementations, there are multiple persons, and the matching unit includes:

[0177] A second determining subunit is configured to determine a distance score between the predicted location information and the current location information of the person, and obtain a plurality of distance scores, wherein the plurality of distance scores correspond to the plurality of persons in a one-to-one manner;

[0178] The third determining subunit is configured to determine the current location information of a person corresponding to a target distance score as the current location information of the target person, wherein the target distance score is a maximum value of at least one distance score greater than a preset distance score among the multiple distance scores.

[0179] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0180] The vehicle alarm device in this embodiment is presented in the form of a functional unit, where the unit refers to an application-specific integrated circuit (ASIC), a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0181] The embodiment of the present invention further provides a vehicle, such as Figure 8As shown, the vehicle includes: one or more processors 810, a memory 820, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses and can be installed on a common motherboard or in other ways as needed. The processor can process instructions executed in the vehicle, including instructions stored in or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Figure 8 A processor 810 is taken as an example.

[0182] Processor 810 may be a central processing unit, a network processor, or a combination thereof. Processor 810 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0183] The memory 820 stores instructions that can be executed by at least one processor 810, so as to enable the at least one processor 810 to execute the method shown in the above embodiment.

[0184] The memory 820 may include a program storage area and a data storage area. The program storage area may store an operating system and applications required for at least one function; the data storage area may store data created based on vehicle usage, etc. Furthermore, the memory 820 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some optional embodiments, the memory 820 may optionally include a memory remotely located relative to the processor 810, and such remote memory may be connected to the vehicle via a network. Examples of the aforementioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0185] The memory 820 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid state drive; the memory 820 may also include a combination of the above types of memory.

[0186] The vehicle also includes a communication interface 830 for the vehicle to communicate with other devices or a communication network.

[0187] The embodiment of the present invention also provides a computer-readable storage medium. The above-mentioned method according to the embodiment of the present invention can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

[0188] A portion of the present invention may be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the vehicle. Those skilled in the art will appreciate that the computer program instructions may exist in a computer-readable medium in the form of, but are not limited to, source files, executable files, installation package files, and the like. Accordingly, the manner in which the computer program instructions are executed by the vehicle includes, but is not limited to: the vehicle directly executing the instruction, or the vehicle compiling the instruction and then executing the corresponding compiled program, or the vehicle reading and executing the instruction, or the vehicle reading and installing the instruction and then executing the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the vehicle.

[0189] In the description of this specification, the description with reference to the terms "this embodiment", "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0190] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "plurality" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0191] Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the present invention.

Claims

1. A vehicle alarm method, characterized in that: include: Perform personnel detection on the current image captured by the vehicle-mounted camera to determine the current location information of the person; Tracking a target person according to the current location information of the person to obtain a tracking result, wherein the tracking result includes the current location information of the target person, and the target person is a person within the alarm range of the vehicle; updating a target sequence according to the tracking result, wherein the target sequence includes location information of the target person at at least one moment; Determine whether to trigger an alarm based on the updated target sequence.

2. The method according to claim 1, characterized in that The number of the target persons and the number of the target sequences are both multiple, and the number of the target sequences is less than or equal to the number of the target persons.

3. The method according to claim 1, characterized in that The step of determining whether to trigger an alarm according to the updated target sequence includes: Determining the status information of the target person according to the updated target sequence, wherein the status information includes time information reflecting that the target person is within the alarm range; Determine whether to trigger an alarm based on the status information of the target person.

4. The method according to claim 3, characterized in that The step of determining whether to trigger an alarm based on the status information of the target person includes: When the time information corresponding to the target person is greater than or equal to the preset alarm duration, an alarm is triggered.

5. The method according to claim 3, characterized in that The number of the vehicle-mounted camera, the target person, and the target sequence is plural, and at least one vehicle-mounted camera corresponds to at least one target sequence; and determining whether to trigger an alarm based on the status information of the target person includes: Determining a first duration based on the status information of the plurality of target persons, wherein the first duration is the sum of the maximum values of the time information corresponding to at least one target person under each vehicle-mounted camera; When the first duration is greater than the preset alarm duration, an alarm is triggered.

6. The method according to claim 5, characterized in that The status information also includes information indicating whether the person is missing, the plurality of vehicle-mounted cameras at least include a front camera, a rear camera, a left camera, and a right camera; and determining whether to trigger an alarm based on the status information of the target person further includes: When the status information of the target person corresponding to the front camera or the rear camera indicates that the target person is lost, and no person is detected in the current images corresponding to the left camera and the right camera, an alarm is triggered; or, When the status information of the target person corresponding to the left camera and the right camera both indicate that the person is lost, and the current image corresponding to the front camera or the rear camera does not detect the person, an alarm is triggered.

7. The method according to any one of claims 3 to 6, characterized in that The alarm range includes a first alarm zone set around the vehicle body and a second alarm zone set around the first alarm zone, and the time information includes the duration and / or continuous duration of the target person in the first alarm zone, the duration and / or continuous duration of the target person in the second alarm zone, the timestamp of the target person's first entry into the first alarm zone, and the timestamp of the target person's first entry into the second alarm zone.

8. The method according to claim 7, characterized in that Before determining whether to trigger an alarm based on the status information of the target person, the method further includes: Determining a level of alarm sensitivity, wherein the alarm sensitivity is divided into multiple levels, each level corresponding to different alarm information; The step of determining whether to trigger an alarm based on the status information of the target person includes: Whether to trigger an alarm is determined based on the status information of the target person and the alarm information corresponding to the level of the alarm sensitivity.

9. The method according to any one of claims 1 to 6, characterized in that The tracking of the target person according to the current location information of the person to obtain a tracking result includes: Determining predicted location information based on the previous location information of the target person and a Kalman filter method, wherein the predicted location information is the current location information of the target person predicted by the Kalman filter method; The predicted location information is matched with the current location information of the person to obtain the tracking result.

10. The method according to claim 9, characterized in that There are multiple persons, and matching the predicted location information with the current location information of the persons to obtain the tracking result includes: Determining a distance score between the predicted location information and the current location information of the person to obtain a plurality of distance scores, wherein the plurality of distance scores correspond one-to-one to the plurality of persons; The current location information of a person corresponding to a target distance score is determined as the current location information of the target person, wherein the target distance score is a maximum value of at least one distance score greater than a preset distance score among the multiple distance scores.

11. A vehicle alarm device, characterized in that: The device comprises: The detection module is used to detect people in the current image captured by the vehicle-mounted camera and determine the current location information of the people; a tracking module, configured to track a target person according to the current location information of the person, and obtain a tracking result, wherein the tracking result includes the current location information of the target person, and the target person is a person within the alarm range of the vehicle; An updating module, configured to update a target sequence according to the tracking result, wherein the target sequence includes location information of the target person at at least one moment; The alarm module is used to determine whether to trigger an alarm based on the updated target sequence.

12. A vehicle, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the vehicle alarm method according to any one of claims 1 to 10 by executing the computer instructions.

13. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the vehicle alarm method according to any one of claims 1 to 10.

14. A computer program product, characterized in that The method comprises computer instructions for causing a vehicle to execute the vehicle alarm method according to any one of claims 1 to 10.

Images