Method and device for determining risk around vehicle, equipment and storage medium

Abstract

The invention discloses a method, device and equipment for determining risks around a vehicle and a computer readable storage medium. The method comprises: determining wireless channel state information (CSI) of a wireless signal wave emitted around a vehicle, the wireless channel state information comprising an amplitude and a phase; behavior actions of moving objects around the vehicle are determined according to the amplitude and the phase of the wireless channel state information; and determining whether the moving object has a safety risk on the vehicle according to the behavior action. The behavior action of the moving object is determined by adopting the wireless channel state information, so that the light intensity of a scene does not need to be considered, a blind area does not exist, and any moving object around the vehicle can be accurately reflected. And on the other hand, the behavior action of the moving object is generated based on the wireless channel state information, invasion of privacy such as a portrait of the moving object does not exist, and whether the moving object around the vehicle has a safety risk on the vehicle or not can be accurately judged under the condition that legal issues are not involved.

Description

Technical Field

[0001] The present application relates to the field of vehicles, and in particular to a method, device, equipment and computer-readable storage medium for determining risks around a vehicle. Background Art

[0002] In the related art, an image acquisition module installed on the vehicle is usually used to collect images around the vehicle and combine it with a video image recognition algorithm to determine whether there are any moving objects that may pose a safety risk to the vehicle.

[0003] However, image acquisition is limited by factors such as video blind spots, visible distance, and scene lighting in which the vehicle is located. On the other hand, collecting image data of passers-by may also involve legal risks such as infringement of portraits and privacy. Summary of the invention

[0004] In order to overcome the problems existing in the related art, the present application provides a method, device, equipment and computer-readable storage medium for determining risks around a vehicle, which can solve the above problems.

[0005] According to a first aspect of an embodiment of the present application, a method for determining risk around a vehicle is provided, the method comprising:

[0006] Determine wireless channel state information CSI of wireless signal waves transmitted to the periphery of the vehicle, wherein the wireless channel state information includes amplitude and phase;

[0007] Determine the behavior of the active objects around the vehicle according to the amplitude and phase of the wireless channel state information;

[0008] Determine whether the active object poses a safety risk to the vehicle according to the behavioral action.

[0009] According to a second aspect of an embodiment of the present application, a risk determination device around a vehicle is provided, the device comprising:

[0010] A CSI determination unit, configured to determine the wireless channel state information CSI of the wireless signal wave transmitted to the periphery of the vehicle, wherein the wireless channel state information includes amplitude and phase;

[0011] an action determination unit, configured to determine a behavior action of an active object around the vehicle according to the amplitude and phase of the wireless channel state information;

[0012] A risk determination unit is used to determine whether the active object poses a safety risk to the vehicle based on the behavioral action.

[0013] According to a third aspect of an embodiment of the present application, there is provided an electronic device, including: a processor and a memory;

[0014] The memory is used to store computer programs;

[0015] The processor is used to execute the risk determination method around the vehicle as described in the first aspect by calling the computer program.

[0016] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method for determining risks around a vehicle as described in the first aspect is implemented.

[0017] The technical solution provided by the embodiments of the present application may have the following beneficial effects:

[0018] This application determines the wireless channel status information around the vehicle, and then determines the behavior of the active objects around the vehicle, and determines whether the active objects pose a safety risk to the vehicle based on the behavior. Since this application uses the wireless channel status information to determine the behavior of the active objects, there is no need to consider the light intensity of the scene, and there is no blind spot when using the wireless channel status information, and it can accurately reflect any active object around the vehicle. On the other hand, the behavior of the active objects is generated based on the wireless channel status information, and there is no infringement on the privacy of the active objects such as their portraits. In the absence of legal issues, it is possible to accurately determine whether the active objects around the vehicle pose a safety risk to the vehicle.

[0019] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings, which are incorporated in the specification and constitute a part of this application, illustrate embodiments consistent with the application and, together with the description, serve to explain the principles of the application.

[0021] Figure 1 It is a flowchart of a method for determining risk around a vehicle according to an exemplary embodiment of the present application.

[0022] Figure 2 It is a schematic diagram showing a method of determining CSI around a vehicle according to an exemplary embodiment of the present application.

[0023] Figure 3 It is a schematic diagram showing a method of determining CSI around a vehicle according to an exemplary embodiment of the present application.

[0024] Figure 4 It is a comparison diagram of CSI before and after denoising according to an exemplary embodiment of the present application.

[0025] Figure 5 It is a comparison diagram of CSI before and after denoising according to an exemplary embodiment of the present application.

[0026] Figure 6 It is a flowchart of a method for determining risk around a vehicle according to an exemplary embodiment of the present application.

[0027] Figure 7 It is a schematic structural diagram of an electronic device in which a risk determination device around a vehicle is located according to an exemplary embodiment of the present application.

[0028] Figure 8 It is a block diagram of a risk determination device around a vehicle according to an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0029] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0030] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0031] It should be understood that although the terms first, second, third, etc. may be used in the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0032] In the related art, some vehicles are equipped with a sentinel mode based on a video image recognition algorithm, which can be used to determine whether there are active objects around the vehicle that pose a safety risk to the vehicle. After turning on the sentinel mode, multiple pre-set image acquisition devices inside and outside the vehicle can be started to record the environment around the vehicle, and the acquired images are recognized by visual algorithms to identify active objects around the vehicle, such as people. In general, image acquisition devices will collect image data from the front, both sides of the body, and the rear of the vehicle respectively. However, due to cost factors, the limited number of image acquisition devices will inevitably cause video blind spots around the vehicle that cannot be collected, and the image acquisition devices have many limitations, such as: the camera's visible distance, installation location, field of view angle limitation, video quality, scene light, obstacle occlusion, etc. In addition, during the collection process, ordinary pedestrians passing by the vehicle will also be collected, which may involve legal risks such as privacy.

[0033] To solve the above problems, the present application proposes a method for determining risks around a vehicle. Figure 1 is a flow chart of a method for determining risk around a vehicle according to an embodiment of the present application, the method comprising:

[0034] In step S101, the wireless channel state information CSI of the wireless signal wave transmitted to the surrounding of the vehicle is determined, and the wireless channel state information includes amplitude and phase;

[0035] In step S102, the behavior of the active objects around the vehicle is determined according to the amplitude and phase of the wireless channel state information;

[0036] In step S103, it is determined whether the active object poses a safety risk to the vehicle according to the behavioral action.

[0037] In one embodiment, the risk determination method around a vehicle proposed in the present application can be executed by the site where the vehicle is located. The risk determination method around a vehicle proposed in the present application is executed by the site where the vehicle is located, so that any vehicle parked on the site can determine whether the active objects around the vehicle pose a safety risk to the vehicle through the risk determination method around the vehicle, and can provide certain protection for any vehicle parked on the site, so that the owner of the vehicle is more inclined to park on the site, which is safer. For example, this method is used in the parking lot of a shopping mall, so that consumers can park their vehicles here with more confidence, thereby protecting the safety of the vehicle and attracting consumers to a certain extent.

[0038] In one embodiment, the risk determination method around a vehicle proposed in the present application can be executed by a vehicle, so that the vehicle can determine whether active objects around the vehicle pose a safety risk to the vehicle through the risk determination method around the vehicle proposed in the present application at any venue, thereby providing certain protection for the vehicle.

[0039] In one embodiment, the wireless channel state information (CSI) can be determined based on the transmitted wireless signal wave and the received wireless signal wave. When there are active objects around the vehicle covered by the wireless signal wave, the channel of the received wireless signal wave will be affected by the active object, causing the amplitude and phase of the wireless signal wave to change. Therefore, the amplitude and phase of the wireless channel state information determined based on the transmitted wireless signal wave and the received wireless signal wave can reflect the behavior performed by the active object.

[0040] Since there is no blind spot within the coverage range of the wireless signal wave, the coverage range of the wireless signal wave is also the sensing range of the risk determination method around the vehicle proposed in this application, and it can avoid the interference of obstacles on the visual image and sense the movements of active objects behind the obstacles.

[0041] In one embodiment, the behavior of the active objects around the vehicle is determined based on the amplitude and phase of the wireless channel state information. The wireless channel state information can be converted into an image or a model through an algorithm, and then the active objects around the vehicle and the behavior of each active object are determined based on the generated image or model.

[0042] In one embodiment, whether the active object poses a safety risk to the vehicle is determined based on the behavioral action.

[0043] Based on the determined behavior of the active object, it is judged whether the active object will pose a safety risk to the vehicle. A partial behavior blacklist may be preset. When the behavior of the active object matches the preset blacklist, it can be determined that the behavior of the active object may pose a safety risk to the vehicle.

[0044] In one embodiment, the moving object may include a non-stationary object, such as a person, a moving object, an animal, etc.

[0045] The technical solution proposed in the present application can generate the behavior actions of active objects within a certain range around the vehicle without any dead angle or blind spot by determining the wireless channel status information around the vehicle. It can also judge whether the active objects around the vehicle pose a safety risk to the vehicle without infringing the privacy of passers-by around the vehicle.

[0046] In one embodiment, the wireless channel state information CSI describes the channel through which the wireless signal passes from the signal's transmitting module to the receiving module, that is, CSI represents the propagation characteristics of the communication link and can describe the combined impact of multiple effects such as scattering, fading, power attenuation, etc. occurring in the channel.

[0047] Therefore, when an active object passes through the coverage of a wireless signal wave, the behavior of the active object can affect the propagation of the wireless signal wave, and the wireless signal wave will be scattered and attenuated due to the active object, and these phenomena will be recorded by CSI. Therefore, by analyzing, processing, and modeling CSI, the behavior of the active object can be restored and simulated.

[0048] In one embodiment, the CSI includes a channel frequency response.

[0049] Response, CFR) and Channel Impulse Response (Channel Impulse Response, CIR).

[0050] Among them, CFR is the response of the signal characteristics of the wireless signal in different frequency ranges. Generally, it includes two responses: amplitude and frequency, and phase and frequency. It is the representation of CSI in the frequency domain.

[0051] CIR is the signal energy value of a wireless signal arriving at the receiving module after passing through different propagation paths and taking different time periods. It is the representation of CSI in the time domain.

[0052] Since the amplitude and phase information on each subcarrier can be regarded as a set of sampled data of the CFR spectrum, the CSI is actually discrete sampling of the CFR on different subcarriers, that is, the CSI used in this application to determine the behavior of active objects around the vehicle includes amplitude and phase.

[0053] In one embodiment, three-dimensional (3D) image modeling of active objects is performed based on the CSI around the vehicle; based on the determined 3D image, the behavior of the active object is identified through a 3D posture algorithm to determine whether the behavior is a dangerous action, that is, to determine whether the active object poses a safety risk to the vehicle.

[0054] In one embodiment, it is possible to determine whether the active object poses a safety risk to the vehicle based on the 3D image of the determined active object, including: identifying the active object based on the 3D image and marking the key points of the activity on the active object; tracking the identified active object and the marked key points of the activity; determining the distance between the active object and the vehicle and determining the behavior of the active object. For example, if the active object is a human body, the key points of the activity can be the skeleton points of the human body. The active object can be marked and determined through the key points of the activity, and the identified active object can be continuously tracked, which can also prevent the loss of the key points of the activity from causing false alarms.

[0055] In one embodiment, it may also include: when the active object is a human body, facial recognition is used to determine the facial orientation of the active object, and when it is determined that the time length for which the active object stares at the vehicle is greater than a first time length, it is determined that the active object poses a safety risk to the vehicle.

[0056] In one embodiment, the behaviors judged as dangerous actions include at least one of the following: peeking, throwing, kicking, stomping, raising hands, smashing, splashing, and approaching.

[0057] In one embodiment, multiple behaviors that are determined to be dangerous can be pre-set with a danger level. A behavior with a higher danger level means that the vehicle has a greater safety risk. By setting the danger level to determine the identified behavior, the degree of danger of the active object to the vehicle can be more accurately determined to avoid misjudgment and false alarm. For example, the danger level of peeping and approaching can be set to be lower, while the danger level of throwing, smashing, and splashing can be set to be higher.

[0058] In one embodiment, a danger level threshold is preset, and if the cumulative value of the danger level exceeds the threshold within a preset time, it is determined that there is a safety risk to the vehicle. For example, the preset time is set to 10 seconds, the danger level threshold is 10, and the cumulative danger level value of peeping and approaching per second is 2, which means that when there is an active object around the vehicle, and the active object continues to approach and peek at the vehicle, the cumulative approach and peeping time within 10 seconds is as long as 2.5 seconds, then it is determined that there is a safety risk to the vehicle. If the active object only peeks at the vehicle but does not approach, it takes a cumulative time of 4 seconds to determine that there is a safety risk to the vehicle. On the other hand, the danger level of throwing, smashing, and splashing can be set to 20, which means that as long as the active object's behavior actions include throwing, smashing, splashing, etc., it can be immediately determined that there is a safety risk to the vehicle.

[0059] In one embodiment, the vehicle can enable different response modes according to different safety risks of the vehicle. For example, in the case of low safety risk, the vehicle can enable low-risk mode to continuously track and monitor active objects. In the case of medium safety risk, the vehicle can enable medium-risk mode, turn on the in-car camera to record the surroundings, and turn on the lights to remind the active objects. In the case of high safety risk, such as someone kicking the car, the vehicle can enable high-risk mode, that is, alert mode. In addition to turning on the in-car camera to record the surroundings, the vehicle can also control the audio system to sound an alarm, flash the lights, send an alarm notification to the owner, etc., to deter and warn the active objects.

[0060] In one embodiment, a plurality of antennas may be provided on the wireless signal wave receiving module. The plurality of antennas may respectively receive wireless signal waves around the vehicle, and the wireless signal waves received by the receiving module are processed to obtain CSI based on the differences of the wireless signal waves received by the plurality of antennas.

[0061] Figure 2 is a schematic diagram of determining CSI around a vehicle according to an exemplary embodiment of the present application.

[0062] like Figure 2 As shown, the vehicle 230 may be provided with a transmitting module 210 and a receiving module 220 for the wireless signal wave, wherein the transmitting module 210 is used to transmit the wireless signal wave to the surrounding of the vehicle 230 , and the receiving module 220 is used to receive the wireless signal wave.

[0063] When the method proposed in this application is applied to a vehicle, the telematics and connection antenna module (TCAM WiFi) on the vehicle and the vehicle's cockpit host can be used, which means that when the method proposed in this application is used on a vehicle, it is only necessary to add a wireless antenna and add the algorithm processing logic applicable to the method of this application. Thus, the method proposed in this application can be implemented on a vehicle at a lower hardware cost.

[0064] When the method of the present application is applied to a vehicle, the vehicle may be provided with a transmitting module and a receiving module for wireless signal waves, wherein the coverage range of the wireless signal waves is the sensing range of the moving objects around the vehicle.

[0065] Figure 3 is a schematic diagram of determining CSI around a vehicle according to an exemplary embodiment of the present application.

[0066] like Figure 3As shown, a scene signal transmitting module 310 and a scene signal receiving module 320 of the wireless signal wave may be provided in the scene 330. When the vehicle 340 is parked in the scene 330, the scene signal transmitting module 310 is used to transmit wireless signal waves around the vehicle 340, and the scene signal receiving module 320 is used to receive wireless signal waves.

[0067] In one embodiment, the scene 330 is a place where the vehicle 340 can be parked, so that the vehicle 340 stays in the scene 330. For example, the scene 330 can be a parking space or a car exhibition stand. Thus, when any vehicle is parked in the scene using the risk determination method around the vehicle proposed in the present application, the safety of the parked vehicle can be guaranteed to a certain extent.

[0068] In one embodiment, when it is determined that the active object poses a safety risk to the vehicle, the method further includes: controlling the vehicle to switch to a predefined alert mode.

[0069] When it is determined that the behavior of the active object will pose a safety risk to the vehicle, the vehicle can be controlled to switch to a predefined warning mode to prevent possible safety risks, or leave evidence to facilitate accountability after a safety risk occurs.

[0070] In one embodiment, the method proposed in this application is executed by a vehicle, and the vehicle can switch to the alert mode by itself. In another embodiment, the method proposed in this application is executed by the site where the vehicle is located, and the site can send a control instruction to the vehicle in the site through a network connection to instruct the vehicle to switch to the alert mode; in the case that some vehicles do not have the alert function, the site can also perform the corresponding alert action to protect the vehicle that has no network connection or no alert function.

[0071] In one embodiment, in the predefined alert mode, the vehicle performs actions including at least one of the following: starting a camera disposed on the vehicle to record the moving object; issuing a warning to the moving object; and notifying the owner of the vehicle.

[0072] The vehicle's predefined warning modes can ensure the vehicle's safety to a certain extent, issue warnings on the behavior of active objects, or record them to facilitate accountability when safety risks occur later.

[0073] In one embodiment, the step of activating a camera disposed on the vehicle to record the moving object includes: determining a target position of the moving object and only activating an image acquisition device for capturing images at the target position.

[0074] Since a vehicle may be equipped with image acquisition devices facing multiple angles and directions, activating all of them will, on the one hand, waste resources, and on the other hand, the remaining image acquisition devices that are not facing the target direction may involve legal issues of infringing the privacy of passers-by around the vehicle. Therefore, only activating the image acquisition device used to collect images at the target direction can realize the collection of image information of the moving object, avoid waste of resources, and avoid unnecessary image collection.

[0075] In one embodiment, issuing a warning to the moving object includes: controlling a vehicle to emit a sound and / or controlling a vehicle light to stay on or flash.

[0076] When a parked vehicle makes unusual noises and lights, it is easy to attract the attention of passers-by. At the same time, the lights and sounds will increase the psychological burden of the active subjects, causing them to spontaneously give up continuing to perform actions that pose a safety risk to the vehicle.

[0077] In one embodiment, notifying the owner of the vehicle includes: sending a notification to the owner of the vehicle through a network, or displaying a notification message in the vehicle after the vehicle is started.

[0078] By sending notifications to the portable terminal carried by the car owner through the network, the car owner can be informed of the vehicle status in time, so that the car owner can decide whether to return to the vehicle immediately to eliminate the safety risk; or, after the vehicle is started, the notification information can be displayed in the vehicle to inform the people in the vehicle that there are objects that may have previously posed a safety risk to the vehicle nearby, so that the driver or the car owner can pay attention to the vehicle status and check whether there is a safety risk during the period when the driver is away from the vehicle. Sending notifications to the car owner through the network can enhance real-time performance and help the car owner to keep track of the vehicle status at any time; and after starting the vehicle, by displaying the notification information in the car, it can avoid misjudgment and mis-triggering that cause excessive disturbance to the car owner.

[0079] In one embodiment, the behavioral action for determining that the active object poses a safety risk to the vehicle includes at least one of the following: moving within a first distance around the vehicle; raising the hand at a speed greater than a first speed; swinging beyond a first angle; or moving at a speed greater than a second speed.

[0080] In one embodiment, the distance between the active object and the vehicle can be determined based on the wireless channel state information. When the distance is less than a first distance, it is determined that the active object is too close to the vehicle and there is a safety risk to the vehicle. For example, the first distance can be 0.5 meters. Generally, the active object will not approach the vehicle within 0.5 meters. Therefore, when it is found that the active object is too close to the vehicle, that is, less than 0.5 meters, it can be determined that the behavior of the active object may cause a safety risk to the vehicle.

[0081] In one embodiment, the arm movements of the active object can be identified through the wireless channel status information. When it is found that the speed of the active object raising hands or waving arms is greater than the first speed, it can be determined that the vehicle may be at risk of safety. Since the coverage of the wireless signal wave is limited, it will not exceed the distance around the vehicle too far. Generally, the active object will not raise its hands or wave its arms quickly when it is close to the vehicle. Therefore, when the active object generated according to the wireless channel status information is identified as raising its hands or waving its arms at a faster speed, it means that the active object may try to lift or throw an object, and it can be determined that the behavior of the active object may cause a safety risk to the vehicle.

[0082] In one embodiment, the body posture of the moving object can be identified through the wireless channel state information, and when it is found that the moving object's body swings more than a first angle, it can be determined that the vehicle may have a safety risk. When the moving object's body swings more than the first angle, it means that the moving object loses balance, whether due to drinking or slipping and tripping, and may hit the vehicle, posing a safety risk to the vehicle.

[0083] In one embodiment, when the moving speed of the moving object is greater than the second speed, it means that the moving object is in high-speed motion, and at this time it can be determined that there is a safety risk to the vehicle.

[0084] In one embodiment, it further includes: preprocessing the wireless channel state information according to the amplitude and phase; wherein the preprocessing includes denoising the wireless channel state information; and performing phase correction on the preprocessed wireless channel state information.

[0085] In one embodiment, not all of the wireless channel state information is needed to determine the behavior of the active object, so part of the wireless channel state information that cannot be used to determine the behavior of the active object can be removed. Because the wireless channel state information can represent objects around the vehicle, when there are no active objects, the wireless channel state information for a period of time is repeated. Even if an active object appears, the wireless channel state information can still represent the static background and static objects around the vehicle. Therefore, by removing noise from the wireless channel state information, only part of the wireless channel state information corresponding to the active object can be analyzed and processed, which helps to reduce the processing volume and speed up the response speed.

[0086] In addition, since the phase of the wireless channel state information will fluctuate after the denoising process, and the phase of the wireless channel state information is related to the behavior of the generated active object, the phase correction algorithm is required to correct the fluctuating phase of the data after the denoising process to ensure that the image of the active object can be correctly generated, and then the behavior can be determined.

[0087] In one embodiment, the wireless channel state information includes amplitude and phase, and the preprocessing includes at least one of the following: removing noise from the amplitude of CSI; removing noise from the phase of CSI.

[0088] In one embodiment, the noise of the amplitude of the CSI may include at least one of the following: uncertainty error caused by power control of Automatic Generation Control (AGC); fluctuation caused by electromagnetic noise around the vehicle.

[0089] In one embodiment, the amplitude noise can be eliminated based on the amplitude ratio of multiple antennas on the receiving module, and the corresponding wireless signal wave used to determine the behavior of the moving object is retained. Regardless of the type of amplitude noise, since the noise is consistent in all antennas on the same receiving module, the amplitude noise can be eliminated by using the amplitude ratio between multiple antennas on the same receiving module. And since the physical space spacing between multiple antennas on the same receiving module is determined, the amplitude fluctuations related to the behavior of the moving object will be different on multiple antennas. Therefore, according to the amplitude ratio, only the amplitude noise can be removed, while the corresponding part of the signal required to determine the behavior of the moving object is retained.

[0090] In one embodiment, the phase noise of the CSI is caused by at least one of the following factors: carrier frequency offset; packet detection delay; sampling frequency offset; sampling clock offset.

[0091] In one embodiment, phase noise can be eliminated based on the phase difference of multiple antennas on the receiving module. Since the same RF oscillator is used, the phase noise is the same on multiple antennas of the receiving module for a specific subcarrier. Therefore, the phase noise of CSI can be eliminated based on the phase difference between multiple antennas on the receiving module.

[0092] In one embodiment, if the phase of the CSI after noise removal fluctuates, the fluctuated phase is corrected using a phase correction algorithm.

[0093] In one embodiment, the CSI noise can be eliminated based on the CSI measurement values ​​of multiple antennas on the receiving module through a CSI quotient model to determine a reference signal that can be used to determine the behavior of the moving object, wherein the CSI noise includes amplitude noise and random phase offset.

[0094] Since the CSI amplitude has noise and the phase has random offset, the phase and amplitude of the CSI are no longer orthogonal and complementary, making them difficult to distinguish. However, since multiple antennas on the same receiving module share a set of crystal oscillator clocks and RF processing circuits, the amplitude noise between the CSI measurement values ​​determined by multiple antennas on the same receiving module is proportional and the phase offset is the same.

[0095] Therefore, the amplitude noise and the random phase offset can be eliminated according to the multiple CSI measurement values ​​of the multiple antennas determined on the receiving module.

[0096]

[0097] The above formula is a CSI quotient model in one embodiment, where CSI 基准 CSI is a reference signal after noise removal that can be used to determine the behavior of the active object. 测量值1 and CSI 测量值2 The CSI measurements are determined for two different antennas on the same receive module, δ(t) is the amplitude noise, is the phase deviation, CSI 理想值1 and CSI 理想值2 It is the ideal CSI value under noise-free conditions for two different antennas of the same receiving module.

[0098] Figure 4 and Figure 5 3 is a schematic diagram showing the comparison of CSI before and after denoising according to an exemplary embodiment of the present application.

[0099] like Figure 4 As shown, Figure 4 It is an image comparison before and after the amplitude denoising process of the measurement values ​​of the two antennas on the same receiving module. Corresponding to the signal waveform caused by the moving object, the quotient of the CSI amplitudes of the two antennas determined by the CSI quotient model is clearer than the amplitude of the original CSI measurement values ​​of the two antennas.

[0100] like Figure 5 As shown, Figure 5 This is an image comparison of the measurement values ​​of two antennas on the same receiving module before and after phase denoising. It can be seen that it is difficult to distinguish the signal waveform changes corresponding to the active object from the original CSI measurement values ​​of the two antennas. Only the phase difference between the original CSI measurement values ​​of the two antennas (that is, the phase of the CSI reference signal obtained after CSI quotient model processing) can clearly show the signal waveform changes caused by the active object.

[0101] It can be seen that after denoising the CSI, the signal waveform caused by the behavior of the active object is clearer, so that determining the behavior of the active object based on the denoised CSI can more accurately reflect the actual behavior of the active object.

[0102] Figure 6 FIG. 1 is a flow chart of a method for determining risk around a vehicle according to an exemplary embodiment of the present application. Figure 6 As shown, the method includes:

[0103] In step S601, the vehicle may transmit a wireless signal wave through a transmitting module and receive the wireless signal wave through a receiving module;

[0104] In step S602, the original CSI around the vehicle is determined;

[0105] In step S603, data cleaning is performed on the original CSI to remove CSI corresponding to other environments and backgrounds of inactive objects;

[0106] In step S604, the CSI quotient model is used to perform noise elimination to obtain a CSI reference signal corresponding to the active object;

[0107] In step S605, the behavior of the moving object is determined according to the reference signal of the CSI, and it is determined whether there is any dangerous action, so as to determine whether the moving object poses a safety risk to the vehicle.

[0108] This embodiment determines the CSI around the vehicle, and after cleaning and removing impurities, can accurately generate a 3D image of the active object, and then determine the behavior of the active object to determine whether the vehicle poses a safety risk. Compared with the sentinel mode of the in-vehicle image acquisition device in the prior art, this embodiment consumes fewer resources and covers the area around the vehicle without dead angles or blind spots. Determining the behavior through CSI also avoids infringing on the privacy of passers-by.

[0109] In one embodiment, the method further includes: determining wireless channel status information of wireless signal waves transmitted to the interior of the vehicle; and monitoring the vital signs of people inside the vehicle based on the wireless channel status information of the wireless signal waves inside the vehicle.

[0110] In addition to determining whether there are active objects around the vehicle and posing a safety risk to the vehicle based on the CSI around the vehicle, the CSI inside the vehicle can also be used to monitor the vital signs of people stranded inside the vehicle. This allows the method to determine the safety risks around the vehicle on the one hand, and to simultaneously ensure the safety of people stranded inside the vehicle and avoid accidents on the other hand.

[0111] Corresponding to the method embodiment of the present application, the present application also provides a corresponding risk determination device embodiment around the vehicle.

[0112] Figure 7 is a schematic structural diagram of a device provided by an exemplary embodiment. Figure 7 At the hardware level, the device includes a processor 710, a network interface 720, a memory 730, and a non-volatile memory 740, and may also include hardware required for other services. One or more embodiments of the present application can be implemented based on software, such as the processor 710 reading the corresponding computer program from the non-volatile memory 740 into the memory 730 and then running it. Of course, in addition to the software implementation, one or more embodiments of the present application do not exclude other implementations, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0113] See also Figure 8 , Figure 8 : is a block diagram of a risk determination device for a vehicle surrounding an embodiment of the present application. The risk determination device for a vehicle surrounding can be applied to Figure 7 In the electronic device shown, the technical solution of the present application is implemented. The device includes:

[0114] A CSI determination unit 810, configured to determine the wireless channel state information CSI of the wireless signal wave transmitted to the periphery of the vehicle, wherein the wireless channel state information includes amplitude and phase;

[0115] An action determination unit 820 is used to determine the behavior of the active objects around the vehicle according to the amplitude and phase of the wireless channel state information;

[0116] The risk determination unit 830 is used to determine whether the active object poses a safety risk to the vehicle according to the behavior action.

[0117] Optionally, the vehicle is provided with a transmitting module and a receiving module for the wireless signal wave, the transmitting module is used to transmit the wireless signal wave to the surrounding of the vehicle, and the receiving module is used to receive the wireless signal wave.

[0118] Optionally, when it is determined that the active object poses a safety risk to the vehicle, the device further includes: a control unit, configured to control the vehicle to switch to a predefined alert mode.

[0119] Optionally, the control unit is used to control the vehicle to perform actions including at least one of the following in the predefined alert mode: starting a camera installed on the vehicle to record the active object; issuing a warning to the active object; and notifying the owner of the vehicle.

[0120] Optionally, controlling the vehicle to switch to a predefined alert mode includes:

[0121] A command is issued to the vehicle to switch to the predefined alert mode.

[0122] Optionally, the behavioral action for determining that the active object poses a safety risk to the vehicle includes at least one of the following: moving within a first distance around the vehicle; raising the hand at a speed greater than a first speed; swinging beyond a first angle; or moving at a speed greater than a second speed.

[0123] Optionally, the action determination unit is also used to: pre-process the wireless channel state information according to the amplitude and phase; wherein the pre-processing includes denoising the wireless channel state information; and performing phase correction on the pre-processed wireless channel state information.

[0124] Optionally, the CSI determination unit is also used to determine wireless channel status information of wireless signal waves transmitted to the interior of the vehicle; the action determination unit is also used to monitor the vital signs of people inside the vehicle based on the wireless channel status information of the wireless signal waves inside the vehicle.

[0125] The implementation process of the functions and effects of each unit in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, and will not be repeated here.

[0126] For the device embodiments, since they basically correspond to the method embodiments, it is sufficient to refer to the partial description of the method embodiments for the relevant points. The device embodiments described above are only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present application scheme. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0127] Those skilled in the art will appreciate that one or more embodiments of the present application may be provided as a method, system or computer program product. Therefore, one or more embodiments of the present application may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, one or more embodiments of the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0128] One or more embodiments of the present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. One or more embodiments of the present application may also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0129] The above is only an example of one or more embodiments of the present application, and is not intended to limit one or more embodiments of the present application. For those skilled in the art, one or more embodiments of the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims.

Claims

1. A method for determining risk around a vehicle, characterized in that: The method comprises: Determine wireless channel state information CSI of wireless signal waves transmitted to the periphery of the vehicle, wherein the wireless channel state information includes amplitude and phase; Determine the behavior of the active objects around the vehicle according to the amplitude and phase of the wireless channel state information; Determine whether the active object poses a safety risk to the vehicle according to the behavioral action.

2. The method according to claim 1, characterized in that The vehicle is provided with a transmitting module and a receiving module for the wireless signal wave, wherein the transmitting module is used for transmitting the wireless signal wave to the surrounding of the vehicle, and the receiving module is used for receiving the wireless signal wave.

3. The method according to claim 1, characterized in that In the case where it is determined that the active object poses a safety risk to the vehicle, the method further includes: The vehicle is controlled to switch to a predefined alert mode.

4. The method according to claim 3, characterized in that In the predefined alert mode, the vehicle performs at least one of the following actions: Starting a camera disposed on the vehicle to record the moving object; issuing a warning to the active object; Notify the owner of said vehicle.

5. The method according to claim 3, characterized in that: The controlling the vehicle to switch to a predefined alert mode comprises: A command is issued to the vehicle to switch to the predefined alert mode.

6. The method according to claim 1, characterized in that The behavior action of determining that the active object poses a safety risk to the vehicle includes at least one of the following: moving to within a first distance around the vehicle; A hand-raising action that is greater than the first speed; Swinging beyond the first angle; Movement greater than the second speed.

7. The method according to claim 1, characterized in that Also includes: Preprocessing the wireless channel state information according to the amplitude and phase; wherein the preprocessing includes removing noise from the wireless channel state information; Perform phase correction on the preprocessed wireless channel state information.

8. The method according to claim 1, characterized in that Also includes: determining wireless channel state information of wireless signal waves transmitted to the interior of the vehicle; The vital signs of the people inside the vehicle are monitored according to the wireless channel status information of the wireless signal waves inside the vehicle.

9. A risk determination device around a vehicle, characterized in that: The device comprises: A CSI determination unit, configured to determine the wireless channel state information CSI of the wireless signal wave transmitted to the periphery of the vehicle, wherein the wireless channel state information includes amplitude and phase; an action determination unit, configured to determine a behavior action of an active object around the vehicle according to the amplitude and phase of the wireless channel state information; A risk determination unit is used to determine whether the active object poses a safety risk to the vehicle based on the behavioral action.

10. An electronic device, characterized in that: include: Processor, memory; The memory is used to store computer programs; The processor is used to execute the risk determination method around the vehicle according to any one of claims 1 to 8 by calling the computer program.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the risk determination method around a vehicle described in any one of claims 1 to 8 is implemented.

Images