A vehicle danger warning light control method, device and automobile

Abstract

The application relates to the technical field of automobiles and provides a vehicle danger warning light control method, a vehicle danger warning light control device and an automobile. The method comprises the following steps: when a vehicle is parked, whether the vehicle is in a preset danger scene range is monitored; if the vehicle is in the danger scene range, whether the vehicle door or the tail door of the vehicle is in an open state is detected; and if the vehicle door or the tail door of the vehicle is in the open state, a danger warning light of the vehicle is turned on. The application does not need manual opening of the danger warning light, realizes the effect that the danger warning light of the vehicle is automatically turned on in the danger scene range, and thus can effectively avoid accidents and improves the safety of vehicle use.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automobiles, and in particular to a vehicle danger warning light control method and device and an automobile. BACKGROUND

[0002] When a vehicle is temporarily parked on a complex road section due to various reasons, some drivers may forget to turn on the vehicle danger warning light due to differences in experience, which poses a great safety hazard and may easily lead to traffic accidents.

[0003] Currently, the danger warning light of a vehicle generally needs to be manually turned on or off by a user. Of course, some vehicles will automatically turn on the danger warning light when a collision accident occurs, but this automatic turning on is after the accident occurs, and the turning-on condition is very limited. However, the existing vehicle does not have the function of intelligently turning on the danger warning light in a complex road or dangerous environment, and needs to be improved. SUMMARY

[0004] Therefore, the embodiments of the present application provide a vehicle danger warning light control method and device and an automobile to solve the problem that the existing vehicle does not have the function of intelligently turning on the danger warning light in a complex road or dangerous environment.

[0005] In a first aspect, the embodiments of the present application provide a vehicle danger warning light control method, which comprises the following steps.

[0006] When the vehicle is parked, it is monitored whether the vehicle is in a preset dangerous scene range.

[0007] If the vehicle is in the dangerous scene range, it is detected whether the vehicle door or tailgate is in an open state.

[0008] If the vehicle door or tailgate is in the open state, the danger warning light of the vehicle is turned on.

[0009] In a second aspect, the embodiments of the present application provide a vehicle danger warning light control device, which comprises the following modules.

[0010] The scene monitoring module is configured to monitor whether the vehicle is in a preset dangerous scene range when the vehicle is parked.

[0011] The door monitoring module is configured to detect whether the vehicle door or tailgate is in an open state if the vehicle is in the dangerous scene range.

[0012] The light control module is configured to turn on the danger warning light of the vehicle if the vehicle door or tailgate is in the open state.

[0013] In a third aspect, the embodiment of the present application provides a car, which comprises a master computer, the master computer comprising a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the above method when executing the computer program.

[0014] The application has the beneficial effects compared with the prior art: the vehicle danger warning light control method monitors whether the vehicle is in a preset dangerous scene range when the vehicle is parked, detects whether the vehicle door or tailgate is in an open state if the vehicle is in the dangerous scene range, and turns on the danger warning light of the vehicle if the vehicle door or tailgate is in the open state, without manually turning on the danger warning light, so as to automatically turn on the danger warning light of the vehicle in the dangerous scene range, effectively avoid accidents and improve the safety of the vehicle. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0016] Figure 1 is a flowchart of a vehicle danger warning light control method provided by the embodiment of the present application;

[0017] Figure 2 is a structural schematic diagram of a vehicle danger warning light control device provided by the embodiment of the present application;

[0018] Figure 3 is a structural schematic diagram of a master computer provided by the embodiment of the present application. DETAILED DESCRIPTION

[0019] In the following description, specific details are set forth in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application can be practiced in other embodiments without these specific details. In other instances, well-known systems, devices, circuits and methods have not been described in detail in order to avoid obscuring the description of the present application.

[0020] Please refer to Figure 1 The embodiment provides a flowchart of a vehicle danger warning light control method, and in actual application, the execution subject of the vehicle danger warning light control method is preferably a control device in a car, and the control device can be a master computer.

[0021] As Figure 1As shown, the vehicle danger warning light control method comprises:

[0022] S101, when the vehicle is parked, whether the vehicle is in a preset dangerous scene range is monitored;

[0023] S102, if the vehicle is in the dangerous scene range, whether the vehicle door or tailgate is in an open state is detected;

[0024] S103, if the vehicle door or tailgate is in an open state, the vehicle danger warning light is turned on.

[0025] The dangerous scene range includes various complex roads and dangerous environments, such as highways, national roads, expressways, and tunnels.

[0026] The embodiment is aimed at monitoring whether the vehicle is in a preset dangerous scene range when the vehicle is parked, detecting whether the vehicle door or tailgate is in an open state if the vehicle is in the dangerous scene range, and turning on the vehicle danger warning light if the vehicle door or tailgate is in an open state, thereby realizing the automatic turning on of the vehicle danger warning light, avoiding the situation that some users forget to turn on the danger warning light, effectively avoiding accidents, and improving the safety of vehicle use.

[0027] In the above step S101, the specific implementation of monitoring whether the vehicle is in a preset dangerous scene range is not unique.

[0028] For example, in an embodiment, monitoring whether the vehicle is in a preset dangerous scene range comprises:

[0029] Obtaining real-time positioning information and a high-precision map of the vehicle;

[0030] Judging whether the position corresponding to the real-time positioning information in the high-precision map is a pre-marked position, wherein the pre-marked position is a position in the high-precision map that is pre-marked as a dangerous parking scene;

[0031] If yes, it is determined that the vehicle is currently in the dangerous scene range;

[0032] If no, it is determined that the vehicle is not currently in the dangerous scene range.

[0033] It can be understood that the vehicle can be connected to the server through a network to obtain more network application services. The network state of the vehicle includes a network online state and a network offline state. When there is a network signal, the vehicle can normally connect to the server, that is, the vehicle is in a network online state; when there is no network signal or the vehicle has a network failure, the vehicle cannot connect to the server, that is, the vehicle is in a network offline state.

[0034] The high-precision map is an electronic map with higher precision and more data dimensions. The higher precision is reflected in centimeter-level accuracy, and the more data dimensions are reflected in the inclusion of surrounding static information related to traffic in addition to road information. In combination with the present embodiment, the high-precision map includes positions pre-marked as dangerous parking scenes, and the number of the positions pre-marked as dangerous parking scenes is multiple. When the vehicle is parked, the position of the vehicle in the high-precision map can be determined according to real-time positioning information of the vehicle, and whether the current position of the vehicle is a dangerous parking scene is determined by using the positions pre-marked as dangerous parking scenes in the high-precision map. If yes, it is determined that the vehicle is in a dangerous scene range, and if no, it is determined that the vehicle is not in the dangerous scene range.

[0035] The high-precision map can be arranged in the vehicle, for example, the high-precision map is pre-installed in the host computer of the vehicle. Alternatively, the high-precision map can also be arranged in the server, and the high-precision map is used by the vehicle through network connection with the server. For example, the vehicle sends the collected real-time positioning information to the server, and the server determines whether the vehicle is currently in a dangerous scene range according to the real-time positioning information and the positions pre-marked as dangerous parking scenes.

[0036] For example, in an embodiment, monitoring whether the vehicle is in a preset dangerous scene range includes:

[0037] Obtaining an image of the surroundings of the vehicle;

[0038] Determining whether the image of the surroundings is the same as the environment of any image in a preset dangerous scene library based on the dangerous scene library, wherein the dangerous scene library includes multiple images marked as dangerous parking environments;

[0039] If yes, it is determined that the vehicle is currently in a dangerous scene range;

[0040] If no, it is determined that the vehicle is not currently in a dangerous scene range.

[0041] The dangerous scene library is a collection of images marked as dangerous parking environments. Specifically, the similarity between the image of the surroundings and each image in the dangerous scene library can be identified, and when the similarity meets a preset requirement, it can be determined whether the image of the surroundings is the same as the environment of the image in the dangerous scene library; or the scene features of each image in the dangerous scene library can be pre-extracted, and then the scene features of the image of the surroundings are extracted, and whether the scene features of the image of the surroundings are the same as the scene features of each image in the dangerous scene library is identified to determine whether the image of the surroundings is the same as the environment of the image in the dangerous scene library.

[0042] Preferably, the embodiment extracts the scene features of each image in the dangerous scene library in advance, collects the surrounding image of the vehicle when the vehicle is parked, extracts the scene features of the surrounding image, and then compares the scene features of the surrounding image with the scene features of each image in the dangerous scene library. If the scene features of the surrounding image are the same as the scene features of each image in the dangerous scene library, it is determined that the parking position of the vehicle is a dangerous parking scene, i.e., the vehicle is in the dangerous scene range. If the scene features of the surrounding image are not the same as the scene features of each image in the dangerous scene library, it is determined that the parking position of the vehicle is not a dangerous parking scene, i.e., the vehicle is not in the dangerous scene range.

[0043] Compared with installing the high-precision map in the server, in the embodiment, the dangerous scene library can be installed locally, such as in the host computer of the vehicle, by comparing the surrounding image with the dangerous scene library locally, so as to avoid the case that the relevant server in the server cannot be obtained due to poor network signal.

[0044] In one embodiment, in combination with the above embodiment, monitoring whether the vehicle is in the preset dangerous scene range comprises:

[0045] detecting the network state of the vehicle, the network state comprising a network online state and a network offline state;

[0046] if the vehicle is in the network online state, obtaining the real-time positioning information and the high-precision map of the vehicle;

[0047] determining whether the position corresponding to the real-time positioning information in the high-precision map is a pre-marked position, wherein the pre-marked position is a position in the high-precision map that is pre-marked as a dangerous parking scene;

[0048] if yes, it is determined that the vehicle is currently in the dangerous scene range;

[0049] if no, obtaining the surrounding image of the vehicle and a dangerous scene library, the dangerous scene library comprising a plurality of images marked as dangerous parking environments;

[0050] determining whether the surrounding image is the same as the environment of any image in the dangerous scene library;

[0051] if yes, it is determined that the vehicle is currently in the dangerous scene range;

[0052] if no, it is determined that the vehicle is not currently in the dangerous scene range.

[0053] Specifically, when it is determined by the high-definition map that the vehicle is currently in the dangerous scene range, the surrounding environment of the vehicle can also be confirmed again by acquiring the surrounding image of the vehicle, to determine whether the vehicle is in the dangerous scene range, so as to improve the accuracy of the dangerous scene range monitoring.

[0054] In another embodiment, immediately after the above embodiment, after detecting the network state of the vehicle, the method further comprises:

[0055] If the vehicle is in the network offline state, acquiring the surrounding image of the vehicle;

[0056] Based on the preset dangerous scene library, determining whether the surrounding image is the same as the environment of any image in the dangerous scene library, wherein the dangerous scene library comprises a plurality of images marked as dangerous environments;

[0057] If the same, it is determined that the vehicle is currently in the dangerous scene range;

[0058] If not the same, it is determined that the vehicle is not currently in the dangerous scene range.

[0059] It can be understood that other embodiments can also be used to monitor whether the vehicle is in the preset dangerous scene range in actual application, and are not limited to the above embodiments.

[0060] In the above step S102, the tail door of the vehicle is also called the trunk door. Detecting that the door of the vehicle is in the open state is for the case that the person in the vehicle gets off the vehicle. When the door is in the open state, the danger warning light is turned on, which can provide warning before the person in the vehicle gets off the vehicle, to ensure the safety of the person. Detecting that the tail door of the vehicle is in the open state is for the case that the person outside the vehicle opens the tail door at the back of the vehicle. When the tail door is in the open state, the danger warning light is turned on, which can provide timely warning for the vehicle behind the vehicle, to ensure the safety of the person outside the vehicle.

[0061] It can be understood that the way of detecting whether the door or the tail door is in the open state is not unique. For example, the opening and closing states of the door and the tail door can be acquired by using the existing door and tail door detection system of the vehicle. Of course, other ways can also be used to acquire the opening state of the door and the tail door in actual application, and the present application is not limited thereto.

[0062] In the above step S103, after the warning light is turned on, the warning effect of the danger warning light can also be detected, and the warning effect of the danger warning light can be dynamically adjusted according to the warning effect. Specifically, the danger warning light can be a flashing light, which can have different brightness and frequency. Different brightness and / or frequency of the danger warning light can be selected according to different scenes to obtain the optimal warning scheme. Of course, the danger warning light can also be other types, and is not limited to the above cases.

[0063] With the hazard warning light as an example, when the hazard warning light is turned on, the rear vehicle information is periodically detected, the current danger degree of the vehicle is determined according to the vehicle information detected in the period, each danger degree corresponds to a warning effect (i.e. a warning scheme) of the hazard warning light, and then the corresponding warning scheme is determined according to the current danger degree of the vehicle. The warning scheme includes that the hazard warning light works at a fixed brightness and frequency, or works at a variable brightness and frequency. The vehicle information includes the number of vehicles appearing within a preset distance behind the vehicle, the speed of the vehicle when changing lanes into the preset distance, and the distance between the vehicle and the current vehicle when changing lanes into the preset distance.

[0064] Specifically, assuming that the danger degree is R, the following calculation formula can be used to determine the danger degree of the vehicle:

[0065]

[0066] Wherein, N represents the number of vehicles in the period, vi represents the speed of the vehicle when changing lanes, and di represents the distance between the vehicle and the current vehicle when changing lanes. It can be understood that different danger degrees R correspond to different warning schemes, such as when R is between 0 and 1, the hazard warning light flashes at a frequency of 1 time per second and a brightness of 300 lumens, when R is between 1 and 10, the hazard warning light flashes at a frequency of 2 times per second and a brightness of 500 lumens, and when R is greater than 10, the hazard warning light flashes at a frequency of 3 times per second and a brightness of 1000 lumens. The detection period can be pre-set by the research and development personnel, or the user can modify it in the central control screen, such as 30 seconds, 1 minute, 3 minutes, etc. In addition, the warning scheme of the next period can also be determined by the danger degree detected in the last period. The speed and distance of the rear vehicle can be detected by the radar installed behind the vehicle.

[0067] In one embodiment, after turning on the hazard warning light of the vehicle, further comprising:

[0068] determining whether the current turning on of the hazard warning light meets the user's demand;

[0069] if it meets, extracting the scene features of the current environment of the vehicle, and updating the preset danger scene range using the scene features;

[0070] if it does not meet, adjusting the preset danger scene range.

[0071] Wherein, the specific implementation of determining whether the current turning on of the hazard warning light meets the user's demand is not unique.

[0072] For example, determining whether the current turning on of the hazard warning light meets the user's demand includes:

[0073] counting the number of times the vehicle turns on the hazard warning light in the current environment;

[0074] obtaining the count value of the vehicle turning on the hazard warning light in the current environment;

[0075] based on the count value, determining whether the vehicle is in the current environment for the first time to turn on the hazard warning light;

[0076] if it is the first time to turn on, obtaining a face image of the user;

[0077] recognizing the expression of the user in the face image;

[0078] if the expression of the user is identified as satisfied, it is determined that the current turning on of the hazard warning light meets the user's demand;

[0079] if the expression of the user is identified as unsatisfied, it is determined that the current turning on of the hazard warning light does not meet the user's demand.

[0080] Specifically, when it is determined that the current location of the vehicle is in the range of the dangerous scene, a count value is assigned to the current location of the vehicle, assuming that the initial value of the count value is 0, and the count value is incremented by 1 each time the vehicle is parked in the location and determined to be in the range of the dangerous scene.

[0081] Since the range of the dangerous scene is pre-set, it may have a lag, and when the vehicle is parked in a location and determined to be in the range of the dangerous scene, the hazard warning light will be automatically turned on. At this time, the environment of the parking location may have changed and no longer belongs to the range of the dangerous scene. Therefore, in order to improve the intelligence of automatically turning on the hazard warning light, the embodiment adjusts or updates the range of the dangerous scene by judging whether the first turning on of the hazard warning light when the vehicle is parked in any location belonging to the range of the dangerous scene meets the user's demand, so as to improve the accuracy of monitoring the range of the dangerous scene.

[0082] For example, in addition to using face recognition to determine whether the turning on of the hazard warning light meets the user's demand, determining whether the current turning on of the hazard warning light meets the user's demand can also include:

[0083] detecting whether the user manually turns off the hazard warning light within a preset time;

[0084] if the user manually turns off the hazard warning light within the preset time, it is determined that the current turning on of the hazard warning light does not meet the user's demand;

[0085] if the user does not manually turn off the hazard warning light within the preset time, it is determined that the current turning on of the hazard warning light meets the user's demand.

[0086] In addition, the user can also exist misoperation, such as when the automatic opening of the danger warning light is manually closed by the user, in order to avoid this situation. The above embodiment can be further optimized.

[0087] In the above embodiment, in an embodiment, detecting whether the user manually closes the danger warning light within a preset time includes:

[0088] Detecting whether the danger warning light is manually closed within a first preset time:

[0089] If yes, a closing prompt option is issued, and the closing prompt option includes a confirmation request for whether the closing of the danger warning light within the first preset time is a misoperation;

[0090] Obtaining feedback on the confirmation request;

[0091] If the feedback is a misoperation, the danger warning light is automatically restarted;

[0092] If the feedback is not a misoperation, the danger warning light is kept closed.

[0093] In addition, if the danger warning light is not manually closed within the first preset time, it is detected whether the danger warning light is manually closed within a second preset time, if yes, the manual closing operation is ignored, and if no, the danger warning light is kept on. In the embodiment, the duration of the first preset time is less than the duration of the second preset time.

[0094] In an embodiment, the above extracting the scene features of the environment where the vehicle currently locates, and updating the preset danger scene range by using the scene features includes:

[0095] Obtaining the surrounding image of the vehicle;

[0096] Extracting the scene features in the surrounding image;

[0097] Adding the extracted scene features of the surrounding image to the danger scene library, and updating the danger scene library.

[0098] It can be understood that if the high-precision map and real-time positioning information are used to detect that the vehicle is in the danger scene range in actual use, there is no problem of updating the preset danger scene range by using the scene features.

[0099] However, in addition to updating the danger scene library, the above updating the preset danger scene range by using the scene features can also be used to update the machine learning model.

[0100] For example, the above extracting the scene features of the environment where the vehicle currently locates, and updating the preset danger scene range by using the scene features further includes:

[0101] Obtaining the surrounding image of the vehicle;

[0102] extracting a scene feature in the surrounding image;

[0103] updating and training the preset machine learning model by using the scene feature as a sample to obtain a new machine learning model, wherein when monitoring whether the vehicle is in the preset dangerous scene range, the surrounding image of the vehicle is input into the machine learning model, and a corresponding monitoring result is obtained at the output of the machine learning model, and the monitoring result includes that the vehicle is currently in the dangerous scene range or the vehicle is not currently in the dangerous scene range.

[0104] Specifically, the trained machine learning model is similar to the high-definition map, which can be arranged on the host computer of the vehicle, or can also be arranged on the server, and the embodiments of the present application do not limit this.

[0105] In one embodiment, the above adjusting the preset dangerous scene range comprises: excluding the position corresponding to the current environment of the vehicle in the high-definition map from the preset dangerous scene range; or deleting the image in the dangerous scene library which is the same as the environment of the surrounding image of the current position of the vehicle.

[0106] It should be understood that the size of the serial number of each step in the above embodiments does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0107] The following is an apparatus embodiment of the present application, which can be used to execute the method embodiments of the present application. For details not disclosed in the apparatus embodiments of the present application, please refer to the method embodiments of the present application.

[0108] Figure 2 is a schematic diagram of a vehicle danger warning light control device provided by an embodiment of the present application. As shown in Figure 2 The vehicle danger warning light control device comprises:

[0109] The scene monitoring module 201 is configured to monitor whether the vehicle is in a preset dangerous scene range when the vehicle is parked;

[0110] The vehicle door monitoring module 202 is configured to detect whether the vehicle door or tailgate of the vehicle is in an open state if the vehicle is in the dangerous scene range;

[0111] The vehicle light control module 203 is configured to turn on the danger warning light of the vehicle if the vehicle door or tailgate is in an open state.

[0112] According to the technical scheme provided in the embodiment of the present application, by monitoring whether the vehicle is in the preset dangerous scene range when the vehicle is parked, if the vehicle is in the dangerous scene range, detecting whether the vehicle door or tailgate is in the open state, if the vehicle door or tailgate is in the open state, the vehicle danger warning light is turned on, the automatic turning on of the vehicle danger warning light is realized, the situation that some users forget to turn on the danger warning light is avoided, the occurrence of accidents can be effectively avoided, and the safety of vehicle use is improved.

[0113] In some embodiments, Figure 2 The scene monitoring module 201 in the embodiment is specifically configured to detect the network state of the vehicle, the network state including a network online state; in the case that the vehicle is in the network online state, real-time positioning information and a high-precision map of the vehicle are acquired; it is judged whether the position corresponding to the real-time positioning information in the high-precision map is a pre-marked position, wherein the pre-marked position is a position in the high-precision map that is pre-marked as a dangerous parking scene; if yes, it is determined that the vehicle is currently in the dangerous scene range; if no, it is determined that the vehicle is not currently in the dangerous scene range.

[0114] In some embodiments, Figure 2 The scene monitoring module 201 in the embodiment is specifically configured to, after determining that the vehicle is not currently in the dangerous scene range, acquire the surrounding image of the vehicle and a dangerous scene library, the dangerous scene library including a plurality of images marked as dangerous environments; it is judged whether the surrounding image is the same as the environment of any image in the dangerous scene library; if yes, it is determined that the vehicle is currently in the dangerous scene range; if no, it is determined that the vehicle is not currently in the dangerous scene range.

[0115] In some embodiments, the network state includes a network offline state, Figure 2 The scene monitoring module 201 in the embodiment is specifically configured to, after detecting the network state of the vehicle, if the vehicle is in the network offline state, acquire the surrounding image of the vehicle; based on a pre-set dangerous scene library, it is determined whether the surrounding image is the same as the environment of any image in the dangerous scene library, wherein the dangerous scene library includes a plurality of images marked as dangerous environments; if yes, it is determined that the vehicle is currently in the dangerous scene range; if no, it is determined that the vehicle is not currently in the dangerous scene range.

[0116] In some embodiments, the vehicle danger warning light control device includes:

[0117] The demand judgment module 204 is configured to judge whether the current turning on of the danger warning light meets the user demand;

[0118] The range updating module 205 is configured to, if yes, extract the scene features of the environment in which the vehicle is currently located, and update the pre-set dangerous scene range by using the scene features;

[0119] The range adjustment module 206 is configured to adjust the preset dangerous scene range if the preset dangerous scene range is not met.

[0120] In some embodiments, the demand judgment module 204 is specifically configured to count the number of times the vehicle turns on the hazard warning light in the current environment; obtain the count value of the vehicle turning on the hazard warning light in the current environment; determine whether the vehicle is in the current environment for the first time based on the count value; if it is the first time to turn on the hazard warning light, obtain the facial image of the user; identify the expression of the user in the facial image; in the case that the expression of the user is identified as satisfied, it is determined that the current opening of the hazard warning light meets the user's demand; in the case that the expression of the user is identified as not satisfied, it is determined that the current opening of the hazard warning light does not meet the user's demand.

[0121] In some embodiments, the demand judgment module 204 is specifically configured to obtain the surrounding image of the vehicle; extract the scene features in the surrounding image; update and train the preset machine learning model using the scene features as samples to obtain a new machine learning model, wherein when monitoring whether the vehicle is in the preset dangerous scene range, the surrounding image of the vehicle is input into the machine learning model, and the corresponding monitoring result is obtained from the output of the machine learning model, and the monitoring result includes that the vehicle is currently in the dangerous scene range or the vehicle is not currently in the dangerous scene range.

[0122] In some embodiments, the demand judgment module 204 is specifically configured to exclude the position corresponding to the current environment of the vehicle in the high-definition map from the preset dangerous scene range; or delete the image in the dangerous scene library that is the same as the environment of the surrounding image of the current position of the vehicle, wherein the dangerous scene range includes the dangerous scene library.

[0123] All the optional technical solutions described above can be combined to form optional embodiments of the present application, which will not be described here.

[0124] In addition, the embodiments of the present application also provide an automobile, which includes but is not limited to a light system, a door lock system, a positioning module and a host computer, wherein the light system, the door lock system, the positioning module and the host computer are connected through a communication bus, for example, are connected through a CAN bus. Specifically, the host computer can be installed with a high-definition map, a multimedia system and a dangerous scene library, etc.

[0125] Specifically, please refer to Figure 3 a schematic diagram of the host computer 3 provided by the embodiments of the present application. As shown in Figure 3As shown, the host computer comprises a processor 301, a memory 302, and a computer program 303 stored in the memory 302 and run on the processor 301. The processor 301 implements the steps of the above method embodiments when running the computer program 303. Alternatively, the processor 301 implements the functions of the modules in the above apparatus embodiments when running the computer program 303.

[0126] The host computer 3 can comprise, but is not limited to, a processor 301 and a memory 302. The skilled person understands that, Figure 3 The host computer 3 is merely an example and does not limit the host computer 3, which can include more or less or different components, more or less or different connections between the components, and / or more or less or different operations performed by the components.

[0127] The processor 301 can be a Central Processing Unit (CPU), a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or the like.

[0128] The memory 302 can be an internal storage unit of the host computer 3, for example, a hard disk or a memory of the host computer 3. The memory 302 can also be an external storage device of the host computer 3, for example, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, or the like. The memory 302 can also include both the internal storage unit and the external storage device of the host computer 3. The memory 302 is used to store computer programs and other programs and data required by the electronic device.

[0129] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of functional modules is exemplified, and in actual application, the above functions can be completed by different functional modules according to needs, i.e. the internal structure of the apparatus is divided into different functional modules to complete all or part of the above described functions. Each functional module in the embodiment can be integrated in one processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit, and the above integrated unit can be realized in the form of hardware or in the form of software functional unit.

[0130] The integrated modules / units, if implemented in the form of software functional units and sold or used as independent products, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various method embodiments can be implemented. The computer program can include computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer readable medium does not include electric carrier signals and telecommunication signals.

[0131] The above embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for some technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method for controlling vehicle hazard warning lights, characterized in that, include: When the vehicle is parked, monitor whether the vehicle is within a preset dangerous scenario range; If the vehicle is in a dangerous situation, check whether the vehicle's doors or tailgate are open; If the vehicle's doors or tailgate are open, turn on the vehicle's hazard warning lights; Determine whether the activation of the hazard warning lights meets the user's needs; If the conditions are met, the scene features of the current environment of the vehicle are extracted, and the preset dangerous scene range is updated using the scene features. If it does not meet the requirements, adjust the preset dangerous scenario range; Monitor whether the vehicle is within a preset hazardous scenario range, including: Detect the vehicle's network status, which includes network online status and network offline status; Acquire images of the vehicle's surroundings when the vehicle is offline from the network; Based on a preset dangerous scene image library, it is determined whether the surrounding images have the same environment as any image in the dangerous scene image library, wherein the dangerous scene image library includes multiple images marked as dangerous environments; If they are the same, then the vehicle is currently in a dangerous situation. If they are different, then it is determined that the vehicle is not currently in a dangerous situation. The determination of whether the activation of the hazard warning light meets the user's needs includes: Count the number of times the vehicle activates its hazard warning lights in the current environment; Obtain the count value of the vehicle's hazard warning lights being activated in the current environment; Based on the count value, determine whether this is the first time the vehicle has turned on its hazard warning lights in the current environment; If this is the first time the service is launched, obtain the user's facial image; Recognize the user's facial expressions in facial images; If the user's expression indicates satisfaction, it is determined that activating the hazard warning flashers meets the user's needs. If the user's expression indicates dissatisfaction, it is determined that activating the hazard warning flashers does not meet the user's needs.

2. The method according to claim 1, characterized in that, Whether the monitoring vehicle is within a preset dangerous scenario range also includes: When the vehicle is online, real-time location information and high-precision map of the vehicle are obtained. The high-precision map includes road information and surrounding static information related to traffic. The surrounding static information includes locations that are pre-marked as dangerous parking scenarios. Determine whether the location corresponding to the real-time positioning information in the high-precision map is a pre-marked location; If so, then the vehicle is currently in a dangerous situation. If not, it is determined that the vehicle is not currently in a dangerous scene, and images of the vehicle's surroundings and a dangerous scene image library are acquired. The dangerous scene image library includes multiple images marked as dangerous environments. Determine whether the surrounding images have the same environment as any image in the hazardous scene image library; If they are the same, then the vehicle is currently in a dangerous situation. If they are different, it is determined that the vehicle is not currently in a dangerous situation.

3. The method according to claim 1, characterized in that, Extracting scene features of the vehicle's current environment and updating the preset hazardous scene range using these features includes: Acquire images of the vehicle's surroundings; Extract scene features from the surrounding images; The preset machine learning model is updated and trained using scene features as samples to obtain a new machine learning model. When monitoring whether the vehicle is in a preset dangerous scene range, the surrounding image of the vehicle is input into the machine learning model, and the corresponding monitoring result is obtained from the output of the machine learning model. The monitoring result includes whether the vehicle is currently in a dangerous scene range or not.

4. The method according to claim 1, characterized in that, Adjusting the preset hazardous scene range includes: removing the location of the vehicle's current environment in the high-precision map from the preset hazardous scene range; Alternatively, delete images from the hazardous scene image library that have the same environment as the surrounding images of the vehicle's current location, where the hazardous scene range includes the hazardous scene image library.

5. A vehicle hazard warning light control device, characterized in that, include: The scene monitoring module is configured to monitor whether the vehicle is in a preset dangerous scene range when the vehicle is parked; The door monitoring module is configured to detect whether the vehicle's doors or tailgate are open if the vehicle is in a dangerous situation. The vehicle lighting control module is configured to activate the vehicle's hazard warning lights if the vehicle's doors or tailgate are open. The requirement judgment module is configured to determine whether the activation of the hazard warning light meets the user's requirements. The range update module is configured to extract the scene features of the current environment of the vehicle if the conditions are met, and update the preset dangerous scene range using the scene features. The range adjustment module is configured to adjust the preset hazardous scene range if it does not meet the requirements. The scene monitoring module is specifically configured to detect the network status of the vehicle, including network online status and network offline status. The scene monitoring module is further configured to: acquire images of the vehicle's surroundings when the vehicle is offline; determine whether the surrounding images are the same as any image in the dangerous scene image library based on a preset dangerous scene image library, wherein the dangerous scene image library includes multiple images marked as dangerous environments; if they are the same, determine that the vehicle is currently in a dangerous scene range; if they are not the same, determine that the vehicle is currently not in a dangerous scene range. The demand judgment module is specifically configured to: count the number of times the vehicle activates its hazard warning lights in the current environment; obtain the count value of the vehicle activating its hazard warning lights in the current environment; based on the count value, determine whether this is the first time the vehicle has activated its hazard warning lights in the current environment; if it is the first time, obtain the user's facial image; recognize the user's expression in the facial image; if the user's expression is recognized as satisfied, determine that activating the hazard warning lights meets the user's needs; if the user's expression is recognized as dissatisfied, determine that activating the hazard warning lights does not meet the user's needs.

6. A vehicle comprising a main control computer, the main control computer including a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 4.

Images