Vehicle whistling control method, device and equipment and storage medium

Abstract

The invention provides a vehicle whistling control method, device and equipment and a storage medium, and relates to the field of artificial intelligence, in particular to the field of unmanned driving. According to the specific implementation scheme, a high-precision map and an environment image of a scene where a vehicle is located currently are obtained; if it is determined that whistling is allowed in the current scene of the vehicle according to the high-precision map, determining the type of an obstacle in the current scene of the vehicle according to the environment image; and controlling the vehicle to whistle according to the type of the obstacle. Whether whistling is allowed on the road or not is judged, and targeted whistling is performed according to different obstacle types, so that the whistling control precision is improved, and the traffic environment of the road is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of unmanned driving in the field of artificial intelligence, and in particular to a method, device, equipment and storage medium for controlling vehicle horn. Background Art

[0002] With the development of driverless cars, driverless cars are gradually changing people's lifestyles. The simple horn system of current driverless cars cannot meet the complex traffic environment and the needs of different audiences for horns, which is likely to affect the traffic environment and the environment of residents.

[0003] Therefore, it is necessary to control vehicles to honk their horns in a targeted manner in different environments, which can not only serve as a reminder but also reduce sound interference to the environment. Summary of the invention

[0004] The present invention provides a method, device, equipment and storage medium for controlling a vehicle horn.

[0005] According to a first aspect of the present disclosure, a method for controlling a vehicle horn is provided, comprising:

[0006] Obtain high-precision maps and environmental images of the vehicle’s current scene;

[0007] If it is determined according to the high-precision map that the scene in which the vehicle is currently located allows honking, then determining the type of obstacles in the scene in which the vehicle is currently located according to the environmental image;

[0008] According to the type of the obstacle, the vehicle is controlled to honk.

[0009] According to a second aspect of the present disclosure, a vehicle horn control device is provided, comprising:

[0010] An acquisition unit, used to acquire a high-precision map and an environmental image of the scene in which the vehicle is currently located;

[0011] a determination unit, configured to determine, based on the environment image, a category of obstacles in the scene currently located by the vehicle if it is determined, based on the high-precision map, that honking is permitted in the scene currently located by the vehicle;

[0012] A control unit is used to control the vehicle to honk according to the type of the obstacle.

[0013] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0014] at least one processor; and

[0015] a memory communicatively coupled to the at least one processor;

[0016] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect of the present disclosure.

[0017] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute the method according to the first aspect of the present disclosure.

[0018] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program, which implements the steps of the method described in the first aspect of the present disclosure when executed by a processor.

[0019] According to the technology disclosed in the present invention, the control accuracy of vehicle horns is improved, and the traffic environment of the road is improved.

[0020] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0022] Figure 1 is a flow chart of a vehicle horn control method provided according to an embodiment of the present disclosure;

[0023] Figure 2 is a flow chart of a vehicle horn control method provided according to an embodiment of the present disclosure;

[0024] Figure 3 is a flow chart of a vehicle horn control method provided according to an embodiment of the present disclosure;

[0025] Figure 4 is a schematic diagram for determining the category of an obstacle provided according to an embodiment of the present disclosure;

[0026] Figure 5 is a flow chart of a whistle control method provided according to an embodiment of the present disclosure;

[0027] Figure 6 is a structural block diagram of a vehicle horn control device provided according to an embodiment of the present disclosure;

[0028] Figure 7 is a structural block diagram of a vehicle horn control device provided according to an embodiment of the present disclosure;

[0029] Figure 8is a block diagram of an electronic device for implementing the vehicle horn control method of the embodiment of the present disclosure;

[0030] Fig. 9 4 is a block diagram of an electronic device used to implement the vehicle horn control method of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0031] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0032] With the development of driverless cars, driverless cars are gradually changing people's lifestyles. The simple horn system of current driverless cars cannot meet the complex traffic environment and the requirements of different audiences for horns, nor can it improve the traffic environment and the living environment through intelligent horns. On the one hand, honking with inappropriate intensity will scare others, which may cause traffic accidents due to excessive reaction to fright, causing personal safety damage. On the other hand, inappropriate honking may cause rebellious psychology in others, which is also not conducive to smooth traffic and cause traffic hazards. At the same time, inappropriate honking in residential areas will also interfere with the environment and life of residents.

[0033] The current car horn system can only trigger the horn according to the recognized scene, and cannot intelligently select the strength, length, timbre, pitch, frequency, etc. of the horn according to different audience groups and environments. The current horn-honking method can be to control the volume of the horn by the intensity of the driver's pressure. The driver can press the steering wheel horn switch. If you touch it lightly, the volume is low, and if you press it hard, the volume is louder. The horn time is consistent with the duration of pressing, which cannot meet the needs of automatic horn for unmanned driving. For the automatic horn system of unmanned vehicles, the unmanned vehicle triggers the horn based on whether there is an obstacle in front, but it cannot determine whether the street can be honked, or intelligently select the horn strength, intensity and type according to the audience group and multiple scenes, nor can it determine whether the horn needs to be honked based on the current road congestion.

[0034] The present invention provides a vehicle horn control method, device, equipment and storage medium, which are applied to the unmanned driving field in the field of artificial intelligence to improve the control accuracy of vehicle horn and improve the traffic environment of the road.

[0035] It should be noted that the data in this embodiment is not targeted at a specific user and cannot reflect the personal information of a specific user. It should be noted that the data in this embodiment comes from a public data set.

[0036] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0037] In order to enable readers to more deeply understand the implementation principle of the present disclosure, the following Figure 1-Figure 9 The embodiment is further refined.

[0038] Figure 1 FIG. 1 is a flow chart of a method for controlling a vehicle horn according to an embodiment of the present disclosure, and the method can be executed by a device for controlling a vehicle horn. Figure 1 As shown, the method comprises the following steps:

[0039] S101. Obtain a high-precision map and environment image of the scene in which the vehicle is currently located.

[0040] For example, the vehicle can obtain a high-precision map and environmental image of the current scene in real time during driving. The current scene can be the area or street where the vehicle is currently located. The vehicle's current location information can be obtained in real time, and the area or street where the vehicle is currently located can be determined based on the current location information, thereby obtaining a high-precision map. The high-precision map can show information such as the layout of the road, the layout of surrounding buildings, the degree of road congestion, whether a traffic accident has occurred, and roadside signboards.

[0041] Environmental images are image data that represent the environment around the vehicle. Various image acquisition devices can be installed on the vehicle, for example, cameras or radars. The actual situation around the vehicle can be acquired in real time through the vehicle-mounted camera and vehicle-mounted radar to obtain environmental images.

[0042] S102: If it is determined based on the high-precision map that the scene in which the vehicle is currently located allows honking, then the category of obstacles in the scene in which the vehicle is currently located is determined based on the environmental image.

[0043] For example, some roads are not allowed to honk when planning, that is, vehicles are prohibited from honking when driving on such roads. The high-precision map stores the honking rules of each road, that is, records the relevant information of whether honking is prohibited on each road. For example, for roads in school areas, it may be stipulated that honking is prohibited, so when a vehicle is driving on a road in a school area, it cannot honk.

[0044] After obtaining a high-precision map of the scene where the vehicle is currently located, it can be determined from the high-precision map whether honking is allowed on the street where the vehicle is currently located. If honking is not allowed, the vehicle cannot honk and continues to drive normally until it exits the road, and then makes a honking judgment for other roads. If honking is allowed, the environmental image can be identified to determine whether there are obstacles in the surrounding environment. For example, obstacles can be identified from the environmental image collected in front of the vehicle. If it is determined that there are no obstacles, the horn may not be honked; if it is determined that there is an obstacle area, the category of the obstacle can be further determined. In this embodiment, a variety of obstacle categories can be pre-set. For example, the obstacle categories can include pedestrians, other vehicles, small animals, etc. Specifically, the obstacles can be divided into large trucks, cars, school buses, motorcycles, electric vehicles, bicycles, the elderly, young people, children, babies, men, women, disabled people, small animals, and other categories.

[0045] The environment image can be recognized by a preset large model, and the large model can output the obstacle category. For example, the large model can first recognize the outline of each object in the environment image, and determine the category to which the object belongs, that is, the category of the obstacle, according to the shape of the outline. In this embodiment, the model structure of the large model is not specifically limited.

[0046] S103: Control the vehicle to honk according to the type of obstacle.

[0047] For example, for different types of obstacles, the vehicle can be controlled to honk to different degrees. For example, the honking parameters such as the strength, duration, timbre, pitch, and frequency of the honking can be controlled, that is, the honking parameters can represent the sound emitted by the honking. Different types of obstacles can correspond to different honking parameters. According to the corresponding honking parameters found, the vehicle can be controlled to emit different sounds, thereby achieving targeted honking.

[0048] In this embodiment, the vehicle is controlled to honk according to the category of the obstacle, including: determining the horn parameters corresponding to the category of the obstacle according to a preset third association relationship; wherein the preset third association relationship represents the association between the category of the obstacle and the horn parameters, the horn parameters include a volume identifier and a content identifier, the volume identifier represents the volume of the horn, and the content identifier represents the content of the horn; according to the horn parameters, the vehicle is controlled to honk.

[0049] Specifically, a third association relationship is pre-set, and the third association relationship represents the association relationship between different obstacle categories and whistle parameters. The whistle parameters may include a volume identifier and a content identifier. The volume identifier represents the volume of the whistle, and the content identifier represents the sound content of the whistle. For example, if the obstacle category is a kitten, the associated content identifier is spv1, and spv1 represents the sound of driving away cats; if the obstacle category is a puppy, the associated content identifier is spv2, and spv2 represents the sound of driving away dogs. For another example, if the obstacle category is an elderly person, the volume identifier is voice3, and the volume represented by voice3 is of moderate intensity, which can prevent the elderly from not being able to hear and from being frightened.

[0050] According to the preset third association relationship, the volume mark and content mark corresponding to the obstacle category are searched. According to the volume mark and content mark, the power amplifier module of the vehicle is controlled to emit a sound, and the power amplifier module can be a speaker, that is, it can emit a whistle. For example, when facing special obstacles such as small animals, a special driving sound can be emitted.

[0051] The beneficial effect of such a setting is that the whistle parameters corresponding to different obstacles can be determined, thereby intelligently adjusting the volume and content of the whistle, improving the control accuracy of the whistle, and ensuring the whistle effect.

[0052] In the disclosed embodiment, by obtaining a high-precision map of the scene in which the vehicle is currently located, it is possible to determine whether honking is allowed in the scene in which the vehicle is currently located. If honking is allowed, obstacles in the environment can be identified and the category of obstacles can be determined based on the environmental image of the scene in which the vehicle is currently located. According to the category of the obstacle, the vehicle is controlled to honk in a targeted manner to improve the control accuracy of the honking. The disclosed embodiment enriches the interaction of honking in an unmanned vehicle environment, honking for different obstacle groups, avoiding traffic accidents caused by the audience being frightened or having a rebellious mentality due to the honking, and intelligently controls the choice of honking based on real-time road conditions and the surrounding residential environment, avoiding rigid and simple honking interactions that disrupt the lives of residents, and intelligently improving the traffic environment and the living environment of residents.

[0053] Figure 2 A flow chart of a method for controlling a vehicle horn provided in an embodiment of the present disclosure.

[0054] In the present embodiment, determining whether the vehicle's current scene allows honking is performed based on a high-precision map, including: determining road information of the vehicle's current scene based on the high-precision map; wherein the road information represents the road layout around the vehicle; if the road information meets preset honking conditions, determining that the vehicle's current scene allows honking; wherein the preset honking conditions include a judgment condition on at least one of the road type, congestion level, honking sign, and building type in the road information.

[0055] This embodiment is based on the above embodiment. Figure 2 As shown, the method comprises the following steps:

[0056] S201. Obtain a high-precision map and environmental image of the scene in which the vehicle is currently located.

[0057] Exemplarily, this step may refer to the above-mentioned step S101 and will not be described in detail.

[0058] S202. Determine the road information of the scene where the vehicle is currently located based on the high-precision map; wherein the road information represents the driving environment around the vehicle.

[0059] Exemplarily, a high-precision map of the scene the vehicle is currently in is obtained, and the high-precision map contains road information related to the surrounding driving environment. The road information of the scene the vehicle is currently in is obtained from the high-precision map. The road information can characterize the driving environment around the vehicle, that is, the road layout. Specifically, the road information can characterize the type of road the vehicle is currently on, the traffic conditions of the road, the enterprises to which the surrounding area belongs, etc. For example, the road information can characterize that the vehicle is currently on a highway, around a school, or in a crowded city center, etc.

[0060] S203. If the road information satisfies the preset honking condition, determine whether honking is allowed in the current scene of the vehicle; wherein the preset honking condition includes a judgment condition on at least one of the road type, congestion level, honking sign, and building type in the road information.

[0061] Exemplarily, a honking condition is preset to determine whether the current road information meets the preset honking condition. If so, it is determined that the vehicle's current scene allows honking; if not, it is determined that the vehicle's current scene does not allow honking.

[0062] For example, the preset honking condition may be to obtain accident information from road information, where the accident information indicates whether an accident has occurred in front of the vehicle. If it is determined that an accident has occurred in front of the vehicle, it is considered that the preset honking condition is not met and the horn cannot be honked; if it is determined that no accident has occurred, it is considered that the current scenario allows honking.

[0063] In this embodiment, by obtaining road information from a high-precision map, it can be determined whether the vehicle is allowed to honk on the current road, thereby avoiding the vehicle from honking when honking is prohibited, meeting actual road conditions, improving the accuracy of honking control, and reducing noise in the environment.

[0064] In this embodiment, the road information includes the road category; if the road information meets the preset honking conditions, it is determined that the vehicle's current scene allows honking, including: if the road category is a preset category, it is determined that the vehicle's current scene allows honking.

[0065] In this embodiment, the road information includes a congestion level, which represents the degree of road congestion in the scene in which the vehicle is currently located; if the road information meets the preset honking conditions, it is determined that the scene in which the vehicle is currently located allows honking, including: if the road category is not a preset category and the congestion level is a preset level, it is determined that the scene in which the vehicle is currently located allows honking.

[0066] Specifically, the road information may include road categories and congestion levels. Road categories may represent the use characteristics, location, and functions of the road. For example, road categories may include urban roads, highways, rural roads, factory and mine roads, and forest roads. The congestion level may represent the degree of road congestion in the scene where the vehicle is currently located. For example, the congestion level may include a light level, a medium level, and a heavy level. A light level indicates that there is almost no congestion on the road and the vehicle is traveling smoothly; a medium level indicates that there is slight congestion on the road and the vehicle can travel slowly; a heavy level indicates that the road is severely congested and the vehicle cannot move forward.

[0067] For road categories, preset categories are preset, and for congestion levels, preset levels are preset. For example, the preset categories are expressways, urban roads, rural roads, and factory roads, and the preset levels are mild and moderate. The current road category and congestion level are obtained from the road information. If the current road category is the preset category, it can be determined that the vehicle is currently in a scene where the horn is allowed to be honked. For example, if the preset category is an expressway, the horn can be honked when the vehicle is traveling on the expressway.

[0068] If the current road category is not a preset category, it can be determined whether honking is allowed in combination with the current congestion level. If the current road category is not a preset category, but the current congestion level is the preset level, it is determined that honking is allowed in the current scene of the vehicle; if the current road category is not a preset category, and the current congestion level is not a preset level, it is determined that honking is not allowed in the current scene of the vehicle. For example, the preset category is a highway, and the preset levels are a mild level and a moderate level. If the current road category is not a highway, but the current congestion level is a mild level or a moderate level, honking is allowed; if the current road category is not a highway, and the current congestion level is a severe level, the vehicle is not allowed to honk.

[0069] If the current road type is a highway, the vehicle is allowed to honk, and since all obstacles on the highway are cars, the vehicle can honk normally without determining the obstacle type based on environmental information. When there is an obstacle in front of the vehicle, the vehicle can honk directly using the preset default volume.

[0070] In this embodiment, it is possible to first determine whether the current road category is a preset category, and if not, further determine whether the current congestion level is a preset level. For example, if the current road category is first determined to be a highway, the vehicle is directly allowed to honk; if the current road category is determined not to be a highway, further determine whether the current congestion level is a severe level, and if so, directly prohibit the vehicle from honking; if not, allow the vehicle to honk, and continue to determine the category of obstacles in the scene where the vehicle is currently located based on the environmental image, so as to control the vehicle to honk according to the category of the obstacle.

[0071] The beneficial effect of this setting is that it can determine whether a vehicle can honk based on the road type and congestion level, avoid vehicle honking affecting the fast driving of other vehicles, and avoid frequent honking in congested conditions causing noise pollution, thereby improving the accuracy of horn control and improving the traffic environment.

[0072] In this embodiment, the road information includes a horn sign on the road, which indicates whether honking is prohibited on the road; if the road information meets the preset horn conditions, it is determined that honking is allowed in the current scene of the vehicle, including: if the road category is not a preset category, and the horn sign indicates that honking is not prohibited on the road, then it is determined that honking is allowed in the current scene of the vehicle.

[0073] Specifically, the high-precision map includes the road name of each road, and the road name may be a unique identifier of the road. The road name of the road where the vehicle is currently located may be obtained from the road information.

[0074] A first association relationship is pre-set in the high-precision map, and the first association relationship represents the association relationship between the road name and the horn sign, and the horn sign represents whether honking is prohibited on the road. For example, each road name is associated with a 0 or a 1, 0 indicates that honking is prohibited on the road, and 1 indicates that honking is allowed on the road. After determining the road name, the horn sign corresponding to the road name can be determined according to the first association relationship. The horn signs of each road can also be directly stored in the high-precision map, and whether honking is allowed in the current scene of the vehicle can be determined according to the horn sign. That is, if the horn sign of the road indicates that honking is not prohibited on the road, then it is determined that honking is allowed in the current scene of the vehicle; if the horn sign of the road indicates that honking is prohibited on the road, then it is determined that honking is not allowed in the current scene of the vehicle.

[0075] In this embodiment, it is possible to first determine whether the road category is a preset category. If it is not a preset category, then confirm the road sign corresponding to the road, and determine whether honking is restricted on the road based on the road sign. It is also possible to first determine whether the road category is a preset category. If it is not a preset category, then determine whether the congestion level is a preset level. If it is a preset level, then confirm the road sign corresponding to the road, and determine whether honking is restricted on the road based on the road sign.

[0076] The beneficial effect of this setting is that, based on the high-precision map, the horn signs on the road can be determined, thereby determining whether honking is restricted on the road, avoiding noise on sections of road where honking is prohibited, improving the control accuracy of honking, and meeting actual traffic regulations.

[0077] In this embodiment, the road information includes the building type, and the building type characterizes the purpose of the building around the vehicle; if the road information meets the preset honking conditions, it is determined that the vehicle's current scene allows honking, including: if the road category is not a preset category, and the building type is a preset type, it is determined that the vehicle's current scene allows honking.

[0078] Specifically, the road information may also include relevant information of buildings around the vehicle, for example, the building type. The building type represents the purpose of the building around the vehicle, for example, the building type may include a shopping mall, a hospital, a school, a residential building, etc.

[0079] One or more building types are preset as preset types. It is determined whether the currently determined building type is a preset type. If so, it is determined that honking is allowed in the scene where the vehicle is currently located; if not, it is determined that honking is prohibited in the scene where the vehicle is currently located. For example, the preset type is a type other than a school and a residential building, that is, if the building type is not a school or a residential building, the vehicle is allowed to honk; if the building type is a school or a residential building, the vehicle is prohibited from honk.

[0080] In this embodiment, it is possible to first determine whether the road category is a preset category. If it is not a preset category, then the current building type is obtained. If the building type is a preset type, it is determined that the scene in which the vehicle is currently located allows honking. It is also possible to first determine whether the road category is a preset category. If it is not a preset category, then determine whether the congestion level is a preset level. If it is a preset level, then confirm the road sign corresponding to the road name, and determine whether honking is restricted on the road based on the road sign. If honking is not restricted on the road, then the current building type is obtained. If the building type is a preset type, then determine that the scene in which the vehicle is currently located allows honking. In this embodiment, the order of judging the road category, congestion level, honking sign, and building type is not specifically limited. When judging whether honking is allowed, at least one of the road category, congestion level, honking sign, and building type can be judged.

[0081] The beneficial effect of such a setting is that, by determining the type of building, vehicles can be prohibited from making noise when there are schools or residential areas around, which is conducive to improving the living environment of residents.

[0082] S204: Determine the category of obstacles in the scene where the vehicle is currently located according to the environment image.

[0083] Exemplarily, this step may refer to the above-mentioned step S102 and will not be described in detail.

[0084] S205: Control the vehicle to honk according to the type of obstacle.

[0085] Exemplarily, this step may refer to the above-mentioned step S103 and will not be described in detail.

[0086] In the disclosed embodiment, by obtaining a high-precision map of the scene in which the vehicle is currently located, it is possible to determine whether honking is allowed in the scene in which the vehicle is currently located. If honking is allowed, obstacles in the environment can be identified and the category of obstacles can be determined based on the environmental image of the scene in which the vehicle is currently located. According to the category of the obstacle, the vehicle is controlled to honk in a targeted manner to improve the control accuracy of the honking. The disclosed embodiment enriches the interaction of honking in an unmanned vehicle environment, honking for different obstacle groups, avoiding traffic accidents caused by the audience being frightened or having a rebellious mentality due to the honking, and intelligently controls the choice of honking based on real-time road conditions and the surrounding residential environment, avoiding rigid and simple honking interactions that disrupt the lives of residents, and intelligently improving the traffic environment and the living environment of residents.

[0087] Figure 3 A flow chart of a method for controlling a vehicle horn provided in an embodiment of the present disclosure.

[0088] In this embodiment, the category of obstacles in the scene where the vehicle is currently located is determined based on the environmental image, including: performing target positioning processing on the environmental image to determine the obstacles from the environmental image; performing feature extraction processing on the obstacles in the environmental image to determine the category of the obstacles.

[0089] This embodiment is based on the above embodiment. Figure 3 As shown, the method comprises the following steps:

[0090] S301. Obtain a high-precision map and environmental image of the scene in which the vehicle is currently located.

[0091] Exemplarily, this step may refer to the above-mentioned step S101 and will not be described in detail.

[0092] S302: If it is determined based on the high-precision map that the vehicle is currently in a scene where honking is allowed, target positioning processing is performed on the environment image to determine obstacles from the environment image.

[0093] For example, based on the high-precision map, determine the road type, congestion level, road name, building type and other road information of the scene where the vehicle is currently located. Based on the road information, determine whether the scene where the vehicle is currently located allows honking. If so, identify obstacles from the environmental image of the scene where the vehicle is currently located. Obstacles can be pedestrians, other vehicles, trees, small animals and other objects in the environment. Specifically, pedestrians can be divided into the elderly, young people, children, babies, men, women, disabled people, etc., and other vehicles can be divided into large trucks, cars, school buses, motorcycles, electric vehicles, bicycles, etc.

[0094] A large model is pre-built, and the environment image can be input into the large model. The large model is used to locate the object in the environment image, that is, to determine where obstacles exist in the environment image, and to recognize the obstacles. For example, contour recognition can be performed on the environment image to determine the contour of the object in the environment image, and the environment image can be segmented according to the position of the contour, that is, the obstacle is segmented from the environment image to obtain the obstacle in the environment image, and a local image of the area where the obstacle is located in the environment image can be obtained.

[0095] S303: Perform feature extraction processing on obstacles in the environment image to determine the category of the obstacles.

[0096] Exemplarily, after obtaining obstacles in the environment image, feature extraction processing is performed on the obstacles, and the feature extraction processing can be performed by a preset large model. The large model classifies the obstacles according to the feature vectors of the obstacles. Multiple obstacle categories can be preset, and the large model can calculate the probability that the obstacle belongs to each category, and determine the category corresponding to the highest probability as the category of the obstacle.

[0097] In this embodiment, by processing the environment image with a large model, the category of the obstacle can be determined, so that different whistle sounds are emitted for different categories, thereby achieving targeted whistle control.

[0098] In this embodiment, feature extraction processing is performed on obstacles in the environment image to determine the category of the obstacle, including: feature extraction processing is performed on the obstacles in the environment image to determine the feature vector of the obstacle; wherein the feature vector represents image information of the obstacle; and the category of the obstacle is determined based on the feature vector of the obstacle.

[0099] Specifically, the obstacle in the environment image is subjected to feature extraction processing through a preset large model, and each obstacle has its own feature vector corresponding to it. The feature vector can represent the image information of the obstacle, and the image information can be feature information such as the appearance of the obstacle.

[0100] For different categories, portrait information of each category is pre-stored. For example, for different categories of obstacles such as pedestrians or vehicles, different user groups are preset, each user group represents an obstacle category, and each user group has its own portrait information corresponding to it, which represents the relevant characteristics of this user group. For example, user groups may include the elderly, young people, pregnant women, children, etc. After obtaining the feature vector of the obstacle, it can be determined which user group the feature vector belongs to, that is, it can be determined in which user group the portrait information corresponding to the feature vector exists. The user group to which the feature vector belongs is determined as the category of the obstacle.

[0101] The beneficial effect of this setting is that the features of obstacles are extracted through a large model, that is, user profiling is performed, and the extracted feature vectors are used as profiling information to identify which category the obstacle belongs to, thereby improving the accuracy and efficiency of determining the obstacle category, and then improving the control accuracy and efficiency of horn honking.

[0102] In this embodiment, determining the category of the obstacle based on the feature vector of the obstacle includes: determining the category corresponding to the feature vector of the obstacle as the category of the obstacle based on a preset second association relationship; wherein the preset second association relationship represents the association relationship between the feature vector and the category.

[0103] Specifically, a second association relationship is pre-set, and the second association relationship represents the association relationship between the feature vector and the obstacle category. After the feature vector of the obstacle is obtained, the category corresponding to the feature vector is searched and used as the category of the obstacle.

[0104] The large model can also convert the feature vector in matrix form into multiple pieces of portrait information, for example, into text-based portrait information. The association between different portrait information and categories is preset to determine which category each piece of portrait information of the obstacle belongs to. If each piece of portrait information belongs to a different category, the category to which each piece of portrait information belongs is determined as a candidate category. The number of obstacle portrait information in the candidate category is determined, and the candidate category with the largest number of portrait information is determined as the category of the obstacle.

[0105] The beneficial effect of such a setting is that the category of the obstacle can be quickly found, accurate horn control of the obstacle can be achieved, and the efficiency and accuracy of horn control can be improved.

[0106] In this embodiment, it also includes: determining a feature vector corresponding to the category of the obstacle from a preset second association relationship as the current stored vector; if it is determined that the feature vector of the obstacle is more than the current stored vector, determining a difference vector between the feature vector of the obstacle and the current stored vector; wherein the difference vector represents the feature vector that is more than the current stored vector; and associating the difference vector with the category of the obstacle and storing it in the preset second association relationship.

[0107] Specifically, after determining the category of the obstacle, all feature vectors corresponding to the category of the obstacle stored in the second association relationship are searched according to the preset second association relationship as the current storage vector, and the feature vector of the obstacle extracted from the environment image is determined as the current extraction vector.

[0108] The current extraction vector is compared with the current storage vector. If the current extraction vector is consistent with the current storage vector, there is no need to update the second association relationship. If the current extraction vector contains a feature vector different from the current storage vector, that is, the current extraction vector contains more feature vectors than the current storage vector, then the difference vector between the current extraction vector and the current storage vector is determined. The difference vector represents the feature vector that is more than the current storage vector in the current extraction vector.

[0109] The second association relationship is supplemented according to the difference vector. The difference vector and the category of the obstacle may be associated and stored in the second association relationship, that is, a feature vector corresponding to the category is added to the second association relationship.

[0110] The beneficial effect of such a setting is that, by updating the second association relationship, it is convenient to continuously perform model training according to the latest second association relationship during the model application process, thereby improving the subsequent accurate recognition of obstacles and further improving the control accuracy of the horn.

[0111] Figure 4 Determine a schematic diagram for the category of obstacle. Figure 4 In the process, an environment image is obtained, and the environment image is preprocessed. For example, the preprocessing may be denoising or image enhancement. The obstacles are located and segmented in the preprocessed image to obtain an obstacle image in the environment image. The obstacle image is normalized to save subsequent calculations. In this embodiment, the VGG-16Net model can be used to classify obstacles. The VGG-16Net model is a convolutional neural network model. Through the VGG-16Net model, obstacles can be classified and identified, and the classification results of the obstacles are output, that is, the categories of the obstacles are obtained.

[0112] S304: Control the vehicle to honk according to the type of obstacle.

[0113] Exemplarily, this step may refer to the above-mentioned step S103 and will not be described in detail.

[0114] In the disclosed embodiment, by obtaining a high-precision map of the scene in which the vehicle is currently located, it is possible to determine whether honking is allowed in the scene in which the vehicle is currently located. If honking is allowed, obstacles in the environment can be identified and the category of obstacles can be determined based on the environmental image of the scene in which the vehicle is currently located. According to the category of the obstacle, the vehicle is controlled to honk in a targeted manner to improve the control accuracy of the honking. The disclosed embodiment enriches the interaction of honking in an unmanned vehicle environment, honking for different obstacle groups, avoiding traffic accidents caused by the audience being frightened or having a rebellious mentality due to the honking, and intelligently controls the choice of honking based on real-time road conditions and the surrounding residential environment, avoiding rigid and simple honking interactions that disrupt the lives of residents, and intelligently improving the traffic environment and the living environment of residents.

[0115] Figure 5 This is a flow chart of the whistle control method provided in the embodiment of the present disclosure. This embodiment is based on the above embodiment. Figure 5 As shown in the figure, when the whistle control is performed:

[0116] Determine the road category, road congestion level, road name, building type and other information of the vehicle's current scene from the high-precision map. According to the road category, it can be determined whether the vehicle is currently on a highway. If so, when there is an obstacle in front of the vehicle, honk normally with the preset default volume and default content; if not, continue to determine whether there is congestion or an accident ahead. If there is congestion or an accident ahead, honking is prohibited; if there is no congestion or an accident ahead, determine whether the road restricts honking based on the road name. If honking is restricted, honking is prohibited; if honking is not restricted, continue to determine whether it is a school area or a residential area. If so, honking is prohibited; if not, honking is controlled in combination with the obstacle information in front.

[0117] The vehicle is equipped with devices such as radar or camera, and the current environmental information can be obtained in real time through radar and camera. Through the preset large model, obstacles are identified from the environmental image to obtain the category of obstacles. The categories of obstacles can include pregnant women, children, the elderly, cats, dogs, sheep, motorcycles, school buses, large vehicles, special vehicles, etc. Different categories of obstacles correspond to different whistle parameters, and the whistle parameters can include volume identification and content identification. The volume identification is voice, and the content identification is content or spv. Among them, the volume identification can be preset with voice1 to voice10, indicating that the volume is divided into ten levels of intensity from low to high. The content identification can be preset with content1 to cintent3, and spv1 to spv3. Among them, content1 can represent piano music, content2 can represent children's songs, content3 can represent guqin music, spv1 can represent cat-driving sound, spv2 can represent dog-driving sound, and spv3 can represent sheep-driving sound. When honking is permitted, if the obstacle in front of the vehicle is a large vehicle, you can honk the horn according to the preset default volume and default content; if the obstacle in front of the vehicle is a special vehicle such as an ambulance, honking is prohibited.

[0118] Figure 6 This is a structural block diagram of a vehicle horn control device provided by an embodiment of the present disclosure. For ease of explanation, only the parts related to the embodiment of the present disclosure are shown. Figure 6 The vehicle horn control device 600 includes: an acquisition unit 601, a determination unit 602 and a control unit 603.

[0119] An acquisition unit 601 is used to acquire a high-precision map and an environment image of the scene in which the vehicle is currently located;

[0120] The determination unit 602 is configured to determine the category of obstacles in the scene currently located by the vehicle according to the environment image if it is determined according to the high-precision map that the scene currently located by the vehicle allows honking;

[0121] The control unit 603 is used to control the vehicle to honk according to the type of the obstacle.

[0122] Figure 7 A structural block diagram of a vehicle horn control device provided by an embodiment of the present disclosure, such as Figure 7 As shown, the vehicle horn control device 700 includes an acquisition unit 701, a determination unit 702 and a control unit 703, wherein the determination unit 702 includes an information determination module 7021, a condition judgment module 7022, a target positioning module 7023 and a category determination module 7024.

[0123] The information determination module 7021 is used to determine the road information of the scene where the vehicle is currently located according to the high-precision map; wherein the road information represents the road layout around the vehicle;

[0124] The condition judgment module 7022 is used to determine whether the vehicle is currently in a scene where the horn is allowed to be honked if the road information satisfies a preset honking condition; wherein the preset honking condition includes a judgment condition on at least one of the road type, congestion level, honking sign, and building type in the road information;

[0125] The target positioning module 7023 is used to perform target positioning processing on the environment image and determine obstacles from the environment image;

[0126] The category determination module 7024 is used to perform feature extraction processing on the obstacles in the environment image to determine the category of the obstacles.

[0127] In one example, the road information includes the road category; the condition judgment module 7022 includes:

[0128] The horn judging submodule is used to determine whether the horn is allowed in the current scene of the vehicle if the road category is a preset category.

[0129] In one example, the road information includes a congestion level, and the congestion level represents the degree of road congestion in the scene where the vehicle is currently located; the condition judgment module 7022 includes:

[0130] The level judgment submodule is used to determine whether honking is allowed in the current scene of the vehicle if the road category is not a preset category and the congestion level is a preset level.

[0131] In one example, the road information includes a horn sign on the road, and the horn sign indicates whether honking is prohibited on the road; the condition judgment module 7022 includes:

[0132] The identification judgment submodule is used to determine that honking is allowed in the current scene of the vehicle if the road category is not a preset category and the honking sign indicates that honking is not prohibited on the road.

[0133] In one example, the road information includes a building type, and the building type represents the purpose of the building around the vehicle; the condition judgment module 7022 includes:

[0134] The building judgment submodule is used to determine whether the vehicle is currently in a scene where honking is allowed if the road category is not a preset category and the building type is a preset type.

[0135] In one example, the category determination module 7024 includes:

[0136] A feature extraction submodule, used to perform feature extraction processing on obstacles in the environment image to determine a feature vector of the obstacle; wherein the feature vector represents image information of the obstacle;

[0137] The category determination submodule is used to determine the category of the obstacle according to the feature vector of the obstacle.

[0138] In one example, the category determination submodule is specifically used for:

[0139] According to a preset second association relationship, a category corresponding to the feature vector of the obstacle is determined as the category of the obstacle; wherein the preset second association relationship represents an association relationship between the feature vector and the category.

[0140] In one example, it also includes:

[0141] A current storage unit, used to determine a feature vector corresponding to the category of the obstacle from the preset second association relationship as a current storage vector;

[0142] A difference determination unit, configured to determine a difference vector between the feature vector of the obstacle and the current stored vector if it is determined that the feature vector of the obstacle is more than the current stored vector; wherein the difference vector represents the feature vector that is more than the current stored vector;

[0143] A difference storage unit is used to associate the difference vector with the category of the obstacle and store it in the preset second association relationship.

[0144] In one example, the control unit 701 includes:

[0145] a parameter determination module, configured to determine a whistle parameter corresponding to the category of the obstacle according to a preset third association relationship; wherein the preset third association relationship represents an association relationship between the obstacle category and the whistle parameter, the whistle parameter includes a volume identifier and a content identifier, the volume identifier represents the volume of the whistle, and the content identifier represents the content of the whistle;

[0146] The horn control module is used to control the vehicle to honk according to the horn parameters.

[0147] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device.

[0148] Figure 8 A structural block diagram of an electronic device provided in an embodiment of the present disclosure, such as Figure 8As shown, the electronic device 800 includes: at least one processor 802; and a memory 801 that is communicatively connected to the at least one processor 802; wherein the memory stores instructions that can be executed by the at least one processor 802, and the instructions are executed by the at least one processor 802 so that the at least one processor 802 can execute the vehicle horn control method disclosed in the present invention.

[0149] The electronic device 800 further includes a receiver 803 and a transmitter 804. The receiver 803 is used to receive instructions and data sent by other devices, and the transmitter 804 is used to send instructions and data to external devices.

[0150] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0151] According to an embodiment of the present disclosure, the present disclosure also provides a computer program product, which includes: a computer program, the computer program is stored in a readable storage medium, at least one processor of an electronic device can read the computer program from the readable storage medium, and at least one processor executes the computer program so that the electronic device executes the solution provided by any of the above embodiments.

[0152] Fig. 9 A schematic block diagram of an example electronic device 900 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0153] like Fig. 9 As shown, the device 900 includes a computing unit 901, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 902 or a computer program loaded from a storage unit 908 into a random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the device 900 can also be stored. The computing unit 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0154] A number of components in the device 900 are connected to the I / O interface 905, including: an input unit 906, such as a keyboard, a mouse, etc.; an output unit 907, such as various types of displays, speakers, etc.; a storage unit 908, such as a disk, an optical disk, etc.; and a communication unit 909, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 909 allows the device 900 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0155] The computing unit 901 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 901 performs the various methods and processes described above, such as a control method for a vehicle horn. For example, in some embodiments, the control method for a vehicle horn may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 908. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 900 via the ROM 902 and / or the communication unit 909. When the computer program is loaded into the RAM 903 and executed by the computing unit 901, one or more steps of the control method for the vehicle horn described above may be performed. Alternatively, in other embodiments, the computing unit 901 may be configured to perform a control method for a vehicle horn by any other appropriate means (e.g., by means of firmware).

[0156] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0157] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0158] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0159] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0160] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0161] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0162] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0163] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for controlling a vehicle horn, comprising: Obtain high-precision maps and environmental images of the vehicle’s current scene; If it is determined according to the high-precision map that the scene in which the vehicle is currently located allows honking, then determining the type of obstacles in the scene in which the vehicle is currently located according to the environmental image; According to the type of the obstacle, the vehicle is controlled to honk.

2. The method according to claim 1, wherein: The determining, based on the high-precision map, whether the scene in which the vehicle is currently located allows honking the horn includes: Determine the road information of the scene where the vehicle is currently located according to the high-precision map; wherein the road information represents the road layout around the vehicle; If the road information satisfies the preset honking conditions, it is determined that the vehicle is currently in a scene that allows honking; wherein the preset honking conditions include a judgment condition on at least one of the road type, congestion level, honking sign, and building type in the road information.

3. The method according to claim 2, wherein: The road information includes a road category; if the road information satisfies a preset honking condition, determining that the vehicle is currently in a scene where honking is allowed includes: If the road category is a preset category, it is determined that the vehicle is currently in a scene where honking is allowed.

4. The method according to claim 3, wherein: The road information includes a congestion level, and the congestion level represents the degree of road congestion in the scene where the vehicle is currently located; if the road information meets a preset honking condition, determining that the scene where the vehicle is currently located allows honking, includes: If the road category is not the preset category and the congestion level is the preset level, it is determined that the vehicle is currently in a scene where honking is allowed.

5. The method according to claim 3 or 4, wherein: The road information includes a horn sign of the road, and the horn sign indicates whether honking is prohibited on the road; if the road information satisfies a preset horn condition, determining that honking is permitted in the current scene of the vehicle, comprises: If the road category is not the preset category, and the horn sign indicates that honking is not prohibited on the road, it is determined that honking is permitted in the current scene of the vehicle.

6. The method according to any one of claims 3 to 5, wherein: The road information includes a building type, and the building type represents the purpose of the building around the vehicle; if the road information satisfies a preset honking condition, determining that the scene where the vehicle is currently located allows honking, includes: If the road category is not the preset category, and the building type is the preset type, it is determined that the scene in which the vehicle is currently located allows honking.

7. The method according to any one of claims 1 to 6, wherein: The step of determining the type of obstacles in the scene currently located by the vehicle according to the environment image includes: Performing target positioning processing on the environment image to determine obstacles from the environment image; Perform feature extraction processing on the obstacles in the environment image to determine the category of the obstacles.

8. The method according to claim 7, wherein: The performing feature extraction processing on the obstacle in the environment image to determine the category of the obstacle includes: Performing feature extraction processing on the obstacle in the environment image to determine a feature vector of the obstacle; wherein the feature vector represents image information of the obstacle; The category of the obstacle is determined according to the feature vector of the obstacle.

9. The method according to claim 8, wherein: The step of determining the category of the obstacle according to the feature vector of the obstacle includes: According to a preset second association relationship, a category corresponding to the feature vector of the obstacle is determined as the category of the obstacle; wherein the preset second association relationship represents an association relationship between the feature vector and the category.

10. The method according to claim 9, further comprising: Determine, from the preset second association relationship, a feature vector corresponding to the category of the obstacle as the current storage vector; If it is determined that the feature vector of the obstacle is more than the current stored vector, then determining a difference vector between the feature vector of the obstacle and the current stored vector; wherein the difference vector represents the feature vector that is more than the current stored vector; The difference vector and the category of the obstacle are associated and stored in the preset second association relationship.

11. The method according to any one of claims 1 to 10, wherein: The step of controlling the vehicle to honk according to the type of the obstacle comprises: Determine, according to a preset third association relationship, a whistle parameter corresponding to the category of the obstacle; wherein the preset third association relationship represents an association relationship between the obstacle category and the whistle parameter, the whistle parameter includes a volume identifier and a content identifier, the volume identifier represents the volume of the whistle, and the content identifier represents the content of the whistle; The vehicle is controlled to honk according to the horn parameters.

12. A vehicle horn control device, comprising: An acquisition unit, used to acquire a high-precision map and an environmental image of the scene in which the vehicle is currently located; a determination unit, configured to determine, based on the environment image, a category of obstacles in the scene currently located by the vehicle if it is determined, based on the high-precision map, that honking is permitted in the scene currently located by the vehicle; A control unit is used to control the vehicle to honk according to the type of the obstacle.

13. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 11.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-11.

15. A computer program product, wherein: The invention comprises a computer program, which implements the steps of the method according to any one of claims 1 to 11 when being executed by a processor.

Images