Parking Safety Control Method, Device, Electronic Device and Storage Medium

Abstract

The present application provides a parking safety control method, apparatus, electronic device, and storage medium. Among them, the method includes: if the vehicle is in a parked state, identifying traffic participant information within a preset range of the vehicle, where the traffic participant information includes the type of each participant and its distance from the vehicle; evaluating the parking risk of the vehicle based on the traffic participant information to obtain an evaluation result, and the evaluation result is used to instruct the vehicle to perform parking control. Through the above method, the present application can enable the vehicle or the driver to perform parking control on the vehicle according to the evaluation result obtained from the identified different risk situations, without the driver making a temporary parking risk judgment, effectively improving the safety parking efficiency and reducing the parking risk.

Description

Technical Field

[0001] This application relates to the technical field of vehicle driving, and particularly to a parking safety control method, device, electronic device, and storage medium. Background Art

[0002] With the continuous development of vehicle driving technology, the traditional handbrake has gradually been replaced by EPB (Electrical Park Brake), which can provide a more convenient and efficient braking experience for passengers after the vehicle is parked.

[0003] However, when the vehicle is in the parked state, if no safety control is performed, it is easily scratched by other vehicles or objects, resulting in safety risks for the vehicle. Based on the perception and computing capabilities of current autonomous driving technology, as well as the vehicle-to-person interaction capabilities of the vehicle network, when the driver leaves the vehicle, the safety monitoring function can be turned on, and on-vehicle cameras, high-computing power platforms, vehicle-side communication devices, etc. remain in the working state, and to a certain extent, the safety monitoring of the parked vehicle can be achieved. However, the current parking safety control solutions cannot perform efficient parking control on the vehicle for different risk situations, resulting in relatively high parking risks.

[0004] Therefore, there is an urgent need to propose a solution that improves the efficiency of parking safety control while reducing parking risks. Summary of the Invention

[0005] In view of the above problems, this application provides a parking safety control method, device, electronic device, and storage medium to solve the problems such as only performing safety monitoring on the vehicle, low parking control efficiency in different risk situations, and relatively high parking risks.

[0006] To achieve the above object, this application provides the following technical solutions:

[0007] According to one aspect of this application, a parking safety control method is provided, including:

[0008] If the vehicle is in the parked state, identify traffic participant information within a preset range of the vehicle, where the traffic participant information includes the type of each participant and its distance from the vehicle;

[0009] Based on the traffic participant information, evaluate the parking risk of the vehicle to obtain an evaluation result, and the evaluation result is used to instruct the vehicle to perform parking control.

[0010] In one implementation, the identifying traffic participant information within a preset range of the vehicle includes:

[0011] Obtain a video stream within a preset range of the vehicle, where the video stream is collected after the vehicle enters the parked state;

[0012] Obtain the corresponding image based on the video stream and preprocess the image;

[0013] Identify traffic participant information of the vehicle within a preset range based on the preprocessed image.

[0014] In one implementation, the identifying traffic participant information of the vehicle within a preset range based on the preprocessed image includes:

[0015] Input the preprocessed image into a perception neural network, where the perception neural network includes a participant type perception module and a distance perception module;

[0016] Perform first deep learning on the preprocessed image based on the participant type perception module to obtain the types of participants of the vehicle within a preset range;

[0017] Perform second deep learning on the preprocessed image based on the distance perception module to obtain the distance between the participants of the vehicle within a preset range and the vehicle.

[0018] In one implementation, it further includes:

[0019] Obtain several defined types of traffic participants, where the several defined types include a first type and a second type;

[0020] The evaluating the parking risk of the vehicle based on the traffic participant information includes:

[0021] If the type of the participant is the first type and the distance from the vehicle is less than a first preset threshold, then evaluate the parking risk of the vehicle as a first level, and the first level is used to indicate that the vehicle changes its parking state;

[0022] If the type of the participant is the second type and the distance from the vehicle is less than a second preset threshold, then evaluate the parking risk of the vehicle as a second level, and the second level is used to indicate that the vehicle sounds a horn for warning.

[0023] In one implementation, after obtaining the video stream of the vehicle within a preset range, it further includes:

[0024] Generate cache information, where the cache information is obtained based on the video stream.

[0025] In one implementation, after obtaining the evaluation result, it further includes:

[0026] Transmit the evaluation result to an in-vehicle terminal, so that the in-vehicle terminal transmits the evaluation result to a user terminal, and enables the user terminal to perform parking control on the vehicle based on the evaluation result.

[0027] In one embodiment, after obtaining the evaluation result, it further includes:

[0028] Map the cache information and the evaluation result to obtain a mapping relationship;

[0029] Transmit the evaluation result and the cache information to the vehicle-mounted terminal, so that the vehicle terminal transmits the evaluation result to the user terminal, and after the user terminal receives the evaluation result, it retrieves the corresponding cache information based on the mapping relationship of the evaluation result, and performs parking control on the vehicle based on the evaluation result and the cache information.

[0030] According to another aspect of the present application, a parking safety control device is provided, including:

[0031] An identification module, configured to identify traffic participant information within a preset range of the vehicle when the vehicle is in a parked state, where the traffic participant information includes the type of each participant and its distance from the vehicle;

[0032] A risk assessment module, configured to evaluate the parking risk of the vehicle based on the traffic participant information to obtain an evaluation result, and the evaluation result is used to instruct the vehicle to perform parking control.

[0033] According to still another aspect of the present application, an electronic device is provided, including: a memory and a processor;

[0034] The memory stores computer execution instructions;

[0035] The processor executes the computer execution instructions stored in the memory, so that the electronic device executes the parking safety control method described above.

[0036] According to yet another aspect of the present application, a computer-readable storage medium is provided, where computer execution instructions are stored in the computer-readable storage medium, and when the computer execution instructions are executed by a processor, they are used to implement the parking safety control method described above.

[0037] According to the parking safety control method, device, electronic device and storage medium provided by the present application, when the vehicle is in a parked state, traffic participant information within a preset range of the vehicle is recognized. The traffic participant information includes the type of each participant and the distance between the participant and the vehicle. Based on the traffic participant information, the parking risk of the vehicle is evaluated to obtain an evaluation result, and the evaluation result is used to instruct the vehicle to perform parking control. Through the above method, the present application can enable the vehicle or the driver to perform parking control on the vehicle according to the evaluation result obtained from the recognized different risk situations, without the driver making a parking risk judgment temporarily, effectively improving the safety parking efficiency and reducing the parking risk. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is a schematic diagram of a possible scenario provided by an embodiment of the present application;

[0039] Figure 2 It is a flowchart of a parking safety control method provided by an embodiment of the present application;

[0040] Figure 3 It is a flowchart of another parking safety control method provided by an embodiment of the present application;

[0041] Figure 4 It is a schematic structural diagram of a parking safety control device provided by an embodiment of the present application;

[0042] Figure 5 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0043] With the continuous development of the intelligent driving industry and the continuous improvement of visual perception algorithms, vehicles are equipped with cameras and high-computing-power computing platforms, enabling the vehicle to achieve full-vehicle perception coverage and high-precision target detection and behavior prediction functions.

[0044] Based on the perception and computing capabilities of current autonomous driving technologies and the vehicle-to-everything (V2X) interaction capabilities of the Internet of Vehicles, the safe monitoring of vehicle parking can be achieved. When the driver leaves the vehicle, the safety monitoring function is turned on, and in-vehicle cameras, high-computing-power computing platforms, vehicle-side communication devices, etc. remain in working state. When a suspicious target is detected approaching the vehicle, autonomous recognition is achieved, and communication is made with the driver to send a possible image. After the remote driver confirms the risk, the driver can select functions such as honking or voice calls according to the safety monitoring situation to achieve safe parking. However, it takes a certain amount of time for the driver to confirm the risk, and the manual recognition efficiency is not good. Moreover, the current parking safety control solutions cannot perform efficient parking control on the vehicle for different risk situations, resulting in a still relatively high parking risk.

[0045] In view of the above technical problems, the embodiments of the present application provide a parking safety control solution. When the vehicle is in the parked state, the traffic participant information within a preset range of the vehicle is identified. The traffic participant information includes the type of each participant and the distance between the participant and the vehicle. The parking risk of the vehicle is evaluated based on the traffic participant information. The vehicle or the driver can then perform parking control on the vehicle according to the evaluation result, without the driver having to make a temporary judgment on the parking risk, improving the safety of parking and reducing the parking risk. Further, after parking, information interaction between the vehicle and the driver, risk information interaction between the calculation platform and the in-vehicle terminal, sending risk flag bits and risk image information, etc., are pushed to the driver's mobile terminal application through the in-vehicle terminal; realizing control of the electrical components of the vehicle by the mobile terminal, and the driver can perform different types of control on the vehicle through the mobile application to avoid further escalation of the risk hazards.

[0046] To make the objectives, technical solutions, and advantages of the present application clearer, the technical solutions in the embodiments of the present application will be described in more detail below with reference to the accompanying drawings in the embodiments of the present application. In the drawings, the same or similar reference numerals denote the same or similar components or components with the same or similar functions throughout. The described embodiments are some, but not all, of the embodiments of the present application. The embodiments described below with reference to the drawings are exemplary and are intended to explain the present application and should not be construed as limiting the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of the present application.

[0047] Figure 1 A possible scenario diagram provided for the embodiments of the present application is applied to the autonomous driving scenario. In some embodiments, it can also be applied to other non-autonomous driving scenarios. As Figure 1 shown, it includes: an autonomous driving domain controller 110, an in-vehicle terminal 120, a body controller 130, and a user terminal 140, where,

[0048] The Automated Driving Control Unit (referred to as CU) is an intelligent computing platform for L3 / L4 level driverless applications. It can integrate computationally intensive sensor data processing and sensor fusion with control strategy development into one control unit, and helps to establish a structured and organized vehicle controller network. In this embodiment, the automated driving domain controller receives in-vehicle video input signals, performs image processing based on the in-vehicle video input signals, uses the perception algorithm of the perception neural network to identify image information, performs risk assessment and image caching on the identified image information, etc., and transmits the processed information (assessment information and caching information) to the in-vehicle terminal. The in-vehicle terminal receives the information from the automated driving domain controller and interacts with the user terminal and the body controller respectively to complete parking control.

[0049] The in-vehicle terminal (Transmission Control Unit, TCU) is the front-end device of the vehicle monitoring and management system, and can also be called the vehicle dispatching and monitoring terminal.

[0050] The Body Control Module (referred to as BCM), also known as the body computer, refers to the electronic control unit used to control the vehicle body electrical system in automotive engineering. It is one of the important components of the vehicle. Its common functions include controlling electric windows, electric mirrors, air conditioners, headlights, turn signals, anti-theft locking systems, central locking, defrosting devices, etc. The body controller can be connected to other in-vehicle electronic control units (Electronic Control Unit, referred to as ECU) through a bus.

[0051] The user terminal may include but is not limited to computers, smartphones, tablets, e-book readers, Moving Picture experts group audio layer III (MP3) players, Moving Picture experts group audio layer IV (MP4) players, portable computers, in-vehicle computers, wearable devices, desktop computers, set-top boxes, smart TVs, and so on.

[0052] The above briefly described the scenario schematic diagram of the present application. Next, taking the automated driving domain controller 110 applied to Figure 1 as an example, the parking safety control method provided by the embodiment of the present application will be described in detail.

[0053] Please refer to Figure 2 , Figure 2The flowchart shows a parking safety control method provided by an embodiment of the present application. The method includes step S201 and step S202.

[0054] Step S201: If the vehicle is in a parked state, identify traffic participant information within a preset range of the vehicle. The traffic participant information includes the type of each participant and its distance from the vehicle.

[0055] Among them, the traffic participant information may include the type of each participant and its distance from the vehicle. The type of participants may include motor vehicles, non-motor vehicles, and pedestrians, etc. Further, various vehicle types are defined, such as sedans, SUVs, vans, police cars, ambulances, sanitation vehicles, light trucks, heavy trucks, etc.; pedestrian types are defined, such as adults, children, traffic police, security personnel, etc.; non-motor vehicle types are defined, such as bicycles, electric bicycles, motorcycles, etc.

[0056] In this embodiment, when the vehicle is in a parked state, the type of traffic participants near the vehicle and their distances from the vehicle are identified and output, and the parking risk of the vehicle is evaluated based on the type of traffic participants and their distances from the vehicle to evaluate different risk situations in the parked state. Further, in order to improve the recognition accuracy of traffic participant information, the vehicle information (such as video information, image information, etc.) when the vehicle is in a parked state is identified through a perception neural network to obtain traffic participant information. This process is described in detail later.

[0057] In a preferred implementation manner, when the vehicle enters the parked state, the video stream of the vehicle is continuously collected, and the traffic participant information of the vehicle is identified based on the video stream to improve the recognition accuracy. Specifically, the step of identifying the traffic participant information within a preset range of the vehicle (step S201) includes the following steps:

[0058] Obtain the video stream within a preset range of the vehicle, which is collected after the vehicle enters the parked state;

[0059] Obtain the corresponding image based on the video stream and preprocess the image;

[0060] Identify the traffic participant information within a preset range of the vehicle based on the preprocessed image.

[0061] In this embodiment, a video stream is collected by an on-vehicle camera for autonomous driving. Specifically, when the vehicle is parked and the driver enables the monitoring function, the camera continuously operates and transmits the video stream to the autonomous driving domain controller for video acquisition and image processing. Here, the camera can be one or more. The autonomous driving domain controller preprocesses the video streams input by each camera, processes the images into formats such as RGB and YUV, and performs image filtering to obtain preprocessed images.

[0062] It should be noted that those skilled in the art can adaptively set the preset range in combination with actual applications. For example, the preset range can be enlarged or reduced according to the vehicle parking position, environment, and vehicle size. For example, if the parking position is in a parking lot, a small-range video stream of the parking area can be collected, while for a parking position on a traffic road, a larger video collection range is set, that is, the preset range is enlarged.

[0063] In a more preferred technical solution of this embodiment, the preprocessed image is input into a perception neural network for deep learning to obtain the types of traffic participants and their distances, so as to improve the recognition accuracy. Specifically, the recognition of traffic participant information of the vehicle within the preset range based on the preprocessed image includes the following steps:

[0064] Input the preprocessed image into the perception neural network, where the perception neural network includes a participant type perception module and a distance perception module;

[0065] Based on the participant type perception module, perform first deep learning on the preprocessed image to obtain the types of participants of the vehicle within the preset range;

[0066] Based on the distance perception module, perform second deep learning on the preprocessed image to obtain the distances between the participants of the vehicle within the preset range and the vehicle.

[0067] It can be understood that the perception neural network (Perception Neural Networks, abbreviated as PNN), also known as the perception neural network model, is an existing network model, and the specific structure of the perception neural network will not be elaborated in this embodiment.

[0068] In this embodiment, a neural network is used to perform deep learning training on the preprocessed image by using the perception algorithm parameters. Different from the prior art, in order to accurately obtain traffic participant information in this embodiment, the participant type and the distance between the participant and the vehicle are trained separately. That is, the perception neural network model is divided into two parts, which is equivalent to that the perception neural network model includes two training models. Their neural network structures can be the same, but the training parameters are different. One part is used to train the participant type, and the other part is used to train the distance between the participant and the vehicle. The separate training method can obtain more accurate traffic participant information.

[0069] Step S202: Evaluate the parking risk of the vehicle based on the traffic participant information to obtain an evaluation result, and the evaluation result is used to instruct the vehicle to perform parking control.

[0070] Compared with the prior art, directly sending the vehicle's safety monitoring situation to the driver and having the driver make a temporary parking risk judgment results in low parking control efficiency and a relatively high parking risk in different risk situations. In this embodiment, the parking risk of the vehicle is evaluated based on the traffic participant information, and the vehicle or the driver can perform corresponding parking control in combination with the evaluation result to effectively improve the parking control efficiency and reduce the parking risk.

[0071] Please refer to Figure 3 , Figure 3 FIG. is a schematic flowchart of another parking safety control method provided by an embodiment of the present application. On the basis of the above embodiment, in this embodiment, the defined types of traffic participants are obtained, and the parking risk of the vehicle is further evaluated according to which defined type the identified participant type corresponds to, so as to further improve the safe parking efficiency and reduce the parking risk. Specifically, this embodiment further includes step S301, and step S202 is further divided into step S202a and step S202b.

[0072] Step S301: Obtain several defined types of traffic participants, and the several defined types include a first type and a second type.

[0073] In one implementation manner, the several defined types are preset by the autonomous driving domain controller before the initial state (not entering the parking state). Among them, those skilled in the art can adaptively set the first type and the second type in combination with the actual application and the prior art. For example, the first type is a motor vehicle type, and the second type is a pedestrian type; in other implementation manners, they can also be received from other devices, and the first type and the second type can also be divided in other ways.

[0074] Step S202a: If the type of the participant is the first type and the distance from the vehicle is less than the first preset threshold, the parking risk of the vehicle is evaluated as the first level, and the first level is used to indicate that the vehicle changes its parking state.

[0075] Step S202b: If the type of the participant is the second type and the distance from the vehicle is less than the second preset threshold, the parking risk of the vehicle is evaluated as the second level, and the second level is used to indicate that the vehicle sounds a horn for warning.

[0076] It should be noted that those skilled in the art can adaptively set the first preset threshold and the second preset threshold in combination with actual applications. Among them, changing the parking state, for example, starting the vehicle, starting the vehicle and driving to a designated location, etc. In some embodiments, more defined types and more levels can also be divided, and this embodiment does not make special limitations in this regard. For example, it also includes a third type, a non-motor vehicle type, and a third level for indicating turning on the warning light, etc.

[0077] In this embodiment, corresponding risk levels are evaluated for different traffic participant information, and corresponding parking control means are carried out for the corresponding risk levels, which can not only improve the efficiency of parking safety control, but also further reduce the parking risk to a certain extent.

[0078] In a preferred technical solution, in this embodiment, cache information is generated in the autonomous driving domain controller, and the cache information and the evaluation result are mapped. When the evaluation result is transmitted to the user terminal, the user terminal can retrieve the corresponding cache information according to the mapping relationship, and further perform parking control on the vehicle according to the evaluation result and the cache information to reduce the parking risk. Specifically, after the step of extracting the video stream of the vehicle within the preset range, the following steps are further included:

[0079] Generate cache information, where the cache information is obtained based on the video stream.

[0080] In this embodiment, the cache information is convenient for the driver to view on the user terminal when performing parking control. The driver can use the cache information as reference information to assist parking control, or as the basis for viewing information after parking control. Among them, the acquisition process of the cache information can be to cache the video information of each camera and perform format conversion to convert it into a video format that can be transmitted through the in-vehicle terminal.

[0081] In one implementation, the generation of cache information is obtained after identifying traffic participant information. The video area corresponding to the risk information flag bit of the traffic participant identified in the video stream is used as the cache information, and other video information of the risk information flag bit can be deleted to avoid excessive cache pressure on the remote driving and the controller. In some embodiments, the cache information within 10s (the time can be configured) can be transmitted to the driver's mobile phone through the vehicle-mounted terminal, and the video file can be archived.

[0082] In one implementation manner, after obtaining the evaluation result, by transmitting the evaluation result to the vehicle-mounted terminal and the user terminal, the remote driver can perform parking control on the vehicle based on the evaluation result, which can further reduce the parking risk. Specifically, after obtaining the evaluation result, the following steps are further included:

[0083] Transmit the evaluation result to the vehicle-mounted terminal, so that the vehicle-mounted terminal transmits the evaluation result to the user terminal, and the user terminal performs parking control on the vehicle based on the evaluation result.

[0084] In this embodiment, the vehicle-mounted terminal undertakes the function of transmitting information between the vehicle and the driver. The vehicle information is pushed to the driver through the vehicle-mounted terminal, and the driver's commands are sent to the vehicle for execution through the vehicle-mounted terminal. The vehicle-mounted terminal communicates with the high-computing power platform and the body controller through in-vehicle wiring, and communicates with the driver's mobile phone through the network.

[0085] In one implementable manner, the driver holds the user terminal, generally a mobile phone and the vehicle control application software. For example, the parking monitoring function will develop a vehicle parking monitoring function module based on the vehicle control application software, which is responsible for receiving the risk information pushed from the vehicle and the function of issuing the driver risk control command. The user terminal can receive the risk prompt information carrying the evaluation result sent by the vehicle-mounted terminal, which can be in-vehicle voice prompts or in-vehicle video information, etc. For example, it can call the driver through the application and prompt the risk category, such as vehicle scratching risk, vehicle theft risk, vehicle non-compliance with traffic rules risk, etc.; or, it will provide the driver with several control options for handling risks, such as turning on the hazard warning lights, sounding the horn, making a voice call, starting the vehicle, starting the vehicle and driving to a designated location, etc., to avoid damage to the vehicle property.

[0086] In one implementation manner, after obtaining the evaluation result, it further includes:

[0087] Map the cache information and the evaluation result to obtain a mapping relationship;

[0088] Transmit the evaluation result and the cache information to the vehicle-mounted terminal, so that the vehicle terminal transmits the evaluation result to the user terminal, and after the user terminal receives the evaluation result, based on the mapping relationship of the evaluation result, retrieve the corresponding cache information, and perform parking control on the vehicle based on the evaluation result and the cache information.

[0089] In this embodiment, by mapping the cache information and the evaluation result, when the evaluation result is transmitted to the user terminal, the user terminal can retrieve the corresponding cache information according to the mapping relationship. For example, after the driver receives the evaluation result on the user terminal, the corresponding cache information can be retrieved through the application and the image information can be viewed, including the panoramic image of the vehicle, the front camera, and the side camera image information, etc., and then the vehicle is parked according to the evaluation result and the cache information. Control to reduce the risk of parking.

[0090] It can be seen that this embodiment can realize the functions of parking safety monitoring, warning and control of autonomous vehicles. At the same time, after predicting risks, it can notify the driver in the first time and remotely control the vehicle through control instructions to avoid the escalation of risk hazards.

[0091] According to another aspect of the present application, an embodiment of the present application provides a parking safety control device, as Figure 4 shown, the device includes:

[0092] An identification module 41, configured to identify traffic participant information of the vehicle within a preset range when the vehicle is in a parking state, where the traffic participant information includes the type of each participant and its distance from the vehicle;

[0093] A risk assessment module 42, configured to evaluate the parking risk of the vehicle based on the traffic participant information to obtain an evaluation result, where the evaluation result is used to instruct the vehicle to perform parking control.

[0094] In one implementation manner, the identification module 41 includes:

[0095] An acquisition unit, configured to acquire a video stream of the vehicle within a preset range, where the video stream is acquired after the vehicle enters the parking state;

[0096] A preprocessing unit, configured to obtain a corresponding image based on the video stream and preprocess the image;

[0097] An identification unit, configured to identify traffic participant information of the vehicle within a preset range based on the preprocessed image.

[0098] In one embodiment, the recognition unit is specifically configured to input the preprocessed image into a perception neural network, which includes a participant type perception module and a distance perception module; perform first deep learning on the preprocessed image based on the participant type perception module to obtain the types of participants within a preset range of the vehicle; and perform second deep learning on the preprocessed image based on the distance perception module to obtain the distance between the participants within the preset range of the vehicle and the vehicle.

[0099] In one embodiment, the device further includes an acquisition module configured to acquire a plurality of defined types of traffic participants, where the plurality of defined types include a first type and a second type;

[0100] The evaluation module is specifically configured to, if the type of the participant is the first type and the distance from the vehicle is less than a first preset threshold, evaluate the parking risk of the vehicle as a first level, where the first level is used to indicate that the vehicle changes its parking state; if the type of the participant is the second type and the distance from the vehicle is less than a second preset threshold, evaluate the parking risk of the vehicle as a second level, where the second level is used to indicate that the vehicle sounds a horn for warning.

[0101] In one embodiment, the device further includes:

[0102] A generation module configured to generate cache information, where the cache information is obtained based on the video stream.

[0103] In one embodiment, the device further includes:

[0104] A transmission module configured to transmit the evaluation result to an in-vehicle terminal, so that the in-vehicle terminal transmits the evaluation result to a user terminal, and the user terminal performs parking control on the vehicle based on the evaluation result.

[0105] In one embodiment, the device further includes:

[0106] A mapping module configured to map the cache information and the evaluation result to obtain a mapping relationship;

[0107] A transmission module configured to transmit the evaluation result and the cache information to the in-vehicle terminal, so that the vehicle terminal transmits the evaluation result to the user terminal, and the user terminal, after receiving the evaluation result, retrieves the corresponding cache information based on the mapping relationship of the evaluation result, and performs parking control on the vehicle based on the evaluation result and the cache information.

[0108] According to another aspect of the present application, an electronic device is further provided in an embodiment of the present application, such as Figure 5As shown in the figure, it includes: a memory 51 and a processor 52;

[0109] The memory 51 stores computer-executable instructions;

[0110] The processor 52 executes the computer-executable instructions stored in the memory 51, so that the electronic device executes the parking safety control method described above.

[0111] According to another aspect of the present application, an embodiment of the present application further provides a computer-readable storage medium. The computer-executable instructions are stored in the computer-readable storage medium, and when the computer-executable instructions are executed by a processor, they are used to implement the parking safety control method described above.

[0112] Those of ordinary skill in the art can understand that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, and their appropriate combinations. In the hardware implementation, the division of the functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be executed by several physical components in cooperation. Some physical components or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or may be implemented as hardware, or may be implemented as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, and the computer-readable medium may include a computer storage medium (or a non-transitory medium) and a communication medium (or a transitory medium).

[0113] As is well known to those of ordinary skill in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data. Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory, or other memory technologies, CD-ROM, digital versatile disc (DVD), or other optical disc storage, magnetic cassette, tape, magnetic disk storage, or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer.

[0114] In addition, as is well known to those of ordinary skill in the art, a communication medium generally contains computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and may include any information delivery medium.

[0115] In the description of the embodiments of the present application, the term "and / or" merely represents an association relationship describing associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the term "at least one" means any one of a plurality or any combination of at least two of a plurality. For example, including at least one of A and B can represent any one or more elements selected from the set including A, B, and C. Furthermore, the meaning of the term "a plurality" is two or more, unless otherwise specifically and precisely defined.

[0116] In the description of the embodiments of the present application, the terms "first", "second", "third", "fourth", etc. (if any) are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0117] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not intended to 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 described in the foregoing embodiments, or perform equivalent replacements for some or all of the technical features. However, such modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A parking safety control method, characterized in that, Including: If the vehicle is in a parked state, identify traffic participant information within a preset range of the vehicle. The traffic participant information includes the type of each participant and its distance from the vehicle, and the preset range is dynamically adjusted; Evaluate the parking risk of the vehicle based on the traffic participant information to obtain an evaluation result, and the evaluation result is used to instruct the vehicle to perform parking control; The identifying traffic participant information within a preset range of the vehicle includes: Obtain a video stream within a preset range of the vehicle, where the video stream is collected after the vehicle enters the parked state; Obtain a corresponding image based on the video stream and preprocess the image. Among them, the preprocessing is to perform image filtering after converting the format of the image; Identify traffic participant information within a preset range of the vehicle based on the preprocessed image; After obtaining the video stream within a preset range of the vehicle, it further includes: Generate cache information based on the video stream; and, After obtaining the evaluation result, it further includes: Map the cache information and the evaluation result to obtain a mapping relationship.

2. The method according to claim 1, characterized in that, The identifying traffic participant information within a preset range of the vehicle based on the preprocessed image includes: Input the preprocessed image into a perception neural network, where the perception neural network includes a participant type perception module and a distance perception module; Perform first deep learning on the preprocessed image based on the participant type perception module to obtain the type of participants within a preset range of the vehicle; Perform second deep learning on the preprocessed image based on the distance perception module to obtain the distance between the participants within a preset range of the vehicle and the vehicle.

3. The method according to claim 1, wherein It further includes: Obtain several defined types of traffic participants, where the several defined types include a first type and a second type; The evaluating the parking risk of the vehicle based on the traffic participant information includes: If the type of the participant is the first type and the distance from the vehicle is less than a first preset threshold, evaluate the parking risk of the vehicle as a first level, and the first level is used to instruct the vehicle to change the parking state; If the type of the participant is the second type and the distance from the vehicle is less than a second preset threshold, evaluate the parking risk of the vehicle as a second level, and the second level is used to instruct the vehicle to sound a horn for warning.

4. The method according to claim 1, characterized in that, After obtaining the evaluation result, it further includes: Transmit the evaluation result to an in-vehicle terminal, so that the in-vehicle terminal transmits the evaluation result to a user terminal, and the user terminal performs parking control on the vehicle based on the evaluation result.

5. The method according to claim 1, wherein After obtaining the mapping relationship, it further includes: Transmit the evaluation result and the cache information to an in-vehicle terminal, so that the in-vehicle terminal transmits the evaluation result to a user terminal, and the user terminal, after receiving the evaluation result, retrieves the corresponding cache information based on the mapping relationship of the evaluation result, and performs parking control on the vehicle based on the evaluation result and the cache information.

6. A parking safety control device, characterized in that, Including: An identification module, configured to identify traffic participant information within a preset range of the vehicle when the vehicle is in a parked state, where the traffic participant information includes the type of each participant and its distance from the vehicle, and the preset range is dynamically adjusted; A risk assessment module, configured to assess the parking risk of the vehicle based on the traffic participant information to obtain an assessment result, and the assessment result is used to instruct the vehicle to perform parking control; The identification module includes: An acquisition unit, configured to acquire a video stream within a preset range of the vehicle, where the video stream is collected after the vehicle enters the parked state; A preprocessing unit, configured to obtain a corresponding image based on the video stream and perform preprocessing on the image, where the preprocessing is to perform image filtering after format conversion of the image; An identification unit, configured to identify traffic participant information within a preset range of the vehicle based on the preprocessed image; A generation module, configured to generate cache information based on the video stream; A mapping module, configured to map the cache information and the assessment result to obtain a mapping relationship.

7. An electronic device, characterized in that, It includes: A memory and a processor; The memory stores computer execution instructions; The processor executes the computer execution instructions stored in the memory, so that the electronic device executes the parking safety control method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, Computer execution instructions are stored in the computer-readable storage medium, and when the computer execution instructions are executed by the processor, they are used to implement the parking safety control method according to any one of claims 1-5.

Images