A pedestrian warning method and device, a storage medium and an electronic device

Abstract

The application relates to the field of data analysis, in particular to a pedestrian warning method and device, a storage medium and an electronic equipment, which solve the problem that in the prior art, at a road intersection without a traffic light, a pedestrian traffic danger cannot be predicted in advance in combination with the behavior characteristics of the pedestrian. The method comprises the following steps: acquiring eye data, age data and distance information between the pedestrian and a target object of the pedestrian; inputting the eye data, the age data and the distance information into a pre-established judgment model to obtain a standard safety distance; and outputting warning information in the case that the distance information is less than the standard safety distance.

Description

Technical Field

[0001] This application relates to the field of data analysis technology, and in particular to a pedestrian warning method, device, storage medium, and electronic device. Background Technology

[0002] As people become more safety-conscious, they are paying more attention to the safety of themselves and their families. Rapid technological advancements are undoubtedly accelerating the fulfillment of these diverse needs. While traffic lights and police assistance allow us to cross streets more safely, some special scenarios, such as scenic spots, campuses, and residential areas, lack traffic lights. Especially at intersections within these areas, pedestrians can easily cross without noticing oncoming vehicles, posing a safety hazard. Summary of the Invention

[0003] To address the aforementioned issues, this application provides a pedestrian warning method, device, storage medium, and electronic device. By analyzing pedestrian eye data, age data, and distance information between pedestrians and vehicles, a safe distance for pedestrians to cross the road is determined. When the distance between pedestrians and vehicles is less than the safe distance, a warning message can be issued to the pedestrian, providing advance warning of the possibility of danger, reminding pedestrians to pay attention to oncoming vehicles, ensuring pedestrians' safe passage through intersections, and improving traffic safety at intersections within the park.

[0004] Firstly, this application provides a pedestrian warning method, the method comprising:

[0005] Acquire pedestrian eye data, age data, and distance information between pedestrians and target objects;

[0006] The eyeball data, age data, and distance information are input into a pre-established judgment model to obtain the standard safe distance;

[0007] If the distance information is less than the standard safe distance, a warning message is output.

[0008] In some embodiments, the method further includes:

[0009] Determine the magnitude relationship between the distance information and the preset absolute safety distance;

[0010] The step of inputting the eyeball data, age data, and distance information into a pre-established judgment model to obtain the standard safe distance includes:

[0011] When the distance information, which is characterized by the size relationship, is less than the preset absolute safe distance, the eyeball data, age data, and distance information are input into a pre-established judgment model to obtain a standard safe distance.

[0012] In some embodiments, the method further includes:

[0013] Obtain a sample dataset, wherein each sample data in the sample dataset includes: sample eyeball data, sample age data, sample distance information between pedestrians and target objects, and standard distance;

[0014] The initial model is trained based on the sample dataset to obtain the decision model.

[0015] In some embodiments, the sample dataset includes a training set and a test set, and the step of training an initial model based on the sample dataset to obtain the judgment model includes:

[0016] The training set is input into the initial model for training to determine the intermediate model;

[0017] The test set is input into the intermediate model to determine the decision model.

[0018] In some embodiments, including:

[0019] The test set is input into the intermediate model to obtain the predicted standard distance;

[0020] The accuracy of the initial model is determined based on the standard distance and the predicted standard distance.

[0021] If the accuracy is greater than the accuracy threshold, the intermediate model is determined as the judgment model.

[0022] Secondly, this application provides a pedestrian warning device, the device comprising:

[0023] The first acquisition module is used to acquire pedestrian eye data, age data, and distance information between pedestrians and target objects;

[0024] The input module is used to input the eye data, age data and distance information into a pre-established judgment model to obtain a standard safe distance;

[0025] The output module is used to output a warning message when the distance information is less than the standard safe distance.

[0026] In some embodiments, the apparatus further includes:

[0027] The first determining module is used to determine the magnitude relationship between the distance information and the preset absolute safety distance;

[0028] The input module is used to input the eyeball data, age data, and distance information into a pre-established judgment model to obtain a standard safe distance, including:

[0029] When the distance information, which is characterized by the size relationship, is less than the preset absolute safe distance, the eyeball data, age data, and distance information are input into a pre-established judgment model to obtain a standard safe distance.

[0030] In some embodiments, the apparatus further includes:

[0031] The second acquisition module is used to acquire a sample dataset, wherein each sample data in the sample dataset includes: sample eyeball data, sample age data, sample distance information between pedestrians and target objects, and standard distance;

[0032] The second determining module is used to train an initial model based on the sample dataset to obtain the determination model.

[0033] Thirdly, this application provides a storage medium storing a computer program that, when executed by one or more processors, is used to implement the pedestrian warning method described above.

[0034] Fourthly, this application provides an electronic device including a memory and a processor, wherein the memory stores a computer program that, when executed by the processor, performs the pedestrian warning method as described above.

[0035] Compared with the prior art, one or more embodiments of the above solutions may have the following advantages or beneficial effects:

[0036] This application provides a pedestrian warning method, device, storage medium, and electronic device that can issue warning information to pedestrians in advance, predict the possibility of danger, remind pedestrians to pay attention to oncoming vehicles, ensure pedestrians' safe passage across intersections, and improve traffic safety at intersections within the park. Attached Figure Description

[0037] The present application will be described in more detail below based on embodiments and with reference to the accompanying drawings.

[0038] Figure 1 This is a schematic diagram illustrating an application scenario of a pedestrian warning device provided in an embodiment of this application.

[0039] Figure 2 A flowchart illustrating a pedestrian warning method provided in an embodiment of this application;

[0040] Figure 3 This is an exemplary flowchart regarding the operation of the determination model;

[0041] Figure 4 A block diagram of a pedestrian warning device provided in an embodiment of this application.

[0042] In the accompanying drawings, the same parts are referred to by the same reference numerals, and the drawings are not drawn to scale. Detailed Implementation

[0043] The following detailed description of the embodiments of this application, in conjunction with the accompanying drawings, will provide a thorough understanding of how this application uses technical means to solve technical problems and achieve corresponding technical effects, enabling its implementation. The embodiments of this application and the various features within them can be combined with each other without conflict, and all resulting technical solutions are within the protection scope of this application.

[0044] Example 1

[0045] Figure 1 This is a schematic diagram illustrating an application scenario of a pedestrian warning device according to some embodiments of this specification.

[0046] In the embodiments of this application, the application scenario 100 of the pedestrian warning device may include a terminal 110, a server 120, a wearable device 130, a network 140, and a vehicle 150.

[0047] In some embodiments, terminal 110 may refer to one or more terminal devices or software used by a user. In some embodiments, terminal 110 refers to a portable device with input and / or output functions. For example, terminal 110 may include a smartphone 110-1, a desktop computer 110-2, a laptop computer 110-3, and a smart mobile device, or any combination thereof. In some embodiments, a smart mobile device may include a smartphone, a personal digital assistant (PDA), a gaming device, a navigation device, a handheld terminal (POS), or any combination thereof.

[0048] In some embodiments, server 120 may process information and / or data related to wearable device 130 to perform one or more functions described herein. In some embodiments, server 120 may acquire data from wearable device 130 via network 140. In some embodiments, server 120 may include one or more processing engines (e.g., a single-core processing engine or a multi-core processing engine). By way of example only, server 120 may include a central processing unit (CPU), application-specific integrated circuit (ASIC), application-specific instruction set processor (ASIP), graphics processing unit (GPU), physical processing unit (PPU), digital signal processor (DSP), field-programmable gate array (FPGA), programmable logic device (PLD), controller, microcontroller unit, reduced instruction set computer (RISC), microprocessor, etc., or any combination thereof.

[0049] In some embodiments, server 120 may include processing devices. Server 120 may be a single server or a group of servers. The server group may be centralized or distributed (e.g., server 120 may be a distributed system). In some embodiments, server 120 may be local or remote. For example, server 120 may access data stored in wearable device 130 via network 140. In some embodiments, server 120 may be implemented on a cloud platform. By way of example only, the cloud platform may include private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, internal cloud, multi-tiered cloud, etc., or any combination thereof.

[0050] In some embodiments, wearable device 130 refers to a portable device that can be worn by a user. Wearable device 130 can interact with devices such as terminal 110 and server 120 via network 140 for data exchange and cloud interaction. Wearable device 130 may include devices such as smart bracelets, smartwatches, Google Glass, and smart sneakers equipped with infrared sensors, proximity sensors, cameras, etc.

[0051] Network 140 can facilitate the exchange of information and / or data. In some embodiments, one or more components in the application scenario of the pedestrian warning device (e.g., terminal 110, server 120) can transmit information and / or data to other components of the wearable device 130 via network 140. In some embodiments, network 140 can be any form of wired or wireless network, or any combination thereof. By way of example only, network 140 may include cable networks, wired networks, fiber optic networks, telecommunications networks, intranets, the Internet, local area networks (LANs), wide area networks (WANs), wireless local area networks (WLANs), metropolitan area networks (MANs), public switched telephone networks (PSTNs), Bluetooth networks, VPNs, near field communication (NFC) networks, etc., or any combination thereof. In some embodiments, network 140 may include one or more network access points.

[0052] In some embodiments, vehicle 150 may have an equivalent structure capable of movement or flight. For example, vehicle 150 may include the structure of a conventional vehicle, such as a chassis, suspension, steering equipment (e.g., a steering wheel), braking equipment (e.g., a brake pedal), accelerator, etc. As another example, vehicle 150 may have a body and at least one wheel. The body can be any type of vehicle, such as a sports car, sedan, pickup truck, van, SUV, minivan, or motorhome. At least one wheel may be configured to use all-wheel drive (AWD), front-wheel drive (FWR), rear-wheel drive (RWD), etc. In some embodiments, vehicle 150 may be an electric vehicle, fuel cell vehicle, hybrid vehicle, conventional internal combustion engine vehicle, etc. In some embodiments, vehicle 150 may be a low-speed autonomous driving vehicle for a park or scenic area. Autonomous driving vehicles may include autonomous sightseeing vehicles, autonomous cruise vehicles, etc.

[0053] Example 2

[0054] This embodiment provides a pedestrian warning method. Figure 2 This is a schematic diagram of a pedestrian warning method 200 provided in an embodiment of this application. In this embodiment, the following method can be executed by an electronic device. Figure 2 The method includes:

[0055] Step S210: Obtain pedestrian eye data, age data, and distance information between pedestrian and target object.

[0056] In some embodiments, pedestrian eye-tracking data refers to data such as the pedestrian's eye state and viewpoint information. In some embodiments, pedestrian eye data can be acquired through wearable devices. For example, pedestrian eye data can be acquired through devices such as eye trackers or infrared sensors configured in smart glasses.

[0057] Age data refers to a pedestrian's physiological age information. In some embodiments, the user (pedestrian) can input age data through a terminal.

[0058] In this embodiment, the target object can refer to a fast-moving object, such as a car or motorcycle. Figure 1 As shown in the application scenario, the target object can refer to vehicle 150.

[0059] In some embodiments, a wearable device can acquire distance information between a pedestrian and a target object, wherein the distance information may include orientation information and straight-line distance information. For example, the wearable device may be configured with a distance sensor and an infrared sensor, using the distance sensor to acquire the straight-line distance between the pedestrian and the vehicle, such as 15m; and using the infrared sensor to acquire the orientation information between the pedestrian and the vehicle.

[0060] Step S220: Input the eye data, age data and distance information into the pre-established judgment model to obtain the standard safe distance.

[0061] In some embodiments, people of different ages have different movement speeds and reaction speeds. Based on sample eye data of pedestrians, sample age data, and sample distance information between pedestrians and targets, the standard safe distance that people of different ages should maintain from targets can be determined.

[0062] In the embodiments of this application, a decision model can be used to determine the standard safe distance that pedestrians of different ages need to maintain between themselves and objects when crossing the road.

[0063] In some embodiments, the size relationship between the distance information and a preset absolute safety distance can be determined; the step of inputting the eye data, age data and the distance information into a pre-established judgment model to obtain a standard safety distance includes: when the size relationship indicates that the distance information is less than the preset absolute safety distance, inputting the eye data, age data and the distance information into a pre-established judgment model to obtain a standard safety distance.

[0064] Step S230: If the distance information is less than the standard safe distance, output a warning message.

[0065] In some embodiments, when the distance information is less than a standard safe distance, it indicates that if the pedestrian continues to move forward, a collision with the target object may occur, resulting in a safety accident. Therefore, when the distance information is less than a standard safe distance, a warning message is output to the pedestrian's wearable device.

[0066] In some embodiments, a warning message can be a way of alerting pedestrians by signaling danger. The form of the warning message can include audible alerts, vibration alerts, buzzer alarms, etc.

[0067] Example 3

[0068] This embodiment provides a process for determining the operation of the model in a pedestrian warning method. Figure 3 This is an exemplary flowchart regarding the operation of the decision model. In some embodiments, a sample dataset can be obtained, and an initial model can be trained based on the sample dataset to obtain the decision model. The method for obtaining the decision model by training the initial model is described below.

[0069] Step S310: Obtain the sample dataset.

[0070] In some embodiments, the sample dataset may be sample data used to train an initial decision model. In some embodiments, the sample dataset is obtained, and each sample data in the sample dataset includes: sample eyeball data, sample age data, sample distance information between pedestrians and target objects, and standard distance.

[0071] Step S320: Train an initial model based on the sample dataset and determine an intermediate model.

[0072] In some embodiments, the initial model is an initial machine learning model. In some embodiments, the sample dataset may include a training set and a test set. In some embodiments, the training set can be input to the initial model, which can convert sample training eye data, sample training age data, and sample training distance information between pedestrians and targets into input vectors. For example, the training set can be converted into a motion vector set, where k represents the device acquiring different data, i represents people of different ages, represents the position vectors of different body parts n collected by the motion sensor in the wearable device, and represents the distance vectors of different body parts n collected by the infrared sensor in the wearable device.

[0073] In some embodiments, an intermediate model can be trained based on the training set. The intermediate model can be an intermediate state of the decision model.

[0074] Step S330: Input the test set into the intermediate model to obtain the predicted standard distance.

[0075] Using manual screening, standard behavioral distances and non-standard safety distances are defined based on existing safety standards, and the standard distance is labeled S, while the non-standard distance is labeled D.

[0076] In some embodiments, the test set can be input into the intermediate model to obtain the predicted standard distance. The test set may include test eye data, test age data, test distance information between pedestrians and objects, and standard distance labels S and non-standard labels D. The predicted standard distance is obtained based on the intermediate model.

[0077] Step S340: Determine the accuracy of the initial model based on the standard distance and the predicted standard distance.

[0078] In some embodiments, each test set can obtain a corresponding predicted standard distance through the intermediate model. The obtained predicted standard distance is compared with the standard distance; when the difference between the predicted standard distance and the standard distance is within a standard range, the corresponding training result is determined to be accurate. In some embodiments, the ratio of the number of predicted standard distances corresponding to accurate training results obtained in the test set to the total number of obtained predicted standard distances determines the accuracy of the intermediate model operation. In some embodiments, the accuracy value can be freely set, for example, 95%, 98%, etc.

[0079] Step S350: If the accuracy is greater than the accuracy threshold, the intermediate model is determined as the judgment model.

[0080] If the accuracy is greater than the accuracy threshold, the intermediate model is determined as the judgment model.

[0081] In some embodiments, the decision model can be trained using common methods, such as gradient descent. In some embodiments, training ends when the trained machine learning model meets preset conditions. These preset conditions may include the loss function convergence or falling below a preset threshold, or the training cycle reaching a threshold. The machine learning model can be a supervised learning model, an unsupervised learning model, a reinforcement learning model, etc.

[0082] In some embodiments, a trained decision model can determine the standard safe distance between a pedestrian and an object in real time.

[0083] In some embodiments, pedestrian eye data can be obtained through wearable devices, pedestrian age data can be input through a terminal, and distance information between pedestrians and target objects can be obtained through wearable devices.

[0084] In some embodiments, a wearable device can acquire distance information between a pedestrian and a target object, wherein the distance information may include orientation information and straight-line distance information. For example, the wearable device may be configured with a distance sensor and an infrared sensor, using the distance sensor to acquire the straight-line distance between the pedestrian and the vehicle, such as 15m; and using the infrared sensor to acquire the orientation information between the pedestrian and the vehicle.

[0085] In some embodiments, the eye data, age data, and distance information are then input into a pre-established judgment model to obtain a standard safe distance.

[0086] In some embodiments, people of different ages have different movement speeds and reaction speeds. Based on sample eye data of pedestrians, sample age data, and sample distance information between pedestrians and targets, the standard safe distance that people of different ages should maintain from targets can be determined.

[0087] In the embodiments of this application, a decision model can be used to determine the standard safe distance that pedestrians of different ages need to maintain between themselves and objects when crossing the road.

[0088] In some embodiments, the size relationship between the distance information and a preset absolute safety distance can be determined; the step of inputting the eye data, age data and the distance information into a pre-established judgment model to obtain a standard safety distance includes: when the size relationship indicates that the distance information is less than the preset absolute safety distance, inputting the eye data, age data and the distance information into a pre-established judgment model to obtain a standard safety distance.

[0089] In some embodiments, a standard safe distance determined by a decision model is compared with distance information, and a warning message is output if the distance information is less than the standard safe distance.

[0090] In some embodiments, when the distance information is less than a standard safe distance, it indicates that if the pedestrian continues to move forward, a collision with the target object may occur, resulting in a safety accident. Therefore, when the distance information is less than a standard safe distance, a warning message is output to the pedestrian's wearable device.

[0091] In some embodiments, a warning message can be a way of alerting pedestrians by signaling danger. The form of the warning message can include audible alerts, vibration alerts, buzzer alarms, etc.

[0092] Example 4

[0093] This embodiment provides a pedestrian warning device. Figure 4 This is a block diagram of a pedestrian warning device provided in an embodiment of this application. Figure 4 As shown, the block diagram of the pedestrian warning device 400 includes:

[0094] The first acquisition module 410 is used to acquire pedestrian eye data, age data, and distance information between the pedestrian and the target object;

[0095] The input module 420 is used to input the eyeball data, age data and distance information into a pre-established judgment model to obtain a standard safe distance;

[0096] The output module 430 is used to output a warning message when the distance information is less than the standard safe distance.

[0097] In some embodiments, the apparatus further includes:

[0098] The first determining module is used to determine the magnitude relationship between the distance information and the preset absolute safety distance;

[0099] The input module is used to input the eyeball data, age data, and distance information into a pre-established judgment model to obtain a standard safe distance, including: when the distance information, which is characterized by a size relationship, is less than the preset absolute safe distance, inputting the eyeball data, age data, and distance information into a pre-established judgment model to obtain a standard safe distance.

[0100] In some embodiments, the apparatus further includes:

[0101] The second acquisition module is used to acquire a sample dataset, wherein each sample data in the sample dataset includes: sample eyeball data, sample age data, sample distance information between pedestrians and target objects, and standard distance;

[0102] The second determining module is used to train an initial model based on the sample dataset to obtain the determination model.

[0103] Example 5

[0104] This embodiment also provides a computer-readable storage medium, such as flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, server, App application store, etc., which stores a computer program. When the computer program is executed by a processor, it can implement the steps of the method described above.

[0105] For specific implementation details of the above method steps, please refer to the above method implementation details. This implementation will not repeat them here.

[0106] Example 6

[0107] This application provides an electronic device, which may be a mobile phone, computer, or tablet computer, etc., including a memory and a processor. The memory stores a calculator program, which, when executed by the processor, implements the application management method as described in Embodiment 1. It is understood that the electronic device may also include multimedia components, input / output (I / O) interfaces, and communication components.

[0108] The processor is used to execute all or part of the steps in the application management method as described in Embodiment 1. The memory is used to store various types of data, which may include, for example, instructions for any application or method in the electronic device, as well as application-related data.

[0109] The processor may be implemented as an Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), controller, microcontroller, microprocessor, or other electronic components, and is used to execute the application management method in Embodiment 1 above.

[0110] The memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0111] The multimedia component may include a screen, which may be a touchscreen, and an audio component for outputting and / or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in memory or transmitted via a communication component. The audio component also includes at least one speaker for outputting audio signals.

[0112] I / O interfaces provide interfaces between the processor and other interface modules, such as keyboards, mice, and buttons. These buttons can be virtual or physical.

[0113] Communication components are used for wired or wireless communication between the electronic device and other devices. Wireless communication includes, for example, Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or one or more combinations thereof. Therefore, the corresponding communication component may include: a Wi-Fi module, a Bluetooth module, or an NFC module.

[0114] In summary, this application provides a pedestrian warning method, device, storage medium, and electronic device.

[0115] In the several embodiments provided in this application, it should be understood that the disclosed systems and methods can also be implemented in other ways. The system and method embodiments described above are merely illustrative.

[0116] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0117] Although the embodiments disclosed in this application are as described above, the content is merely for the purpose of facilitating understanding of this application and is not intended to limit this application. Any person skilled in the art to which this application pertains may make any modifications and changes in the form and details of the implementation without departing from the spirit and scope disclosed in this application; however, the scope of patent protection of this application shall still be determined by the scope defined in the appended claims.

Claims

1. A pedestrian warning method, characterized in that, The method includes: Acquire pedestrian eye data, age data, and distance information between the pedestrian and the target object; the eye data includes at least the pedestrian's eye state and viewpoint information; the target object is a fast-moving object; The eyeball data, age data, and distance information are input into a pre-established judgment model to obtain the standard safe distance; If the distance information is less than the standard safe distance, a warning message is output.

2. The method according to claim 1, characterized in that, The method further includes: Determine the magnitude relationship between the distance information and the preset absolute safety distance; The step of inputting the eyeball data, age data, and distance information into a pre-established judgment model to obtain the standard safe distance includes: When the distance information, which is characterized by the size relationship, is less than the preset absolute safe distance, the eyeball data, age data, and distance information are input into a pre-established judgment model to obtain a standard safe distance.

3. The method according to claim 1, characterized in that, The method further includes: Obtain a sample dataset, wherein each sample data in the sample dataset includes: sample eyeball data, sample age data, sample distance information between pedestrians and target objects, and standard distance; The initial model is trained based on the sample dataset to obtain the decision model.

4. The method according to claim 3, characterized in that, The sample dataset includes a training set and a test set. Training the initial model based on the sample dataset to obtain the judgment model includes: The training set is input into the initial model for training to determine the intermediate model; The test set is input into the intermediate model to determine the decision model.

5. The method according to claim 4, characterized in that, The step of inputting the test set into the intermediate model to determine the decision model includes: The test set is input into the intermediate model to obtain the predicted standard distance; The accuracy of the initial model is determined based on the standard distance and the predicted standard distance. If the accuracy is greater than the accuracy threshold, the intermediate model is determined as the judgment model.

6. A pedestrian warning device, characterized in that, The device includes: The first acquisition module is used to acquire pedestrian eye data, age data, and distance information between the pedestrian and the target object; the eye data includes at least the pedestrian's eye state and viewpoint information; the target object is a fast-moving object; The input module is used to input the eye data, age data and distance information into a pre-established judgment model to obtain a standard safe distance; The output module is used to output a warning message when the distance information is less than the standard safe distance.

7. The apparatus according to claim 6, characterized in that, The device further includes: The first determining module is used to determine the magnitude relationship between the distance information and the preset absolute safety distance; The input module is used to input the eyeball data, age data, and distance information into a pre-established judgment model to obtain a standard safe distance, including: When the distance information, which is characterized by the size relationship, is less than the preset absolute safe distance, the eyeball data, age data, and distance information are input into a pre-established judgment model to obtain a standard safe distance.

8. The apparatus according to claim 7, characterized in that, The device further includes: The second acquisition module is used to acquire a sample dataset, wherein each sample data in the sample dataset includes: sample eyeball data, sample age data, sample distance information between pedestrians and target objects, and standard distance; The second determining module is used to train an initial model based on the sample dataset to obtain the determination model.

9. A storage medium, characterized in that, The computer program stored in the storage medium, when executed by one or more processors, is used to implement the pedestrian warning method as described in any one of claims 1-5.

10. An electronic device, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program that, when executed by the processor, performs the pedestrian warning method as described in any one of claims 1-5.

Images