Method and system for detecting dangerous behavior of children when the vehicle is traveling at high speed

Abstract

The application provides a child dangerous behavior detection method and system when a vehicle is running at high speed, when the running speed of the vehicle is greater than a set speed threshold, child monitoring data in the vehicle is acquired; according to the acquired child monitoring data in the vehicle, a child dangerous behavior recognition result is obtained; when the child dangerous behavior recognition result is a dangerous action, and the same dangerous action is continuously recognized and exceeds a first set time threshold or exceeds a first set number threshold, alarm information is generated to perform in-vehicle voice alarm, and the alarm information is synchronously sent to an external terminal; the application improves the recognition and alarm accuracy of child dangerous behavior when running at high speed, and improves user experience.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicles, in particular to a method and system for detecting dangerous behavior of children when a vehicle is running at high speed. BACKGROUND

[0002] The statements in this section merely provide background information related to the present application and do not necessarily constitute the prior art.

[0003] Vehicles have become an important part of family life, and driving has become the main way for people to travel, and self-driving has become the first choice for most parents. When the car is running at high speed, children in the car are attracted by the scenery outside the car, and if they stretch their body parts out of the car or play with each other, some accidents will occur, which will cause very serious consequences.

[0004] The inventor found that the existing recognition model often only recognizes the position of children in the car, for example, patent No. CN114475507A discloses a method and device for warning children in the car, electronic equipment and storage medium, which identifies the area where the child is located through image processing, and determines whether the child is safe according to the comparison between the child's location and the preset safe location. However, children in the car have many dangerous actions, and only position recognition cannot accurately identify dangerous behavior. Moreover, the existing method directly identifies the dangerous behavior of children in the car, and does not match the driving speed, so that frequent warnings may occur when the vehicle is stationary, and the user experience is poor. SUMMARY

[0005] In order to solve the problems of the prior art, the present application provides a method and system for detecting dangerous behavior of children when a vehicle is running at high speed. When the vehicle is running at high speed, the dangerous behavior of children in the car is automatically detected, and voice warning and warning information are automatically pushed when dangerous behavior of children is found, thereby improving the user experience.

[0006] In order to achieve the above purpose, the present application adopts the following technical scheme:

[0007] The present application provides a method for detecting dangerous behavior of children when a vehicle is running at high speed.

[0008] A method for detecting dangerous behavior of children when a vehicle is running at high speed, comprising the following processes:

[0009] When the vehicle speed is greater than the set speed threshold, the child monitoring data in the car is obtained;

[0010] According to the obtained child monitoring data in the car, the child dangerous behavior recognition result is obtained;

[0011] When the child dangerous behavior recognition result is a dangerous action, and the same dangerous action is continuously recognized and exceeds a first set time threshold or exceeds a first set number threshold, alarm information is generated for in-vehicle voice alarm, and the alarm information is synchronously sent to the external terminal.

[0012] As optional implementation modes of the first aspect of the present application, the dangerous action at least includes one or more of the following: child body stretching out of the vehicle, child in-vehicle fighting, and child in-vehicle use of a knife.

[0013] As optional implementation modes of the first aspect of the present application, the child monitoring data includes in-vehicle image data, and the child dangerous behavior recognition result is obtained according to the in-vehicle image data and a preset dangerous behavior recognition model.

[0014] As a further limitation of the first aspect of the present application, a face recognition result of the child in the vehicle is generated according to the in-vehicle image data, the child dangerous behavior recognition result is matched with the face recognition result, and then sent to the external terminal or stored in the vehicle-end memory, and a child dangerous behavior habit recognition result is obtained according to matching results obtained during multiple drives.

[0015] As a further limitation of the first aspect of the present application, when multiple children are recognized and each child performs a dangerous action in turn, the dangerous action time of each child is added, and when the added time is greater than a second set time threshold, alarm information is generated for in-vehicle voice alarm, and the alarm information is synchronously sent to the external terminal.

[0016] As a further limitation of the first aspect of the present application, when multiple children are recognized and each child performs a dangerous action in turn, the dangerous action number of each child is added, and when the added number is greater than a second set number threshold, alarm information is generated for in-vehicle voice alarm, and the alarm information is synchronously sent to the external terminal.

[0017] The second aspect of the present application provides a child dangerous behavior detection system during high-speed driving of a vehicle.

[0018] A child dangerous behavior detection system during high-speed driving of a vehicle includes:

[0019] A data acquisition module is configured to acquire child monitoring data in the vehicle when the driving speed of the vehicle is greater than a set speed threshold.

[0020] A dangerous behavior recognition module is configured to obtain a child dangerous behavior recognition result according to the acquired child monitoring data in the vehicle.

[0021] The alarm module is configured to: when the child dangerous behavior recognition result is a dangerous action, and the same dangerous action is continuously recognized and exceeds a first set time threshold or exceeds a first set number threshold, generate alarm information for in-vehicle voice alarm, and synchronously send the alarm information to an external terminal.

[0022] The third aspect of the present application provides a child dangerous behavior detection system when a vehicle is running at high speed.

[0023] The child dangerous behavior detection system when a vehicle is running at high speed comprises:

[0024] An in-vehicle image shooting unit, a dangerous behavior recognition unit, a voice alarm unit, a vehicle-mounted communication unit, and a vehicle networking background;

[0025] The in-vehicle image shooting unit and the voice alarm unit respectively communicate with the dangerous behavior recognition unit, the dangerous behavior recognition unit communicates with the vehicle networking background through the vehicle-mounted communication unit, and the vehicle networking background is used for communicating with an external terminal.

[0026] The dangerous behavior recognition unit is used for executing the child dangerous behavior detection method when a vehicle is running at high speed as described in the first aspect of the present application.

[0027] The fourth aspect of the present application provides a computer readable storage medium, which stores a program, and the program is executed by a processor to realize the steps in the child dangerous behavior detection method when a vehicle is running at high speed as described in the first aspect of the present application.

[0028] The fifth aspect of the present application provides an electronic device, which comprises a memory, a processor, and a program stored in the memory and executable on the processor, and the processor executes the program to realize the steps in the child dangerous behavior detection method when a vehicle is running at high speed as described in the first aspect of the present application.

[0029] Compared with the prior art, the present application has the following beneficial effects:

[0030] 1、The present application innovatively proposes a child dangerous behavior detection method and system when a vehicle is running at high speed, which automatically detects dangerous behaviors of children in the vehicle when the vehicle is running at high speed, automatically performs voice alarm and alarm information pushing when dangerous behaviors of children are found, and improves user experience.

[0031] 2、The present application innovatively proposes a child dangerous behavior detection method and system when a vehicle is running at high speed, which combines an in-vehicle image shooting unit, a dangerous behavior recognition unit, a voice alarm unit, a vehicle-mounted communication unit, and a vehicle networking background, and avoids some driving accidents caused by dangerous behaviors of children in the vehicle.

[0032] 3. The vehicle high-speed driving child dangerous behavior detection method and system innovatively provided by the application can superimpose the dangerous behavior time or the dangerous action times of multiple children, further improve the recognition and alarm accuracy of the child dangerous behavior during high-speed driving, and improve the user experience. BRIEF DESCRIPTION OF DRAWINGS

[0033] The accompanying drawings, which form a part of this specification, are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification. The embodiments of these drawings are set to explain the application, and do not constitute an improper limitation on the application.

[0034] Figure 1 A flowchart of the vehicle high-speed driving child dangerous behavior detection method provided for the embodiment 1 of the application is shown in the figure;

[0035] Figure 2 A structure diagram of the vehicle high-speed driving child dangerous behavior detection system provided for the embodiment 2 of the application is shown in the figure;

[0036] Figure 3 A principle diagram of the vehicle high-speed driving child dangerous behavior detection system provided for the embodiment 3 of the application is shown in the figure Figure 1 ;

[0037] Figure 4 A principle diagram of the vehicle high-speed driving child dangerous behavior detection system provided for the embodiment 3 of the application is shown in the figure Figure 2 ;

[0038] Figure 5 A principle diagram of the vehicle high-speed driving child dangerous behavior detection system provided for the embodiment 3 of the application is shown in the figure Figure 3 . DETAILED DESCRIPTION

[0039] The application will be further described below in conjunction with the drawings and embodiments.

[0040] It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the application. Unless otherwise indicated, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the application pertains.

[0041] It should be noted that the terms used herein are only for the purpose of describing specific embodiments, and are not intended to limit the exemplary embodiments according to the application. As used herein, unless the context clearly indicates otherwise, the singular form is intended to include the plural form, and in addition, it should be understood that when the terms "comprise" and / or "include" are used in the specification, they indicate the presence of a feature, step, operation, device, component and / or combination thereof.

[0042] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0043] Example 1:

[0044] like Figure 1 As shown, Embodiment 1 of the present invention provides a method for detecting dangerous behaviors of children when a vehicle is traveling at high speed. This improves the intelligence of the vehicle. When the car is traveling at high speed (speed > 60 km / h, where the speed can be freely set, either by the vehicle manufacturer or by the driver and passengers), the method detects the behavior of children inside the car in real time and uses a dangerous behavior detection system to detect dangerous behaviors such as children sticking their bodies out of the car, children playing or roughhousing inside the car, and children using knives inside the car. This enhances the customer experience. When a child is detected engaging in continuous dangerous behavior (such as sticking their body out of the car, playing or roughhousing inside the car, or using knives inside the car), a voice reminder can be given: "A dangerous behavior has been detected in the car (such as children sticking their bodies out of the car, children playing or roughhousing inside the car, or children using knives inside the car). Please be careful!" This enhances the technological feel of car manufacturing by automatically detecting and reminding about dangerous behaviors inside the car, and can also provide voice reminders to children. This improves driving safety by using voice reminders to stop dangerous behaviors of children inside the car, thus preventing unnecessary traffic accidents caused by dangerous behaviors of children at high speeds.

[0045] Specifically, it includes the following processes:

[0046] When the vehicle speed exceeds a set speed threshold, data on children inside the vehicle is acquired.

[0047] Based on the acquired in-vehicle child monitoring data, the results of identifying dangerous behaviors of children were obtained;

[0048] When a child’s dangerous behavior is identified as a dangerous action, and the same dangerous action is identified continuously for more than a first set time threshold (which can be set to 1 minute, but those skilled in the art can choose according to the specific working conditions, such as 30 seconds, 10 seconds, etc., which will not be elaborated here) or more than a first set number threshold (e.g., 4 times), an alarm message is generated to provide an in-vehicle voice alarm, and the alarm message is sent to an external terminal simultaneously.

[0049] In this embodiment, optional dangerous actions include at least one or more of the following: a child extending their body outside the vehicle, playing roughly inside the vehicle, and using a knife inside the vehicle. It is understood that in some other embodiments, dangerous actions also include standing on the seat, punching the window, jumping inside the vehicle, etc. Those skilled in the art can choose according to the specific working conditions, which will not be elaborated here.

[0050] In this embodiment, the child monitoring data includes in-vehicle image data, and a child dangerous behavior recognition result is obtained according to the in-vehicle image data and a preset dangerous behavior recognition model. It can be understood that the dangerous behavior recognition model herein is trained by various preset dangerous actions.

[0051] It can be understood that the child recognition herein can be performed in a face recognition manner, that is, whether the current person is a child is determined through face recognition, or the weight of the occupant is automatically recognized through a pressure sensor arranged on the seat, and whether the person is a child is determined according to the weight recognition result, or the above two manners are combined to determine and recognize. The skilled in the art can select according to the specific working conditions, which will not be described here.

[0052] For example, when it is recognized that child A is performing a knife-holding action, continuous recognition is performed, it is determined that the knife-holding action time of child A is 70 seconds, which is greater than the first set time threshold of 1 minute, and alarm information is generated at this time. Or, when it is recognized that child A is performing a knife-holding action, continuous recognition is performed, it is determined that the number of knife-holding actions of child A is 5 times, which is greater than the first set number threshold of 4 times, and alarm information is generated at this time.

[0053] In this embodiment, a face recognition result of the child in the vehicle is generated according to the in-vehicle image data, the child dangerous behavior recognition result and the face recognition result are matched, and then sent to an external terminal or stored in a memory at the vehicle end. According to the matching results obtained during multiple driving, a child dangerous behavior habit recognition result is obtained.

[0054] In this embodiment, when multiple children are recognized and each child performs a dangerous action in turn, the dangerous action time of each child is added, and when the added time is greater than a second set time threshold (which can be set to 90 seconds), alarm information is generated for in-vehicle voice alarm, and the alarm information is synchronously sent to an external terminal.

[0055] For example, when it is recognized that child A is performing a knife-holding action, continuous recognition is performed, it is determined that the knife-holding action time of child A is 60 seconds, and it is again recognized that child B is performing a knife-holding action, continuous recognition is again performed, it is determined that the knife-holding action time of child B is 40 seconds, and the total knife-holding time of child A and child B is 100 seconds, which is greater than the second set time threshold (90 seconds), and alarm information is generated at this time.

[0056] Alternatively, for example, when it is identified that child A is performing the action of punching in play, continuous identification is performed, it is determined that the punching action of child A lasts for 10 seconds, and it is again identified that child B is performing the punching action, continuous identification is again performed, it is determined that the punching action of child B lasts for 10 seconds, and continuous identification is continued until the punching action is not identified for both child A and child B, and it is obtained that the total punching time of child A and child B is 120 seconds, which is greater than the second set time threshold (90 seconds), and alarm information is generated at this time;

[0057] Alternatively, for example, when it is identified that child A is performing the action of sticking his head out of the window, continuous identification is performed, it is determined that the action of child A of sticking his head out of the window lasts for 70 seconds, and it is again identified that child B is performing the action of sticking his head out of the window, continuous identification is again performed, it is determined that the action of child B of sticking his head out of the window lasts for 80 seconds, and continuous identification is continued until the action of sticking his head out of the window is not identified for both child A and child B, and it is obtained that the total action of child A and child B of sticking his head out of the window is 150 seconds, which is greater than the second set time threshold (90 seconds), and alarm information is generated at this time.

[0058] Optionally, when multiple children are identified, and each child performs a dangerous action in turn, the number of dangerous actions of each child is added, and when the added number is greater than the second set number threshold (4 times are optionally used here), alarm information is generated to perform in-vehicle voice alarm, and the alarm information is synchronously sent to the external terminal

[0059] For example, when it is identified that child A is performing the action of holding a knife, continuous identification is performed, it is determined that the number of actions of child A of holding a knife is 3 times, and it is again identified that child B is performing the action of holding a knife, continuous identification is again performed, it is determined that the number of actions of child B of holding a knife is 2 times, and the total number of actions of holding a knife of child A and child B is 5 times, which is greater than the second set number threshold (4 times), and alarm information is generated at this time.

[0060] Alternatively, for example, when it is identified that child A is performing the action of punching in play, continuous identification is performed, it is determined that the number of actions of child A of punching is 3 times, and it is again identified that child B is performing the action of punching, continuous identification is again performed, it is determined that the number of actions of child B of punching is 3 times, and continuous identification is continued until the action of punching is not identified for both child A and child B, and it is obtained that the total number of actions of child A and child B of punching is 6 times, which is greater than the second set number threshold (90 seconds), and alarm information is generated at this time.

[0061] Alternatively, for example, when child A is detected sticking their head out of the window, continuous detection is performed, and it is determined that child A has stuck their head out of the window 3 times. At the same time, child B is detected sticking their head out of the window, and continuous detection is performed again, determining that child B has stuck their head out of the window 3 times. This continuous detection continues until no more children A or B are detected sticking their heads out of the window. When the total number of times children A and B have stuck their heads out of the window is 3, which is greater than the second set threshold (90 seconds), an alarm message is generated.

[0062] Example 2:

[0063] like Figure 2 As shown, Embodiment 2 of the present invention provides a child dangerous behavior detection system when a vehicle is traveling at high speed, comprising:

[0064] The data acquisition module is configured to acquire in-vehicle child monitoring data when the vehicle speed exceeds a set speed threshold.

[0065] The dangerous behavior recognition module is configured to: obtain the result of recognizing dangerous behaviors of children based on the acquired in-vehicle child monitoring data;

[0066] The alarm module is configured to generate an alarm message to provide in-vehicle voice alarm when the child's dangerous behavior is identified as a dangerous action, and the same dangerous action is continuously identified and exceeds a first set time threshold or a first set number of times threshold, and the alarm message is synchronously sent to an external terminal.

[0067] The alarm module specifically includes:

[0068] When child A is detected holding a knife, continuous identification is performed. If the duration of child A's knife-holding action is determined to be 70 seconds, which is greater than a first set time threshold of 1 minute, an alarm message is generated. Alternatively, when child A is detected holding a knife, continuous identification is performed. If the number of times child A holds the knife is determined to be 5, which is greater than a first set number threshold of 4, an alarm message is generated.

[0069] In this embodiment, the facial recognition result of the child in the vehicle is generated based on the in-vehicle image data. The child's dangerous behavior recognition result is matched with the facial recognition result and then sent to an external terminal or stored in the vehicle's memory. Based on the matching results obtained from multiple driving sessions, the child's dangerous behavior habit recognition result is obtained.

[0070] In this embodiment, when multiple children are identified and each child performs a dangerous action in turn, the dangerous action time of each child is added, and when the added time is greater than the second set time threshold (which can be set to 90 seconds here), an alarm information is generated for in-vehicle voice alarm, and the alarm information is synchronously sent to the external terminal.

[0071] For example, when it is identified that child A is performing a knife-holding action, continuous identification is performed, and it is determined that the knife-holding action time of child A is 60 seconds. At the same time, it is identified again that child B is performing a knife-holding action, and continuous identification is performed again, and it is determined that the knife-holding action time of child B is 40 seconds. The total knife-holding time of child A and child B is 100 seconds, which is greater than the second set time threshold (90 seconds). At this time, the alarm information is generated.

[0072] Alternatively, for example, when it is identified that child A is performing a punching action for fighting, continuous identification is performed, and it is determined that the punching action time of child A is 10 seconds. At the same time, it is identified again that child B is performing a punching action, and continuous identification is performed again, and it is determined that the punching action time of child B is 10 seconds. Continuous identification is continued until neither child A nor child B can be identified to perform a punching action, and the total punching time of child A and child B is 120 seconds, which is greater than the second set time threshold (90 seconds). At this time, the alarm information is generated.

[0073] Alternatively, for example, when it is identified that child A is performing a head-outside-window action, continuous identification is performed, and it is determined that the head-outside-window time of child A is 70 seconds. At the same time, it is identified again that child B is performing a head-outside-window action, and continuous identification is performed again, and it is determined that the head-outside-window time of child B is 80 seconds. Continuous identification is continued until neither child A nor child B can be identified to perform a head-outside-window action, and the total head-outside-window time of child A and child B is 150 seconds, which is greater than the second set time threshold (90 seconds). At this time, the alarm information is generated.

[0074] Alternatively, when multiple children are identified and each child performs a dangerous action in turn, the dangerous action times of each child are added, and when the added times are greater than the second set time threshold (which can be selected to be 4 times), the alarm information is generated for in-vehicle voice alarm, and the alarm information is synchronously sent to the external terminal.

[0075] For example, when it is identified that child A is performing a knife-holding action, continuous identification is performed, and it is determined that the knife-holding action time of child A is 60 seconds. At the same time, it is identified again that child B is performing a knife-holding action, and continuous identification is performed again, and it is determined that the knife-holding action time of child B is 40 seconds. The total knife-holding time of child A and child B is 100 seconds, which is greater than the second set time threshold (90 seconds). At this time, the alarm information is generated.

[0076] Or, for example, when it is identified that child A is performing a playful punching action, continuous identification is performed, it is determined that the number of punching actions of child A is 3 times, and it is identified again that child B is performing a punching action, continuous identification is performed again, it is determined that the number of punching actions of child B is 3 times, and continuous identification is continued until child A and child B cannot identify a punching action, and it is obtained that the total number of punching actions of child A and child B is 6 times, which is greater than the second set number threshold (90 seconds), at which time the alarm information is generated;

[0077] Or, for example, when it is identified that child A is performing a head sticking out of the window action, continuous identification is performed, it is determined that the number of head sticking out of the window actions of child A is 3 times, and it is identified again that child B is performing a head sticking out of the window action, continuous identification is performed again, it is determined that the number of head sticking out of the window actions of child B is 3 times, and continuous identification is continued until child A and child B cannot identify a head sticking out of the window action, and it is obtained that the number of sticking out of the window actions of child A and child B is 3 times, which is greater than the second set number threshold (90 seconds), at which time the alarm information is generated.

[0078] Embodiment 3:

[0079] As shown in Figure 3 , Figure 4 and Figure 5 , the embodiment 3 of the present application provides a child dangerous behavior detection system when a vehicle is running at high speed, which comprises:

[0080] a smart mobile terminal device (APP) or a sound host 1, a vehicle networking background 2, a vehicle communication module 3 (i.e. a vehicle communication unit), a CAN bus 4, an in-vehicle image and child behavior detection system 5 (i.e. an in-vehicle image shooting unit), a dangerous behavior detection system 6 (i.e. a dangerous behavior recognition unit) and a voice reminding alarm system 7 (i.e. a voice alarm unit);

[0081] The in-vehicle image and child behavior detection system 5 and the voice reminding alarm system 7 respectively communicate with the in-vehicle image and child behavior detection system 5, the in-vehicle image and child behavior detection system 5 communicates with the vehicle networking background 2 through the vehicle communication module 3, and the vehicle networking background is used for communicating with the smart mobile terminal device (APP) or the sound host 1 (i.e. an external terminal).

[0082] The in-vehicle image and child behavior detection system 5 is used for performing the child dangerous behavior detection method when a vehicle is running at high speed as described in the embodiment 1 of the present application.

[0083] Optionally, a working method example is provided, which comprises:

[0084] S1: The user downloads and installs the APP application developed by the vehicle enterprise on the intelligent terminal, sets the contact account that needs to receive information reminders in the APP application or the sound host 1 software, and uploads it to the vehicle networking background 2 through the network or through the remote communication module after the setting is completed. The vehicle networking background 2 stores the personnel information that needs to be reminded;

[0085] S2: When the vehicle enters the high-speed driving state (vehicle speed > 60km / h), the in-vehicle image and child behavior detection system 5 starts to detect the behavior mode of the personnel in the vehicle;

[0086] S3: The in-vehicle image and child behavior detection system will transmit the collected data to the dangerous behavior detection system 6, which will analyze, detect and judge in real time whether the passengers in the vehicle have dangerous behaviors (children's bodies stretching out of the vehicle, children's fighting in the vehicle, children's use of knives in the vehicle, etc.) based on the received data;

[0087] S4: If it is found that the child in the vehicle has dangerous behavior, the system will continue to detect, and when the dangerous behavior of the child in the vehicle continues for more than one minute, the vehicle detection module will send a dangerous behavior signal to the voice reminder alarm system 7, and at the same time transmit the alarm information to the vehicle communication module;

[0088] S5: After receiving the instruction, the voice reminder alarm system 7 will activate the reminder alarm voice, and the vehicle voice will broadcast "dangerous behavior of children in the vehicle is detected (children's bodies stretching out of the vehicle, children's fighting in the vehicle, children's use of knives in the vehicle, etc.), please pay attention to safety!" and repeat 3 times.

[0089] S6: After receiving the information that the child in the vehicle has dangerous behavior for a long time in the high-speed driving state, the vehicle communication module 3 can report the detected child dangerous behavior information to the vehicle networking background 2 in real time, and update the related information in the APP application 1;

[0090] S7: After receiving the information sent by the vehicle communication unit 3, the vehicle networking background 2 records the information in real time, and after recording that the passengers in the vehicle have dangerous behavior, the vehicle networking background 2 immediately sends an alarm information to the set contact person; through a series of alarm reminding behaviors, the purpose of reminding the child in the vehicle to pay attention to safety is achieved, and the occurrence of accidents is reduced.

[0091] Optionally, the vehicle of the present application can be a new energy vehicle, a car, an SUV, an MPV, a commercial vehicle, etc., and the vehicle needs to be equipped with a product containing a communication module;

[0092] The vehicle-mounted communication module 3 is a communication module with 2G / 3G / 4G, and the product has the ability of network communication and vehicle internal network exchange; the intelligent mobile terminal device (APP) or the sound host 1 is a device bearing the required APP application and the specific wireless communication ability; the dangerous behavior detection system 6 can detect the continuous dangerous behavior of children in the vehicle in real time when the vehicle is running at high speed; the voice reminding alarm system 7 has the ability of voice broadcast reminding and warning the dangerous behavior of children; the Internet of vehicles background 2 is the Internet of vehicles service platform of the enterprise; and the APP is a software application for users.

[0093] Embodiment 4:

[0094] Embodiment 4 of the present application provides a computer readable storage medium, which stores a program, and the program is executed by a processor to realize the steps in the child dangerous behavior detection method when a vehicle is running at high speed according to Embodiment 1 of the present application.

[0095] Embodiment 5:

[0096] Embodiment 5 of the present application provides an electronic device, which includes a memory, a processor, and a program stored in the memory and executable on the processor, and the processor executes the program to realize the steps in the child dangerous behavior detection method when a vehicle is running at high speed according to Embodiment 1 of the present application.

[0097] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0098] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system), and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the computer or other programmable data processing devices produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The device that implements the functions specified in one flow or multiple flows and / or blocks. Figure 1 The device that implements the functions specified in one flow or multiple flows and / or blocks.

[0099] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the flow Figure 1 of the flow or flows and / or blocks Figure 1 of the block or blocks specified in the flow.

[0100] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions that are executed on the computer or other programmable apparatus provide steps for implementing the flow Figure 1 of the flow or flows and / or blocks Figure 1 of the block or blocks specified in the flow.

[0101] Those of ordinary skill in the art can understand that all or part of the flow of the above-mentioned embodiment method can be completed by a computer program instructing relevant hardware, and the program can be stored in a computer readable storage medium. When the program is executed, it can include the flow of the above-mentioned embodiment method. The storage medium can be a magnetic disc, an optical disc, a read-only memory (ROM), a random access memory (RAM), or the like.

[0102] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. Those of ordinary skill in the art can make various changes and modifications to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for detecting a child dangerous behavior when a vehicle is traveling at a high speed, characterized by, The method comprises the following steps: obtaining child monitoring data in the vehicle when the vehicle driving speed is greater than a set speed threshold; the child monitoring data comprises in-vehicle image data, and a child dangerous behavior recognition result is obtained according to the in-vehicle image data and a preset dangerous behavior recognition model; a face recognition result of the child in the vehicle is generated according to the in-vehicle image data, the child dangerous behavior recognition result is matched with the face recognition result, and then the matched result is sent to an external terminal or stored in a memory at the vehicle end; the child dangerous behavior habit recognition result is obtained according to the matching result obtained during multiple driving times; when the child dangerous behavior recognition result is a dangerous action, and the same dangerous action is continuously recognized and exceeds a first set time threshold or exceeds a first set number threshold, an alarm information is generated to perform in-vehicle voice alarm, and the alarm information is synchronously sent to the external terminal; when multiple children are recognized, and each child performs a dangerous action in turn, the dangerous action time or the dangerous action number of each child is added, and when the added time or the added number is greater than a second set time threshold, an alarm information is generated to perform in-vehicle voice alarm, and the alarm information is synchronously sent to the external terminal.

2. The child dangerous behavior detection method when the vehicle is driving at high speed according to claim 1, wherein the dangerous action at least comprises one or more of the following: the child's body stretching out of the vehicle, the child's fighting in the vehicle, and the child's using a knife in the vehicle. The method comprises the following steps:

3. A child dangerous behavior detection system for a vehicle traveling at a high speed, employing the child dangerous behavior detection method for a vehicle traveling at a high speed according to any one of claims 1 to 2, characterized by a data acquisition module configured to obtain child monitoring data in the vehicle when the vehicle driving speed is greater than a set speed threshold; a dangerous behavior recognition module configured to obtain a child dangerous behavior recognition result according to the obtained child monitoring data in the vehicle; an alarm module configured to generate an alarm information to perform in-vehicle voice alarm when the child dangerous behavior recognition result is a dangerous action, and the same dangerous action is continuously recognized and exceeds a first set time threshold or exceeds a first set number threshold, and synchronously send the alarm information to an external terminal; when multiple children are recognized, and each child performs a dangerous action in turn, the dangerous action time or the dangerous action number of each child is added, and when the added time or the added number is greater than a second set time threshold, an alarm information is generated to perform in-vehicle voice alarm, and the alarm information is synchronously sent to the external terminal. The method comprises the following steps:

4. A child dangerous behavior detection system for a vehicle traveling at a high speed, characterized by an in-vehicle image shooting unit, a dangerous behavior recognition unit, a voice alarm unit, a vehicle-mounted communication unit, and a vehicle networking background; the in-vehicle image shooting unit and the voice alarm unit are in communication with the dangerous behavior recognition unit, the dangerous behavior recognition unit is in communication with the vehicle networking background through the vehicle-mounted communication unit, and the vehicle networking background is used for communication with an external terminal; wherein the dangerous behavior recognition unit is used to execute the child dangerous behavior detection method when the vehicle is driving at high speed according to any one of claims 1-2. The program is executed by the processor to implement the steps in the child dangerous behavior detection method when the vehicle is driving at high speed according to any one of claims 1-2.

5. A computer-readable storage medium having stored thereon a program, characterized in that, The processor executes the program to implement the steps in the child dangerous behavior detection method when the vehicle is driving at high speed according to any one of claims 1-2.

6. An electronic device comprising a memory, a processor, and a program stored in the memory and executable on the processor, characterized by ​

Images