Vehicle-mounted attendance checking method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a vehicle-mounted attendance checking method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring first image data; determining whether a target face exists in the first image data according to a pre-stored personnel information base; under the condition that the target face exists in the first image data, judging whether the acquisition time of the first image data is within a first preset time period or not; under the condition that the acquisition time of the first image data is within a first preset time period, determining that a target person corresponding to the target face is on the vehicle; under the condition that the vehicle arrives at the preset position, if the staying time of the target person on the vehicle exceeds the preset value, the left person of the target person is determined, in the embodiment of the invention, whether the target person gets on the vehicle on time or not is judged, and whether the target person gets off the vehicle at the preset position or not is judged, so that whether the left person is on the vehicle or not is judged; therefore, missing persons in the vehicle can be monitored, and dangers can be avoided.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a vehicle-mounted attendance method, device, electronic device and storage medium. Background Art

[0002] The enclosed space of a vehicle can provide a safe and comfortable environment for the vehicle, but when the vehicle is parked in a high temperature environment, the enclosed space will increase the temperature inside the vehicle and the content of volatile toxic gases in the vehicle will also increase. Therefore, how to monitor the missing persons inside the vehicle has become an urgent problem to be solved. Summary of the invention

[0003] Some embodiments of the present application aim to provide a vehicle-mounted attendance method, device, electronic device and storage medium. Through the technical solution of the embodiments of the present application, first image data is obtained; according to a pre-stored personnel information database, it is determined whether a target face exists in the first image data; if the target face exists in the first image data, it is determined whether the acquisition time of the first image data is within a first preset time period; if the acquisition time of the first image data is within the first preset time period, it is determined that a target person corresponding to the target face is on the vehicle; when the vehicle arrives at a preset position, if the target person stays on the vehicle for more than a preset value, it is determined whether the target person is left behind. In the embodiments of the present application, it is determined whether the target person gets on the vehicle on time and whether he gets off the vehicle at the preset position, thereby determining whether there are left behind in the vehicle. In this way, the monitoring of missed persons in the vehicle is achieved to avoid danger.

[0004] In a first aspect, some embodiments of the present application provide a vehicle-mounted attendance method, including:

[0005] Acquiring first image data;

[0006] Determining whether a target face exists in the first image data according to a pre-stored personnel information database;

[0007] In the case where the target face exists in the first image data, determining whether the acquisition time of the first image data is within a first preset time period;

[0008] When the acquisition time of the first image data is within the first preset time period, determining that a target person corresponding to the target face is on a vehicle;

[0009] When the vehicle arrives at the preset position, if the target person stays on the vehicle for longer than a preset value, the left-behind persons of the target person are determined.

[0010] Some embodiments of the present application determine whether there are any left-behind persons in the vehicle by judging whether the target person gets on the vehicle on time and whether he gets off the vehicle at a preset location. In this way, it is possible to monitor the missing persons in the vehicle and avoid danger.

[0011] Optionally, when the vehicle arrives at a preset location, if the target person stays on the vehicle for a time longer than a preset value, determining that the target person is a left-behind person includes:

[0012] acquiring second image data every second preset time period;

[0013] Determining whether a target face exists in the second image data according to a pre-stored personnel information database;

[0014] If the target face exists in the second image data and the stay time on the vehicle exceeds a preset value, it is determined that the target person corresponding to the target face is a left-behind person.

[0015] Some embodiments of the present application collect image data at regular intervals, and determine whether there is a target in the image data, and then determine whether the target person gets off the vehicle, so as to avoid left-behind persons.

[0016] Optionally, determining whether a target face exists in the first image data according to a pre-stored personnel information database includes:

[0017] Recognize the face in the first image data according to a pre-trained face recognition model to obtain feature information of the face in the first image data; wherein the pre-trained face recognition model is obtained by training a neural network model using sample data;

[0018] Comparing the feature information of the face in the first image data with the preset feature information in the pre-stored personnel information database; the pre-stored personnel information database at least includes a personnel identification and preset feature information corresponding to the personnel identification;

[0019] If the feature information of the face in the first image data matches the set feature information, it is determined that the target face exists in the first image data.

[0020] Some embodiments of the present application train a neural network model to obtain a face recognition model, and then use the face recognition model to recognize faces in image data to improve the accuracy of face recognition.

[0021] Optionally, when the target face exists in the first image data, determining whether the acquisition time of the first image data is within a first preset time period includes:

[0022] If the acquisition time of the first image data is within the first preset time period, it is determined that the attendance of the target person is successful;

[0023] If the acquisition time of the first image data is not within the first preset time period, it is determined that the attendance of the target person is unsuccessful, and attendance failure information is generated.

[0024] In some embodiments of the present application, it is determined whether the attendance is successful by determining whether the acquisition time of the first image data is within a first preset time period, that is, determining whether the acquisition time of the first image data is within the attendance time period.

[0025] Optionally, when the vehicle arrives at a preset location, if the target person stays on the vehicle for a time longer than a preset value, determining the person left behind by the target person includes:

[0026] Obtaining location information of the vehicle;

[0027] Determining whether the vehicle is in a stopped operation state according to the location information of the vehicle;

[0028] When the vehicle is in a stopped operating state, determining whether the target person's stay time on the vehicle exceeds a preset value;

[0029] If the target person's stay time on the vehicle exceeds a preset value, the left-behind persons of the target person are determined.

[0030] In some embodiments of the present application, when the vehicle is in a stopped operating state and a preset time is reached, it is determined whether the target person has stayed on the vehicle for longer than a preset value, and then it is determined whether the target person is a left-behind person, thereby improving the accuracy of left-behind person detection.

[0031] Optionally, the method further comprises:

[0032] Determining whether the vehicle is located on a preset driving track according to the location information of the vehicle;

[0033] If the vehicle is not on the preset driving trajectory, a first alarm signal is triggered.

[0034] Some embodiments of the present application determine the position of the vehicle and issue an alarm if it deviates from a preset driving trajectory.

[0035] Optionally, the method further comprises:

[0036] identifying the dangerous behavior of the target person according to the image data;

[0037] When it is determined that the target person has the dangerous behavior, a second alarm signal is triggered.

[0038] Some embodiments of the present application monitor dangerous behaviors on the vehicle, and issue an alarm when dangerous behaviors occur, thereby improving the safety of vehicle driving.

[0039] In a second aspect, some embodiments of the present application provide a vehicle-mounted attendance device, including:

[0040] An acquisition module, used for acquiring first image data;

[0041] A first determination module, used to determine whether a target face exists in the first image data according to a pre-stored personnel information database;

[0042] A judgment module, used for judging whether the acquisition time of the first image data is within a first preset time period when the target face exists in the first image data;

[0043] A second determination module is used to determine that a target person corresponding to the target face is on a vehicle when the acquisition time of the first image data is within the first preset time period;

[0044] The third determination module is used to determine the persons left behind by the target person when the vehicle arrives at the preset position and the target person's stay time on the vehicle exceeds a preset value.

[0045] Some embodiments of the present application determine whether there are any left-behind persons in the vehicle by judging whether the target person gets on the vehicle on time and whether he gets off the vehicle at a preset location. In this way, it is possible to monitor the missing persons in the vehicle and avoid danger.

[0046] Optionally, the third determining module is used to:

[0047] acquiring second image data every second preset time period;

[0048] Determining whether a target face exists in the second image data according to a pre-stored personnel information database;

[0049] If the target face exists in the second image data and the stay time on the vehicle exceeds a preset value, it is determined that the target person corresponding to the target face is a left-behind person.

[0050] Some embodiments of the present application collect image data at regular intervals, and determine whether there is a target in the image data, and then determine whether the target person gets off the vehicle, so as to avoid people being left behind.

[0051] Optionally, the first determining module is used to:

[0052] Recognize the face in the first image data according to a pre-trained face recognition model to obtain feature information of the face in the first image data; wherein the pre-trained face recognition model is obtained by training a neural network model using sample data;

[0053] Comparing the feature information of the face in the first image data with the preset feature information in the pre-stored personnel information database; the pre-stored personnel information database at least includes a personnel identification and preset feature information corresponding to the personnel identification;

[0054] If the feature information of the face in the first image data matches the set feature information, it is determined that the target face exists in the first image data.

[0055] Some embodiments of the present application train a neural network model to obtain a face recognition model, and then use the face recognition model to recognize faces in image data to improve the accuracy of face recognition.

[0056] Optionally, the judging module is used to:

[0057] If the acquisition time of the first image data is within the first preset time period, it is determined that the attendance of the target person is successful;

[0058] If the acquisition time of the first image data is not within the first preset time period, it is determined that the attendance of the target person is unsuccessful, and attendance failure information is generated.

[0059] In some embodiments of the present application, it is determined whether the attendance is successful by determining whether the acquisition time of the first image data is within a first preset time period, that is, determining whether the acquisition time of the first image data is within the attendance time period.

[0060] Optionally, the third determining module is used to:

[0061] Obtaining location information of the vehicle;

[0062] Determining whether the vehicle is in a stopped operation state according to the location information of the vehicle;

[0063] When the vehicle is in a stopped operating state, determining whether the target person's stay time on the vehicle exceeds a preset value;

[0064] If the target person's stay time on the vehicle exceeds a preset value, the left-behind persons of the target person are determined.

[0065] In some embodiments of the present application, when the vehicle is in a stopped operating state and a preset time is reached, it is determined whether the target person has stayed on the vehicle for longer than a preset value, and then it is determined whether the target person is a left-behind person, thereby improving the accuracy of left-behind person detection.

[0066] Optionally, the third determining module is used to:

[0067] Determining whether the vehicle is located on a preset driving track according to the location information of the vehicle;

[0068] If the vehicle is not on the preset driving trajectory, a first alarm signal is triggered.

[0069] Some embodiments of the present application determine the position of the vehicle and issue an alarm if it deviates from a preset driving trajectory.

[0070] Optionally, the third determining module is used to:

[0071] identifying the dangerous behavior of the target person according to the image data;

[0072] When it is determined that the target person has the dangerous behavior, a second alarm signal is triggered.

[0073] Some embodiments of the present application monitor dangerous behaviors on the vehicle, and issue an alarm when dangerous behaviors occur, thereby improving the safety of vehicle driving.

[0074] In a third aspect, some embodiments of the present application provide an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the program, the in-vehicle attendance method as described in any embodiment of the first aspect can be implemented.

[0075] In a fourth aspect, some embodiments of the present application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, can implement the in-vehicle attendance method as described in any embodiment of the first aspect.

[0076] In a fifth aspect, some embodiments of the present application provide a computer program product, comprising a computer program, wherein the computer program, when executed by a processor, can implement the in-vehicle attendance method as described in any embodiment of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] In order to more clearly illustrate the technical solutions of some embodiments of the present application, the drawings required for use in some embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0078] Figure 1 A flowchart of a vehicle attendance method provided in an embodiment of the present application;

[0079] Figure 2 A flowchart of another vehicle attendance method provided in an embodiment of the present application;

[0080] Figure 3 A schematic diagram of the structure of a vehicle-mounted attendance device provided in an embodiment of the present application;

[0081] Figure 4 A schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0082] The technical solutions in some embodiments of the present application will be described below in conjunction with the drawings in some embodiments of the present application.

[0083] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0084] The enclosed vehicle space can provide a safe and comfortable environment for the vehicle, but when the vehicle is parked in a high temperature environment, the enclosed space will increase the temperature inside the vehicle, and the content of volatile toxic gases in the vehicle will also increase. Therefore, how to realize the monitoring of missed personnel inside the vehicle has become an urgent problem to be solved. In view of this, some embodiments of the present application provide a vehicle attendance method, which obtains first image data; determines whether there is a target face in the first image data according to a pre-stored personnel information library; if there is a target face in the first image data, determines whether the acquisition time of the first image data is within a first preset time period; if the acquisition time of the first image data is within the first preset time period, determines that the target person corresponding to the target face is on the vehicle; when the vehicle arrives at the preset position, if the target person stays on the vehicle for more than a preset value, determines the target person left behind. In the embodiment of the present application, by judging whether the target person gets on the vehicle on time, and by judging whether he gets off at the preset position, it is determined whether there are left behind in the vehicle, so that the monitoring of missed personnel inside the vehicle is realized to avoid danger.

[0085] like Figure 1 As shown, an embodiment of the present application provides a vehicle-mounted attendance method, the method comprising:

[0086] S101, acquiring first image data;

[0087] Specifically, an image acquisition device and a terminal device are installed at a preset position of the vehicle. The image acquisition device can be an RGB camera or a combination of an RGB camera and an infrared camera. The image acquisition device is used to acquire first image data and transmit the first image data to the terminal device, thereby obtaining a facial image, which can reduce the time that target users spend queuing for attendance when commuting.

[0088] S102, determining whether a target face exists in the first image data according to a pre-stored personnel information database;

[0089] Specifically, a personnel information database is pre-stored on the terminal device, which includes personnel identification and corresponding feature information. A pre-trained face recognition model is used to identify the face in the collected first image data, and then compared with the pre-stored personnel information database to determine whether there is a target face in the first image data.

[0090] S103: if the target face exists in the first image data, determining whether the acquisition time of the first image data is within a first preset time period;

[0091] The first preset time period is the attendance time range.

[0092] S104, when the acquisition time of the first image data is in the first preset time period, determining that the target person corresponding to the target face is on the vehicle;

[0093] S105. When the vehicle arrives at the preset location, if the target person stays on the vehicle for a time longer than a preset value, determine the person left behind by the target person.

[0094] Specifically, in the embodiment of the present application, based on the image acquisition device, the facial information of the target user is collected; based on the facial information and the attendance time range, it is determined whether the target user has successfully completed attendance; based on the attendance information, it is determined whether there is a target user missing in the vehicle. Compared with the related art, the embodiment of the present application obtains the facial information of the target user through a preset image acquisition device set inside the vehicle, and completes the attendance management through a preset algorithm; after the vehicle stops operating, the vehicle is inspected to determine whether there is a target user missing. The embodiment of the present application can effectively avoid the occurrence of safety accidents caused by the target user missing in the vehicle by using the attendance equipment inside the vehicle to detect whether there is a target user missing in the vehicle.

[0095] Some embodiments of the present application determine whether there are any left-behind persons in the vehicle by judging whether the target person gets on the vehicle on time and whether he gets off the vehicle at a preset location. In this way, it is possible to monitor the missing persons in the vehicle and avoid danger.

[0096] Another embodiment of the present application further supplements the vehicle-mounted attendance method provided in the above embodiment.

[0097] Optionally, when the vehicle arrives at the preset location, if the target person stays on the vehicle for a time exceeding a preset value, determining that the target person is a left-behind person includes:

[0098] acquiring second image data every second preset time period;

[0099] Determining whether a target face exists in the second image data according to a pre-stored personnel information database;

[0100] If the target face exists in the second image data and the stay time on the vehicle exceeds a preset value, it is determined that the target person corresponding to the target face is a left-behind person.

[0101] Specifically, the attendance information is the attendance information generated after the target user completes the attendance. After the target user completes the commuting, it is determined according to the attendance information whether all the target users who have completed the attendance have gotten off the bus.

[0102] The embodiment of the present application uses an image acquisition device to collect image information to determine whether a target user is missing in the vehicle. However, due to the occlusion of the seats in the vehicle, it may lead to the erroneous recognition that no person is missing in the vehicle; therefore, attendance information is used to further determine whether a target user is missing in the vehicle.

[0103] Some embodiments of the present application collect image data at regular intervals, and determine whether there is a target in the image data, and then determine whether the target person gets off the vehicle, so as to avoid left-behind persons.

[0104] Optionally, determining whether a target face exists in the first image data according to a pre-stored personnel information database includes:

[0105] According to a pre-trained face recognition model, a face in the first image data is recognized to obtain feature information of the face in the first image data; wherein the pre-trained face recognition model is obtained by training a neural network model using sample data;

[0106] Comparing the feature information of the face in the first image data with the preset feature information in a pre-stored personnel information database; the pre-stored personnel information database at least includes a personnel identification and preset feature information corresponding to the personnel identification;

[0107] If the feature information of the face in the first image data matches the preset feature information, it is determined that the target face exists in the first image data.

[0108] The embodiment of the present application obtains preset facial information (i.e. preset feature information) of the target user; based on the preset facial information, the registered information database is established. The preset facial information is pre-acquired image information for comparison during attendance check; the preset facial information can be image information acquired using a preset image acquisition device when attendance is checked for the first time, or it can be image information of the target user uploaded to a server platform or a local database backend.

[0109] The registered information database is an information database pre-registered according to the facial information of the target user. The preset facial information is used to establish an identity identifier and uploaded to the server platform or the local database background.

[0110] Some embodiments of the present application train a neural network model to obtain a face recognition model, and then use the face recognition model to recognize faces in image data to improve the accuracy of face recognition.

[0111] Optionally, when the target face exists in the first image data, determining whether the acquisition time of the first image data is within a first preset time period includes:

[0112] If the acquisition time of the first image data is within the first preset time period, it is determined that the attendance of the target person is successful;

[0113] If the acquisition time of the first image data is not within the first preset time period, it is determined that the attendance of the target person is unsuccessful, and attendance failure information is generated.

[0114] Specifically, after the preset algorithm performs identity authentication, the attendance of the target user is determined based on the result of the identity authentication and the preset attendance time threshold. The preset attendance time threshold can be a certain time point or a certain time period, and also includes threshold information such as the minimum working hours.

[0115] In case of unsuccessful identity verification, the target user is reminded to take a new photo to re-perform the identity verification process.

[0116] When the identity authentication is successful, the attendance of the target user is determined according to the preset attendance time threshold. For example, when the target user clocks in for off-duty work, the time of attendance is less than the preset attendance time threshold when clocking in for work; it can be considered that the target user has left early.

[0117] When it is determined that a target user is left behind in the vehicle, passenger missing information is generated, and the passenger missing information is promptly transmitted to the staff or guardian, thereby avoiding the occurrence of safety accidents caused by missing a target user in the vehicle.

[0118] In some embodiments of the present application, it is determined whether the attendance is successful by determining whether the acquisition time of the first image data is within a first preset time period, that is, determining whether the acquisition time of the first image data is within the attendance time period.

[0119] Optionally, when the vehicle arrives at the preset location, if the target person stays on the vehicle for a time longer than a preset value, determining the person left behind by the target person includes:

[0120] Get the vehicle's location information;

[0121] According to the location information of the vehicle, determine whether the vehicle is in a stopped operation state;

[0122] When the vehicle is in a stopped operating state, determining whether the target person's stay time on the vehicle exceeds a preset value;

[0123] If the target person stays in the vehicle for longer than a preset time, the target person's remaining persons are determined.

[0124] Specifically, in the embodiment of the present application, based on the preset positioning device, it is determined whether the vehicle has stopped operating; when it is determined that the vehicle has stopped operating, it is determined whether a target user is missing in the vehicle based on the preset image acquisition device and the attendance information; if it is determined that the target user is missing in the vehicle, passenger missing information is generated.

[0125] In some embodiments of the present application, when the vehicle is in a stopped operating state and a preset time is reached, it is determined whether the target person has stayed on the vehicle for longer than a preset value, and then it is determined whether the target person is a left-behind person, thereby improving the accuracy of left-behind person detection.

[0126] Optionally, the method further comprises:

[0127] According to the location information of the vehicle, determine whether the vehicle is located on a preset driving track;

[0128] If the vehicle is not on the preset driving trajectory, the first alarm signal is triggered.

[0129] Specifically, the embodiment of the present application obtains the real-time position of the vehicle based on a preset positioning device; determines whether the driving trajectory of the vehicle exceeds the preset driving trajectory; and triggers a first alarm signal when it exceeds the preset driving range.

[0130] Some embodiments of the present application determine the position of the vehicle and issue an alarm if it deviates from a preset driving trajectory.

[0131] Optionally, the method further comprises:

[0132] Identify the target person’s dangerous behavior based on image data;

[0133] When it is determined that the target person has dangerous behavior, a second alarm signal is triggered.

[0134] Specifically, the embodiment of the present application monitors the dangerous behavior of the target user based on the preset image acquisition device; after determining that the target user has performed a dangerous behavior, a second alarm signal is triggered. The open and closed state of the vehicle's door lock is obtained, and whether there is human activity in the vehicle is monitored through the preset image acquisition device. The behavior information of the target user after getting on the vehicle is obtained through the preset image acquisition device; the dangerous behavior of the target user is monitored through the dangerous behavior monitoring algorithm. Exemplarily, the target user is monitored for falling or other dangerous behaviors. After determining that the target user has performed a dangerous behavior, the second alarm signal is triggered. The second alarm signal can be prompted by the vehicle's alarm device. The second preset alarm signal can be a voice signal, or a vibration prompt or other signal, such as an alarm light, a speaker, etc.

[0135] Some embodiments of the present application monitor dangerous behaviors on the vehicle, and issue an alarm when dangerous behaviors occur, thereby improving the safety of vehicle driving.

[0136] Based on the preset gas monitoring module, the concentration of the preset gas inside the vehicle is monitored;

[0137] When the concentration of the preset gas exceeds a preset threshold, a third alarm signal is triggered.

[0138] Specifically, the enclosed space in the vehicle cannot exchange gas with the outside world; in order to reduce the harm of toxic gases to target users in the vehicle, a preset gas monitoring module is set inside the vehicle's attendance machine to achieve real-time monitoring of the gas inside the vehicle, which can be achieved by but not limited to the following methods: Based on the preset gas monitoring module, the concentration of the preset gas inside the vehicle is monitored; when the concentration of the preset gas exceeds a preset threshold, a third alarm signal is triggered.

[0139] Specifically, plastic parts and other accessories in the vehicle will volatilize some toxic gases under natural conditions, especially after the vehicle has been exposed to the sun, the content of toxic gases in the vehicle will be higher. By setting a preset gas monitoring module inside the attendance device, the content of toxic gases in the vehicle is monitored. If the concentration of toxic gases is detected to exceed the preset threshold, the third alarm signal is triggered. The preset gas can be, for example, carbon dioxide, or toxic gases such as formaldehyde that volatilize in the vehicle, which is not limited in this application. The third alarm signal can be a voice signal, or a vibration prompt or other signal, which is not limited in this disclosure.

[0140] In the embodiment of the present application, the target person may be a student, and the attendance method is applied to a school bus. The driving track of a school bus is generally a fixed route. The driving track of the school bus is sent to the cloud and further sent to the mobile phones and other devices of each parent. After the user fails the test, the attendance failure information is sent to the cloud. The omission of the target person in the vehicle is likely to cause a safety accident. Through the preset positioning device, it is determined whether the vehicle has stopped operating; after determining that the vehicle has stopped operating, the target user of the vehicle is checked to see if he is missing in the vehicle, which can avoid the occurrence of more safety accidents. When the target user gets off the bus, the facial information of the target person is collected by the preset image acquisition device, and compared with the attendance information to determine whether the target person has gotten off the bus.

[0141] It should be noted that each implementable method in this embodiment may be implemented separately, or may be implemented in combination in any combination without conflict, and this application is not limited thereto.

[0142] Another embodiment of the present application provides a vehicle-mounted attendance device for executing the vehicle-mounted attendance method provided in the above embodiment.

[0143] like Figure 3 The structure diagram of the vehicle attendance device provided in the embodiment of the present application is shown in FIG. The vehicle attendance device includes an acquisition module 301, a first determination module 302, a judgment module 303, a second determination module 304 and a third determination module 305, wherein:

[0144] The acquisition module 301 is used to acquire first image data;

[0145] The first determination module 302 is used to determine whether a target face exists in the first image data according to a pre-stored personnel information database;

[0146] The judgment module 303 is used to judge whether the acquisition time of the first image data is within a first preset time period when the target face exists in the first image data;

[0147] The second determination module 304 is used to determine that the target person corresponding to the target face is on the vehicle when the acquisition time of the first image data is in the first preset time period;

[0148] The third determining module 305 is used to determine the persons left behind by the target person when the vehicle arrives at the preset location and the target person's stay time on the vehicle exceeds a preset value.

[0149] Regarding the device in this embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0150] Some embodiments of the present application determine whether there are any left-behind persons in the vehicle by judging whether the target person gets on the vehicle on time and whether he gets off the vehicle at a preset location. In this way, it is possible to monitor the missing persons in the vehicle and avoid danger.

[0151] Another embodiment of the present application further supplements the vehicle-mounted attendance device provided in the above embodiment.

[0152] Optionally, the third determining module is used to:

[0153] acquiring second image data every second preset time period;

[0154] Determining whether a target face exists in the second image data according to a pre-stored personnel information database;

[0155] If the target face exists in the second image data and the stay time on the vehicle exceeds a preset value, it is determined that the target person corresponding to the target face is a left-behind person.

[0156] Some embodiments of the present application collect image data at regular intervals, and determine whether there is a target in the image data, and then determine whether the target person gets off the vehicle, so as to avoid people being left behind.

[0157] Optionally, the first determining module is used to:

[0158] According to a pre-trained face recognition model, a face in the first image data is recognized to obtain feature information of the face in the first image data; wherein the pre-trained face recognition model is obtained by training a neural network model using sample data;

[0159] Comparing the feature information of the face in the first image data with the preset feature information in a pre-stored personnel information database; the pre-stored personnel information database at least includes a personnel identification and preset feature information corresponding to the personnel identification;

[0160] If the feature information of the face in the first image data matches the set feature information, it is determined that the target face exists in the first image data.

[0161] Some embodiments of the present application train a neural network model to obtain a face recognition model, and then use the face recognition model to recognize faces in image data to improve the accuracy of face recognition.

[0162] Optionally, the judging module is used to:

[0163] If the acquisition time of the first image data is within the first preset time period, it is determined that the attendance of the target person is successful;

[0164] If the acquisition time of the first image data is not within the first preset time period, it is determined that the attendance of the target person is unsuccessful, and attendance failure information is generated.

[0165] In some embodiments of the present application, it is determined whether the attendance is successful by determining whether the acquisition time of the first image data is within a first preset time period, that is, determining whether the acquisition time of the first image data is within the attendance time period.

[0166] Optionally, the third determining module is used to:

[0167] Get the vehicle's location information;

[0168] According to the location information of the vehicle, determine whether the vehicle is in a stopped operation state;

[0169] When the vehicle is in a stopped operating state, determining whether the target person's stay time on the vehicle exceeds a preset value;

[0170] If the target person stays in the vehicle for longer than a preset time, the target person's remaining persons are determined.

[0171] In some embodiments of the present application, when the vehicle is in a stopped operating state and a preset time is reached, it is determined whether the target person has stayed on the vehicle for longer than a preset value, and then it is determined whether the target person is a left-behind person, thereby improving the accuracy of left-behind person detection.

[0172] Optionally, the third determining module is used to:

[0173] According to the location information of the vehicle, determine whether the vehicle is located on a preset driving track;

[0174] If the vehicle is not on the preset driving trajectory, the first alarm signal is triggered.

[0175] Some embodiments of the present application determine the position of the vehicle and issue an alarm if it deviates from a preset driving trajectory.

[0176] Optionally, the third determining module is used to:

[0177] Identify the target person’s dangerous behavior based on image data;

[0178] When it is determined that the target person has dangerous behavior, a second alarm signal is triggered.

[0179] Some embodiments of the present application monitor dangerous behaviors on the vehicle, and issue an alarm when dangerous behaviors occur, thereby improving the safety of vehicle driving.

[0180] Regarding the device in this embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0181] It should be noted that each implementable method in this embodiment may be implemented separately, or may be implemented in combination in any combination without conflict, and this application is not limited thereto.

[0182] An embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the operation of the method corresponding to any embodiment of the vehicle-mounted attendance method provided in the above embodiments can be implemented.

[0183] An embodiment of the present application also provides a computer program product, wherein the computer program product includes a computer program, wherein when the computer program is executed by a processor, it can implement the operations corresponding to the method of any embodiment of the in-vehicle attendance method provided in the above embodiments.

[0184] like Figure 4As shown, some embodiments of the present application provide an electronic device 400, which includes: a memory 410, a processor 420, and a computer program stored in the memory 410 and executable on the processor 420, wherein the processor 420 reads the program from the memory 410 through a bus 430 and executes the program to implement a method of any embodiment of the above-mentioned vehicle attendance method.

[0185] Processor 420 can process digital signals and can include various computing structures, such as complex instruction set computer structure, reduced instruction set computer structure, or a structure that implements a combination of multiple instruction sets. In some examples, processor 420 can be a microprocessor.

[0186] The memory 410 may be used to store instructions executed by the processor 420 or data related to the execution of instructions. These instructions and / or data may include codes for implementing some or all functions of one or more modules described in the embodiments of the present application. The processor 420 of the disclosed embodiment may be used to execute instructions in the memory 410 to implement the method shown above. The memory 410 includes a dynamic random access memory, a static random access memory, a flash memory, an optical memory, or other memory known to those skilled in the art.

[0187] The above are only embodiments of the present application and are not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0188] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0189] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

Claims

1. A vehicle-mounted attendance method, characterized in that: The method comprises: Acquiring first image data; Determining whether a target face exists in the first image data according to a pre-stored personnel information database; In the case where the target face exists in the first image data, determining whether the acquisition time of the first image data is within a first preset time period; When the acquisition time of the first image data is within the first preset time period, determining that a target person corresponding to the target face is on a vehicle; When the vehicle arrives at the preset position, if the target person stays on the vehicle for longer than a preset value, the left-behind persons of the target person are determined.

2. The vehicle-mounted attendance method according to claim 1, characterized in that: When the vehicle arrives at the preset location, if the target person stays on the vehicle for a time longer than a preset value, determining that the target person is a left-behind person includes: acquiring second image data every second preset time period; Determining whether a target face exists in the second image data according to a pre-stored personnel information database; If the target face exists in the second image data and the stay time on the vehicle exceeds a preset value, it is determined that the target person corresponding to the target face is a left-behind person.

3. The vehicle-mounted attendance method according to claim 2, characterized in that: The determining, based on a pre-stored personnel information database, whether a target face exists in the first image data comprises: Recognize the face in the first image data according to a pre-trained face recognition model to obtain feature information of the face in the first image data; wherein the pre-trained face recognition model is obtained by training a neural network model using sample data; Comparing the feature information of the face in the first image data with the preset feature information in the pre-stored personnel information database; the pre-stored personnel information database at least includes a personnel identification and preset feature information corresponding to the personnel identification; If the feature information of the face in the first image data matches the set feature information, it is determined that the target face exists in the first image data.

4. The vehicle-mounted attendance method according to claim 1, characterized in that: In the case where the target face exists in the first image data, determining whether the acquisition time of the first image data is within a first preset time period includes: If the acquisition time of the first image data is within the first preset time period, it is determined that the attendance of the target person is successful; If the acquisition time of the first image data is not within the first preset time period, it is determined that the attendance of the target person is unsuccessful, and attendance failure information is generated.

5. The vehicle-mounted attendance method according to claim 1, characterized in that: When the vehicle reaches the preset position, if the target person stays on the vehicle for a time longer than a preset value, determining the person left behind by the target person includes: Obtaining location information of the vehicle; Determining whether the vehicle is in a stopped operation state according to the location information of the vehicle; When the vehicle is in a stopped operating state, determining whether the target person's stay time on the vehicle exceeds a preset value; If the target person's stay time on the vehicle exceeds a preset value, the left-behind persons of the target person are determined.

6. The vehicle-mounted attendance method according to claim 5, characterized in that: The method further comprises: Determining whether the vehicle is located on a preset driving track according to the location information of the vehicle; If the vehicle is not on the preset driving trajectory, a first alarm signal is triggered.

7. The vehicle-mounted attendance method according to claim 4, characterized in that: The method further comprises: identifying the dangerous behavior of the target person according to the image data; When it is determined that the target person has the dangerous behavior, a second alarm signal is triggered.

8. A vehicle-mounted attendance device, characterized in that: The device comprises: An acquisition module, used for acquiring first image data; A first determination module, used to determine whether a target face exists in the first image data according to a pre-stored personnel information database; A judgment module, used for judging whether the acquisition time of the first image data is within a first preset time period when the target face exists in the first image data; A second determination module is used to determine that a target person corresponding to the target face is on a vehicle when the acquisition time of the first image data is within the first preset time period; The third determination module is used to determine the persons left behind by the target person when the vehicle arrives at the preset position and the target person's stay time on the vehicle exceeds a preset value.

9. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor can implement the vehicle-mounted attendance method as claimed in any one of claims 1 to 7 when executing the program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the program, when executed by a processor, can implement the vehicle-mounted attendance method described in any one of claims 1 to 7.

Images