Vehicle safety monitoring method, device and system and storage medium

Abstract

The invention relates to a vehicle safety monitoring method. The method comprises the steps that whether a target vehicle is in a flameout parking state or not is judged; if the target vehicle is in the flameout parking state, the frame rate of the data collection device is adjusted to be a target frame rate, monitoring data, collected based on the target frame rate, of the target vehicle is obtained, and the target collection frame rate is lower than the frame rate of data collected by the data collection device when the target vehicle is in the driving state; inputting the monitoring data into an image processing model to obtain an analysis result corresponding to the target vehicle, and determining whether there is an abnormality around the target vehicle based on the analysis result; and when abnormity exists around the target vehicle, generating an alarm signal based on the abnormal data, and sending the alarm signal to a user terminal of a user corresponding to the target vehicle. The problem that in the prior art, when an automobile data recorder uses a PIR sensor to achieve wakeup of an alarm mode, power consumption is large, and therefore timely alarm for abnormity of a vehicle parking environment cannot be maintained for a long time is solved.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a vehicle safety monitoring method, device, system and storage medium. Background Art

[0002] With the development of automobile technology, vehicle safety systems are becoming more and more perfect. Among them, the vehicle alarm system, as a key component, plays an important role in preventing traffic accidents and protecting vehicle safety. And as a driving recorder for data collection in the alarm system, it needs to be in alarm mode not only during driving, but also during parking to ensure the safety of the vehicle. However, the alarm mode of the existing parking recorder uses PIR wake-up technology to wake up, that is, when a heat source such as a person or an animal enters the detection range of the PIR sensor, the sensor will capture the change in infrared radiation and generate a high-level signal, thereby triggering the camera system to start from sleep or standby state and start recording or monitoring. However, the PIR sensor is easily interfered by various heat sources and light sources, resulting in false triggering, thereby increasing system power consumption, affecting the battery life of the device, and failing to maintain timely alarms for abnormalities in the vehicle parking environment for a long time. Summary of the invention

[0003] The present application provides a vehicle safety monitoring method, device, system and storage medium to solve the problem in the prior art that the driving recorder uses a PIR sensor to realize the wake-up of the alarm mode, which consumes a lot of power and makes it impossible to maintain timely alarms for abnormalities in the vehicle parking environment for a long time.

[0004] In a first aspect, the present application provides a vehicle safety monitoring method, the method comprising:

[0005] Determine whether the target vehicle is in a shutdown state;

[0006] If the target vehicle is in a stalled state, the frame rate of the data acquisition device is adjusted to a target frame rate, wherein the data acquisition device is a device installed on the target vehicle for monitoring the surrounding environment of the target vehicle, and the target frame rate is lower than the frame rate at which the data acquisition device collects data when the target vehicle is in a driving state;

[0007] Acquire monitoring data of the target vehicle collected based on the target frame rate;

[0008] Inputting the monitoring data into an image processing model to obtain an analysis result corresponding to the target vehicle, and determining whether there is an abnormality around the target vehicle based on the analysis result, wherein the analysis result includes a behavior analysis result and a distance analysis result;

[0009] When an abnormality exists around the target vehicle, an alarm signal is generated based on the abnormality, and the alarm signal is sent to a user terminal of a user corresponding to the target vehicle.

[0010] In a second aspect, the present application provides a vehicle safety monitoring device, the device comprising:

[0011] A state determination module is used to determine whether the target vehicle is in a shutdown state;

[0012] A frame rate adjustment module, used for adjusting the frame rate of the data acquisition device to a target frame rate if the target vehicle is in a stalled state, wherein the data acquisition device is a device installed on the target vehicle for monitoring the surrounding environment of the target vehicle, and the target frame rate is lower than the frame rate at which the data acquisition device collects data when the target vehicle is in a driving state;

[0013] A data acquisition module, used to acquire monitoring data of the target vehicle collected based on the target frame rate;

[0014] A data processing module, used for inputting the monitoring data into an image processing model, obtaining an analysis result corresponding to the target vehicle, and determining whether there is an abnormality around the target vehicle based on the analysis result, wherein the analysis result includes a behavior analysis result and a distance analysis result;

[0015] The abnormality alarm module is used to generate an alarm signal based on the abnormality when there is an abnormality around the target vehicle, and send the alarm signal to the user terminal of the user corresponding to the target vehicle.

[0016] In a third aspect, the present application provides a vehicle safety monitoring system, including an alarm system and a user terminal, wherein the alarm system includes a data acquisition terminal, a control center and a communication terminal;

[0017] The data acquisition terminal is used to receive control instructions from the control center and collect video information of the surrounding environment of the target vehicle in real time based on the control instructions to form monitoring data;

[0018] A control center, for adjusting the frame rate of data collected by the data collection terminal of the target vehicle to a target frame rate when the target vehicle is in a stalled and parked state, and receiving the monitoring data collected by the data collection terminal in real time; for analyzing the monitoring data to determine the target moving object in the monitoring data and the relative distance between the target moving object and the target vehicle, and for performing behavior analysis on the target monitoring data whose relative distance to the target moving object is less than or equal to a preset safety distance, so as to determine whether there is an abnormality around the target vehicle; for analyzing the target monitoring data whose relative distance to the target moving object is greater than a preset safety distance, determining the residence time of the target moving object in the target monitoring data, and analyzing the behavior of the target moving object in the target monitoring data whose residence time is greater than or equal to the preset safety time, so as to determine whether there is an abnormality around the target vehicle; and for generating an alarm signal based on the abnormality when there is abnormal data around the target vehicle, and sending the alarm signal to the user terminal through the communication terminal, wherein the target frame rate is lower than the frame rate of data collected by the data collection terminal when the target vehicle is in a driving state;

[0019] Communication terminal, used to realize the communication connection between the alarm system and the user terminal;

[0020] The user terminal is used to receive the alarm signal sent by the alarm system and display the alarm signal.

[0021] In a fourth aspect, the present application also provides a computer storage medium storing computer executable instructions, wherein the computer executable instructions are used to execute the vehicle safety monitoring method described in any one of the above items of the present application.

[0022] The above technical solution provided by the embodiment of the present application has the following advantages over the prior art: the method provided by the embodiment of the present application adjusts the frame rate of the data acquisition device to the target frame rate, the target frame rate is 1 frame / 2 seconds to 2 frames / second, and the target frame rate is lower than the frame rate of the data acquisition device when the target vehicle is in a driving state, so that when the image processing model processes the monitoring data collected based on the target frame rate, the amount of data processed is reduced, thereby reducing the power consumption of the image processing model, and at the same time, the image processing model is used to first analyze and process the monitoring data to determine whether there are objects with abnormal behavior around the target vehicle or objects with abnormal distances from the target vehicle, and then trigger the alarm mode of the target vehicle when there is an abnormality, that is, generate a corresponding alarm signal according to the abnormality, and send the alarm signal to the user terminal of the user corresponding to the target vehicle, so as to achieve the prompting effect for the user. In the present application, the monitoring data is collected at a lower frame rate to reduce the power consumption of data processing, and at the same time, the monitoring data is first analyzed before the alarm mode of the target vehicle is triggered, and the alarm mode is triggered after determining that there is an abnormality, thereby reducing the power consumption of the alarm mode of the driving recorder, thereby extending the time for timely alarm of abnormal parking environment of the target vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0024] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0025] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0026] Figure 1 A schematic diagram of a vehicle safety monitoring method provided in an embodiment of the present application;

[0027] Figure 2 A schematic diagram of a vehicle safety monitoring method provided in an embodiment of the present application;

[0028] Figure 3 A schematic diagram of an example process of abnormal analysis of a vehicle safety monitoring method provided in an embodiment of the present application;

[0029] Figure 4 A schematic diagram of a vehicle safety monitoring method provided in an embodiment of the present application;

[0030] Figure 5 A schematic diagram of the structure of a vehicle safety monitoring device provided in an embodiment of the present application;

[0031] Figure 6 A schematic diagram of the architecture of a vehicle safety monitoring system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0033] The disclosure below provides many different embodiments or examples to implement different structures of the present invention. In order to simplify the disclosure of the present invention, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present invention. In addition, the present invention can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.

[0034] In order to solve the problem in the prior art that the dash cam uses a PIR sensor to wake up the alarm mode, which consumes a lot of power and makes it impossible to maintain timely alarms for abnormalities in the vehicle parking environment for a long time, the present application provides a vehicle safety monitoring method, device, system and storage medium, which can extend the time for timely alarms for abnormalities in the vehicle parking environment.

[0035] Figure 1 A flow chart of a vehicle safety monitoring method provided in an embodiment of the present application. Figure 1 As shown, the method described in the embodiment of the present application may include the following steps:

[0036] S101, determining whether the target vehicle is in a parked state.

[0037] In the embodiment of the present application, when the vehicle is in the starting state, the auxiliary equipment such as the driving recorder on the vehicle will be automatically powered to ensure that the auxiliary equipment will not be short of power, and when the vehicle stops, the auxiliary equipment will no longer be powered. Therefore, when the target vehicle enters the parking state, in order to ensure that the driving recorder can maintain monitoring of the surrounding environment of the target vehicle for a long time to achieve timely alarm, the driving recorder of the target vehicle needs to be switched to a low power consumption mode.

[0038] S102, if the target vehicle is in a parked state, the frame rate of the data acquisition device is adjusted to a target frame rate, wherein the data acquisition device is a device installed on the target vehicle for monitoring the surrounding environment of the target vehicle, and the target frame rate is lower than the frame rate at which the data acquisition device collects data when the target vehicle is in a driving state.

[0039] In an embodiment of the present application, when the target vehicle is in a parked state, the frame rate of a data acquisition device installed on the target vehicle for acquiring data about the surrounding environment of the target vehicle is adjusted to a target frame rate.

[0040] The target frame rate may range from 1 frame / 2 seconds to 2 frames / second, such as 1fps, 2fps, etc. The target frame rate is a lower frame rate than a normal smooth video.

[0041] The data acquisition device can be a device with a recording function such as a driving recorder installed on the target vehicle, or it can be a variety of sensors such as radar, laser radar (LiDAR) that perceive the vehicle's surrounding environment.

[0042] S103, acquiring monitoring data of the target vehicle collected based on the target frame rate.

[0043] In an embodiment of the present application, monitoring data collected by a data acquisition device based on a target frame rate is received in real time, and the monitoring data is real-time data of the surrounding environment of the target vehicle.

[0044] In this application, the data acquisition device is described by taking a driving recorder installed on a target vehicle as an example. The viewing range of the monitoring data collected by the data acquisition device can be determined according to the camera angle, resolution and installation position of the driving recorder, and can be between 90 degrees and 180 degrees, such as 90 degrees, 100 degrees, 140 degrees and 170 degrees. The distance of the picture in the monitoring data can be 0-15 meters, such as 3 meters, 4 meters, etc.

[0045] S104, inputting the monitoring data into an image processing model to obtain an analysis result corresponding to the target vehicle, and judging whether there is an abnormality around the target vehicle based on the analysis result, wherein the analysis result includes a behavior analysis result and a distance analysis result.

[0046] In an embodiment of the present application, the collected surveillance video or image data of the target frequency is imported into the image processing model. The model is usually based on a deep learning algorithm and has powerful feature extraction and image analysis capabilities. Once the data is input, the model begins to process the data, including but not limited to tasks such as target detection, behavior recognition, and scene understanding. After calculation and analysis, the image processing model outputs the analysis results. The analysis results include information such as the target objects detected in the monitoring screen, their positions, motion trajectories, and possible behavior patterns. And based on the detected target objects and the positions, motion trajectories, and behaviors of the target objects, it is determined whether the detected target objects are abnormal.

[0047] Among them, when detecting the target object in the monitoring data, movable objects such as people, motor vehicles, non-motor vehicles, etc. in the monitoring data are detected.

[0048] In one feasible manner, when analyzing the monitoring data, because the data collection range of the data collection device of the target vehicle is limited, and there may be situations where no people, motor vehicles or non-motor vehicles are approaching in the collected monitoring data, it is possible to first detect whether there is a target moving object in the monitoring data. When the target moving object is detected, the monitoring data containing the target moving object is filtered out from all the collected monitoring data as target monitoring data, and then the target moving object in the target monitoring data is analyzed to determine whether there is an abnormality in the target moving object, thereby reducing the amount of data processing when performing abnormal analysis on the target moving object, thereby speeding up the data analysis rate.

[0049] Among them, when determining whether there is an abnormality, the image processing model may compare the analysis results with preset normal behavior patterns or scene features, or apply additional anomaly detection algorithms to identify any unexpected behaviors or changes. The specific implementation logic of the model is not limited in the embodiment of the present application, and it is sufficient to be able to analyze the monitoring data to determine whether there is an abnormality in the environment surrounding the target vehicle.

[0050] Abnormality refers to the event or behavior that the target moving object may cause damage to the target vehicle, such as collision, scratching, smashing, etc. Whether the target moving object is abnormal can be judged by judging the distance between the target moving object and the target vehicle.

[0051] It is understandable that when an abnormality is detected around the target vehicle, an alarm signal may be issued through an alarm system installed on the vehicle to alert the object that is damaging the target vehicle.

[0052] For example, if a person A is detected in the monitoring data, it is possible to determine whether A is rapidly approaching the target vehicle based on his movement trajectory, or whether the target moving object is in a state of paralysis due to alcohol or other reasons causing unconsciousness based on his movement trajectory, or whether the target moving object is holding a sharp or heavy weapon in his hand and is too close to the target vehicle, etc.

[0053] S105, when there is an abnormality around the target vehicle, an alarm signal is generated based on the abnormality, and the alarm signal is sent to a user terminal of a user corresponding to the target vehicle.

[0054] In an embodiment of the present application, when there are abnormalities around the target vehicle that may cause damage, the alarm mode is awakened, a corresponding alarm signal is generated based on the monitoring data with the abnormality, and the alarm signal is sent to the user terminal of the user corresponding to the target vehicle.

[0055] Among them, the alarm signal can generate different alarm signals according to different types of abnormalities. Different alarm signals can be signals of different forms, or signals carrying different contents.

[0056] The types of abnormal data include but are not limited to damage to the target vehicle caused by humans, damage to the target vehicle caused by motor vehicles, damage to the target vehicle caused by non-motor vehicles, damage to the target vehicle to varying degrees caused by humans, damage to the target vehicle to varying degrees caused by motor vehicles, damage to the target vehicle to varying degrees caused by non-motor vehicles, etc.

[0057] Among them, the degree of damage caused to the target vehicle includes slight friction causing paint loss; slight friction causing scratches; impact causing large-area damage to the front face, engine hood, fenders and other parts; impact causing large-area damage to the engine hood, doors, etc., and even affecting the top cover and bottom plate, and the entire body structure may be deformed; the vehicle is scrapped, etc.

[0058] When the alarm signal is sent to the user corresponding to the target vehicle, a corresponding signal that can quickly remind the user can be generated according to the user's habits or user settings, and when the user's user terminal receives the alarm signal, it can be displayed in different presentation forms on the user terminal.

[0059] The presentation forms include, but are not limited to, vibrating the user terminal, popping up a prompt on the display interface of the user terminal, sending a text message to the user terminal, making a phone call to the user terminal, etc.

[0060] In the embodiment of the present application, when it is detected that the vehicle is in a parking state, the frame rate of the data acquisition device is adjusted to the target frame rate, the target frame rate is 1 frame / 2 seconds-2 frames / second, and the target frame rate is lower than the frame rate of the data acquisition device when the target vehicle is in a driving state. Therefore, when the image processing model processes the monitoring data collected based on the target frame rate, the amount of data processed is reduced, thereby reducing the power consumption of the image processing model. At the same time, the image processing model is used to analyze and process the monitoring data first to determine whether there is an abnormality around the target vehicle, and then trigger the alarm mode of the target vehicle when there is an abnormality, that is, generate a corresponding alarm signal according to the abnormality, and send the alarm signal to the user terminal of the user corresponding to the target vehicle, so as to achieve the prompting effect for the user. In the present application, a lower frame rate is used to collect monitoring data, reduce the power consumption of data processing, and at the same time, the monitoring data is first analyzed before triggering the alarm mode of the target vehicle, and the alarm mode is triggered after determining that there is an abnormality, thereby reducing the power consumption of the alarm mode of the driving recorder, thereby extending the time for timely alarm of abnormalities in the parking environment of the target vehicle.

[0061] like Figure 2 -3 is a flow chart of a vehicle safety monitoring method provided in an embodiment of the present application. Figure 2As shown in FIG. 3 , the method may include the following steps:

[0062] S201, obtaining the power status of the power supply of the data acquisition device to determine whether the power supply has external power input.

[0063] In an embodiment of the present application, the power status of the power supply of the data acquisition device of the target vehicle can be obtained. The data acquisition device is an auxiliary device of the target vehicle. When the target vehicle is shut down and parked, the data acquisition device will no longer be powered. Therefore, it is possible to determine whether the target vehicle is in a shut-down and parked state based on whether the power supply of the data acquisition device receives input from an external power supply.

[0064] The method for obtaining the current speed of the target vehicle can be through analyzing the data collected by the data acquisition device, or it can be determined by combining GPS positioning and time. In this application, the calculation method of the current speed of the target vehicle is not limited.

[0065] S202: When the power status indicates that there is no external power input, the target vehicle is currently in a shutdown and parking state.

[0066] S203, when the power status indicates that there is external power input, the target vehicle is currently in a startup state.

[0067] In the embodiment of the present application, the data acquisition device is illustrated by taking a driving recorder as an example. The driving recorder is usually equipped with a power detection module, which is responsible for monitoring the input status of the external power supply in real time. When the vehicle is started, the vehicle's power system is turned on, and the vehicle's power system is an external power supply relative to the driving recorder. When an external power supply (such as a vehicle-mounted cigarette lighter interface or a dedicated power cord) provides power to the driving recorder, the power detection module detects the presence of voltage or current, thereby confirming that the external power supply has been normally input.

[0068] However, when the vehicle is parked and turned off, the onboard power system will be shut down, causing the dashcam to lose external power input. At this time, the power detection module will detect the disappearance of voltage or current, thereby realizing that the external power supply has been disconnected.

[0069] Therefore, by real-time monitoring of the input state of the external power supply, it is possible to determine whether the vehicle is in an engine-off parking state.

[0070] S204, if the target vehicle is in a shutdown and parked state, the frame rate of the data acquisition device is adjusted to a target frame rate, wherein the data acquisition device is a device installed on the target vehicle for monitoring the surrounding environment of the target vehicle, and the target frame rate is lower than the frame rate at which the data acquisition device collects data when the target vehicle is in a driving state.

[0071] The specific implementation of this step can refer to step S102 and will not be described in detail here.

[0072] S205, acquiring monitoring data of the target vehicle collected based on the target frame rate.

[0073] The specific implementation of this step can refer to step S103 and will not be described in detail here.

[0074] S206: Analyze the monitoring data using target detection technology to determine whether there is a target moving object.

[0075] In an embodiment of the present application, each frame of the monitoring data is carefully scanned, and the image is processed by feature extraction, classification and regression using algorithms and models, so as to identify whether there is a target moving object in each frame of the monitoring data. The target moving object may include but is not limited to people, motor vehicles, non-motor vehicles, etc.

[0076] Among them, the target detection algorithm can be the R-CNN series: including R-CNN, Fast R-CNN, Faster R-CNN, etc., which selects candidate boxes and applies convolutional neural networks to each candidate box for target classification and bounding box regression; it can also be the YOLO series, which regards the target detection task as a regression problem to achieve real-time target detection, etc.

[0077] S207, when there is a target moving object, the target monitoring data corresponding to the target moving object is acquired, and the target moving object is analyzed based on the target monitoring data to obtain an analysis result corresponding to the target vehicle.

[0078] In an embodiment of the present application, after the target moving object is determined from the monitoring data, the monitoring data containing the target moving object can be screened out as target monitoring data, and then the target monitoring data can be analyzed to obtain an analysis result of the environment surrounding the target vehicle, and based on the analysis result, it can be determined whether there is an abnormality around the target vehicle. The abnormality may include the target moving object staying around the target vehicle for a long time, or being too close to the target vehicle, or taking actions that damage the target vehicle, or judging that the target vehicle may be damaged based on the behavior of the target moving object, etc. When an abnormality exists in the target moving object, the monitoring data containing the abnormality of the target moving object is used as the target monitoring data, and the target monitoring data is screened out for further analysis and processing, thereby reducing the amount of data for subsequent analysis and processing.

[0079] When analyzing monitoring data, the image processing model may detect the target moving object in the monitoring data, and analyze the trajectory, behavior, position, etc. of the target moving object to obtain the analysis result corresponding to the target moving vehicle.

[0080] Judging whether there is an abnormality around the target vehicle based on the analysis results can be judging whether the target moving object will cause damage to the target vehicle based on the position of the target moving object; it can also be judging whether the target moving object will cause damage to the target vehicle if it continues to move along the trajectory based on the trajectory; it can also be judging whether the target moving object will cause damage to the target vehicle based on the behavior of the target moving object, etc.

[0081] It is understandable that when the target vehicle is damaged, it may be caused by an object thrown from a distance away from the target vehicle or thrown to the target vehicle. Therefore, for this type of damage, sensors such as proximity sensors and gyroscopes installed on the target vehicle can be used to determine whether there is an object approaching the target vehicle or whether it is tilted when the target vehicle is turned off and parked.

[0082] In the embodiment of the present application, after the target moving object is detected in the monitoring data, the data processing amount for analyzing the target moving object based on the target monitoring data can also be reduced by the following methods, such as Figure 5 The method includes: S208, obtaining the biometric characteristics of the target moving object, and determining whether the target moving object is an authorized user based on the biometric characteristics; S209, when the target moving object is an unauthorized user, performing a step of analyzing the target moving object based on the target monitoring data to obtain an analysis result corresponding to the target vehicle.

[0083] In an embodiment of the present application, after the target moving object is identified and detected in the monitoring data, target monitoring data in which the target moving object exists is obtained, and then the biometric features of the target moving object in the target monitoring data are extracted, and whether the target moving object is an authorized user of the target vehicle is determined by identifying, analyzing and comparing the biometric features, and unique data such as facial information and fingerprint information of the authorized user is pre-stored. When the target moving object is detected in the target monitoring data and the biometric features of the target moving object are analyzed, when it is determined that the target moving object is an authorized user, it indicates that the target moving object will not damage the target vehicle. If it is determined that the target moving object is an unauthorized user after comparing the biometric features, the target object in the target monitoring data is analyzed again, thereby avoiding waking up the alarm system for analysis when the owner of the target vehicle or a user who can normally use the target vehicle approaches the vehicle, thereby reducing the power consumption of the alarm system of the target vehicle.

[0084] When analyzing the target monitoring data corresponding to the target moving object to determine whether the target moving object is abnormal, it can be achieved by the following method. In one achievable manner, Figure 3As shown, it includes: S2071, determining the relative distance between the target moving object and the target vehicle based on the target monitoring data, and comparing the relative distance with the preset safety distance; S2072, determining the monitoring data whose relative distance is less than or equal to the preset safety distance as abnormal data, and S2073, analyzing the behavior of the target moving object based on the abnormal data to determine the abnormal analysis result of the behavior of the target moving object.

[0085] In an embodiment of the present application, the position of the target moving object in the first target data is identified to obtain the corresponding target position, and the relative distance between the target position and the target vehicle is analyzed and calculated using visual ranging technology, and the relative distance of the target moving object is compared with a preset safety distance. When the relative distance is less than or equal to the preset safety distance, it indicates that the target moving object is too close to the target vehicle and may cause damage to the target vehicle. Therefore, the monitoring data corresponding to the relative distance being less than or equal to the preset safety distance is determined as abnormal data, and then the behavior of the target moving object in the abnormal data is analyzed to determine whether the target moving object has abnormal behavior.

[0086] When comparing the relative distance of the target moving object with the preset safety distance to determine that the target moving object is outside the preset safety distance of the target vehicle, but within the range of data collection of the target measurement data collection device, in order to further strengthen the protection of the target vehicle, the following methods can be used, such as Figure 4 The shown figure may also include: S2074, when the relative distance is greater than the preset safety distance, obtaining the residence time of the target moving object in the target monitoring data; S2075, comparing the residence time with the preset safety time, when the residence time is greater than or equal to the preset safety time, analyzing the behavior of the target moving object based on the target monitoring data to obtain the behavior analysis result of the target moving object.

[0087] In an embodiment of the present application, when a target moving object is detected in the monitoring data collected by the data acquisition device, but the relative distance between the target moving object and the target vehicle is greater than the preset safety distance, the duration during which the target moving object appears in the monitoring data, that is, the duration during which the target moving object stays around the target vehicle, is obtained, and then the stay duration is compared with the preset safety duration. When the stay duration is greater than or equal to the preset safety duration, the behavior of the target moving object in the monitoring data is analyzed to determine whether the target moving object has abnormal behavior.

[0088] When the relative distance between the target moving object and the target vehicle is greater than or equal to the preset safety distance, the target moving object may be staying around the target vehicle, which may be waiting for someone, resting, parking the vehicle, etc. The behavior of the target moving object is analyzed to determine whether the target moving object has abnormal behavior, which includes looking at the target vehicle multiple times within a certain period of time, throwing objects at the target vehicle, approaching the target vehicle from a preset safety distance in a short period of time, etc.

[0089] S210, generating an alarm signal based on the abnormality, and sending the alarm signal to a user terminal corresponding to the user of the target vehicle.

[0090] The specific implementation of this step can refer to step S105 and will not be described in detail here.

[0091] S211, sending an alarm signal to a user terminal of the user at a preset time interval, and receiving a confirmation instruction from the user terminal in response to the alarm signal.

[0092] S212, stop sending the alarm signal based on the confirmation instruction.

[0093] In an embodiment of the present application, an alarm signal is sent to the user terminal of the user at a preset time interval to remind the user. When the alarm signal is displayed on the user terminal, a confirmation indication of the alarm signal will be displayed. After the user receives the alarm signal, he enters a confirmation receipt on the user terminal to indicate that he is aware of the alarm signal. When the confirmation instruction sent by the user terminal is received, the alarm signal is stopped from being sent to the user terminal.

[0094] During the period when no confirmation instruction for the alarm signal is received, the alarm signal is continuously sent to the user terminal at a preset time interval, and the number of transmissions, the preset continuous transmission duration, etc. can be preset. For example, if the preset number of transmissions is 10 times and the preset time interval is 1 minute, the alarm signal is sent for the first time when it is generated, the second time after an interval of 1 minute, and the third time after another interval of 1 minute, and the alarm signal is sent once every 1 minute until it is sent 10 times. If the confirmation instruction of the user terminal is not received during the 10 alarm signal transmissions, the alarm signal is stopped after 10 continuous transmissions; the preset continuous transmission duration is to use the moment when the alarm signal is generated as the starting time of the transmission duration, and send the alarm signal at the preset time interval within the preset continuous transmission duration until the end time of the preset continuous transmission duration is reached. For example, the preset continuous sending duration is 20 minutes, the preset time interval is 2 minutes, and the time when the alarm signal is generated after data analysis is 10:20, then 10:20 will be used as the starting time of the preset continuous sending duration, and the alarm signal will be sent to the user terminal at intervals of 2 minutes. If no confirmation instruction is received from the user terminal during the sending of the alarm signal, the sending of the alarm signal will be terminated at 10:40.

[0095] It can be understood that the form and content of the alarm signal can be changed according to whether a confirmation instruction from the user terminal is received during the sending period. If the confirmation instruction from the user terminal is not received after sending multiple times or for a long time, the reminder level of the alarm signal on the user terminal can be enhanced, such as from popping up a prompt message on the display interface of the user terminal, to sending a short message to the user terminal, and then to making a phone call to the user terminal, etc.

[0096] In an embodiment of the present application, the power status of the power supply of the data acquisition device of the target vehicle is obtained to determine whether an external power supply is input into the data acquisition device, thereby determining whether the target vehicle is in a parked state, and then adjusting the frame rate of the data acquisition device of the target vehicle to a target frame rate of 1 frame / 2 seconds to 2 frames / second to reduce the amount of data processing, thereby reducing power consumption; at the same time, the monitoring data collected by the data acquisition device based on the target frame rate is detected for the target moving object, and the monitoring data where the target moving object exists is analyzed to determine whether the target moving object has abnormal behavior, and the method for determining the abnormal behavior of the target moving object may include: when the relative distance between the target moving object and the target vehicle is less than or equal to a preset safety distance, analyzing the behavior of the target moving object in the target monitoring data; when the relative distance is greater than the preset safety distance and the target moving object stays around the target vehicle for a period of time greater than or equal to a preset safety period, analyzing the behavior of the target moving object in the target monitoring data where the target moving object exists. Before analyzing the behavior of the target moving object, the biometrics of the target moving object are extracted, and whether the target moving object is an authorized user is determined based on the biometrics, and then the relative distance between the target moving object and the target vehicle is analyzed, thereby reducing the amount of data analyzed and processed for monitoring data, and determining whether the target moving object is abnormal according to the above method, if there is an abnormality, when there is an abnormality, the alarm system of the target vehicle is awakened, and an alarm signal is generated based on the abnormality analysis result by the alarm system, and the alarm signal is sent to the user terminal of the user corresponding to the target vehicle, thereby realizing timely alarm of the surrounding environment of the target vehicle. By analyzing the low frame rate monitoring data collected by the data acquisition device based on the target frame rate, and judging whether the target moving object is abnormal based on the position of the target moving object, the behavior of the target moving object, the length of stay at the location of the target vehicle, the biometrics and other information, the alarm system is awakened after the abnormality exists, thereby reducing the awakening frequency of the alarm system, thereby achieving the goal of reducing the power consumption of the alarm mode of the target vehicle and extending the time for timely alarm of abnormalities in the parking environment of the target vehicle.

[0097] like Figure 5 As shown in FIG. 1 , a schematic diagram of the structure of a vehicle safety monitoring device provided by the present application is shown. Figure 5 As shown, the vehicle safety monitoring device:

[0098] A state determination module is used to determine whether the target vehicle is in a parking state;

[0099] A frame rate adjustment module, used for adjusting the frame rate of the data acquisition device to a target frame rate if the target vehicle is in a parked state, wherein the data acquisition device is a device installed on the target vehicle for monitoring the surrounding environment of the target vehicle, and the target frame rate is lower than the frame rate at which the data acquisition device collects data when the target vehicle is in a driving state;

[0100] A data acquisition module, used to acquire monitoring data of the target vehicle collected based on the target frame rate;

[0101] A data processing module, used for inputting the monitoring data into an image processing model, obtaining an analysis result corresponding to the target vehicle, and judging whether there is an abnormality around the target vehicle based on the analysis result, wherein the analysis result includes a behavior analysis result and a distance analysis result;

[0102] The abnormality alarm module is used to generate an alarm signal based on the abnormality when there is an abnormality around the target vehicle, and send the alarm signal to the user terminal corresponding to the user of the target vehicle

[0103] Furthermore, the data processing module includes:

[0104] A target detection unit, used to analyze the monitoring data using target detection technology to determine whether there is a target moving object;

[0105] The abnormality determination unit is used to obtain target monitoring data corresponding to the target moving object when there is a target moving object, and analyze the target moving object based on the target monitoring data to obtain an analysis result corresponding to the target vehicle.

[0106] Further, the abnormality determination unit includes:

[0107] a distance determination subunit, configured to determine a relative distance between the target moving object and the target vehicle based on the target monitoring data, and compare the relative distance with a preset safety distance;

[0108] A data determination subunit, configured to determine the monitoring data whose relative distance is less than or equal to a preset safety distance as abnormal data;

[0109] The abnormality determination subunit is used to analyze the behavior of the target moving object based on the abnormal data to determine the analysis result of the target vehicle.

[0110] Further, the data determination unit includes:

[0111] A duration determination subunit, configured to obtain a duration of stay of the target moving object in the target monitoring data when the relative distance is greater than the preset safety distance;

[0112] The abnormality analysis subunit is used to compare the stay time with the preset safety time. When the stay time is greater than or equal to the preset safety time, the behavior of the target moving object is analyzed based on the target monitoring data to obtain the abnormal behavior analysis result of the target moving object.

[0113] Furthermore, the vehicle safety monitoring device further comprises:

[0114] A feature acquisition subunit, configured to acquire a biometric feature of the target moving object, and determine whether the target moving object is an authorized user based on the biometric feature;

[0115] The user determination unit is used to perform the step of analyzing the target moving object based on the target monitoring data to obtain the analysis result corresponding to the target vehicle when the target moving object is an unauthorized user.

[0116] Further, the state determination module includes:

[0117] A state acquisition unit, used to acquire the power state of the power supply of the data acquisition device to determine whether the power supply has external power input;

[0118] A duration acquisition unit, used for determining that the target vehicle is currently in a shutdown parking state when the power state indicates that there is no external power input;

[0119] A state determination unit is used to determine that when the power state indicates that there is external power input, the target vehicle is currently in the start state.

[0120] Furthermore, the vehicle safety monitoring device further comprises:

[0121] An instruction receiving module, used to send the alarm signal to the user terminal of the user at a preset time interval, and receive a confirmation instruction from the user terminal in response to the alarm signal;

[0122] The sending stop module is used to stop sending the alarm signal based on the confirmation instruction.

[0123] In the embodiment of the present application, by adjusting the frame rate of the data acquisition device to the target frame rate, the target frame rate is 1 frame / 2 seconds to 2 frames / second, and the target frame rate is lower than the frame rate of the data acquisition device when the target vehicle is in a driving state, so that when the image processing model processes the monitoring data collected based on the target frame rate, the amount of data processed is reduced, thereby reducing the power consumption of the image processing model, and at the same time, the image processing model is used to first analyze and process the monitoring data to determine whether there are objects with abnormal behavior around the target vehicle or objects with abnormal distances from the target vehicle, and then trigger the alarm mode of the target vehicle when there is an abnormality, that is, generate a corresponding alarm signal according to the abnormality, and send the alarm signal to the user terminal of the user corresponding to the target vehicle, so as to achieve a prompt effect on the user. In the present application, a lower frame rate is used to collect monitoring data, reduce the power consumption of data processing, and at the same time, the monitoring data is analyzed before triggering the alarm mode of the target vehicle, and the alarm mode is triggered after determining that there is an abnormality, thereby reducing the power consumption of the alarm mode of the driving recorder, thereby extending the time for timely alarm of abnormal parking environment of the target vehicle.

[0124] like Figure 6 As shown, an embodiment of the present application provides a vehicle safety monitoring system, including an alarm system and a user terminal, wherein the alarm system includes a data acquisition terminal, a control center and a communication terminal;

[0125] The data acquisition terminal is used to receive control instructions from the control center and collect video information of the surrounding environment of the target vehicle in real time based on the control instructions to form monitoring data;

[0126] A control center is used to adjust the frame rate of data collected by the data collection end of the target measurement to the target frame rate when the target vehicle is in a parking state, and receive the monitoring data collected by the data collection end in real time; it is also used to analyze the monitoring data to determine the target moving object in the monitoring data and the relative distance between the target moving object and the target vehicle, and to perform behavior analysis on the target monitoring data whose relative distance to the target moving object is less than or equal to the preset safety distance, so as to determine whether there is an abnormality around the target vehicle; it is also used to analyze the target monitoring data whose relative distance to the target vehicle is greater than the preset safety distance, determine the stay time of the target moving object in the target monitoring data, and analyze the behavior of the target moving object in the target monitoring data whose stay time is greater than or equal to the preset safety time, so as to determine whether there is an abnormality around the target vehicle; it is also used to generate an alarm signal based on the abnormality when there is an abnormality around the target vehicle, and send the alarm signal to the user terminal through the communication end;

[0127] Communication terminal, used to realize the communication connection between the alarm system and the user terminal;

[0128] The user terminal is used to receive the alarm signal sent by the alarm system and display the alarm signal.

[0129] In an embodiment of the present application, when the control center detects that the target vehicle is in an ignition-off state, a control instruction is sent to the data acquisition terminal to adjust the frame rate of the data acquisition terminal to a target frame rate. The target frame rate is higher than the data acquisition frame rate of the target vehicle in a driving state. Then, the data acquisition terminal acquires data at the target frame rate to obtain monitoring data of the target vehicle's surrounding environment, and the data acquisition terminal maintains real-time communication with the control center. The data acquisition terminal sends the monitoring data acquired based on the target frame rate to the control center in real time. The control center analyzes and processes the monitoring data to determine whether there is a target moving object and the position of the target moving object in the monitoring data, thereby determining the relative distance between the target moving object and the target vehicle, and determining the monitoring data whose relative distance is less than or equal to the preset safety distance as the target monitoring data. According to the data, the behavior of the target moving object in the target monitoring data is analyzed to determine whether the target moving object has abnormal behavior, so as to determine whether there is any abnormality around the target vehicle; at the same time, when the relative distance between the target moving object and the target vehicle is greater than the preset safety distance, the stay time of the target moving object in the target monitoring data is determined, and the stay time is compared with the preset safety time. The behavior of the target moving object in the target monitoring data with a stay time greater than or equal to the preset safety time is analyzed to determine whether there is any abnormality in the target moving object, and then determine whether there is any abnormality around the target vehicle. When there is an abnormality around the target vehicle, a corresponding alarm signal is generated based on the abnormality, and the alarm signal is sent to the user terminal of the user to remind the user.

[0130] In an embodiment of the present application, by detecting whether there is a target moving object in the monitoring data, and analyzing the biological characteristics of the target moving object, the relative distance between the target moving object and the target vehicle, and the behavior of the target moving object, it is determined whether there is an abnormality around the target vehicle. When an abnormality exists, the alarm system of the target vehicle is awakened to issue an alarm, thereby reducing the power consumption of the alarm system.

[0131] Among them, the alarm system can generate different alarm signals according to the different types of abnormalities. The difference in alarm signals can be achieved through different reminders on the user terminal and different contents of prompt information when prompting the user on the user terminal. The reminder method can be pop-up window, text message, phone call, etc. For example, the content can be "Warning warning! Suspicious persons / vehicles appear around your vehicle with license plate *******. Please check the situation at the vehicle location in time.", or "Warning warning! There are abnormalities around your vehicle with license plate *******. You can view the surveillance video in **APP / **Mini Program.", etc.

[0132] A communication connection is achieved between the alarm system and the user terminal through the communication terminal. The communication method can be a wide area network communication method such as 4G communication. When the monitoring data is analyzed to determine that there is no target mobile object with abnormal behavior at present, the communication terminal can be in a standby state, and the communication terminal can be awakened once at a certain interval. When the communication terminal wakes up, it detects whether an instruction to send an alarm signal is received. If the sending instruction is received, the alarm signal is sent to the user terminal. If the sending instruction is not detected, the standby state is entered again, thereby reducing the power consumption of the communication terminal.

[0133] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the vehicle safety monitoring method provided in any of the aforementioned method embodiments are implemented.

[0134] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0135] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0136] It should be understood that the terms used herein are only for the purpose of describing specific example embodiments and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0137] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A vehicle safety monitoring method, characterized in that: The method comprises: Determine whether the target vehicle is in a shutdown state; If the target vehicle is in a stalled state, the frame rate of the data acquisition device is adjusted to a target frame rate, wherein the data acquisition device is a device installed on the target vehicle for monitoring the surrounding environment of the target vehicle, and the target frame rate is lower than the frame rate of the data acquisition device when the target vehicle is in a driving state; Acquire monitoring data of the target vehicle collected based on the target frame rate; Inputting the monitoring data into an image processing model to obtain an analysis result corresponding to the target vehicle, and determining whether there is an abnormality around the target vehicle based on the analysis result, wherein the analysis result includes a behavior analysis result and a distance analysis result; When an abnormality exists around the target vehicle, an alarm signal is generated based on the abnormality, and the alarm signal is sent to a user terminal of a user corresponding to the target vehicle.

2. The method according to claim 1, characterized in that The step of inputting the monitoring data into an image processing model to obtain an analysis result corresponding to the target vehicle includes: Analyzing the monitoring data using target detection technology to determine whether there is a target moving object; When there is a target moving object, target monitoring data corresponding to the target moving object is acquired, and the target moving object is analyzed based on the target monitoring data to obtain an analysis result corresponding to the target vehicle.

3. The method according to claim 2, characterized in that The analyzing the target moving object based on the target monitoring data to obtain an analysis result corresponding to the target vehicle includes: Determine the relative distance between the target moving object and the target vehicle based on the target monitoring data, and compare the relative distance with a preset safety distance; Determine the monitoring data whose relative distance is less than or equal to the preset safety distance as abnormal data; The behavior of the target moving object is analyzed based on the abnormal data to determine an analysis result of the target vehicle.

4. The method according to claim 2, characterized in that: After comparing the relative distance with the preset safety distance, the method further includes: When the relative distance is greater than the preset safety distance, obtaining the duration of stay of the target moving object in the target monitoring data; The dwell time is compared with a preset safety time. When the dwell time is greater than or equal to the preset safety time, the behavior of the target moving object is analyzed based on the target monitoring data to obtain an analysis result of the target vehicle.

5. The method according to claim 2, characterized in that: The step of acquiring the target monitoring data corresponding to the target moving object includes: Acquire the biometric feature of the target moving object, and determine whether the target moving object is an authorized user based on the biometric feature, and end the process when the target moving object is an authorized user; When the target moving object is an unauthorized user, a step of analyzing the target moving object based on the target monitoring data to obtain an analysis result corresponding to the target vehicle is performed.

6. The method according to claim 1, characterized in that The step of determining whether the target vehicle is in an engine-off parking state comprises: Obtaining the power status of the power supply of the data acquisition device to determine whether the power supply has external power input; When the power status indicates that there is no external power input, the target vehicle is currently in a shutdown parking state; When the power state indicates that there is external power input, the target vehicle is currently in a startup state.

7. The method according to claim 1, characterized in that The step of sending the alarm signal to a user terminal of the user to remind the user includes: Sending the alarm signal to a user terminal of the user at a preset time interval, and receiving a confirmation instruction from the user terminal in response to the alarm signal; Stop sending the alarm signal based on the confirmation instruction.

8. A vehicle safety monitoring device, characterized in that: The device comprises: A state determination module is used to determine whether the target vehicle is in a shutdown state; A frame rate adjustment module, used for adjusting the frame rate of the data acquisition device to a target frame rate if the target vehicle is in a stalled state, wherein the data acquisition device is a device installed on the target vehicle for monitoring the surrounding environment of the target vehicle, and the target frame rate is lower than the frame rate at which the data acquisition device collects data when the target vehicle is in a driving state; A data acquisition module, used to acquire monitoring data of the target vehicle collected based on the target frame rate; A data processing module, used for inputting the monitoring data into an image processing model, obtaining an analysis result corresponding to the target vehicle, and determining whether there is an abnormality around the target vehicle based on the analysis result, wherein the analysis result includes a behavior analysis result and a distance analysis result; The abnormality alarm module is used to generate an alarm signal based on the abnormality when there is an abnormality around the target vehicle, and send the alarm signal to the user terminal of the user corresponding to the target vehicle.

9. A vehicle safety monitoring system, characterized in that: It includes an alarm system and a user terminal, wherein the alarm system includes a data collection terminal, a control center and a communication terminal; The data acquisition terminal is used to receive control instructions from the control center and collect video information of the surrounding environment of the target vehicle in real time based on the control instructions to form monitoring data; The control center is used to adjust the frame rate of data collected by the data collection terminal of the target vehicle to the target frame rate when the target vehicle is in a shutdown and parking state, and receive the monitoring data collected by the data collection terminal in real time; and is also used to analyze the monitoring data to determine the target moving object in the monitoring data and the relative distance between the target moving object and the target vehicle, and perform behavior analysis on the target monitoring data whose relative distance to the target moving object is less than or equal to the preset safety distance, so as to determine whether there is any abnormality around the target vehicle; It is also used to analyze target monitoring data where the relative distance between the target moving object and the target vehicle is greater than a preset safety distance, determine the residence time of the target moving object in the target monitoring data, and analyze the behavior of the target moving object in the target monitoring data where the residence time is greater than or equal to the preset safety time, to determine whether there is an abnormality around the target vehicle; It is also used to generate an alarm signal based on the abnormality when there is an abnormality around the target vehicle, and send the alarm signal to the user terminal through the communication terminal, wherein the target frame rate is lower than the frame rate of the data collected by the data collection terminal when the target vehicle is in a driving state; Communication terminal, used to realize the communication connection between the alarm system and the user terminal; The user terminal is used to receive the alarm signal sent by the alarm system and display the alarm signal.

10. A storage medium, characterized in that: Computer executable instructions are stored, and the computer executable instructions are used to execute the vehicle safety monitoring method described in any one of the above items of the present application.

Images