Vehicle monitoring method and related equipment

Abstract

The embodiment of the invention discloses a vehicle monitoring method, a vehicle monitoring device, electronic equipment, a computer readable storage medium and a computer program product containing instructions, which are used for monitoring a vehicle under the condition of achieving an energy-saving effect. The method comprises the steps that a trigger signal for starting monitoring is detected, the trigger signal is actively generated based on vehicle state information obtained by a target sensor or is passively generated based on a remote monitoring starting request sent by a client side, and according to the detected trigger signal for starting monitoring, the remote monitoring starting request is sent to the client side; controlling the cabin domain controller, the communication controller and the vehicle body domain controller to enter a dormant state, determining whether a risk identification result of a risk exists or not based on multiple frames of images acquired by the vehicle-mounted fisheye camera, determining a risk relief condition when the risk exists, and determining the risk of the vehicle on the basis of the risk identification result and the risk relief condition. And determining whether to wake up at least one of the cabin domain controller, the communication controller and the vehicle body domain controller to perform corresponding monitoring operation.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of vehicle monitoring, and more specifically, to a vehicle monitoring method, a vehicle monitoring device, an electronic device, a computer-readable storage medium, and a computer program product containing instructions. Background Art

[0002] With the popularization of smart car technology, the demand for vehicle monitoring is growing, so there is an urgent need for a vehicle monitoring method that can better meet user needs.

[0003] The existing vehicle monitoring method is "Sentry Mode", which is managed by the intelligent cockpit domain controller. Once started, all related devices / controllers (such as the body domain controller, communication controller, etc.) are activated and run continuously.

[0004] However, in existing vehicle monitoring methods, all devices / controllers run continuously during the monitoring process, and the power consumption of unnecessary devices / controllers will accumulate, resulting in unnecessary energy loss in vehicle monitoring and failing to achieve energy-saving effects. Summary of the Invention

[0005] Embodiments of the present application provide a vehicle monitoring method, a vehicle monitoring device, an electronic device, a computer-readable storage medium, and a computer program product containing instructions, for performing vehicle monitoring while achieving energy-saving effects.

[0006] In a first aspect, an embodiment of the present application provides a vehicle monitoring method, which is applied to an intelligent driving domain controller, and the method includes:

[0007] Detecting a trigger signal for starting monitoring, where the trigger signal is actively generated based on vehicle status information acquired by a target sensor, or passively generated based on a request for remote start monitoring sent by a client;

[0008] According to the detected trigger signal for starting monitoring, the cockpit domain controller, the communication controller and the body domain controller are controlled to enter a dormant state;

[0009] Determine the risk identification result based on the multi-frame images obtained by the vehicle-mounted fisheye camera, and determine the risk elimination status if the risk exists;

[0010] Based on the risk identification result and the risk elimination situation, determine whether to wake up at least one of the cockpit domain controller, the communication controller and the body domain controller to perform corresponding monitoring operations.

[0011] In a second aspect, an embodiment of the present application provides a vehicle monitoring device, comprising:

[0012] a detection unit, configured to detect a trigger signal for starting monitoring, wherein the trigger signal is actively generated based on vehicle status information acquired by a target sensor, or passively generated based on a request for remotely starting monitoring sent by a client;

[0013] A control unit, configured to control the cockpit domain controller, the communication controller, and the body domain controller to enter a dormant state according to a detected trigger signal for starting monitoring;

[0014] a determination unit, configured to determine a risk identification result of whether a risk exists based on multiple frames of images acquired by the vehicle-mounted fisheye camera, and to determine a risk elimination status when a risk exists;

[0015] The determination unit is further configured to determine whether to wake up at least one of the cockpit domain controller, the communication controller, and the body domain controller to perform corresponding monitoring operations based on the risk identification result and the risk elimination status.

[0016] In a third aspect, an embodiment of the present application provides an electronic device, including:

[0017] CPU, memory, input and output interfaces, wired or wireless network interfaces, and power supply;

[0018] The memory is a transient storage memory or a persistent storage memory;

[0019] The central processing unit is configured to communicate with the memory and execute instructions in the memory to perform the aforementioned vehicle monitoring method.

[0020] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which includes instructions. When the instructions are executed on a computer, the computer executes the aforementioned vehicle monitoring method.

[0021] In a fifth aspect, an embodiment of the present application provides a computer program product comprising instructions, which, when the computer program product is run on a computer, enables the computer to execute the aforementioned vehicle monitoring method.

[0022] As can be seen from the above technical solution, the embodiments of the present application have the following advantages: when monitoring is initiated, only the onboard fisheye camera is turned on, and the cockpit domain controller, communication controller, and body domain controller are first controlled to enter a dormant state. Based on the risk identification results and the risk elimination status, it is determined whether to wake up the cockpit domain controller, communication controller, and body domain controller to perform the corresponding monitoring operations. This more refined low-power management avoids the unnecessary energy loss caused by turning on all devices / controllers for vehicle monitoring at all times, thereby achieving energy savings. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1A schematic diagram of the architecture of a vehicle monitoring system disclosed in an embodiment of the present application;

[0024] Figure 2 A schematic flow chart of a vehicle monitoring method disclosed in an embodiment of the present application;

[0025] Figure 2-1 A flow chart of another vehicle monitoring method disclosed in an embodiment of the present application;

[0026] Figure 3 A schematic structural diagram of a vehicle monitoring device disclosed in an embodiment of the present application;

[0027] Figure 4 This is a schematic structural diagram of an electronic device disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0028] Embodiments of the present application provide a vehicle monitoring method, a vehicle monitoring device, an electronic device, a computer-readable storage medium, and a computer program product containing instructions, for performing vehicle monitoring while achieving energy-saving effects.

[0029] See also Figure 1 The architecture of the vehicle monitoring system in the embodiment of the present application includes:

[0030] Intelligent driving domain controller 101 and client 102. When performing vehicle monitoring, the intelligent driving domain controller 101 can be connected to the client 102. The intelligent driving domain controller 101 can detect the trigger signal for starting monitoring. The trigger signal is actively generated based on the vehicle status information obtained by the target sensor, or passively generated based on the request for remote start monitoring sent by the client 102. Then, according to the detected trigger signal for starting monitoring, the cockpit domain controller, the communication controller and the body domain controller can be controlled to enter a dormant state, and a risk identification result is determined based on the multi-frame images obtained by the on-board fisheye camera to determine whether there is a risk, and the risk relief status is determined when there is a risk. Finally, based on the risk identification result and the risk relief status, it is determined whether to wake up at least one of the cockpit domain controller, the communication controller and the body domain controller to perform corresponding monitoring operations.

[0031] Based on the above introduction, the vehicle monitoring method in this application is introduced below. Figure 2 , the embodiment of the present application discloses a vehicle monitoring method, which is applied to an intelligent driving domain controller, and the method includes:

[0032] 201. Detect a trigger signal for starting monitoring, where the trigger signal is actively generated based on vehicle status information acquired by a target sensor, or passively generated based on a request for remotely starting monitoring sent by a client.

[0033] In an optional embodiment, the target sensor refers to various sensors on the vehicle used to obtain vehicle status information, such as a position sensor (GNSS+IMU), an IMU (used to obtain three-axis acceleration), a four-door and two-hood illegal opening signal sensor, etc., and the vehicle status information refers to various status data of the vehicle, such as the vehicle's position information (provided by GNSS+IMU, used to determine whether the vehicle is in the parking space list), the vehicle's three-axis acceleration information (provided by the IMU, used to determine whether the vehicle has collided), the door status information (obtained by the door detection sensor, used to determine whether the door is illegally opened), etc.

[0034] 202. According to the detected trigger signal for starting monitoring, the cockpit domain controller, the communication controller, and the body domain controller are controlled to enter a dormant state.

[0035] In an optional embodiment, the dormant state refers to a low-power state of an electronic device in which some non-essential functional modules of the device are temporarily shut down or in standby mode, but the device can still receive a wake-up signal to achieve energy conservation. When necessary, a specific wake-up signal can be used to restore the device to normal operation.

[0036] 203. Determine the risk identification result based on the multi-frame images obtained by the vehicle-mounted fisheye camera to determine whether there is a risk, and determine the risk elimination status when there is a risk.

[0037] In an optional embodiment, a vehicle-mounted fisheye camera is a camera installed on a vehicle with wide-angle imaging capabilities, capable of capturing image information within a wide range of the vehicle's surroundings, providing video data support for monitoring the vehicle's surroundings. A risk-relief situation refers to a situation where, after a risk event is identified, the vehicle is no longer at risk, as the factors causing the risk disappear or the associated dangerous behavior ceases. Examples include situations where a suspicious person moves a certain distance away from the vehicle or a collision-hazardous object is removed.

[0038] 204. Based on the risk identification result and the risk elimination status, determine whether to wake up at least one of the cockpit domain controller, the communication controller, and the body domain controller to perform corresponding monitoring operations.

[0039] In an optional implementation, specifically, if it is necessary to turn on the in-vehicle monitoring and central control display, the cockpit domain controller is woken up; if it is necessary to send the monitoring video to the car cloud to notify the user, the communication controller is woken up; if a double flash alarm is required, the body domain controller is woken up, etc.

[0040] In this way, when monitoring is started, only the on-board fisheye camera is turned on, and the cockpit domain controller, communication controller and body domain controller are first controlled to enter a dormant state. Based on the risk identification results and the risk elimination status, it is determined whether to wake up the cockpit domain controller, communication controller and body domain controller to perform the corresponding monitoring operations. This more refined low-power management avoids unnecessary energy loss caused by turning on all devices / controllers for vehicle monitoring at all times, thereby achieving energy-saving effects. Furthermore, the trigger signal is actively generated based on the vehicle status information obtained by the target sensor, or passively generated based on the request for remote start of monitoring sent by the client, which can realize active and passive triggered vehicle monitoring, thereby improving the timeliness and flexibility of vehicle monitoring.

[0041] In an optional embodiment, based on the risk identification results and the risk resolution status, it is determined whether to wake up at least one of the cabin domain controller, communication controller and body domain controller to perform corresponding monitoring operations, including at least one of the following situations: if there is a risk and the risk has not been resolved, wake up at least one of the cabin domain controller, communication controller and body domain controller to perform corresponding monitoring operations; if there is a risk and the risk has been resolved, do not wake up the cabin domain controller, communication controller and body domain controller; if there is no risk, do not wake up the cabin domain controller, communication controller and body domain controller.

[0042] Specifically, when a risk exists and hasn't been resolved, at least one controller is awakened to perform monitoring operations to address the risk. When a risk exists but has been resolved or no longer exists, no controller is awakened to avoid unnecessary energy consumption. This allows precise control of the controller's wake-up timing, avoiding unnecessary device wake-ups and further saving energy, while ensuring timely monitoring operations when risks arise.

[0043] In an optional embodiment, the target sensor includes a position sensor, and the method also includes at least one of the following situations: if the target sensor detects that the current parking position of the vehicle is not within the preset parking space list, a trigger signal for starting monitoring is actively generated; if a request for remotely starting the monitoring system is received from the client through the vehicle cloud, a trigger signal for starting the monitoring system is passively generated.

[0044] Specifically, the position sensor consists of a GNSS (Global Navigation Satellite System) and an IMU (Inertial Measurement Unit). GNSS is a satellite navigation system, such as GPS, that can provide global position information for the vehicle. The IMU can measure information such as the vehicle's acceleration and angular velocity to infer changes in the vehicle's relative position when the GNSS signal is weak or lost. The combination of GNSS and IMU can provide precise vehicle location information, which the system uses to determine whether the vehicle is parked within a preset parking space list. If the vehicle is parked in a space on the list, the monitoring system will automatically shut down; if it is parked in a space outside the list, the monitoring system will automatically turn on.

[0045] In this way, combined with vehicle location information and remote control requirements, the monitoring system can be started and stopped intelligently, improving the targeted nature of monitoring and energy-saving effects.

[0046] In an optional embodiment, the target sensor includes a vehicle collision detection module, and the method further includes: if the target sensor detects that the standard deviation of the current vehicle's three-axis acceleration exceeds a preset standard deviation threshold, it is determined that the vehicle has collided, and a trigger signal for starting monitoring is actively generated.

[0047] Specifically, the vehicle collision detection module can use an IMU. An IMU typically contains an accelerometer and a gyroscope, which are used to measure an object's motion state, such as acceleration and angular velocity. The IMU provides acceleration data for the vehicle along three axes. By calculating statistical features such as the standard deviation of this acceleration data, the system can determine whether the vehicle has collided. For example, when a vehicle is suddenly hit, the acceleration detected by the IMU will change significantly. When the standard deviation exceeds a certain threshold, it can be determined that a collision has occurred. In this way, monitoring can be automatically triggered when a collision occurs, and accident information can be recorded in a timely manner, thereby improving vehicle safety.

[0048] In an optional embodiment, the method further includes: if a request to remotely shut down monitoring is received from the client through the vehicle cloud, the cockpit domain controller and the body domain controller are controlled to enter a sleep state and then lower the high voltage to shut down monitoring.

[0049] Specifically, a user can send a remote monitoring shutdown request through a client (such as a mobile phone). The car cloud receives the request and sends it to the intelligent driving domain controller. Upon receiving the shutdown signal, the intelligent driving domain controller controls the body domain controller and the cockpit domain controller to enter a dormant state and sends a low-voltage signal to the body domain controller to shut down the monitoring system.

[0050] In this way, we can respond to user needs, facilitate users to remotely control and shut down monitoring, and ensure equipment safety while reducing energy consumption through standardized high-voltage operations.

[0051] In an optional embodiment, the method further includes: if it is determined that there is no risk within a preset time, controlling the cockpit domain controller and the body domain controller to enter a dormant state and then lowering the high voltage to shut down monitoring.

[0052] Specifically, if the system detects no risk events around the vehicle within a preset period of time, using onboard fisheye cameras and other devices, it automatically puts the cockpit domain controller and body domain controller into a dormant state and performs a high-voltage shutdown to shut down the monitoring system. This avoids unnecessary energy consumption and achieves energy conservation.

[0053] In an optional embodiment, a risk identification result is determined based on multiple frames of images acquired by a vehicle-mounted fisheye camera to determine whether there is a risk, including: inputting the multiple frames of images into a pre-trained risk identification model, using the risk identification model to determine the distance between the target and the vehicle in the multiple frames of images, and the motion state of the target, and based on the determination results of whether the distance reaches a preset risk distance threshold and whether the motion state is a preset motion state, obtaining the risk identification result corresponding to the multiple frames of images output by the risk identification model.

[0054] Specifically, during the risk identification process, the target can be various objects, such as people and vehicles. The motion state includes the target's speed and behavior (such as wandering, rapid approach, etc.). The system determines whether the motion state is a preset dangerous motion state by analyzing whether the target's speed reaches a preset threshold and whether the behavior state conforms to a preset dangerous behavior pattern. For example, if a target (such as a person) approaches a vehicle at a relatively fast speed and wanders around the vehicle, these behaviors may be judged as preset dangerous behavior states. In this way, image recognition technology can be used to quickly and accurately identify risks around the vehicle, providing a basis for subsequent monitoring measures.

[0055] In an optional embodiment, the method further includes shutting down or placing sensors unrelated to the monitoring task, such as Radar (Radio Detection and Ranging), Uss (Ultrasonic Sensor), Scam (surround camera system), and Lidar (Light Detection and Ranging), into a dormant state based on the detected trigger signal for initiating monitoring. This can reduce energy consumption.

[0056] Specifically, radar is a sensor that uses radio waves to detect the distance, speed, and direction of a target object. Ultrasonic sensors (USSs) measure distance and are commonly used in parking assistance systems. Scam surround-view cameras provide a 360-degree panoramic view of the vehicle's surroundings. Lidar (Lidar) uses laser pulses to measure distance and is used for high-precision environmental perception. When monitoring is enabled, sensors not relevant to the task are turned off or put into a dormant state to reduce energy consumption.

[0057] In an optional embodiment, at least one of the cockpit domain controller, the communication controller and the body domain controller is woken up to perform corresponding monitoring operations, including at least one of the following situations: waking up the cockpit domain controller to perform in-vehicle monitoring and central control display; waking up the communication controller to send the target monitoring video stream to the vehicle cloud to send to the client, the target monitoring video stream is the risk event video stream outside the vehicle, or the risk event video stream outside and inside the vehicle; waking up the body domain controller to perform a double flash alarm.

[0058] Specifically, the cockpit domain controller is awakened to activate in-vehicle monitoring (such as in-vehicle cameras) and the central control display, displaying monitoring information or warning messages inside the vehicle. The communication controller is awakened to send video streams of risk events captured outside the vehicle, or both, to the vehicle cloud. The vehicle cloud then synchronizes the video to the client (such as the user's mobile phone), allowing users to remotely view the surveillance video. The body domain controller is awakened to control the vehicle's hazard warning lights, alerting nearby people or objects to leave the vehicle, providing both a deterrent and a reminder.

[0059] In this way, different controllers can be flexibly awakened and work together to meet various operational requirements in different monitoring scenarios, thereby improving the functional diversity and practicality of the monitoring system.

[0060] In an optional embodiment, the target monitoring video is a risk event video outside and inside the vehicle, and the vehicle status information obtained by the target sensor includes the door status information obtained by the door detection sensor; before waking up the communication controller to send the target monitoring video stream to the vehicle cloud to send it to the client, the method also includes: if there is a risk and the risk has not been eliminated, determining whether the door is open based on the door status information, and if the door is open, turning on the in-vehicle camera device; obtaining the target monitoring video stream based on the multi-frame images obtained by the in-vehicle camera device and the multi-frame images obtained by the on-board fisheye camera.

[0061] Specifically, the door detection sensor acquires door status information to determine whether the door has been illegally opened. If this is detected and the risk event remains, the system notifies the cockpit domain controller to activate the in-car camera to capture the interior. Simultaneously, the system combines the exterior images captured by the onboard fisheye camera to generate a target monitoring video stream containing both exterior and interior footage. The communication controller then wakes up and transmits these video streams to the vehicle cloud, which is then synchronized with the user's client, allowing users to gain timely insight into the vehicle's interior and exterior, enhancing vehicle safety monitoring.

[0062] In this way, when the risk has not been eliminated and the car door is open, the video information inside the car can be obtained in time and sent to the user, which enhances the monitoring of the internal situation of the vehicle and improves the user's comprehensive understanding of the vehicle's safety status.

[0063] In an optional embodiment, after controlling the cockpit domain controller, the communication controller and the body domain controller to enter a sleep state according to the detected trigger signal for starting monitoring, the method further includes: if a request for remotely viewing the monitoring video stream sent by the client through the vehicle cloud is received, the cockpit domain controller, the communication controller and the body domain controller are woken up to perform corresponding monitoring operations.

[0064] In this way, the user's need to remotely view surveillance videos (active viewing needs) can be met, and the system will wake up the relevant controllers to cooperate with the operation, without being restricted by the risk status, enhancing interactivity and convenience.

[0065] The following further describes the vehicle monitoring solution provided by this application. Figure 2-1 , Figure 2-1 This is a flow chart of another vehicle monitoring method disclosed in an embodiment of this application, which is applied to a vehicle monitoring system (energy-saving active and passive vehicle monitoring system). Figure 2-1As can be seen, the vehicle monitoring system includes: an intelligent driving domain controller, a Tbox / Pbox (communication controller), a body domain controller, a cockpit domain controller, a vehicle cloud, and a mobile app (client). The intelligent driving domain controller includes a monitoring control module and a low-power management module. The monitoring control module performs both active and passive monitoring. Active monitoring involves receiving information from sensors (such as fisheye cameras, GNSS, IMUs, and signals of illegal door and hood opening) to identify risk events. Once a risk is identified, it proactively wakes up the body domain controller, cockpit domain controller, Tbox / Pbox, and other devices to perform monitoring operations, such as alarms, video storage, and in-vehicle monitoring, thus achieving proactive protection. Passive monitoring involves processing remote control requests from the mobile app and waking up relevant devices to allow users to view the vehicle's surroundings. The low-power management module provides low-power management: when the monitoring system is enabled, sensors not relevant to monitoring (such as radar, Uss, Scan, and Lidar) are turned off or dormant, reducing power consumption of non-essential devices. Secondly, device hibernation can be controlled based on risk status. Specifically, when there are no risk events or the risk has been resolved, devices such as the Tbox / Pbox, body domain controller, and cockpit domain controller can be put into hibernation to reduce power consumption. When processing high-voltage up / down requests, this module controls the body domain controller to perform high-voltage up / down operations. When monitoring is enabled, an up / down request is sent to wake the device; when monitoring is disabled, a down / down request is sent to put the device into hibernation. The body domain controller receives commands from the intelligent driving domain controller. It wakes up and activates the hazard warning when a risk event occurs; it goes into hibernation when there is no risk or the risk has been resolved, reducing energy consumption. The cockpit domain controller, controlled by the intelligent driving domain controller, wakes up and activates the in-vehicle monitoring and central control display when a risk event occurs; it goes into hibernation when there is no risk, reducing power consumption. The Tbox / Pbox is responsible for communication between the vehicle and the vehicle-to-cloud. When a risk event occurs, it sends the alarm and video to the vehicle-to-cloud, which then synchronizes the alarm to the mobile app to notify the driver. Furthermore, it receives requests from the mobile app to remotely view the surveillance video stream via the vehicle-to-cloud, coordinates with the intelligent driving domain controller to wake up relevant devices and transmit real-time video. It can go into hibernation when not in use to save energy. As a data transfer station, the car cloud receives alarm events and video streams sent by Tbox / Pbox and synchronizes them to the mobile app; it forwards the remote control requests sent by the mobile app to the vehicle's intelligent driving domain controller, enabling users to remotely control the vehicle monitoring system and obtain information.

[0066] In summary, the vehicle monitoring system of the present application is energy-saving and supports human-computer interaction. It can actively and passively turn on and off monitoring, achieving energy-saving effects. Specifically, passive opening: when the mobile phone remotely turns on monitoring, the intelligent driving domain controller wakes up the body domain controller and sends an upper high-voltage signal, and supports remote real-time viewing of monitoring videos. Active opening: when the vehicle is parked in an unused parking space, the intelligent driving domain controller automatically turns on monitoring. Passive closing: when the mobile phone remotely turns off monitoring, the intelligent driving domain controller puts the body domain controller and the cockpit domain controller into hibernation and sends a lower high-voltage signal. Active closing: monitoring is automatically turned off if there is no danger within the preset time.

[0067] For further information, see Figure 3 One embodiment of the vehicle monitoring device in the embodiment of the present application includes:

[0068] a detection unit, configured to detect a trigger signal for starting monitoring, wherein the trigger signal is actively generated based on vehicle status information acquired by a target sensor, or passively generated based on a request for remotely starting monitoring sent by a client;

[0069] A control unit, configured to control the cockpit domain controller, the communication controller, and the body domain controller to enter a dormant state according to a detected trigger signal for starting monitoring;

[0070] a determination unit, configured to determine a risk identification result of whether a risk exists based on multiple frames of images acquired by the vehicle-mounted fisheye camera, and to determine a risk elimination status when a risk exists;

[0071] The determination unit is further configured to determine whether to wake up at least one of the cockpit domain controller, the communication controller, and the body domain controller to perform corresponding monitoring operations based on the risk identification result and the risk elimination status.

[0072] The determination unit is specifically configured to wake up at least one of the cockpit domain controller, the communication controller, and the body domain controller to perform corresponding monitoring operations if a risk exists and the risk has not been resolved; and not wake up the cockpit domain controller, the communication controller, and the body domain controller if a risk exists and the risk has been resolved; and not wake up the cockpit domain controller, the communication controller, and the body domain controller if no risk exists.

[0073] The vehicle monitoring device further comprises:

[0074] The generation unit is used to actively generate a trigger signal for starting monitoring if it detects through the target sensor that the current parking position of the vehicle is not within the preset parking space list. If it receives a request for remotely starting the monitoring system sent by the client through the vehicle cloud, it passively generates a trigger signal for starting the monitoring system.

[0075] The control unit is also used to control the cockpit domain controller and the body domain controller to enter a dormant state and then lower the high voltage to turn off the monitoring if a request for remote shutdown of the monitoring is received from the client through the vehicle cloud.

[0076] The determination unit is specifically used to input the multiple-frame images into a pre-trained risk identification model, use the risk identification model to determine the distance between the target and the vehicle and the motion state of the target in the multiple-frame images, and based on the determination results of whether the distance reaches a preset risk distance threshold and whether the motion state is a preset motion state, obtain the risk identification results corresponding to the multiple-frame images output by the risk identification model.

[0077] The determination unit is specifically used to wake up the cockpit domain controller to perform in-vehicle monitoring and central control display; and / or wake up the communication controller to send the target monitoring video stream to the vehicle cloud to send it to the client, and the target monitoring video stream is a risk event video stream outside the vehicle, or outside and inside the vehicle; and / or wake up the body domain controller to perform a double flash alarm.

[0078] The determination unit is further used to determine whether the door is open based on the door status information if a risk exists and the risk has not been eliminated. If the door is open, the in-vehicle camera device is turned on, and the target monitoring video stream is obtained based on the multi-frame images obtained by the in-vehicle camera device and the multi-frame images obtained by the on-board fisheye camera. The target monitoring video is a risk event video outside and inside the vehicle, and the vehicle status information obtained by the target sensor includes the door status information obtained by the door detection sensor.

[0079] The vehicle monitoring device further comprises:

[0080] The wake-up unit is used to wake up the cockpit domain controller, the communication controller and the body domain controller to perform corresponding monitoring operations if a request for remote viewing of the monitoring video stream is received from the client through the vehicle cloud.

[0081] For further information, see Figure 4 , an embodiment of the electronic device in the embodiments of the present application includes:

[0082] CPU 401, memory 405, input / output interface 404, wired or wireless network interface 403 and power supply 402;

[0083] The memory 405 is a temporary storage memory or a permanent storage memory;

[0084] The CPU 401 is configured to communicate with the memory 405 and execute the instructions in the memory 405 to perform the aforementioned Figure 2 The method in the embodiment shown.

[0085] Furthermore, the embodiment of the present application also provides a computer-readable storage medium, which includes instructions. When the instructions are executed on a computer, the computer executes the aforementioned Figure 2 The method in the embodiment shown.

[0086] Furthermore, the present invention also provides a computer program product comprising instructions, which, when executed on a computer, causes the computer to execute the aforementioned Figure 2 The method in the embodiment shown.

[0087] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0088] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0089] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0090] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0091] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0092] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, read-only memory), random access memory (RAM, random access memory), disk or optical disk, and other media that can store program code.

Claims

1. A vehicle monitoring method, characterized in that: Applied to an intelligent driving domain controller, the method includes: Detecting a trigger signal for starting monitoring, where the trigger signal is actively generated based on vehicle status information acquired by a target sensor, or passively generated based on a request for remote start monitoring sent by a client; According to the detected trigger signal for starting monitoring, the cockpit domain controller, the communication controller and the body domain controller are controlled to enter a dormant state; Determine the risk identification result based on the multi-frame images obtained by the vehicle-mounted fisheye camera to determine whether there is a risk, and determine the risk elimination status if there is a risk; Based on the risk identification result and the risk elimination situation, determine whether to wake up at least one of the cockpit domain controller, the communication controller and the body domain controller to perform corresponding monitoring operations.

2. The method according to claim 1, characterized in that The determining, based on the risk identification result and the risk resolution condition, whether to wake up at least one of the cockpit domain controller, the communication controller, and the body domain controller to perform corresponding monitoring operations includes at least one of the following conditions: If the risk exists and has not been resolved, waking up at least one of the cockpit domain controller, the communication controller, and the body domain controller to perform corresponding monitoring operations; If the risk exists and has been resolved, the cockpit domain controller, the communication controller, and the body domain controller are not awakened; If there is no risk, the cockpit domain controller, the communication controller, and the body domain controller are not awakened.

3. The method according to claim 1, characterized in that The target sensor includes a position sensor, and the method further includes at least one of the following situations: If the target sensor detects that the current parking position of the vehicle is not within the preset parking space list, it will actively generate a trigger signal to start monitoring; If a request to remotely start the monitoring system is received from the client through the vehicle cloud, a trigger signal to start the monitoring system is passively generated.

4. The method according to claim 1, wherein The method further comprises: If a request for remotely shutting down monitoring is received from the client via the vehicle cloud, the cockpit domain controller and the body domain controller are controlled to enter a dormant state and then lower the high voltage to shut down monitoring.

5. The method according to claim 1, wherein The risk identification result of determining whether there is a risk based on the multi-frame images obtained by the vehicle-mounted fisheye camera includes: Inputting the multiple frames of images into a pre-trained risk identification model; The risk identification model is used to determine the distance between the target and the vehicle and the motion state of the target in the multiple-frame images, and based on the determination results of whether the distance reaches a preset risk distance threshold and whether the motion state is a preset motion state, the risk identification results corresponding to the multiple-frame images output by the risk identification model are obtained.

6. The method according to claim 1, characterized in that The waking up at least one of the cockpit domain controller, the communication controller, and the body domain controller to perform corresponding monitoring operations includes at least one of the following situations: Waking up the cockpit domain controller to perform in-vehicle monitoring and central control display; Waking up the communication controller to send a target monitoring video stream to the vehicle cloud to be sent to the client, wherein the target monitoring video stream is a risk event video stream outside the vehicle, or a risk event video stream outside and inside the vehicle; Wake up the vehicle body domain controller to perform a double flash alarm.

7. The method according to claim 6, characterized in that The target monitoring video is a risk event video outside and inside the vehicle, and the vehicle status information obtained by the target sensor includes door status information obtained by the door detection sensor; Before waking up the communication controller to send the target monitoring video stream to the vehicle cloud to send to the client, the method further includes: If the risk exists and has not been resolved, determining whether the door is open based on the door status information, and if the door is open, turning on the in-car camera device; The target monitoring video stream is obtained based on the multiple frames of images acquired by the in-vehicle camera device and the multiple frames of images acquired by the vehicle-mounted fisheye camera.

8. The method according to any one of claims 1 to 7, characterized in that After controlling the cockpit domain controller, the communication controller, and the body domain controller to enter a dormant state according to the detected trigger signal for starting monitoring, the method further includes: If a request for remote viewing of a monitoring video stream is received from a client via the vehicle cloud, the cockpit domain controller, the communication controller, and the body domain controller are awakened to perform corresponding monitoring operations.

9. An electronic device, characterized in that: include: central processing unit and memory; The memory is a transient storage memory or a persistent storage memory; The central processing unit is configured to communicate with the memory and execute instructions in the memory to perform the method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium comprises instructions, which, when executed on a computer, enable the computer to perform the method according to any one of claims 1 to 8.

Images