Vehicle monitoring method and device, vehicle and storage medium

Abstract

The application provides a monitoring method and device of a vehicle, the vehicle and a storage medium. The method is applied to the vehicle and includes the following steps: identifying attribute information of one or more objects in a driving direction of the vehicle; predicting an intersection probability and an intersection time of each object with the vehicle according to the attribute information; regarding an object with an intersection probability greater than a preset probability as a monitoring object, determining a next monitoring start time of the vehicle according to the intersection time of all monitoring objects, regarding a possible appearance area of the monitoring object at the next monitoring start time of the vehicle as a target area, and controlling a monitoring device of the vehicle to monitor the target area. The method can realize active intervention on the monitoring object of the vehicle and the target area where the monitoring object of the vehicle is likely to appear, can perform focused monitoring on the determined monitoring object while ensuring comprehensive monitoring, can reduce interference of invalid information, can reduce resource consumption, and can reduce waste of chip computing power resources.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of vehicles, and more particularly, to a monitoring method and device of a vehicle, a vehicle and a storage medium. BACKGROUND

[0002] With the development of the intelligent driving industry, more and more sensors such as cameras and radars are used in the intelligent industry, and the chips used in intelligent driving have higher and higher requirements for computing power. Since the intelligent industry has been doing addition, the high power consumption and low utilization behind high computing power have become more and more obvious, and further lead to the contradiction between the computing power requirement, development speed and cost in intelligent driving becoming more and more obvious.

[0003] Therefore, making subtraction in the computing power of the intelligent driving industry is a good technical means to solve the problem that the intelligent driving has higher and higher requirements for computing power, but the utilization rate is low. The technical solution of the subtraction idea in the related art is mainly to classify the importance of the local part of the current frame and detect the key area in detail. The measure is still limited to the processing of the current frame, and the monitoring of part of the object is abandoned, which is easy to lead to incomplete monitoring. Or some solutions limit the monitoring scene, but still have the problem of insufficient comprehensiveness. SUMMARY

[0004] The present application provides a monitoring method and device of a vehicle, a vehicle and a storage medium. The method can make intersection prediction according to the objects in the driving direction of the vehicle, determine the objects with high intersection probability with the vehicle as monitoring objects, and determine the target area where the monitoring objects may appear at the next monitoring time, actively intervene in the monitoring of the subsequent target area, focus on monitoring the determined monitoring objects to ensure comprehensive monitoring, reduce the interference of invalid information, reduce resource consumption and waste of chip computing power resources.

[0005] In a first aspect, a monitoring method of a vehicle is provided. The method includes: identifying attribute information of one or more objects in a driving direction of the vehicle; predicting an intersection probability and an intersection time of each object with the vehicle according to the attribute information; determining an object with an intersection probability greater than a preset probability as a monitoring object, determining a next monitoring time of the vehicle according to the intersection time of all monitoring objects, and determining a target area where the monitoring object may appear at the next monitoring time of the vehicle; and controlling a monitoring device of the vehicle to monitor the target area.

[0006] By the technical solution, the object that has a large intersection possibility with the vehicle can be taken as a monitoring object, and the area where the monitoring object can appear at the monitoring moment can be taken as a target area that needs to be monitored, so that the target area is defined, the area where the monitoring object appears is taken as the target area, the monitoring is more targeted, the invalid information can be effectively reduced from interfering with the monitoring without affecting the safety monitoring of the surrounding environment, the monitoring resource consumption can be effectively reduced, the target area is mainly monitored, the monitoring frequency of the monitoring object is higher, the performance of the monitoring can be effectively improved, the better monitoring effect can be realized with lower resource consumption, the requirement of the chip for the computing power of the monitoring is effectively reduced, the chip with general performance can also meet the requirement of the monitoring, and the cost of the monitoring is reduced.

[0007] With reference to the first aspect, in some possible implementation manners, the control of the monitoring device of the vehicle on the monitoring of the target area comprises: dividing an area outside the target area into one or more non-target areas; setting a priority of the target area as a first priority and setting a priority of each non-target area as a second priority, wherein a monitoring level of the first priority is higher than a monitoring level of the second priority; and generating a monitoring sequence in an order of the first priority and the second priority, wherein the monitoring sequence is monitoring the target area once every interval of a non-target area.

[0008] By the technical solution, the target area and the non-target area can be divided into priorities, the priority of the target area is higher than that of the non-target area, the target area is monitored as a focus, the monitoring frequency of the non-target area is lower than that of the target area, and the monitoring resource is effectively reduced.

[0009] With reference to the first aspect and the implementation manners, in some possible implementation manners, the determination of the next monitoring start moment of the vehicle according to the intersection moments of all the monitoring objects comprises: identifying the earliest intersection moment in the intersection moments of all the monitoring objects and the vehicle; obtaining a safety reaction time length required for braking of the vehicle; and determining the latest monitoring start moment of the vehicle according to the earliest intersection moment and the safety reaction time length.

[0010] By the technical solution, the latest monitoring start moment of the vehicle can be determined according to the earliest intersection moment in the intersection moments of all the monitoring objects and the vehicle and the safety reaction time length required for braking of the vehicle, and the target area is determined subsequently according to the latest monitoring start moment.

[0011] With reference to the first aspect and the implementation manners, in some possible implementation manners, the identification of the attribute information of the one or more objects in the driving direction of the vehicle comprises: obtaining a panoramic image in the driving direction of the vehicle; and identifying the attribute information of the one or more objects in the panoramic image.

[0012] According to the technical solution, the attribute information of the object in the panoramic image in the driving direction of the vehicle can be recognized, so as to subsequently predict the intersection time and the intersection probability.

[0013] With reference to the first aspect and the above implementation manners, in some possible implementation manners, the panoramic image in the driving direction of the vehicle is acquired, including: if the vehicle is in a monitoring state, the panoramic image is acquired at intervals of a first preset time length; and if the vehicle is in a non-monitoring state, the panoramic image is acquired at intervals of a second preset time length.

[0014] According to the technical solution, whether the panoramic image is acquired at intervals of the first preset time length or the second preset time length can be determined according to whether the vehicle is in the monitoring state, so as to ensure the comprehensiveness of the monitoring.

[0015] With reference to the first aspect and the above implementation manners, in some possible implementation manners, before the panoramic image is acquired at intervals of the second preset time length, the method further includes: if the vehicle has determined a time when the vehicle will start monitoring next time; determining the interval acquisition time length of the panoramic image according to the current time of the vehicle and the time when the vehicle will start monitoring next time, or otherwise acquiring the panoramic image at intervals of the second preset time length.

[0016] According to the technical solution, when the vehicle has determined the time when the vehicle will start monitoring next time, the interval acquisition time length of the panoramic image can be determined according to the current time of the vehicle and the time when the vehicle will start monitoring next time, or otherwise the panoramic image is acquired at intervals of the second preset time length, so as to improve the real-time performance of the monitoring.

[0017] With reference to the first aspect and the above implementation manners, in some possible implementation manners, after the monitoring device of the vehicle controls the monitoring of the target area, the method further includes: if the intersection probability of the monitoring object is less than or equal to a preset probability, stopping the monitoring of the area where the monitoring object is likely to appear.

[0018] According to the technical solution, when the intersection probability of the monitoring object is less than or equal to the preset probability, the monitoring of the area where the monitoring object is likely to appear can be stopped, so as to reduce the interference of invalid information on the monitoring and the waste of computing resources.

[0019] In a second aspect, a monitoring device of a vehicle is provided, which comprises: an identifying module configured to identify attribute information of one or more objects in a driving direction of the vehicle; a predicting module configured to predict an intersection probability and an intersection time of each object with the vehicle according to the attribute information; and a monitoring module configured to take the object with the intersection probability greater than a preset probability as a monitoring object, determine a next monitoring start time of the vehicle according to the intersection time of all monitoring objects, take a region where the monitoring object is likely to appear when the next monitoring start time of the vehicle arrives as a target region, and control a monitoring device of the vehicle to monitor the target region.

[0020] With reference to the second aspect, in some possible implementation manners, the monitoring module is further configured to: divide a region other than the target region into one or more non-target regions; set a priority of the target region as a first priority, and set a priority of each non-target region as a second priority, where a monitoring level of the first priority is higher than a monitoring level of the second priority; and generate a monitoring sequence according to an order of the first priority and the second priority, where the monitoring sequence is monitoring the target region once every interval of a non-target region.

[0021] With reference to the second aspect and the above implementation manner, in some possible implementation manners, the monitoring module is further configured to: identify an earliest intersection time among the intersection times of all monitoring objects with the vehicle; and obtain a safety reaction time length required for braking of the vehicle, and determine a latest next monitoring start time of the vehicle according to the earliest intersection time and the safety reaction time length.

[0022] With reference to the second aspect and the above implementation manner, in some possible implementation manners, the identifying module is further configured to: obtain a panoramic image in the driving direction of the vehicle; and identify the attribute information of the one or more objects in the panoramic image.

[0023] With reference to the second aspect and the above implementation manner, in some possible implementation manners, the identifying module is further configured to: obtain the panoramic image at an interval of a first preset time length if the vehicle is in a monitoring state; and obtain the panoramic image at an interval of a second preset time length if the vehicle is in a non-monitoring state.

[0024] With reference to the second aspect and the above implementation manner, in some possible implementation manners, the monitoring device of the vehicle further comprises a determining module configured to: if the next monitoring start time of the vehicle has been determined before the panoramic image is obtained at the interval of the second preset time length, determine an interval obtaining time length of the panoramic image according to a current time of the vehicle and the next monitoring start time of the vehicle, or obtain the panoramic image at the interval of the second preset time length.

[0025] In some possible implementation manners, in combination with the second aspect and the foregoing implementation manners, the monitoring device of the vehicle further includes a stopping module configured to stop monitoring the area where the monitoring object is likely to appear after the monitoring device of the host vehicle monitors the target area, if the intersection probability of the monitoring object is less than or equal to a preset probability.

[0026] In a third aspect, a vehicle is provided, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and the processor executes the program to implement the method in the first aspect or any possible implementation manner of the first aspect.

[0027] In a fourth aspect, a computer readable storage medium is provided, which stores computer program code, and when the computer program code runs on a computer, the computer executes the method in the first aspect or any possible implementation manner of the first aspect. BRIEF DESCRIPTION OF DRAWINGS

[0028] Figure 1 FIG. 1 is a flowchart of a monitoring method of a vehicle according to an embodiment of the present application;

[0029] Figure 2 FIG. 2 is a schematic diagram of intersection of an object and a vehicle according to an embodiment of the present application;

[0030] Figure 3 FIG. 3 is a schematic diagram of a target area according to an embodiment of the present application;

[0031] Figure 4 FIG. 4 is a flowchart of a monitoring method of a vehicle according to an embodiment of the present application;

[0032] Figure 5 FIG. 5 is a schematic diagram of a monitoring device of a vehicle according to an embodiment of the present application. DETAILED DESCRIPTION

[0033] The technical solutions in the present application will be described clearly and exhaustively in combination with the drawings. In the description of the embodiments of the present application, unless otherwise specified, " / " represents the meaning of or, for example, A / B can represent A or B: "and / or" in the text is only a description of the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which means that there are three cases of A alone, A and B together, and B alone. In addition, in the description of the embodiments of the present application, "multiple" means two or more than two.

[0034] Hereinafter, the terms "first", "second", "third", etc. are used only for the purpose of description, and cannot be understood as implying or suggesting relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second", etc. can explicitly or implicitly include one or more of the features.

[0035] Figure 1 is a schematic flowchart of a monitoring method of a vehicle provided by an embodiment of the present application.

[0036] As shown in Figure 1 , the method comprises the following steps:

[0037] In step S101, attribute information of one or more objects in the driving direction of the vehicle is identified.

[0038] The objects can be pedestrians, vehicles, cyclists, animals, etc.; the attribute information includes the size, type, position, speed and direction of the objects, etc.

[0039] In the embodiment of the present application, the attribute information of one or more objects in the driving direction of the vehicle is identified, including: obtaining a panoramic image in the driving direction of the vehicle; identifying attribute information of one or more objects in the panoramic image.

[0040] The panoramic image can be obtained by scanning the panoramic area by sensors of devices such as cameras, laser radars or millimeter wave radars, and the specific acquisition method is not limited.

[0041] It can be understood that the embodiment of the present application can obtain the panoramic image in the driving direction of the vehicle by using some devices that can obtain panoramic images, and further identify the attribute information of the objects in the obtained panoramic image.

[0042] In step S102, the intersection probability and intersection time of each object with the vehicle are predicted according to the attribute information.

[0043] It can be understood that the embodiment of the present application can predict the intersection probability and intersection time t of each object with the vehicle according to the attribute information of each object, such as predicting the intersection probability and intersection time t of each object with the vehicle according to the identified object attribute such as the direction of travel and speed.

[0044] In step S103, the object with an intersection probability greater than a preset probability is taken as a monitoring object, the intersection time of all monitoring objects is determined to determine the next monitoring start time of the vehicle, the area where the monitoring object is likely to appear when the vehicle starts monitoring next time is taken as a target area, and the monitoring device of the vehicle is controlled to monitor the target area.

[0045] The preset probability can be set according to specific conditions, and is not specifically limited; the monitoring device can be a fixed camera of the vehicle or a camera with variable focal length and variable angle, and is not specifically limited.

[0046] It should be noted that the object with the intersection probability greater than the preset probability is taken as the monitoring object in the embodiment of the application, and the object with the intersection probability less than or equal to the preset probability is not taken as the monitoring object, so that important objects (monitoring objects) can be monitored on the basis of comprehensive monitoring, and the interference of invalid information on monitoring and the waste of computing power are greatly reduced.

[0047] It can be understood that the object with the intersection probability greater than the preset probability is taken as the monitoring object in the embodiment of the application, the time at which the vehicle starts monitoring next time is further determined according to the intersection time of all monitoring objects, and the area in which the monitoring object is likely to appear when the vehicle starts monitoring next time is taken as a key monitoring area (target area), so that the vehicle is controlled to monitor the target area by using the monitoring device, panoramic area monitoring and key area monitoring are realized, and the comprehensiveness of monitoring is ensured.

[0048] In addition, if a sensor such as a camera with variable focal length and variable angle is used, the sensor can be aimed at the corresponding area for sampling and detection (the camera with variable focal length and variable angle can reduce the number of fixed cameras and improve the accuracy of a specific area), and if a fixed camera is used, the specified area is directly drawn for identification and analysis. In particular, when the vehicle is installed with a camera with variable focal length and variable angle or other sensing devices, the number of sensing devices can be further reduced, and the flexibility of detection is increased.

[0049] In the embodiment of the application, the time at which the vehicle starts monitoring next time is determined according to the intersection time of all monitoring objects, including: identifying the earliest intersection time in the intersection time of all monitoring objects and the vehicle; obtaining a safety reaction time required for braking of the vehicle, and determining the latest time at which the vehicle starts monitoring next time according to the earliest intersection time and the safety reaction time.

[0050] It can be understood that the latest time at which the vehicle starts monitoring next time is further determined according to the earliest intersection time of all monitoring objects and the vehicle and the safety reaction time required for braking of the vehicle, wherein the latest time t' should be less than the intersection time and should consider the braking reaction time of the vehicle and the redundancy time.

[0051] For example, as Figure 2As shown, the bicycle speed is 2 m / s, the distance from the bicycle lane is 3 m, the bicycle needs 1.5 s to enter the bicycle lane, the bicycle lane width is 4 m, the bicycle needs 3.5 s to open the bicycle lane; the pedestrian speed with a backpack is 1 m / s, the distance from the bicycle lane is 2 m, the pedestrian needs 2 s to enter the bicycle lane, and the pedestrian needs 6 s to leave the bicycle lane; the distance from the bicycle to the sidewalk is 5 m, and the speed is 5 m / s, so the intersection time t with the bicycle is 1.5 s. Assuming that according to the braking performance of the vehicle and the existing speed of the pedestrian, the vehicle brakes again after 300 ms, there is still enough safety space, and then the next monitoring time T can be set to be less than t' = 300 ms, for example, set to 200 ms. It should be noted that the above calculation process is different from the speed of each object, the braking reaction time, the distance, and the like because of the safety distance in the setting strategy.

[0052] After determining the latest time T of the next start of monitoring of the vehicle, the area that can appear at the next monitoring time T of the monitoring object is taken as a key monitoring area (target area), for example Figure 2 The next monitoring time of the three monitoring objects in the above example is T = 200 ms, and the objects that are farther away can have different priorities, such as T = 700 ms and T = 1500 ms. Within 200 ms, panoramic scanning can be arranged, and the area that can appear within 200 ms is determined according to the direction and speed of the different objects at 200 ms, as shown in the black square area in the above example (the bicycle speed is faster, so the area that can appear is larger than that of the pedestrian). Figure 3

[0053] In the embodiments of the present application, the monitoring device of the vehicle controls the target area, including: dividing the area outside the target area into one or more non-target areas; setting the priority of the target area as a first priority, and setting the priority of each non-target area as a second priority, wherein the monitoring level of the first priority is higher than the monitoring level of the second priority; generating a monitoring sequence in the order of the first priority and the second priority, wherein the monitoring sequence is to monitor the target area once every interval of a non-target area.

[0054] The area that can appear at the next start of monitoring of the vehicle is the target area, and the area outside the target area in the panoramic image is the non-target area, that is, the area that is not monitored as a key, such as the target area in the above example Figure 3 The area within the preset range around the black square range can be set as a non-target area, and the non-target area can be divided into multiple, and the number of non-target areas and the preset range can be set according to specific conditions, such as the non-target area being the area within 2 m or 3 m around the target area, and the non-target area being divided into multiple.

[0055] ​It is understood that, in the embodiments of this application, the area outside the target area can be divided into one or more non-target areas, and the target area has a higher priority than the non-target areas. The target area has the first priority, and the non-target areas have the second priority. The monitoring is carried out in the order of first priority → second priority → first priority → second priority, and so on, so as to achieve key monitoring of the target area with a high monitoring frequency, and monitoring of the non-target areas with a lower monitoring frequency than the target area, thereby effectively reducing monitoring resources.

[0056] For example, if an intelligent driving system composed of multiple cameras has a total of 40 megapixels, and the platform's computing power can process 10 megapixels every 10 ms, then monitoring the entire system would take 40 ms. After dividing the system into first priority (high priority) and second priority, for example, if the high priority target area to be monitored is only 8 megapixels (e.g., ... Figure 3 (As shown in the black box area), taking 5 non-target areas as an example, the monitoring can be set to monitor the screen every 10ms, with the monitoring order being high → low → high → low → high → low → high → low. This reduces the monitoring cycle for key monitoring targets from once every 40ms to once every 20ms. Because monitoring is done every 10ms, one high-priority (target area) monitoring is interspersed with one low-priority (non-target area) monitoring. Therefore, the monitoring cycle for the target area is 20ms (5 low-priority screen checks cover all pixels, including one high-priority screen check). This improves the focus on monitoring the target area, increases the monitoring frequency, and enhances monitoring performance. Alternatively, from another perspective, combined with... Figure 3 And the calculations in the above embodiments Figure 3 The monitoring time for the next appearance of the monitored object is T=200ms. Therefore, the above-mentioned target (key) area only needs to be monitored once every 200ms. A panoramic monitoring is interspersed within 200ms, which reduces the computing power of the chip by more than 80% and greatly reduces the performance requirements of the chip.

[0057] In this embodiment of the application, after controlling the vehicle's monitoring equipment to monitor the target area, the method further includes: if the intersection probability of the monitored objects is less than or equal to a preset probability, then stop monitoring the area where the monitored objects may appear.

[0058] Understandably, if the probability of intersection of monitored objects is less than or equal to the preset probability, monitoring of the area where the monitored objects may appear will be stopped, thereby enabling monitoring of key monitored objects and reducing resource consumption.

[0059] It should be noted that regarding the entry and removal of monitored objects, once an object has been identified, it will continue to be monitored and even controlled as long as there is still theoretical feasibility, even if it is temporarily blocked by an object, such as a pedestrian being briefly blocked by a vehicle on the side of the road while crossing the road. Unless the vehicle has moved away and there is no theoretical possibility of intersection, the object will be removed from the monitoring.

[0060] In this embodiment of the application, acquiring a panoramic image in the direction of the vehicle's travel includes: if the vehicle is under monitoring, acquiring a panoramic image at a first preset time interval; if the vehicle is not under monitoring, acquiring a panoramic image at a second preset time interval.

[0061] The first and second preset durations can be set according to specific circumstances.

[0062] Understandably, if the vehicle is under monitoring, a panoramic image is acquired at a first preset interval; if the vehicle is not under monitoring, a panoramic image is acquired at a second preset interval, ensuring that a panoramic image is scanned once per unit time, thus guaranteeing the comprehensiveness of the monitoring.

[0063] In this embodiment of the application, before acquiring the panoramic image at a second preset time interval, the method further includes: if the vehicle has already determined the time when monitoring will start again; determining the time interval for acquiring the panoramic image based on the vehicle's current time and the time when monitoring will start again; otherwise, acquiring the panoramic image at a second preset time interval.

[0064] It is understood that, in this embodiment of the application, before acquiring panoramic images at a second preset time interval, if the vehicle has already determined the time when monitoring will start again, the time interval for acquiring panoramic images is determined based on the vehicle's current time and the time when monitoring will start again; otherwise, panoramic images are acquired at a second preset time interval.

[0065] like Figure 4 As shown, the specific process of the vehicle monitoring method in this application embodiment includes the following steps:

[0066] Step 1. Scan the panoramic or designated area using at least one of the following sensors: camera, lidar, and millimeter-wave radar.

[0067] Step 2. Identify all or part of the attributes of objects in the specified area, including size, type, location, speed, and direction, and build or update the 3D base map.

[0068] Step 3. Determine the next detection time T for different objects. Based on the attributes of the vehicle and the identified objects, such as direction of travel and speed, predict the probability of each object intersecting with the vehicle and the intersection time t, and determine the latest next monitoring time t'. t' should be less than t and should take into account the vehicle's braking reaction time and redundancy time.

[0069] Step 4. The objects and attributes in the current identification area in the complete 3D space, including size, speed, direction t and t', etc., are constructed or updated. The objects and attributes that have no influence on the possibility are removed from the 3D space and are no longer monitored.

[0070] Step 5. According to the set strategy, the panoramic image or the specific area to be monitored is determined by considering the length of t' of each object in the 3D space under the premise that the panoramic image must be scanned once per unit time, and the scanning time T (T < t') of the specific area is determined.

[0071] Step 6. If it is a specific area, the area where each object is likely to appear during the current detection is determined as the detection and identification area during the current detection according to the object attributes such as the speed and direction detected last time.

[0072] Step 7. If it is a camera or other sensor with adjustable focal length and angle, it can be aligned to the specified area for sampling.

[0073] It should be noted that the embodiments of the present application refer to the trajectory trend prediction of the detected object by using the thinking mode of the human brain, calculate the monitoring area, and monitor the key target object, which can greatly reduce the interference of invalid information on the system and the waste of computing power. At the same time, panoramic scanning and focus area insertion can ensure the comprehensiveness and real-time of monitoring and reduce resource consumption. At present, the event camera and pulse neural network, which also refer to the working of the human brain, cannot be directly connected with the existing software and hardware ecology, so the present application can be deployed on the existing software and hardware ecology, greatly improving the working efficiency of vehicle monitoring.

[0074] According to the vehicle monitoring method provided by the embodiments of the present application, the objects that have a high possibility of intersection with the vehicle are taken as the monitoring objects, and the area where the monitoring objects are likely to appear at the monitoring moment is taken as the target area to be monitored, so that the target area is defined by the area where the monitoring objects appear, the monitoring is more targeted, the interference of invalid information on the monitoring can be effectively reduced without affecting the safety monitoring of the surrounding environment, the monitoring resource consumption can be effectively reduced, the target area is mainly monitored, the monitoring frequency of the monitoring objects is higher, the performance of the monitoring can be effectively improved, the better monitoring effect can be achieved by lower resource consumption, the computing power requirement of the chip for monitoring is effectively reduced, the general performance chip can also meet the requirements of the monitoring, and the cost of the monitoring is reduced.

[0075] Figure 5 FIG. 1 is a structural schematic diagram of a vehicle monitoring device provided by an embodiment of the present application.

[0076] For example, Figure 5As shown, the device 10 can include an identification module 100, a prediction module 200 and a monitoring module 300.

[0077] The identification module 100 is configured to identify attribute information of one or more objects in the driving direction of the vehicle.

[0078] The prediction module 200 is configured to predict, according to the attribute information, a meeting probability and a meeting time of each object with the vehicle.

[0079] The monitoring module 300 is configured to take the object with a meeting probability greater than a preset probability as a monitoring object, determine a next monitoring start time of the vehicle according to the meeting time of all the monitoring objects, take a region where the monitoring object is likely to appear at the next monitoring start time of the vehicle as a target region, and control a monitoring device of the vehicle to monitor the target region.

[0080] In the embodiment of the present application, the monitoring module 300 is further configured to divide a region other than the target region into one or more non-target regions, set a priority of the target region as a first priority and set a priority of each non-target region as a second priority, wherein a monitoring level of the first priority is higher than a monitoring level of the second priority, and generate a monitoring sequence in the order of the first priority and the second priority, wherein the monitoring sequence is monitoring the target region once every interval of a non-target region.

[0081] In the embodiment of the present application, the monitoring module 300 is further configured to identify an earliest meeting time in the meeting time of all the monitoring objects with the vehicle, obtain a safety reaction time length required for braking of the vehicle, and determine a latest next monitoring start time of the vehicle according to the earliest meeting time and the safety reaction time length.

[0082] In the embodiment of the present application, the identification module 100 is further configured to obtain a panoramic image in the driving direction of the vehicle, and identify the attribute information of one or more objects in the panoramic image.

[0083] In the embodiment of the present application, the identification module 100 is further configured to obtain the panoramic image at an interval of a first preset time length if the vehicle is in a monitoring state, and obtain the panoramic image at an interval of a second preset time length if the vehicle is in a non-monitoring state.

[0084] In the embodiment of the present application, the device 10 of the present application further includes a determination module.

[0085] The determination module is configured to, before obtaining the panoramic image at an interval of the second preset time length, determine the next monitoring start time of the vehicle if the next monitoring start time of the vehicle has been determined, determine an interval obtaining time length of the panoramic image according to a current time of the vehicle and the next monitoring start time of the vehicle, or otherwise obtain the panoramic image at an interval of the second preset time length.

[0086] In the embodiment of the present application, the device 10 further comprises a stopping module.

[0087] The stopping module is configured to stop monitoring the area where the monitoring object is likely to appear after the monitoring device of the vehicle monitors the target area.

[0088] The monitoring device of the vehicle provided in the embodiment of the present application can take the object having a large intersection probability with the vehicle as the monitoring object, and take the area where the monitoring object is likely to appear at the monitoring time as the target area to be monitored, so that the target area is defined, the area where the monitoring object appears is taken as the target area, the monitoring is more targeted, the invalid information can be effectively reduced from interfering with the monitoring without affecting the safety monitoring of the surrounding environment, so that the consumption of monitoring resources can be effectively reduced, the target area is mainly monitored, the monitoring frequency of the monitoring object is higher, the performance of the monitoring can be effectively improved, and then better monitoring effect can be achieved with lower resource consumption, the requirement of the chip for the computing power of the monitoring is effectively reduced, the chip with general performance can also meet the requirement of the monitoring, and the cost of the monitoring is reduced.

[0089] In addition, the embodiment of the present application also protects a vehicle, which can include a memory and a processor, wherein the memory stores executable program code, and the processor is configured to call and execute the executable program code to execute the monitoring method of the vehicle provided in the embodiment of the present application.

[0090] The embodiment also provides a computer readable storage medium, which stores computer program code, and when the computer program code is run on a computer, the computer executes the related method steps to implement the monitoring method of the vehicle provided in the above embodiment.

[0091] The device, the computer readable storage medium or the chip provided in the embodiment are all used to execute the corresponding method provided above, and thus the beneficial effects achieved thereby can refer to the beneficial effects in the corresponding method provided above, which will not be described herein again.

[0092] Through the description of the above embodiments, those skilled in the art can understand that, for the convenience and brevity of description, only the division of the above functional modules is taken as an example for illustration, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above.

[0093] In the embodiments of the present disclosure, it should be understood that the disclosed apparatus and method can be implemented in other ways. For example, the apparatus embodiments described above are merely schematic, and the division of the modules or units is merely a logical function division. In actual implementation, another division manner can be adopted, for example, a plurality of units or components can be combined or integrated into another apparatus, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, apparatuses or units, and can be electrical, mechanical or in other forms.

[0094] The above merely describes specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present disclosure, which should be covered by the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. A method for monitoring vehicles, characterized in that, The method includes: Identify the attribute information of one or more objects in the direction of travel of this vehicle; Based on the attribute information, predict the probability and time of intersection between each object and the vehicle; Objects with a convergence probability greater than a preset probability are designated as monitoring objects. The time when the vehicle will start monitoring again is determined based on the convergence time of all monitoring objects. The area where the monitoring objects may appear when the vehicle starts monitoring again is designated as the target area. The vehicle's monitoring equipment is then controlled to monitor the target area. The monitoring equipment controlling the vehicle to monitor the target area includes: The area outside the target area is divided into one or more non-target areas; The target area is set to the first priority, and each non-target area is set to the second priority, wherein the monitoring level of the first priority is higher than the monitoring level of the second priority. The monitoring order is generated according to the first priority and the second priority, wherein the monitoring order is to monitor the target area once every non-target area.

2. The method according to claim 1, characterized in that, The step of determining the next start time for monitoring of this vehicle based on the intersection time of all monitored objects includes: Identify the earliest intersection time among all the intersection times between the monitored objects and this vehicle; Obtain the safe reaction time required for the vehicle to brake, and determine the latest time when the vehicle will start monitoring next based on the earliest intersection time and the safe reaction time.

3. The method according to claim 1, characterized in that, The identification of attribute information of one or more objects in the direction of travel of this vehicle includes: Obtain a panoramic image along the vehicle's direction of travel; Identify the attribute information of one or more objects in the panoramic image.

4. The method according to claim 3, characterized in that, The acquisition of a panoramic image along the vehicle's driving direction includes: If the vehicle is under monitoring, the panoramic image is acquired at a first preset time interval; If the vehicle is not under monitoring, the panoramic image will be acquired at a second preset time interval.

5. The method according to claim 4, characterized in that, Before acquiring the panoramic image at a second preset time interval, the process also includes: If the time for the next start of monitoring for this vehicle has been determined; The interval for acquiring the panoramic image is determined based on the current time of the vehicle and the time when monitoring will start next; otherwise, the panoramic image is acquired at a second preset interval.

6. The method according to claim 1, characterized in that, After controlling the vehicle's monitoring equipment to monitor the target area, the method further includes: If the intersection probability of the monitored objects is less than or equal to the preset probability, then monitoring of the area where the monitored objects may appear will be stopped.

7. A vehicle monitoring device, characterized in that, The apparatus for implementing the method as described in any one of claims 1 to 6 comprises: The identification module is used to identify the attribute information of one or more objects in the direction of travel of this vehicle; The prediction module is used to predict the probability and time of intersection between each object and the vehicle based on the attribute information. The monitoring module is used to identify objects with a convergence probability greater than a preset probability as monitoring objects, determine the time when the vehicle will start monitoring again based on the convergence time of all monitoring objects, and identify the area where the monitoring objects may appear when the vehicle starts monitoring again as the target area, and control the vehicle's monitoring equipment to monitor the target area.

8. A vehicle, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the method as claimed in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed, implements the method as described in any one of claims 1 to 6.

Images