Road monitoring method and device and terminal equipment

Abstract

The invention is suitable for the technical field of Internet of Vehicles, and provides a road monitoring method and device and terminal equipment, and the method comprises the steps: obtaining current target recognition results corresponding to a plurality of base stations in a target road at a current moment; obtaining a historical target recognition result corresponding to each historical target; fusing the current target recognition results corresponding to the base stations to generate a fused target recognition result corresponding to the target road; according to the fusion target identification result and the historical target identification result corresponding to each historical target, generating a current driving track corresponding to each current target; and according to the current driving track corresponding to each current target, detecting a traffic event occurring in the target road. Therefore, effective transmission of the target identity among a plurality of base stations is realized, long-distance continuous tracking of the target is realized, and the reliability of traffic incident detection is improved.

Description

Technical Field

[0001] This application belongs to the technical field of vehicle networking, and particularly relates to a road monitoring method, device, terminal device, and computer-readable storage medium. Background Art

[0002] With the continuous in-depth application of information and communication technologies in the vehicle and road monitoring industries, roadside base stations containing various radars, various sensors, cameras and other sensing devices have emerged, and the roadside base stations are deployed on roads to monitor the running conditions of vehicles on the roads in real time.

[0003] In related technologies, the discrimination and monitoring of traffic events of vehicles by intelligent transportation rely on the continuous tracking of vehicles in the entire traffic scene, and the tracking of vehicles first depends on the perception of vehicle information by roadside base stations. Since multiple roadside base stations usually need to be deployed in the entire traffic scene to monitor vehicles, and after a vehicle travels from the perception range of one roadside base station to the perception range of another roadside base station, effective identity transfer usually cannot be achieved, so long-distance continuous tracking of vehicles cannot be achieved. Summary of the Invention

[0004] Embodiments of this application provide a road monitoring method, device, terminal device, and storage medium, which can solve the problem that multiple roadside base stations usually need to be deployed in the entire traffic scene to monitor vehicles, and after a vehicle travels from the perception range of one roadside base station to the perception range of another roadside base station, effective identity transfer usually cannot be achieved, so long-distance continuous tracking of vehicles cannot be achieved.

[0005] In a first aspect, an embodiment of this application provides a road monitoring method, including: obtaining current target recognition results respectively corresponding to multiple base stations on a target road at a current moment, where the current target recognition results include recognition results of current targets within the perception ranges corresponding to the base stations; obtaining historical target recognition results corresponding to each historical target, where a historical target refers to a target detected by any base station before the current moment, and the historical target recognition results include target recognition results corresponding to each moment before the current moment of the historical target; fusing the current target recognition results respectively corresponding to the base stations to generate a fused target recognition result corresponding to the target road; generating current driving trajectories corresponding to each current target according to the fused target recognition result and the historical target recognition results corresponding to each historical target; and detecting traffic events occurring on the target road according to the current driving trajectories corresponding to each current target.

[0006] In a second aspect, an embodiment of the present application provides a road monitoring device, including: a first acquisition module, configured to acquire current target recognition results respectively corresponding to a plurality of base stations in a target road at a current moment, where the current target recognition results include recognition results of current targets within the sensing range corresponding to the base stations; a second acquisition module, configured to acquire historical target recognition results corresponding to each historical target, where a historical target refers to a target detected by any base station before the current moment, and the historical target recognition results include target recognition results corresponding to each moment before the current moment of the historical target; a first generation module, configured to fuse the current target recognition results respectively corresponding to each base station to generate a fused target recognition result corresponding to the target road; a second generation module, configured to generate a current driving trajectory corresponding to each current target according to the fused target recognition result and the historical target recognition results corresponding to each historical target; and a first detection module, configured to detect traffic events occurring in the target road according to the current driving trajectories corresponding to each current target.

[0007] In a third aspect, an embodiment of the present application provides a terminal device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, where when the processor executes the computer program, the road monitoring method as described above is implemented.

[0008] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, where when the computer program is executed by a processor, the road monitoring method as described above is implemented.

[0009] In a fifth aspect, an embodiment of the present application provides a computer program product, when the computer program product runs on a terminal device, enabling the terminal device to execute the road monitoring method as described above.

[0010] The beneficial effects of the embodiment of the present application compared with the prior art are as follows: By fusing the current target recognition results corresponding to each base station in the target road, a fused target recognition result corresponding to the target road is generated, and according to the historical target recognition results of the historical targets detected before the current moment and the fused target recognition result corresponding to the target road, the current target is matched with each historical target to generate a current driving trajectory corresponding to the current target, and traffic events occurring in the target road are detected according to the current driving trajectories corresponding to each current target, thereby not only realizing the effective transfer of target identities among multiple base stations, realizing long-distance continuous tracking of the target, but also improving the reliability of traffic event detection. Description of the Drawings

[0011] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the accompanying drawings required for use in the embodiments or the description of the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0012] Figure 1 is a schematic flowchart of a road monitoring method provided by an embodiment of the present application;

[0013] Figure 2 is a schematic installation diagram of a road monitoring system provided by an embodiment of the present application;

[0014] Figure 3 is a schematic installation diagram of a road monitoring system provided by another embodiment of the present application;

[0015] Figure 4 is a schematic flowchart of a road monitoring method provided by another embodiment of the present application;

[0016] Figure 5 is a schematic structural diagram of a road monitoring device provided by an embodiment of the present application;

[0017] Figure 6 is a schematic structural diagram of a terminal device provided by an embodiment of the present application. Detailed implementation manners

[0018] In the following description, for the purpose of illustration rather than limitation, specific details such as specific system structures and technologies are proposed to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0019] It should be understood that when used in the specification and appended claims of the present application, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0020] It should also be understood that the term " / and" as used in the specification and appended claims of the present application refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0021] As used in the specification of this application and the appended claims, the term "if" may be construed contextually as "when", "once", "in response to determining", or "in response to detecting". Similarly, the phrase "if determined" or "if [the described condition or event] is detected" may be construed contextually to mean "once determined", "in response to determining", "once [the described condition or event] is detected", or "in response to detecting [the described condition or event]".

[0022] In addition, in the description of the specification of this application and the appended claims, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and should not be construed as indicating or implying relative importance.

[0023] The reference to "one embodiment" or "some embodiments" etc. described in the specification of this application means that a specific feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of this application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "comprising", "including", "having", and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0024] The road monitoring method, device, terminal device, storage medium, and computer program provided by this application will be described in detail below with reference to the accompanying drawings.

[0025] Figure 1 A flowchart showing a road monitoring method provided by an embodiment of this application is shown.

[0026] As Figure 1 shown, the road monitoring method includes the following steps:

[0027] Step 101, obtain the current target recognition results respectively corresponding to multiple base stations in the target road at the current moment, where the current target recognition results include the recognition results of the current targets within the sensing range corresponding to the base stations.

[0028] It should be noted that the road monitoring method in the embodiments of the present application can be executed by the road monitoring device in the embodiments of the present application. The road monitoring device in the embodiments of the present application can be configured in any terminal device to execute the road monitoring method in the embodiments of the present application. For example, in the field of vehicle-to-everything (V2X) communication technology, the road monitoring device in the embodiments of the present application can be configured in the upper computer of the roadside base station of the V2X system, so that the V2X system can continuously track vehicles on the road over a long distance through multiple base stations deployed on the road.

[0029] Each base station may include one or more monitoring devices such as lidar, millimeter-wave radar, cameras, etc., and is deployed on the road to monitor targets such as vehicles on the road.

[0030] As a possible implementation, the base station can also adopt a layout scheme of pure video cameras. For example, each base station can include two short-focus cameras and one fisheye camera.

[0031] As an example, when the road monitoring method in the embodiments of the present application is applied to an intersection, that is, when the target road is an intersection, the base stations can be deployed at the intersection in the manner as Figure 2 shown. Deploy one base station at the traffic police pole at a first preset distance (such as 15-20 meters) from the stop line in each road direction at the intersection, for a total of 4 base stations. Each base station includes two short-focus cameras and one fisheye camera respectively. One short-focus camera faces the intersection direction, and the other short-focus camera faces the road section direction. The fisheye camera can be placed under the traffic police pole to cover the blind areas of the two short-focus cameras. Deploy one base station in each direction of the intersection, and finally, full-coverage monitoring of the entire intersection area can be achieved.

[0032] As an example, when the road monitoring method in the embodiments of the present application is applied to a tunnel, that is, when the target road is a tunnel, the base stations can be deployed at the intersection in the manner as Figure 3 shown. Among them, the base station includes a bayonet traffic police, a laser base station, and multiple camera base stations; among them, the bayonet traffic police includes a bayonet camera, the laser base station includes a lidar, and each camera base station includes two short-focus cameras and one fisheye camera; the bayonet traffic police, the laser base station, and each camera base station are arranged in a straight line along the driving direction of the tunnel. The distance between the bayonet traffic police and the lidar can be a second preset distance (such as 10m), the distance between the laser base station and the first camera base station can be a third preset distance (such as 30m), and the distance between two adjacent cameras can be a fourth preset distance (such as 90m); the bayonet traffic police and the lidar are used to identify and bind the target before it enters the tunnel.

[0033] Among them, the current target recognition result may refer to the recognition results of each target within its sensing range generated based on the monitoring data collected by the base station at the current moment.

[0034] Among them, the current target may refer to each target monitored by the base station at the current moment.

[0035] In the embodiments of the present application, each base station can monitor the targets within its sensing range at a certain frequency, analyze and integrate the monitoring data collected at each monitoring moment, and generate the recognition results of the targets monitored at each monitoring moment. Therefore, in the embodiments of the present application, for each monitoring moment, after generating the target recognition result of that monitoring moment, the target recognition results corresponding to each base station can be integrated to determine all the targets monitored by each base station at that monitoring moment, and combined with the target recognition results of the previous moment, the identities of the targets monitored at that monitoring moment can be recognized and transmitted. Therefore, when the current moment is a monitoring moment, the current target recognition results respectively corresponding to each base station at the current moment can be obtained to perform identity transmission on each current target monitored at the current moment.

[0036] As an example, the target in the embodiments of the present application can be a vehicle. Correspondingly, the recognition result can include at least one of the license plate number, feature data, and real-time driving data of the vehicle. For example, the feature data can include data such as the color, size, and category of the vehicle, and the real-time driving data can include data such as the real-time position, heading angle, speed, and acceleration of the vehicle. The present application does not make any limitations in this regard.

[0037] Furthermore, since a base station can include multiple sensing devices, such as two short-focus cameras and one fisheye camera, the current target recognition result corresponding to a base station can be determined by integrating the sensing data of each sensing device it includes. That is, in a possible implementation manner of the embodiments of the present application, each base station can include multiple sensing devices; correspondingly, step 101 above can include:

[0038] Obtain the current target recognition results corresponding to each sensing device in the first base station, where the first base station is any base station, and the current target recognition result corresponding to the sensing device includes the recognition result of the current target within the sensing range corresponding to the sensing device;

[0039] Fuse the current target recognition results corresponding to each sensing device to generate the current target recognition result corresponding to the first base station.

[0040] In the embodiments of the present application, for a first base station, each of the included sensing devices can monitor the targets within the sensing range at a certain frequency, analyze and integrate the monitoring data collected at each monitoring moment, and generate the recognition results of the targets monitored at each monitoring moment. Therefore, in the embodiments of the present application, for each monitoring moment, the target recognition results corresponding to each sensing device can be integrated to determine all the targets monitored by the first base station at that monitoring moment. Therefore, when the current moment is a monitoring moment, the current target recognition results respectively corresponding to each sensing device in the first base station at the current moment can be obtained and fused to generate the current target recognition result corresponding to the base station.

[0041] Further, since there may be differences in the time and space coordinates of each sensing device in the base station, when fusing the current target recognition results corresponding to each sensing device, time registration and space registration of each sensing device can also be performed first to further improve the reliability of target recognition and long-term monitoring. That is, in a possible implementation manner of the embodiments of the present application, before obtaining the current target recognition results corresponding to each sensing device in the first base station, it may further include:

[0042] Perform time registration on each sensing device;

[0043] Correspondingly, fusing the current target recognition results corresponding to each sensing device to generate the current target recognition result corresponding to the first base station includes:

[0044] According to the preset spatial reference coordinate system, perform spatial registration on the current target recognition results corresponding to each sensing device to generate the spatially registered current target recognition results corresponding to each sensing device;

[0045] Match and correct the spatially registered current target recognition results corresponding to each sensing device to generate the current target recognition result corresponding to the first base station.

[0046] In the embodiments of the present application, time registration can be performed on each sensing device to synchronize the clocks between each sensing device to ensure the accuracy of data fusion and target matching between each sensing device. For example, each sensing device can use GPS, GNSS, or PTP time to time each sensing device for time registration.

[0047] In the embodiments of the present application, since each base station continuously acquires monitoring data within the sensing range at a certain frequency, when integrating the data of each base station, it is necessary to ensure that the integrated data is the data acquired by each base station at the same moment. Thus, when obtaining the current target tracking results of each base station at the current moment, it is possible to determine whether each target tracking result is the target tracking result generated by each base station at the same moment according to the difference between the acquisition times of the target tracking results corresponding to each base station.

[0048] As a possible implementation manner, since time registration has been performed on each sensing device in each first base station, if the acquisition times of the target recognition results corresponding to different sensing devices are very close, it can be determined that these target recognition results are acquired by different sensing devices at the same moment. Therefore, if the time interval between the acquisition time of a target recognition result of a base station and the current moment is less than the time difference threshold, it can be determined that the target recognition result is acquired at the current moment or near the current moment, and thus the target recognition result can be determined as the current target tracking result corresponding to the sensing device; and so on, the current target tracking results corresponding to each sensing device at the current moment can be obtained in sequence.

[0049] As a possible implementation manner, the rotation and translation parameters between each sensing device and the preset spatial reference coordinate system can be determined according to the displacement and angle difference between the preset coordinate system corresponding to each sensing device and the preset spatial reference coordinate system, and the current target recognition result corresponding to each sensing device can be spatially registered respectively according to the rotation and translation parameters between each sensing device and the preset spatial reference coordinate system, so as to represent the current target recognition results of each sensing device in the same coordinate system, and then generate the spatially registered current target recognition results corresponding to each sensing device, that is, the spatially registered recognition results corresponding to each current target sensed by each sensing device; furthermore, matching and correction can be performed according to the spatially registered recognition results corresponding to each current target to remove duplicate current targets; and according to the recognition results corresponding to the duplicate current targets sensed by different sensing devices, the recognition results corresponding to the current target are corrected (such as target category correction, position correction, etc.) to obtain the accurate current target recognition results corresponding to the first base station, that is, to obtain the accurate target recognition results of all current targets detected by the first base station at the current time and space.

[0050] It can be understood that since the sensing ranges of the sensing devices in the same base station usually overlap to ensure that there are as few blind spots as possible in the entire traffic sensing scenario, different sensing devices may simultaneously monitor the same target at the same moment. Therefore, when generating the current target recognition result corresponding to the entire traffic sensing scenario, duplicate removal processing can be performed on the current targets simultaneously monitored by different sensing devices, so that the final generated current target recognition result corresponding to the entire traffic sensing scenario does not contain duplicate targets.

[0051] Step 102: Obtain the historical target recognition results corresponding to each historical target, where a historical target refers to a target detected by any base station before the current moment, and the historical target recognition result includes the target recognition results corresponding to each moment before the current moment for the historical target.

[0052] In the embodiment of the present application, each time a new target is detected by each base station, a tracker corresponding to the new target can be established, and the recognition results of the monitored new target are sequentially recorded in the tracker corresponding to the new target at each subsequent monitoring moment until the new target leaves the sensing ranges of all base stations. Therefore, for a historical target that has been detected before the current moment, the historical target recognition result corresponding to the historical target includes all the historical target recognition results before the current moment. For example, when the target is a vehicle, the historical target recognition result of the historical target can include fixed feature data such as the license plate number, color, category, and size of the historical target, and can also include real-time driving data such as the real-time position, speed, acceleration, and heading angle of the historical target monitored at each moment; or, when a unique serial number is assigned to each target to identify each target, the historical target recognition result of the historical target can also include the serial number of the historical target, such as 0001, 0002, etc.

[0053] Step 103: Fuse the current target recognition results respectively corresponding to each base station to generate a fused target recognition result corresponding to the target road.

[0054] In the embodiments of the present application, each base station can monitor the targets within its sensing range at a certain frequency, analyze and integrate the monitoring data collected at each monitoring moment, and generate the recognition results of the targets monitored at each monitoring moment. Therefore, in the embodiments of the present application, for each monitoring moment, after generating the target recognition results corresponding to each base station at this monitoring moment, the target recognition results corresponding to each base station can be integrated to determine all the targets monitored by each base station at this monitoring moment, and in combination with the target recognition results at the previous moment, the identities of the targets monitored at this monitoring moment can be recognized and transmitted. Therefore, when the current moment is a monitoring moment, the current target recognition results corresponding to each base station can be received through a transmission method such as UDP, and the current target recognition results corresponding to each base station are fused to generate the fused target recognition result corresponding to the target road, so as to perform identity transmission on each current target monitored at the current moment.

[0055] Furthermore, since there may be differences in the time and space coordinates of different base stations, when fusing the current target recognition results corresponding to each base station, time registration and space registration can also be performed on each base station first to further improve the reliability of target recognition and long-term monitoring. That is, in a possible implementation manner of the embodiments of the present application, the above step 103 may include:

[0056] Perform spatio-temporal registration on the current target recognition results corresponding to each base station respectively to generate the spatio-temporally registered current target recognition results corresponding to each base station;

[0057] Match the spatio-temporally registered current target recognition results corresponding to each base station respectively to perform duplicate removal processing on each current target and generate the fused target recognition result.

[0058] In the embodiments of the present application, time registration can be performed on each base station to synchronize the clocks between each base station to ensure the accuracy of data fusion and target matching between each base station. For example, each base station can use GPS, GNSS or PTP time to time each base station for time registration.

[0059] As a possible implementation manner, after time registration, the rotation and translation parameters between any two base stations can be determined according to the displacement and angle difference between the preset coordinate systems corresponding to each base station, and according to the rotation and translation parameters between any two base stations, the current target recognition results corresponding to each base station are spatially registered to generate the spatio-temporally registered current target recognition results corresponding to each base station.

[0060] Specifically, since different base stations are deployed at different locations, the extrinsic parameters of different base stations may be different. Therefore, the monitoring data of the same position in space by different base stations may be inconsistent, resulting in inaccurate fusion due to mismatched extrinsic parameters when fusing the monitoring data between different base stations. Therefore, in the embodiments of the present application, the extrinsic parameter coordinate system of each monitoring device in the base station can be determined as the preset coordinate system corresponding to the base station. Then, according to the rotational and translational position relationships between the preset coordinate systems corresponding to each base station, the rotational and translational parameters between each base station can be determined, so that when fusing the monitoring data of each base station, the monitoring data of each base station can be transformed into the same coordinate system for representation according to the rotational and translational parameters of each base station. Therefore, according to the rotational and translational parameters between any two base stations, spatial registration can be performed on the current target identifications corresponding to each base station, so as to transform the current target identifications corresponding to each base station into the same coordinate system for representation, and generate the current target identification results after spatio-temporal registration corresponding to each base station respectively.

[0061] In the embodiments of the present application, since the sensing ranges of adjacent base stations usually overlap to ensure that there are as few omitted areas as possible in the entire traffic sensing scenario, different base stations may simultaneously monitor the same target at the same time. Therefore, when generating the current target identification result corresponding to the entire traffic sensing scenario, duplicate removal processing can be performed on the current targets simultaneously monitored by different base stations, so that the final generated fusion target identification result corresponding to the entire traffic sensing scenario does not contain duplicate targets.

[0062] As a possible implementation manner, the current position of the current target can be determined according to the identification results of each current target included in the current target identification results after spatio-temporal registration corresponding to each base station. Then, the current position of the current target can be used as the center point of the target box corresponding to the current target, and the size of the target box corresponding to the current target can be determined according to the size of the current target, so as to determine the target boxes corresponding to each current target. Then, according to the intersection-over-union ratio between the target boxes corresponding to each current target, it can be determined whether there are duplicate targets among each current target.

[0063] It can be understood that when the intersection-over-union ratio between the target boxes corresponding to two current targets is greater than or equal to the intersection-over-union ratio threshold, these two current targets can be determined as duplicate targets, and one of them can be removed; if the intersection-over-union ratio between the target boxes corresponding to two current targets is less than the intersection-over-union ratio threshold, these two current targets can be determined as different targets, and no duplicate removal processing is required for these two current targets.

[0064] Step 104, generate the current driving trajectories corresponding to each current target according to the fusion target identification result and the historical target identification results corresponding to each historical target.

[0065] In the embodiment of the present application, the fusion target recognition result corresponding to the target road includes the target recognition results corresponding to each current target in the target road. Therefore, the current target can be matched with each historical target respectively according to the target recognition results corresponding to each current target and the historical target recognition results corresponding to each historical target. If the current target matches any historical target, the target recognition result corresponding to the current target can be fused with the historical target recognition result corresponding to the historical target to generate the current driving trajectory corresponding to the current target. If the current target does not match all historical targets, it can be determined that the current target is a new target that appears in the target road, and then the current driving trajectory corresponding to the current target can be generated according to the target recognition result corresponding to the current target.

[0066] As a possible implementation, if data is missing due to bad weather or base station disconnection, and the complete trajectory of the target within the target road range cannot be obtained, the current driving trajectory corresponding to the current target can also be smoothed by a trajectory smoothing algorithm based on polynomial fitting to improve the accuracy and reliability of target trajectory generation.

[0067] Step 105: Detect traffic events occurring on the target road according to the current driving trajectories corresponding to each current target.

[0068] As a possible implementation, it is possible to determine whether there is an abnormal target in the target road where a traffic event occurs according to the current driving trajectories corresponding to each current target and the map data corresponding to the target road, where the abnormal target is any current target. And when there is an abnormal target, determine the occurrence location, occurrence time, event type and warning level of the traffic event corresponding to the abnormal target.

[0069] Among them, the event type may include instantaneous events, periodic events and abnormal events, but is not limited thereto.

[0070] It should be noted that in actual use, the specific event types corresponding to the traffic events to be detected and the division principles of the warning levels can be set according to actual needs, and the embodiments of the present application do not limit this.

[0071] As a possible implementation, when the event type of the traffic event occurring in the abnormal target is an abnormal event, evidence can also be obtained for the abnormal event. That is, in a possible implementation of the embodiment of the present application, after determining the occurrence location, occurrence time, event type and warning level of the traffic event corresponding to the abnormal target when there is the abnormal target, it may further include:

[0072] According to the occurrence time, obtain the abnormal data corresponding to the abnormal target from the historical target recognition result corresponding to the abnormal target.

[0073] As an example, when it is determined that an abnormal event occurs to an abnormal target, video data corresponding to the abnormal target can be intercepted respectively before and after the occurrence time of the abnormal event according to the occurrence time of the abnormal event, as abnormal data corresponding to the abnormal target, and the abnormal data corresponding to the abnormal target can also be sent to the driver of the abnormal target or the management platform of the target road, such as the traffic police system, etc.

[0074] It should be noted that N is a positive integer. In actual use, the specific value of N and the abnormal data interception method can be determined according to actual needs and specific application scenarios, and the embodiments of the present application do not limit this.

[0075] As a possible implementation manner, the traffic flow of the target road before the current time can also be counted according to the current driving trajectories of each current target.

[0076] Among them, the traffic flow can refer to the total number of targets or the average number of targets passing through the target road within a period of time, but is not limited thereto.

[0077] As an example, the traffic flow of the target road can be counted only within a certain period of time before the current time. For example, the traffic flow of the target road can be counted within 1 hour, 1 day, 1 week or 1 month before the current time, etc., and the embodiments of the present application do not limit this.

[0078] The road monitoring method provided by the embodiments of the present application generates a fused target recognition result corresponding to the target road by fusing the current target recognition results corresponding to each base station in the target road, and matches the current target with each historical target according to the historical target recognition result of the historical target detected before the current time and the fused target recognition result corresponding to the target road, so as to generate the current driving trajectory corresponding to the current target, and detect traffic events occurring in the target road according to the current driving trajectories corresponding to each current target, thereby not only realizing the effective transfer of the target identity between multiple base stations, realizing the long-distance continuous tracking of the target, but also improving the reliability of traffic event detection.

[0079] The following combines Figure 4 to further illustrate the road monitoring method provided by the embodiments of the present application.

[0080] Figure 4 shows a schematic flow chart of another road monitoring method provided by the embodiments of the present application.

[0081] As Figure 4 shown, the road monitoring method includes the following steps:

[0082] Step 401: Obtain the current target recognition results corresponding to multiple base stations in the target road at the current moment, where the current target recognition results include the recognition results of the current targets within the sensing range corresponding to the base stations.

[0083] Step 402: Obtain the historical target recognition results corresponding to each historical target, where a historical target refers to a target detected by any base station before the current moment, and the historical target recognition results include the target recognition results corresponding to each moment before the current moment of the historical target.

[0084] Step 403: Fuse the current target recognition results corresponding to each base station to generate a fused target recognition result corresponding to the target road.

[0085] For the specific implementation process and principle of the above steps 401 - 403, reference can be made to the detailed description of the above embodiments, which will not be elaborated here.

[0086] Step 404: Predict the recognition result of each historical target at the current moment according to the historical target recognition result corresponding to each historical target, so as to generate a predicted recognition result of each historical target at the current moment.

[0087] In the embodiment of the present application, since the historical target recognition result corresponding to a historical target may include all historical target recognition results of the historical target before the current moment, the target recognition result of the historical target at the next moment can be predicted according to the historical target recognition result corresponding to the historical target, that is, the recognition result of the historical target at the current moment is predicted, and the predicted recognition result corresponding to the historical target is compared with the recognition results of each current target actually monitored at the current moment to determine whether each current target monitored at the current moment has been monitored before the current moment, so as to realize the identity transfer of the target.

[0088] As a possible implementation manner, assume that the current moment is the k-th moment, then the historical target recognition results Trk i (k - 1) of each historical target at the (k - 1)-th moment can be obtained, where 1 ≤ i ≤ n and n is the number of historical targets. Then, the Kalman filter algorithm can be used to predict the predicted recognition result Trk i (k|k - 1) of the i-th historical target at the k-th moment according to the historical target recognition result Trk i (k - 1) of the i-th historical target at the (k - 1)-th moment.

[0089] As an example, when the target is a vehicle, since the characteristic data such as the license plate number, category, color, and size of the vehicle are fixed, and the real-time driving data such as the real-time position, speed, acceleration, and heading angle are changing in real time, when making a prediction, it is possible to only predict the real-time driving data of the historical target, and the data such as the license plate number, category, color, and size in the recognition result of the historical target at the k-1 moment can be directly determined as the predicted license plate number, category, color, and size at the k moment.

[0090] Step 405: Determine whether the recognition result of the current target matches the predicted recognition result of any historical target; if so, execute Step 406; otherwise, execute Step 407.

[0091] In the embodiments of the present application, since the predicted recognition result of the historical target can reflect the actual recognition result of the historical target at the current moment, after determining the predicted recognition results of each historical target, it is possible to determine whether there is a historical target whose predicted recognition result matches the recognition result of the current target, so as to determine whether the current target is a historical target that has been monitored before the current moment or a new target that has just been monitored at the current moment according to the matching result, so as to achieve the identity transfer of the target.

[0092] It should be noted that when there are multiple current targets and multiple historical targets, the recognition result of each current target can be compared with the predicted recognition results of each historical target respectively to determine whether there is a matching historical target for each current target.

[0093] Furthermore, since the current target and the historical target may be monitored by different base stations respectively, and the sensing devices in different base stations may be different, resulting in the data types included in the recognition result of the current target and the data types included in the predicted recognition result of the historical target may be different. Therefore, when comparing the predicted recognition result of the historical target with the recognition result of the current target, the data that exists in both the predicted recognition result of the historical target and the recognition result of the current target can be compared. That is, in a possible implementation manner of the present application, the above Step 405 may include:

[0094] Determine whether the license plate number of the current target matches the license plate number of any historical target.

[0095] As a possible implementation, if the predicted recognition results of the historical target and the recognition results of the current target both contain license plate numbers, that is, if cameras are included in the base stations of both the historical target and the current target, the license plate number of the current target can be matched with the license plate number of the historical target. If the license plate number of the current target is the same as that of the historical target, it can be determined that the current target and the historical target are the same target; if the license plate number of the current target is different from that of the historical target, it can be determined that the current target and the historical target are not the same target.

[0096] Furthermore, when the recognition results of the current target and the predicted recognition results of the historical target both contain feature data, the feature data of the two can be matched. That is, in a possible implementation manner of the embodiments of the present application, step 405 above may include:

[0097] Determine whether the feature data of the current target matches the feature data of any historical target.

[0098] As a possible implementation, if the predicted recognition results of the historical target and the recognition results of the current target both contain feature data, that is, if cameras and / or lidar are included in the base stations of both the historical target and the current target, the feature data of the current target can be matched with the feature data of the historical target. If the feature data of the current target matches the feature data of the historical target, it can be determined that the current target and the historical target are the same target; if the feature data of the current target does not match the feature data of the historical target, it can be determined that the current target and the historical target are not the same target.

[0099] Furthermore, when the target is a vehicle, the feature data may include at least one of category, color, size, and speed. Since these feature data are not quantitative data, the matching degree between the feature data can be determined by means of vector matching. That is, in a possible implementation manner of the embodiments of the present application, the above determination of whether the feature data of the current target matches the feature data of any historical target may include:

[0100] Determine a first feature vector corresponding to the current target according to the feature data of the current target;

[0101] Determine a second feature vector corresponding to any historical target according to the feature data of any historical target;

[0102] Determine a feature similarity matrix between the current target and any historical target according to the first feature vector and the second feature vector;

[0103] Determine whether the feature data of the current target matches the feature data of any historical target according to the feature similarity matrix.

[0104] As a possible implementation, for the current target, when there are multiple data in the feature data, vector mapping can be performed on each data in the feature data to generate vectors corresponding to each data in the feature data. Then, the vectors corresponding to each data in the feature data can be concatenated to generate a first feature vector corresponding to the current target. Similarly, the second feature vector corresponding to the historical target can be determined in the same way. Then, according to the similarity between each element of the first feature vector and the corresponding element in the second feature vector, the similarity matrix between the first feature vector and the second feature vector can be determined.

[0105] For example, if the feature data of the current target and the historical target both include vehicle category, color, size, and speed data, then vector mapping can be performed on the vehicle category, color, size, and speed of the current target and the historical target respectively to generate a first feature vector [A1, B1, C1, D1] of the current target and a second feature vector [A2, B2, C2, D2] of the historical target. Furthermore, the similarity matrix between the first feature vector and the second feature vector can be determined as [a, b, c, d], where a is the similarity between A1 and A2, b is the similarity between B1 and B2, c is the similarity between C1 and C2, and d is the similarity between D1 and D2.

[0106] As a possible implementation, after determining the similarity matrix between the current target and the historical target, when each similarity in the similarity matrix is greater than the similarity threshold, it can be determined that the current target and the historical target are the same target; otherwise, it can be determined that the current target and the historical target are not the same target.

[0107] Furthermore, when the recognition result of the current target and the predicted recognition result of the historical target both include real-time driving data, the real-time driving data of both can be matched. That is, in a possible implementation of the embodiments of the present application, step 405 described above can include:

[0108] Determine whether the real-time driving data of each current target matches the predicted driving data of any historical target.

[0109] As a possible implementation, the real-time driving data can include real-time position, and the predicted driving data can include predicted position. Correspondingly, the following method can be used to determine whether the real-time driving data of the current target matches the predicted driving data of the historical target:

[0110] According to the real-time position of the current target at the current moment, determine the first target box corresponding to the current target;

[0111] Determine a second target box corresponding to any historical target according to the predicted position of any historical target at the current moment;

[0112] Determine the intersection over union (IoU) between the first target box and the second target box;

[0113] Judge whether the real-time driving data of the current target matches the predicted driving data of any historical target according to the intersection over union (IoU) between the first target box and the second target box.

[0114] In the embodiment of the present application, the real-time position of the current target at the current moment can be used as the center of the first target box, and the size of the first target box can be determined according to the size of the current target, so as to determine the first target box corresponding to the current target; similarly, the predicted position of the historical target at the current moment can be used as the center of the second target box, and the size of the first target box can be determined according to the size of the historical target, so as to determine the second target box corresponding to the historical target. Then, the intersection over union (IoU) between the first target box and the second target box can be determined, and further, the Hungarian association can be performed on each current target and each historical target according to the intersection over union (IoU) between the first target box and the second target box. When the intersection over union (IoU) between the first target box of a current target and the second target box of a historical target is greater than or equal to the IoU threshold, the Hungarian association between the current target and the historical target is successful, that is, it can be determined that the current target and the historical target are the same target; if the intersection over union (IoU) between the first target box of a current target and the second target box of a historical target is less than the IoU threshold, it can be determined that the current target does not match the historical target, that is, the current target and the historical target are not the same target.

[0115] It should be noted that the above three matching methods, namely license plate number matching, feature matching, and real-time driving data matching, can meet the identity transfer between different base stations under different sensor combinations. When both base stations are equipped with cameras and radars, the three different schemes can be combined for identity transfer at the same time; when at least one party does not have a camera, the identity transfer can also be performed by combining real-time driving data matching and partial feature data matching; when at least one party does not have a radar, but both have cameras and can detect the license plate well, the identity transfer can be performed by combining license plate number and feature matching; when at least one party does not have a radar, and at least one party fails to detect the license plate number, the identity transfer can also be performed by feature matching.

[0116] Step 406, determine that the current target and any historical target are the same target, and generate the current driving trajectory corresponding to the current target according to the recognition result of the current target and the historical target recognition result corresponding to any historical target.

[0117] In an embodiment of the present application, if it is determined that a current target is the same target as any historical target, it can be determined that the current target has been detected before. Thus, the recognition result of the current target can be added to the historical target recognition result corresponding to the historical target, so as to update the historical target recognition result corresponding to the historical target, and a current driving trajectory corresponding to the current target can be generated according to the new historical target recognition result, thereby realizing the identity transfer between the current target and the historical target.

[0118] Step 407: Determine that the current target is a new target detected at the current moment, and generate a current driving trajectory corresponding to the current target according to the recognition result of the current target.

[0119] In an embodiment of the present application, if it is determined that a current target does not match any of the historical targets, it can be determined that the current target is a new target detected at the current moment. Thus, a tracker for the current target can be newly created, and the recognition result of the current target at the current moment can be recorded in the tracker to generate a historical target recognition result for the current target, so as to facilitate subsequent continuous tracking and identity transfer of the current target; and a current driving trajectory corresponding to the current target can be generated according to the recognition result of the current target.

[0120] Step 408: Detect traffic events occurring on the target road according to the current driving trajectories corresponding to each current target.

[0121] For the specific implementation process and principle of the above step 408, reference can be made to the detailed description of the above embodiment, which will not be elaborated here.

[0122] The road monitoring method provided by the embodiment of the present application obtains the current target recognition results respectively corresponding to multiple base stations at the current moment and the historical target recognition results corresponding to each historical target, and predicts the recognition results of each historical target at the current moment according to the historical target recognition results corresponding to each historical target, so as to generate the predicted recognition results of each historical target at the current moment. Then, when the recognition result of the current target matches the predicted recognition result of any historical target, it is determined that the current target and any historical target are the same target, and according to the recognition result of the current target and the historical target recognition result corresponding to the historical target, the current driving trajectory corresponding to the current target is generated. When the recognition result of the current target does not match the predicted recognition results of all historical targets, it is determined that the current target is a new target detected at the current moment, and the current driving trajectory corresponding to the current target is generated according to the recognition result of the current target. Thus, by predicting the predicted recognition results of each historical target at the current moment according to the recognition results of the monitored historical targets, and matching the recognition results of the current targets monitored by all base stations in the target road with the predicted recognition results of each historical target, it is judged whether the current target is a historical target monitored by each base station, so as to realize the effective transfer of the target identity between different base stations, realize the long-distance continuous tracking of the target, and further improve the reliability of traffic event detection.

[0123] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The order of execution of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0124] Corresponding to the road monitoring method described in the above embodiments, Figure 5 The structural block diagram of the road monitoring device provided by the embodiment of the present application is shown. For the convenience of description, only the parts related to the embodiment of the present application are shown.

[0125] Referring to Figure 5 , the device 50 includes:

[0126] The first acquisition module 51 is used to acquire the current target recognition results respectively corresponding to multiple base stations in the target road at the current moment, where the current target recognition results include the recognition results of the current targets within the sensing range corresponding to the base stations;

[0127] The second acquisition module 52 is used to acquire the historical target recognition results corresponding to each historical target, where the historical target refers to the target detected by any base station before the current moment, and the historical target recognition results include the target recognition results corresponding to each moment before the current moment of the historical target;

[0128] The first generation module 53 is configured to fuse the current target recognition results respectively corresponding to each base station to generate a fused target recognition result corresponding to the target road;

[0129] The second generation module 54 is configured to generate the current driving trajectory corresponding to each current target according to the fused target recognition result and the historical target recognition results corresponding to each historical target;

[0130] The first detection module 55 is configured to detect traffic events occurring on the target road according to the current driving trajectories corresponding to each current target.

[0131] In actual use, the road monitoring device provided by the embodiment of the present application can be configured in any terminal device to execute the foregoing road monitoring method.

[0132] The road monitoring device provided by the embodiment of the present application fuses the current target recognition results corresponding to each base station on the target road to generate a fused target recognition result corresponding to the target road, and matches the current target with each historical target according to the historical target recognition results of the historical targets detected before the current moment and the fused target recognition result corresponding to the target road, so as to generate the current driving trajectory corresponding to the current target, and detect traffic events occurring on the target road according to the current driving trajectories corresponding to each current target, thereby not only realizing the effective transfer of the target identity among multiple base stations, realizing the long-distance continuous tracking of the target, but also improving the reliability of traffic event detection.

[0133] In a possible implementation form of the present application, each of the above-mentioned base stations includes a plurality of sensing devices; correspondingly, the first acquisition module 51 includes:

[0134] The first acquisition unit is configured to acquire the current target recognition results corresponding to each sensing device in the first base station, where the first base station is any base station, and the current target recognition result corresponding to the sensing device includes the recognition result of the current target within the sensing range corresponding to the sensing device;

[0135] The first generation unit is configured to fuse the current target recognition results corresponding to each sensing device to generate the current target recognition result corresponding to the first base station.

[0136] Further, in another possible implementation form of the present application, the first acquisition module 51 further includes:

[0137] The first time registration unit is configured to perform time registration on each sensing device;

[0138] Correspondingly, the first generation unit is specifically configured to:

[0139] Perform spatial registration on the current target recognition results corresponding to each perception device according to a preset spatial reference coordinate system to generate the spatially registered current target recognition results corresponding to each perception device;

[0140] Match and correct the spatially registered current target recognition results corresponding to each perception device to generate the current target recognition result corresponding to the first base station.

[0141] Furthermore, in another possible implementation form of the present application, the above-mentioned first generation module 53 includes:

[0142] The first spatio-temporal registration unit is configured to perform spatio-temporal registration on the current target recognition results respectively corresponding to each base station to generate the spatio-temporally registered current target recognition results respectively corresponding to each base station;

[0143] The second generation unit is configured to match the spatio-temporally registered current target recognition results respectively corresponding to each base station to perform duplicate removal processing on each current target and generate a fused target recognition result.

[0144] Furthermore, in another possible implementation form of the present application, the above-mentioned second generation module 54 includes:

[0145] The third generation unit is configured to predict the recognition result of each historical target at the current moment according to the historical target recognition result corresponding to each historical target to generate the predicted recognition result of each historical target at the current moment;

[0146] The first judgment unit is configured to judge whether the recognition result of the current target matches the predicted recognition result of any historical target;

[0147] The fourth generation unit is configured to, when the recognition result of the current target matches the predicted recognition result of any historical target, determine that the current target and any historical target are the same target, and generate the current driving trajectory corresponding to the current target according to the recognition result of the current target and the historical target recognition result corresponding to any historical target;

[0148] The fifth generation unit is configured to, when the recognition result of the current target does not match the predicted recognition results of all historical targets, determine that the current target is a new target detected at the current moment, and generate the current driving trajectory corresponding to the current target according to the recognition result of the current target.

[0149] Furthermore, in another possible implementation form of the present application, the above-mentioned first detection module 55 includes:

[0150] A first determination unit, configured to determine whether there is an abnormal target with a traffic event in a target road according to the current driving trajectory corresponding to each current target and the map data corresponding to the target road, where the abnormal target is any current target.

[0151] When there is an abnormal target, determine the occurrence location, occurrence time, event type, and warning level of the traffic event corresponding to the abnormal target.

[0152] Further, in another possible implementation form of the present application, when the event type of the traffic event is an abnormal event, the above-mentioned first detection module 55 further includes:

[0153] A second acquisition unit, configured to acquire abnormal data corresponding to the abnormal target from the historical target recognition results corresponding to the abnormal target according to the occurrence time.

[0154] Further, in another possible implementation form of the present application, the above-mentioned first detection module 55 further includes:

[0155] A first statistics unit, configured to count the traffic flow of the target road before the current moment according to the current driving trajectories corresponding to each of the current targets.

[0156] It should be noted that the information interaction, execution process, etc. between the above-mentioned device / units, due to being based on the same concept as the method embodiment of the present application, for the specific functions and the technical effects brought by them, reference can be specifically made to the method embodiment part, and details are not described here again.

[0157] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the above-mentioned division of each functional unit and module is used as an example for illustration. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of the present application. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiment, and details are not described here again.

[0158] To implement the above embodiment, the present application also proposes a terminal device.

[0159] Figure 6 It is a structural schematic diagram of a terminal device according to an embodiment of the present application.

[0160] As Figure 6 shown, the above terminal device 200 includes:

[0161] A memory 210 and at least one processor 220, a bus 230 connecting different components (including the memory 210 and the processor 220), where the memory 210 stores a computer program, and when the processor 220 executes the program, the road monitoring method described in the embodiments of the present application is implemented.

[0162] The bus 230 represents one or more of several types of bus architectures, including a memory bus or a memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any bus architecture in a variety of bus architectures. By way of example, these architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

[0163] The terminal device 200 typically includes a variety of electronic device-readable media. These media can be any available media that can be accessed by the terminal device 200, including volatile and non-volatile media, removable and non-removable media.

[0164] The memory 210 may further include a computer system-readable medium in the form of volatile memory, such as random access memory (RAM) 240 and / or cache memory 250. The terminal device 200 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, a storage system 260 may be used for reading and writing on non-removable, non-volatile magnetic media ( Figure 6 not shown, commonly referred to as a "hard disk drive"). Although Figure 6 not shown in the figure, a disk drive for reading and writing on a removable non-volatile disk (such as a "floppy disk") and an optical disk drive for reading and writing on a removable non-volatile optical disk (such as a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 230 through one or more data media interfaces. The memory 210 may include at least one program product, and the program product has a set of (for example, at least one) program modules, and these program modules are configured to execute the functions of the embodiments of the present application.

[0165] A program / utilities 280 having a set (at least one) of program modules 270 can be stored, for example, in a memory 210. Such program modules 270 include—but are not limited to—an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment. The program modules 270 generally execute the functions and / or methods in the embodiments described in this application.

[0166] The terminal device 200 can also communicate with one or more external devices 290 (such as a keyboard, a pointing device, a display 291, etc.), and can also communicate with one or more devices that enable a user to interact with the terminal device 200, and / or communicate with any device that enables the terminal device 200 to communicate with one or more other computing devices (such as a network card, a modem, etc.). Such communication can be carried out through an input / output (I / O) interface 292. Moreover, the terminal device 200 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 293. As shown in the figure, the network adapter 293 communicates with other modules of the terminal device 200 through a bus 230. It should be understood that although not shown in the figure, other hardware and / or software modules can be used in combination with the terminal device 200, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0167] The processor 220 executes various functional applications and data processing by running programs stored in the memory 210.

[0168] It should be noted that for the implementation process and technical principle of the terminal device in this embodiment, refer to the foregoing explanation of the road monitoring method in the embodiments of this application, and details are not described herein again.

[0169] The embodiments of this application also provide a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the foregoing method embodiments can be implemented.

[0170] The embodiments of this application provide a computer program product. When the computer program product runs on a terminal device, the terminal device can implement the steps in the foregoing method embodiments when executed.

[0171] When 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, to implement all or part of the processes in the above-described embodiment methods of this application, a computer program can be used to instruct the relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the device / terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk, or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0172] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0173] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0174] In the embodiments provided in this application, it should be understood that the disclosed device / terminal device and method can be implemented in other ways. For example, the device / terminal device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there can be other division methods. For example, 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 displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical, mechanical, or other form.

[0175] The unit described as a separation component may or may not be physically separated. The component displayed as a unit may or may not be a physical unit, that is, it may be located in one place or distributed across multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0176] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A road monitoring method, characterized in that, Including: Obtaining current target recognition results respectively corresponding to multiple base stations in a target road at a current moment, where the current target recognition results include recognition results of current targets within the sensing range corresponding to the base stations; Obtaining historical target recognition results corresponding to each historical target, where the historical target refers to a target detected by any of the base stations before the current moment, and the historical target recognition results include target recognition results corresponding to each moment before the current moment of the historical target; Fusing the current target recognition results respectively corresponding to each of the base stations to generate a fused target recognition result corresponding to the target road; Generating current driving trajectories corresponding to each of the current targets according to the fused target recognition result and the historical target recognition results corresponding to each of the historical targets; Detecting traffic events occurring in the target road according to the current driving trajectories corresponding to each of the current targets; 2. The method according to claim 1, wherein Each of the base stations includes multiple sensing devices, and the obtaining of the current target recognition results respectively corresponding to multiple base stations in the target road at the current moment includes: Obtaining current target recognition results corresponding to each of the sensing devices in a first base station, where the first base station is any of the base stations, and the current target recognition results corresponding to the sensing devices include recognition results of current targets within the sensing range corresponding to the sensing devices; Fusing the current target recognition results corresponding to each of the sensing devices to generate a current target recognition result corresponding to the first base station.

3. The method according to claim 2, wherein Before obtaining the current target recognition results corresponding to each of the sensing devices in the first base station, it further includes: Performing time registration on each of the sensing devices; The fusing of the current target recognition results corresponding to each of the sensing devices to generate a current target recognition result corresponding to the first base station includes: Performing spatial registration on the current target recognition results corresponding to each of the sensing devices according to a preset spatial reference coordinate system to generate spatially registered current target recognition results corresponding to each of the sensing devices; Performing matching and correction on the spatially registered current target recognition results corresponding to each of the sensing devices to generate a current target recognition result corresponding to the first base station.

4. The method according to claim 1, wherein The fusing of the current target recognition results respectively corresponding to each of the base stations to generate a fused target recognition result corresponding to the target road includes: Performing spatio-temporal registration on the current target recognition results respectively corresponding to each of the base stations to generate spatio-temporally registered current target recognition results respectively corresponding to each of the base stations; Performing matching on the spatio-temporally registered current target recognition results respectively corresponding to each of the base stations to perform duplicate removal processing on each of the current targets and generate the fused target recognition result.

5. The method according to claim 1, wherein The generating of the current driving trajectories corresponding to each of the current targets according to the fused target recognition result and the historical target recognition results corresponding to each of the historical targets includes: Predict the recognition result of each historical target at the current moment according to the historical target recognition result corresponding to each historical target, so as to generate the predicted recognition result of each historical target at the current moment; Determine whether the recognition result of the current target matches the predicted recognition result of any historical target; If the recognition result of the current target matches the predicted recognition result of any historical target, determine that the current target and the any historical target are the same target, and generate the current driving trajectory corresponding to the current target according to the recognition result of the current target and the historical target recognition result corresponding to the any historical target; If the recognition result of the current target does not match the predicted recognition results of all historical targets, determine that the current target is a new target detected at the current moment, and generate the current driving trajectory corresponding to the current target according to the recognition result of the current target; 6. The method according to any one of claims 1-5, characterized in that The detecting of traffic events occurring in the target road according to the current driving trajectories corresponding to each current target includes: Determine whether there is an abnormal target in the target road where a traffic event occurs according to the current driving trajectories corresponding to each current target and the map data corresponding to the target road, where the abnormal target is any current target; When there is the abnormal target, determine the occurrence location, occurrence time, event type and warning level of the traffic event corresponding to the abnormal target; 7. The method according to claim 6, wherein When the event type of the traffic event is an abnormal event, after determining the occurrence location, occurrence time, event type and warning level of the traffic event corresponding to the abnormal target when there is the abnormal target, it further includes: Obtain the abnormal data corresponding to the abnormal target from the historical target recognition result corresponding to the abnormal target according to the occurrence time; 8. The method according to any one of claims 1-5, characterized in that, The detecting of traffic events occurring in the target road according to the current driving trajectories corresponding to each current target includes: Statistically analyze the traffic flow of the target road before the current moment according to the current driving trajectories corresponding to each current target; 9. A road monitoring device, characterized in that, Including: A first obtaining module, configured to obtain the current target recognition results respectively corresponding to multiple base stations in the target road at the current moment, where the current target recognition result includes the recognition result of the current target within the sensing range corresponding to the base station; A second obtaining module, configured to obtain the historical target recognition results corresponding to each historical target, where the historical target refers to the target detected by any base station before the current moment, and the historical target recognition result includes the target recognition results corresponding to each moment before the current moment of the historical target; A first generating module, configured to fuse the current target recognition results respectively corresponding to each base station to generate a fused target recognition result corresponding to the target road; A second generating module, configured to generate the current driving trajectories corresponding to each current target according to the fused target recognition result and the historical target recognition results corresponding to each historical target; The first detection module is used to detect traffic events occurring in the target road according to the current driving trajectories corresponding to the respective current targets.

10. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, the method described in any one of claims 1-8 is implemented.

11. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, the method described in any one of claims 1-8 is implemented.

Images