Multi-input fusion perception accuracy and continuity enhancement method and device, equipment, storage medium and program product

Abstract

The application relates to a multi-input fusion perception accuracy and continuity enhancement method, device, equipment, storage medium and program product. The method comprises the following steps: determining a first perception trajectory of a target object; in the case that the first perception trajectory is interrupted, mapping a target perception trajectory point to a predetermined route matched with the first perception trajectory, determining information of a projection point corresponding to the target perception trajectory point on the predetermined route, the target perception trajectory point being the last perception trajectory point before the interruption of the first perception trajectory; performing kinematic deduction on the target object along the predetermined route according to the information of the target perception trajectory point and the information of the projection point, and determining a virtual trajectory point of the target object at the interruption of the first perception trajectory; and obtaining a completed trajectory of the target object according to the virtual trajectory point and residual perception data of the target object at the interruption of the first perception trajectory. The method can improve the accuracy of the perception trajectory.

Description

Technical Field

[0001] This application relates to the field of wireless communication sensing technology, and in particular to a method, apparatus, device, storage medium, and program product for enhancing sensing accuracy and continuity through multi-input fusion. Background Technology

[0002] In scenarios such as drone surveillance, intelligent transportation, and shipping, it is necessary to determine the current position of moving target objects such as drones, vehicles, and ships in real time. Therefore, trajectory tracking of moving target objects is crucial.

[0003] In related technologies, multi-source sensors, such as 5G-Advanced (5G-A) sensing devices, millimeter-wave radar, and remote identification (Remote ID) systems for unmanned aerial vehicles, are mainly used to collect sensing data of moving target objects. The collected sensing data is then fused in real time to obtain the perceived trajectory of the target object.

[0004] However, when the target object fails to be tracked due to occlusion, signal interference, or sensor malfunction, the sensing trajectory is prone to interruption, which makes it impossible to guarantee the continuity of the sensing trajectory and reduces the accuracy of the sensing trajectory. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, apparatus, device, storage medium, and program product for enhancing the perception accuracy and continuity of multi-input fusion, which can improve the accuracy of the perceived trajectory, in order to address the above-mentioned technical problems.

[0006] Firstly, this application provides a method for enhancing the perceptual accuracy and continuity of multi-input fusion, including:

[0007] Determine the first perception trajectory of the target object, the first perception trajectory including multiple perception trajectory points of the target object during its movement;

[0008] In the event of an interruption of the first sensing trajectory, the target sensing trajectory point is mapped onto a predetermined route that matches the first sensing trajectory, and the information of the projection point corresponding to the target sensing trajectory point on the predetermined route is determined. The target sensing trajectory point is the last sensing trajectory point of the first sensing trajectory before the interruption.

[0009] Based on the information of the target object at the target perception trajectory point and the information of the projection point, kinematic deduction is performed on the target object along the predetermined route to determine the virtual trajectory point of the target object when the first perception trajectory is interrupted.

[0010] Based on the virtual trajectory points and the residual perception data of the target object when the first perception trajectory is interrupted, the completed trajectory of the target object is obtained.

[0011] In one embodiment, the kinematic deduction includes uniform or uniformly accelerated motion deduction; the step of performing kinematic deduction on the target object along the predetermined route based on the information of the target object at the target perception trajectory point and the information of the projection point, to determine the virtual trajectory point of the target object when the first perception trajectory is interrupted, includes:

[0012] Using the information of the target perception trajectory points as initial conditions, and based on the information of the projection points, the target object is simulated to move at a constant speed or uniform acceleration along the predetermined route to determine the virtual trajectory points of the target object when the first perception trajectory is interrupted.

[0013] The information of the target sensing trajectory point includes the position and velocity information of the target sensing trajectory point, and the information of the projection point includes the progress information along the route.

[0014] In one embodiment, determining the first perceived trajectory of the target object includes:

[0015] Acquire sensing data collected by multiple sensors;

[0016] The perceived data is time-aligned and correlated and fused to obtain multiple first perception trajectory points of the target object during its movement;

[0017] The first perception trajectory of the target object is determined based on multiple perception trajectory points of the target object during its movement.

[0018] In one embodiment, after determining the first perceived trajectory of the target object, the method further includes:

[0019] If the interruption time of the valid sensing data corresponding to the target object exceeds a time threshold, the first sensing trajectory is determined to be interrupted; wherein, the valid sensing data is sensing data that has been continuously received for a duration exceeding a first duration.

[0020] In one embodiment, before mapping the target sensing trajectory point to a predetermined route matching the first sensing trajectory and determining the information of the projection point corresponding to the target sensing trajectory point on the predetermined route in the event of interruption of the first sensing trajectory, the method further includes:

[0021] Obtain the route identifier or object identifier of the target object;

[0022] Based on the route identifier or the object identifier, a predetermined route matching the first perceived trajectory is retrieved from the database.

[0023] In one embodiment, after obtaining the completed trajectory of the target object based on the virtual trajectory points and the residual sensing data of the target object when the first sensing trajectory is interrupted, the method further includes:

[0024] When valid perception data corresponding to the target object is received again and the positional deviation between the target object and the completed trajectory is within the deviation range, the completed trajectory of the target object and the second perception trajectory are fused to obtain the final output trajectory of the target object.

[0025] The second sensing trajectory is the sensing trajectory corresponding to the valid sensing data that is re-received after the first sensing trajectory is interrupted.

[0026] In one embodiment, fusing the completed trajectory and the second perceived trajectory of the target object to obtain the final output trajectory of the target object includes:

[0027] A gradual hybrid weighting strategy is used to perform weighted fusion of the completed trajectory and the second perceived trajectory to obtain the recovered segment trajectory of the target object;

[0028] Based on the first perceived trajectory, the completed trajectory, and the recovered segment trajectory, the final output trajectory of the target object is obtained.

[0029] Secondly, this application provides a multi-input fusion sensing accuracy and continuity enhancement device, comprising:

[0030] The trajectory determination module is used to determine the first perception trajectory of the target object, which includes multiple perception trajectory points of the target object during its movement.

[0031] The matching and mapping module is used to map the target sensing trajectory point to a predetermined route matched by the first sensing trajectory when the first sensing trajectory is interrupted, and to determine the information of the projection point corresponding to the target sensing trajectory point on the predetermined route. The target sensing trajectory point is the last sensing trajectory point of the first sensing trajectory before the interruption.

[0032] The virtual simulation module is used to perform kinematic simulation of the target object along the predetermined route based on the information of the target object at the target perception trajectory point and the information of the projection point, and to determine the virtual trajectory point of the target object when the first perception trajectory is interrupted.

[0033] The trajectory completion module is used to obtain the completed trajectory of the target object based on the virtual trajectory points and the residual sensing data of the target object when the first sensing trajectory is interrupted.

[0034] In one embodiment, the kinematic deduction includes uniform or uniformly accelerated motion deduction; the virtual deduction module is specifically used to perform uniform or uniformly accelerated motion deduction on the target object along the predetermined route based on the information of the target sensing trajectory point as the initial condition and the information of the projection point, to determine the virtual trajectory point of the target object when the first sensing trajectory is interrupted.

[0035] The information of the target sensing trajectory point includes the position and velocity information of the target sensing trajectory point, and the information of the projection point includes the progress information along the route.

[0036] In one embodiment, the trajectory determination module is specifically used to acquire the sensing data collected by the plurality of sensors; perform time alignment and correlation fusion on the sensing data to obtain multiple first sensing trajectory points of the target object during its movement; and determine the first sensing trajectory of the target object based on the multiple sensing trajectory points of the target object during its movement.

[0037] In one embodiment, the matching mapping module is further configured to determine that the first sensing trajectory is interrupted when the interruption time of the valid sensing data corresponding to the target object exceeds a time threshold; wherein the valid sensing data is sensing data that has been continuously received for a duration exceeding a first duration.

[0038] In one embodiment, the matching mapping module is further configured to obtain the route identifier or object identifier of the target object; and retrieve the predetermined route matching the first perceived trajectory from the database based on the route identifier or object identifier.

[0039] In one embodiment, the trajectory completion module is further configured to, when valid perception data corresponding to the target object is received again and the positional deviation between the target object and the completed trajectory is within the deviation range, fuse the completed trajectory of the target object and the second perception trajectory to obtain the final output trajectory of the target object;

[0040] The second sensing trajectory is the sensing trajectory corresponding to the valid sensing data that is re-received after the first sensing trajectory is interrupted.

[0041] In one embodiment, the trajectory completion module is specifically used to employ a gradual hybrid weighting strategy to perform weighted fusion of the completed trajectory and the second perceived trajectory to obtain the restored segment trajectory of the target object; and to obtain the final output trajectory of the target object based on the first perceived trajectory, the completed trajectory, and the restored segment trajectory.

[0042] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the multi-input fusion perception accuracy and continuity enhancement method of the first aspect described above.

[0043] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the multi-input fusion perception accuracy and continuity enhancement method of the first aspect described above.

[0044] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the multi-input fusion perception accuracy and continuity enhancement method of the first aspect described above.

[0045] The aforementioned multi-input fusion-based method, apparatus, device, storage medium, and program product for enhancing perception accuracy and continuity determine a first perception trajectory of a target object. This first perception trajectory includes multiple perception trajectory points of the target object during its movement. In the event of an interruption in the first perception trajectory, the target perception trajectory points are mapped onto a predetermined route matching the first perception trajectory. Information about the projection points corresponding to the target perception trajectory points on the predetermined route is determined. The target perception trajectory points are the last perception trajectory points of the first perception trajectory before the interruption. Based on the information of the target object at the target perception trajectory points and the projection point information, kinematic deduction is performed along the predetermined route to determine the virtual trajectory points of the target object at the time of the interruption. Based on the virtual trajectory points and the residual perception data of the target object at the time of the interruption, the completed trajectory of the target object is obtained. Because the last perception trajectory point of the first perception trajectory before the interruption is matched and mapped to the predetermined route when the first perception trajectory is interrupted, kinematic deduction can be performed along the predetermined route to obtain virtual trajectory points, and trajectory completion can be performed based on the virtual trajectory points and the residual perception data. This method allows for the fusion and completion of the predetermined route as prior information with the initial perceived trajectory before the interruption, thereby improving the continuity and robustness of the perceived trajectory and ultimately enhancing its accuracy. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1An application environment diagram for a multi-input fusion sensing accuracy and continuity enhancement method provided in an embodiment of this application;

[0048] Figure 2 A flowchart illustrating a method for enhancing perception accuracy and continuity through multi-input fusion, provided in an embodiment of this application;

[0049] Figure 3 A schematic diagram of the projection of a trajectory point provided in an embodiment of this application;

[0050] Figure 4 A flowchart illustrating another method for enhancing perception accuracy and continuity through multi-input fusion provided in this application embodiment;

[0051] Figure 5 A flowchart illustrating another method for enhancing perception accuracy and continuity through multi-input fusion provided in an embodiment of this application;

[0052] Figure 6 A flowchart illustrating another method for enhancing perception accuracy and continuity through multi-input fusion provided in this application embodiment;

[0053] Figure 7 A structural block diagram of a multi-input fusion sensing accuracy and continuity enhancement device provided in an embodiment of this application;

[0054] Figure 8 This is an internal structural diagram of a computer device provided in an embodiment of this application. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0056] The relevant technologies will be explained below.

[0057] In scenarios such as drone surveillance, intelligent transportation, and shipping, it is necessary to determine the current position of moving target objects such as drones, vehicles, and ships in real time. Therefore, trajectory tracking of moving target objects is crucial. Related technologies primarily utilize multi-source sensors, including 5G-Advanced (5G-A) sensing devices, millimeter-wave radar, and drone remote identification (Remote ID) systems, to collect sensor data on moving target objects. This collected sensor data is then fused in real time to obtain the perceived trajectory of the target object.

[0058] However, when tracking fails due to occlusion, signal interference, or sensor malfunction, the perceived trajectory is prone to interruption, compromising its continuity. Uncertainty increases rapidly after short-term extrapolation, reducing the accuracy of the perceived trajectory. Furthermore, target objects often follow predetermined flight paths, but current technologies relying solely on sensing data for trajectory tracking fail to fully integrate these predetermined paths, limiting the accuracy and reliability of the perceived trajectory.

[0059] To address the aforementioned issues, embodiments of this application provide a method, apparatus, device, storage medium, and program product for enhancing the accuracy and continuity of perception through multi-input fusion. In the event of an interruption of the first perception trajectory, the last perception trajectory point before the interruption is matched and mapped with a predetermined route. This allows for kinematic deduction of the target object along the predetermined route to obtain virtual trajectory points, which are then used to complete the trajectory based on the virtual trajectory points and residual perception data. This method allows the predetermined route to be used as prior information for fusion and completion with the first perception trajectory before the interruption, thereby improving the continuity and robustness of the perception trajectory and ultimately enhancing its accuracy.

[0060] The following describes the application scenarios of the multi-input fusion perception accuracy and continuity enhancement method proposed in the embodiments of this application.

[0061] The multi-input fusion sensing accuracy and continuity enhancement method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, sensor 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104, or it can be located in the cloud or on another network server.

[0062] Sensor 102 collects real-time sensing data of target object 106 during its movement and sends the data to server 104. Server 104 first determines the first sensing trajectory of target object 106, which includes multiple sensing trajectory points during its movement. Second, if the first sensing trajectory is interrupted, server 104 maps the target sensing trajectory points to a predetermined route matching the first sensing trajectory, determining the information of the projection points corresponding to the target sensing trajectory points on the predetermined route. The target sensing trajectory points are the last sensing trajectory points before the interruption of the first sensing trajectory. Third, based on the information of the target object's sensing trajectory points and the projection point information, server 104 performs kinematic deduction along the predetermined route to determine the virtual trajectory points of the target object when the first sensing trajectory was interrupted. Finally, server 104 obtains the completed trajectory of target object 106 based on the virtual trajectory points and the remaining sensing data of the target object when the first sensing trajectory was interrupted.

[0063] Sensor 102 may include multi-source sensors such as 5G-A sensing devices, millimeter-wave radar, and Remote ID systems. Server 104 may be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. Target object 106 may include any object with motion capabilities, such as drones, vehicles, and ships.

[0064] It should be noted that the multi-input fusion perception accuracy and continuity enhancement method provided in this application embodiment can be applied to multiple fields such as UAV air traffic control, autonomous driving, logistics tracking, and maritime monitoring, and this application embodiment does not limit it.

[0065] In one exemplary embodiment, such as Figure 2 As shown, a method for enhancing perceptual accuracy and continuity through multi-input fusion is presented, which is then applied to... Figure 1 The following explanation uses the servers in the example, including S201 to S204. Among them:

[0066] S201. Determine the first perception trajectory of the target object.

[0067] The first perception trajectory includes multiple perception trajectory points of the target object during its movement. In other words, the first perception trajectory is a perception trajectory composed of multiple perception trajectory points detected during the target object's movement.

[0068] For example, the target object may include drones, vehicles, ships, etc. Accordingly, if the target object is a drone, the movement of the target object is the flight process of the drone, and the first perception trajectory is the flight trajectory of the drone collected by the sensor; if the target object is a vehicle, the movement of the target object is the driving process of the vehicle, and the first perception trajectory is the driving trajectory of the vehicle collected by the sensor; if the target object is a ship, the movement of the target object is the navigation process of the ship, and the first perception trajectory is the navigation trajectory of the ship collected by the sensor.

[0069] In some embodiments, the server can acquire sensing data collected by multiple sensors. Subsequently, the server performs time alignment and correlation fusion on the sensing data to obtain multiple first sensing trajectory points of the target object during its movement. Finally, the server determines the first sensing trajectory of the target object based on these multiple sensing trajectory points.

[0070] For example, during the movement of a target object, multiple sensors can track the target object, obtain sensing data, and send the sensing data to a server. The server can then perform preprocessing, including time alignment of the sensing data sent by different sensors, correlation and fusion of the target object's trajectories, thereby outputting multiple sensing trajectory points including noise and interruptions. Correspondingly, a sequence based on these multiple sensing trajectory points is generated. The server can connect multiple sensing trajectory points to obtain the first sensing trajectory of the target object.

[0071] For example, taking a drone as the target, the drone takes off as planned and flies along a predetermined route. The server can receive multi-source sensing data in real time from low-altitude 5G-A sensing base stations, RemoteID, and ground-based electro-optical tracking equipment to continuously track the drone. After receiving the sensing data, the server can perform time alignment and correlation fusion to obtain multiple first sensing trajectory points of the drone during its flight, thereby determining the drone's first sensing trajectory and steadily advancing based on the progress along the route.

[0072] S202. In the event of an interruption of the first sensing trajectory, the target sensing trajectory point is mapped onto a predetermined route matching the first sensing trajectory, and the information of the projection point corresponding to the target sensing trajectory point on the predetermined route is determined.

[0073] In this step, after the server determines the first perception trajectory of the target object, it can perform interruption detection of the first perception trajectory. If the first perception trajectory is interrupted, the server can map the target perception trajectory points to a predetermined flight path that matches the first perception trajectory, and determine the information of the projection point corresponding to the target perception trajectory points on the predetermined flight path.

[0074] In other embodiments, if the first sensing trajectory is not interrupted, the server can continue to generate the first sensing trajectory of the target object according to the fusion mode of the sensing data.

[0075] The target sensing trajectory point is the last sensing trajectory point of the first sensing trajectory before its interruption. The information of the projection point can be deviation information, such as position deviation and progress along the route. Position deviation characterizes the degree to which the target sensing trajectory point deviates from the predetermined route, while progress along the route indicates the logical position of the projection point corresponding to the target sensing trajectory point on the predetermined route.

[0076] It should be understood that the embodiments of this application do not limit how the interruption detection of the first sensing trajectory is performed. In some embodiments, the server can determine the interruption time of the valid sensing data corresponding to the target object based on the received sensing data. If the interruption time of the valid sensing data corresponding to the target object exceeds a time threshold, the first sensing trajectory is determined to be interrupted.

[0077] Among them, effective sensing data refers to sensing data that has been continuously received for a duration exceeding the first duration.

[0078] It should be understood that the embodiments of this application do not limit the first duration and the time threshold, and can be set according to the actual situation. For example, the first duration can be two seconds, then only sensing data received continuously for more than two seconds is considered valid sensing data, and sensing data received continuously for less than two seconds is considered invalid sensing data. For example, the time threshold ( If the effective sensing data interruption time exceeds five seconds, it can be determined that the first sensing trajectory is interrupted. If the effective sensing data interruption time does not exceed five seconds, it can be determined that the first sensing trajectory is normal (uninterrupted).

[0079] In some embodiments, after determining whether the first sensing trajectory is interrupted, the server may output the discrete trajectory status identifier of the first sensing trajectory. The discrete trajectory status identifier can be updated in real time according to whether the first sensing trajectory is interrupted, thereby indicating whether the first sensing trajectory is currently in an interrupted state or a normal state.

[0080] In some embodiments, the server may pre-obtain a predetermined flight path for the target object and load the information of the predetermined flight path into a priori database. This predetermined flight path information may be sent to the server by the user via a terminal.

[0081] For example, the information of a scheduled route may include the node sequence of the scheduled route, the topology information of the scheduled route, and the attribute information of the scheduled route. The node sequence of the scheduled route may include a set of ordered geographic waypoints corresponding to the scheduled route. Each geographic waypoint can include latitude, longitude, and altitude information. The topology information of the planned route can include the connection relationships between a set of ordered geographic waypoints corresponding to the planned route (i.e., the navigation topology). The attribute information of the planned route can include the identifier of the target object and the associated attribute information of the route. The identifier of the target object can be, for example, a product serial number (SN) identifier, and the associated attribute information of the route can include the desired speed range, channel width, time information, etc.

[0082] For example, taking a drone as the target, before performing an inspection mission, the drone can pre-plan and submit the information of its predetermined route for the mission. The server can then load the drone's route information into the prior database. The drone's predetermined route information may include a sequence of continuous waypoints along the high-voltage transmission line, as well as hovering inspection points at key towers.

[0083] It should be understood that the embodiments of this application do not limit how the target sensing trajectory points are mapped to the predetermined route matching the first sensing trajectory. In some embodiments, the server can obtain the route identifier or object identifier of the target object. Subsequently, the server retrieves the predetermined route matching the first sensing trajectory from the database based on the route identifier or object identifier.

[0084] The object identifier mentioned above may include a route identifier or a target object identifier. The target object identifier may be the target object's serial number (SN).

[0085] For example, the server can query the prior database for the predetermined route matched by the current first perception trajectory based on the route identifier or the target object identifier. Alternatively, the server can extract the spatial location features of the target object during its movement from the first perception trajectory, and then query the prior database for the predetermined route matched by the current first perception trajectory based on these spatial location features. The predetermined route matched by the first perception trajectory is the most likely predetermined route corresponding to the first perception trajectory.

[0086] For example, Figure 3 A schematic diagram of the projection of a trajectory point provided in an embodiment of this application, such as... Figure 3 As shown, after determining the predetermined route that matches the first sensing trajectory, the server can then identify the target sensing trajectory points. (That is, the first sensing trajectory is the last sensing trajectory point before the interruption) projected onto the predetermined route R, and the projection point is found. Subsequently, based on the target-aware trajectory points The distance from the predetermined flight path R is used to calculate the target's perceived trajectory point. Positional deviation Based on projection points The target perception trajectory point is calculated by accumulating the path length starting from the origin of the booked route R. Progress along the route .

[0087] For example, taking a drone as the target, when the drone flies over a large high-voltage power tower, its body is completely blocked by the tower's metal structure, resulting in the simultaneous loss of 5G-A signal, Remote ID, and visual link. After the server receives no valid perception data from the drone for 5 seconds, it can determine that the drone's first perception trajectory has been interrupted. At this time, the server can map the last target perception trajectory point before the interruption of the drone's first perception trajectory onto the drone's predetermined flight path, and determine the information of the projection point corresponding to the target perception trajectory point on the predetermined flight path (e.g., along the flight path progress). Simultaneously, the server can also collect information about the target's perceived trajectory points, including their location and velocity information. .

[0088] It should be understood that the position information of the target perception trajectory point is the position information of the target object at the target perception trajectory point; the velocity information of the target perception trajectory point is the velocity information of the target object at the target perception trajectory point.

[0089] S203. Based on the information of the target object at the target perception trajectory point and the projection point, perform kinematic deduction of the target object along the predetermined route to determine the virtual trajectory point of the target object when the first perception trajectory is interrupted.

[0090] In this step, after the server maps the target perception trajectory point to the predetermined route matching the first perception trajectory and determines the information of the projection point corresponding to the target perception trajectory point on the predetermined route, it can perform kinematic deduction on the target object along the predetermined route based on the information of the target object at the target perception trajectory point and the information of the projection point, and determine the virtual trajectory point of the target object when the first perception trajectory is interrupted.

[0091] The aforementioned kinematic deductions include deductions of uniform or uniformly accelerated motion. The information of the target sensing trajectory points includes their position and velocity information, while the information of the projection points includes their progress along the flight path.

[0092] It should be understood that the position information of the target perception trajectory point is the position information of the target object at the target perception trajectory point; the velocity information of the target perception trajectory point is the velocity information of the target object at the target perception trajectory point.

[0093] In some embodiments, the server can use the information of the target sensing trajectory points as initial conditions, and according to the information of the projection points, perform uniform or uniformly accelerated motion simulation of the target object along a predetermined route to determine the virtual trajectory points of the target object when the first sensing trajectory is interrupted.

[0094] For example, the target sensing trajectory point is the last sensing trajectory point of the first sensing trajectory before the interruption. Correspondingly, the information of the target sensing trajectory point is the information of the last reliable trajectory point before the flight path was interrupted. Therefore, the server can obtain the flight path progress of the target sensing trajectory point. as well as location information and speed information Subsequently, the server will track the progress along the flight path. Location information and speed information As initial conditions, kinematic deduction is performed along the predetermined route R at a constant speed or with constant acceleration to predict a series of virtual trajectory points of the target object when the first sensing trajectory is interrupted, thus obtaining a sequence of virtual trajectory points. .

[0095] For example, taking a drone as the target object, the progress along the flight path is based on the target perception trajectory points of the drone. Location information and speed information The server can continuously predict virtual trajectory points for the next 30 seconds at a frequency of 10Hz, and each virtual trajectory point has a corresponding progress along the flight path. and positional deviation It generates predicted trajectories and continuously outputs them to maintain monitoring continuity.

[0096] It should be noted that the aforementioned virtual trajectory points can be fused with potentially residual, low-confidence real-world perception data to output a continuous and reasonable completed trajectory. Simultaneously, the interruption status is continuously evaluated to prepare for trajectory recovery.

[0097] In this application, a predetermined flight path is used to reliably complete the trajectory during interruptions, thereby fundamentally solving the problem of trajectory breakage caused by long-term occlusion or signal loss of the target object. During the completion process, in the event of sensor performance degradation or partial failure, the highly reliable predetermined flight path is relied upon as prior knowledge to maintain basic trajectory tracking capability, reducing over-reliance on instantaneous sensing quality.

[0098] S204. Based on the virtual trajectory points and the residual sensing data of the target object when the first sensing trajectory is interrupted, obtain the completed trajectory of the target object.

[0099] In some embodiments, after determining the virtual trajectory point of the target object when the first sensing trajectory is interrupted, the server can obtain the completed trajectory of the target object based on the virtual trajectory point and the residual sensing data of the target object when the first sensing trajectory is interrupted.

[0100] It should be understood that the embodiments of this application do not limit how the completed trajectory of the target object is obtained based on the virtual trajectory points and the residual sensing data of the target object when the first sensing trajectory is interrupted. In some embodiments, the server can generate low-confidence sensing trajectory points based on the residual sensing data. Subsequently, the low-confidence sensing trajectory points and the virtual trajectory points are weighted and fused using preset weights to obtain the fused virtual trajectory points. Finally, the server completes the first sensing trajectory using the fused virtual trajectory points to obtain the completed trajectory of the target object.

[0101] It should be understood that in the embodiments of this application, after the first sensing trajectory is interrupted, the server can also perform trajectory recovery and resynchronization to ensure a smooth connection between the completed trajectory and the second sensing trajectory after the interruption is recovered.

[0102] In some embodiments, when the server receives valid sensing data corresponding to the target object again and the positional deviation between the target object and the completed trajectory is within the deviation range, it can fuse the completed trajectory of the target object and the second sensing trajectory to obtain the final output trajectory of the target object.

[0103] The second sensing trajectory is the sensing trajectory corresponding to the valid sensing data that is re-received after the first sensing trajectory is interrupted.

[0104] It should be understood that the above deviation range can be set according to the actual situation. Taking a drone as an example, the flight path width (i.e., flight path tolerance) of the drone can be set as the deviation range, for example, 10 meters.

[0105] For example, the server's triggering condition for trajectory fusion of the second sensing trajectory and the completed trajectory includes triggering when continuous valid sensing data is received again after an interruption, and the positional deviation returns to the normal range. For instance, if a drone flies out of an obstructed area, the 5G-A base station re-captures its sensing signal and sends it to the server. If the server receives continuous valid sensing data again, and determines based on the valid sensing data that the positional deviation between the new sensing trajectory point of the drone and the completed trajectory is less than or equal to 10 meters, the server can trigger trajectory fusion of the second sensing trajectory and the completed trajectory.

[0106] In some embodiments, the server may employ a gradual weighting strategy to weight and fuse the completed trajectory and the second sensing trajectory to obtain the recovered segment trajectory of the target object. Subsequently, the server obtains the final output trajectory of the target object based on the first sensing trajectory, the completed trajectory, and the recovered segment trajectory.

[0107] The gradual blending weight strategy may include giving the completion trajectory a higher weight and the second sensing trajectory a lower weight in the early stages of recovery, and then gradually increasing the weight of the second sensing trajectory and decreasing the weight of the completion trajectory to smoothly transition to a state where the second sensing trajectory dominates over a specific time (e.g., 3 seconds).

[0108] For example, the recovered segment trajectory generated in the trajectory fusion stage can be merged together with the first sensing trajectory and the completed trajectory to obtain the final output trajectory of the target object.

[0109] For example, taking a drone as the target, after a 30-second interruption, the drone flies out of the obstruction area, and the 5G-A base station re-captures its sensing signal and reports the new sensing trajectory points of the second sensing trajectory. The server first... Perform fast matching and mapping, associate it with the original planned route R, and calculate the progress along the route. Lateral deviation Subsequently, a resynchronization mechanism is initiated to transfer the new sensing trajectory points. Spatiotemporal matching is performed with the completed trajectory to determine the sensing trajectory points. Progress along the flight path for the corresponding virtual trajectory points in the completed trajectory. If satisfied If the prediction is successful, it is deemed valid. Subsequently, the server uses a 3-second short-time-window smoothing algorithm to fuse the completed trajectory based on the flight path projection with the actual second-sensor trajectory, achieving smooth and coherent trajectory connection, and finally outputting an uninterrupted and highly complete full-process inspection trajectory.

[0110] In this application, the completion of the predetermined route provides the optimal prediction area for the sensor to reacquire the target, which greatly shortens the reacquisition time and ensures the logical consistency of the trajectory before and after reacquisition.

[0111] The multi-input fusion-based method for enhancing perception accuracy and continuity provided in this application determines a first perception trajectory of a target object, which includes multiple perception trajectory points of the target object during its movement. If the first perception trajectory is interrupted, the target perception trajectory points are mapped onto a predetermined route matching the first perception trajectory, and the information of the projection points corresponding to the target perception trajectory points on the predetermined route is determined. The target perception trajectory points are the last perception trajectory points of the first perception trajectory before the interruption. Based on the information of the target object at the target perception trajectory points and the information of the projection points, kinematic inference is performed on the target object along the predetermined route to determine the virtual trajectory points of the target object when the first perception trajectory is interrupted. Based on the virtual trajectory points and the residual perception data of the target object when the first perception trajectory is interrupted, the completed trajectory of the target object is obtained. Because the last perception trajectory point of the first perception trajectory before the interruption is matched and mapped to the predetermined route when the first perception trajectory is interrupted, kinematic inference can be performed on the target object along the predetermined route to obtain virtual trajectory points, and trajectory completion can be performed based on the virtual trajectory points and the residual perception data. This method allows for the fusion and completion of the predetermined route as prior information with the initial perceived trajectory before the interruption, thereby improving the continuity and robustness of the perceived trajectory and ultimately enhancing its accuracy.

[0112] In one exemplary embodiment, such as Figure 4 As shown, another method for enhancing perceptual accuracy and continuity through multi-input fusion is presented, which is then applied to... Figure 1 Taking the server in the example, the process of generating the first sensing trajectory and determining the interruption of the first sensing trajectory is explained, including S301 to S307. Among them:

[0113] S301. Acquire sensing data collected by multiple sensors.

[0114] S302. Perform time alignment and correlation fusion on the perceived data to obtain multiple first perception trajectory points of the target object during its movement.

[0115] S303. Determine the first perception trajectory of the target object based on multiple perception trajectory points during the target object's movement.

[0116] S304. If the interruption time of the valid sensing data corresponding to the target object exceeds the time threshold, the first sensing trajectory is determined to be interrupted; wherein, the valid sensing data is the sensing data that has been continuously received for a duration exceeding the first duration.

[0117] S305. Map the target sensing trajectory point to the predetermined route matched by the first sensing trajectory, and determine the information of the projection point corresponding to the target sensing trajectory point on the predetermined route. The target sensing trajectory point is the last sensing trajectory point of the first sensing trajectory before the interruption.

[0118] S306. Based on the information of the target object at the target perception trajectory point and the projection point, perform kinematic deduction of the target object along the predetermined route to determine the virtual trajectory point of the target object when the first perception trajectory is interrupted.

[0119] S307. Based on the virtual trajectory points and the residual sensing data of the target object when the first sensing trajectory is interrupted, obtain the completed trajectory of the target object.

[0120] In one exemplary embodiment, such as Figure 5 As shown, another method for enhancing perceptual accuracy and continuity through multi-input fusion is presented, which is then applied to... Figure 1 Taking the server in the example, the process of determining virtual trajectory points is explained, including S401 to S404. Among them:

[0121] S401. Determine the first perception trajectory of the target object, which includes multiple perception trajectory points of the target object during its movement.

[0122] S402. If the interruption time of the valid sensing data corresponding to the target object exceeds the time threshold, the first sensing trajectory is determined to be interrupted; wherein, the valid sensing data is the sensing data that has been continuously received for a duration exceeding the first duration.

[0123] S403. Using the information of the target perception trajectory points as initial conditions, and based on the information of the projection points, perform uniform or uniformly accelerated motion simulation of the target object along a predetermined route to determine the virtual trajectory point of the target object when the first perception trajectory is interrupted.

[0124] The information of the target perception trajectory points includes the position and velocity information of the target perception trajectory points, and the information of the projection points includes the progress information along the route.

[0125] S404. Based on the virtual trajectory points and the residual sensing data of the target object when the first sensing trajectory is interrupted, obtain the completed trajectory of the target object.

[0126] In one exemplary embodiment, such as Figure 6 As shown, another method for enhancing perceptual accuracy and continuity through multi-input fusion is presented, which is then applied to... Figure 1 Taking the server in the example, the process of trajectory fusion after determining the interruption recovery is explained, including S501 to S507. Among them:

[0127] S501. Determine the first perception trajectory of the target object, which includes multiple perception trajectory points of the target object during its movement.

[0128] S502. In the event of an interruption of the first sensing trajectory, the target sensing trajectory point is mapped onto a predetermined route matching the first sensing trajectory, and the information of the projection point corresponding to the target sensing trajectory point on the predetermined route is determined. The target sensing trajectory point is the last sensing trajectory point of the first sensing trajectory before the interruption.

[0129] S503. Based on the information of the target object at the target perception trajectory point and the projection point, perform kinematic deduction of the target object along the predetermined route to determine the virtual trajectory point of the target object when the first perception trajectory is interrupted.

[0130] S504. Based on the virtual trajectory points and the residual sensing data of the target object when the first sensing trajectory is interrupted, obtain the completed trajectory of the target object.

[0131] S505. When valid perception data corresponding to the target object is received again and the positional deviation between the target object and the completed trajectory is within the deviation range, trajectory fusion is triggered.

[0132] S506. A gradual mixed weighting strategy is adopted to perform weighted fusion of the completed trajectory and the second sensing trajectory to obtain the restored segment trajectory of the target object.

[0133] S507. Based on the first perception trajectory, the completed trajectory, and the restored segment trajectory, the final output trajectory of the target object is obtained.

[0134] The multi-input fusion-based method for enhancing perception accuracy and continuity provided in this application determines a first perception trajectory of a target object, which includes multiple perception trajectory points of the target object during its movement. If the first perception trajectory is interrupted, the target perception trajectory points are mapped onto a predetermined route matching the first perception trajectory, and the information of the projection points corresponding to the target perception trajectory points on the predetermined route is determined. The target perception trajectory points are the last perception trajectory points of the first perception trajectory before the interruption. Based on the information of the target object at the target perception trajectory points and the information of the projection points, kinematic inference is performed on the target object along the predetermined route to determine the virtual trajectory points of the target object when the first perception trajectory is interrupted. Based on the virtual trajectory points and the residual perception data of the target object when the first perception trajectory is interrupted, the completed trajectory of the target object is obtained. Because the last perception trajectory point of the first perception trajectory before the interruption is matched and mapped to the predetermined route when the first perception trajectory is interrupted, kinematic inference can be performed on the target object along the predetermined route to obtain virtual trajectory points, and trajectory completion can be performed based on the virtual trajectory points and the residual perception data. This method allows for the fusion and completion of the predetermined route as prior information with the initial perceived trajectory before the interruption, thereby improving the continuity and robustness of the perceived trajectory and ultimately enhancing its accuracy.

[0135] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0136] Based on the same inventive concept, this application also provides a multi-input fusion perception accuracy and continuity enhancement device for implementing the multi-input fusion perception accuracy and continuity enhancement method described above. The solution provided by this device is similar to the implementation scheme described in the above method. Therefore, the specific limitations in one or more multi-input fusion perception accuracy and continuity enhancement device embodiments provided below can be found in the limitations of the multi-input fusion perception accuracy and continuity enhancement method described above, and will not be repeated here.

[0137] In one exemplary embodiment, such as Figure 7As shown, a multi-input fusion sensing accuracy and continuity enhancement device 700 is provided, including: a trajectory determination module 701, a matching mapping module 702, a virtual inference module 703, and a trajectory completion module 704, wherein:

[0138] The trajectory determination module 701 is used to determine the first perception trajectory of the target object, which includes multiple perception trajectory points of the target object during its movement.

[0139] The matching and mapping module 702 is used to map the target sensing trajectory point to a predetermined route matched by the first sensing trajectory when the first sensing trajectory is interrupted, and to determine the information of the projection point corresponding to the target sensing trajectory point on the predetermined route. The target sensing trajectory point is the last sensing trajectory point of the first sensing trajectory before the interruption.

[0140] The virtual simulation module 703 is used to perform kinematic simulation of the target object along a predetermined route based on the information of the target object at the target perception trajectory point and the information of the projection point, and to determine the virtual trajectory point of the target object when the first perception trajectory is interrupted.

[0141] The trajectory completion module 704 is used to obtain the completed trajectory of the target object based on the virtual trajectory points and the residual sensing data of the target object when the first sensing trajectory is interrupted.

[0142] In one embodiment, the kinematic deduction includes uniform or uniformly accelerated motion deduction; the virtual deduction module 703 is specifically used to perform uniform or uniformly accelerated motion deduction on the target object along a predetermined route based on the information of the target perception trajectory points as initial conditions and the information of the projection points, to determine the virtual trajectory points of the target object when the first perception trajectory is interrupted.

[0143] The information of the target perception trajectory points includes the position and velocity information of the target perception trajectory points, and the information of the projection points includes the progress information along the route.

[0144] In one embodiment, the trajectory determination module 701 is specifically used to acquire perception data collected by multiple sensors; perform time alignment and correlation fusion on the perception data to obtain multiple first perception trajectory points of the target object during its movement; and determine the first perception trajectory of the target object based on the multiple perception trajectory points of the target object during its movement.

[0145] In one embodiment, the matching mapping module 702 is further configured to determine that the first sensing trajectory is interrupted when the interruption time of the valid sensing data corresponding to the target object exceeds a time threshold; wherein, the valid sensing data is sensing data that has been continuously received for a duration exceeding a first duration.

[0146] In one embodiment, the matching mapping module 702 is further configured to obtain the route identifier or object identifier of the target object; and retrieve the predetermined route matching the first perception trajectory from the database based on the route identifier or object identifier.

[0147] In one embodiment, the trajectory completion module 704 is further configured to, when receiving valid perception data corresponding to the target object again and the positional deviation between the target object and the completed trajectory is within the deviation range, fuse the completed trajectory of the target object and the second perception trajectory to obtain the final output trajectory of the target object.

[0148] The second sensing trajectory is the sensing trajectory corresponding to the valid sensing data that is re-received after the first sensing trajectory is interrupted.

[0149] In one embodiment, the trajectory completion module 704 is specifically used to employ a gradual hybrid weighting strategy to perform weighted fusion of the completed trajectory and the second sensing trajectory to obtain the restored segment trajectory of the target object; and to obtain the final output trajectory of the target object based on the first sensing trajectory, the completed trajectory and the restored segment trajectory.

[0150] Each module in the aforementioned multi-input fusion sensing accuracy and continuity enhancement device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0151] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 8 As shown, this computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network. When the computer program is executed by the processor, it implements a method for enhancing the accuracy and continuity of perception through multi-input fusion.

[0152] Those skilled in the art will understand that Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0153] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described method for enhancing the perception accuracy and continuity of multi-input fusion.

[0154] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the above-described method for enhancing the perception accuracy and continuity of multi-input fusion.

[0155] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the above-described method for enhancing the perception accuracy and continuity of multi-input fusion.

[0156] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0157] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0158] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0159] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for enhancing the perception accuracy and continuity through multi-input fusion, characterized in that, The method includes: Determine the first perception trajectory of the target object, the first perception trajectory including multiple perception trajectory points of the target object during its movement; In the event of an interruption of the first sensing trajectory, the target sensing trajectory point is mapped onto a predetermined route that matches the first sensing trajectory, and the information of the projection point corresponding to the target sensing trajectory point on the predetermined route is determined. The target sensing trajectory point is the last sensing trajectory point of the first sensing trajectory before the interruption. Based on the information of the target object at the target perception trajectory point and the information of the projection point, kinematic deduction is performed on the target object along the predetermined route to determine the virtual trajectory point of the target object when the first perception trajectory is interrupted. Based on the virtual trajectory points and the residual perception data of the target object when the first perception trajectory is interrupted, the completed trajectory of the target object is obtained.

2. The method according to claim 1, characterized in that, The kinematic deduction includes uniform or uniformly accelerated motion deduction; the step of performing kinematic deduction on the target object along the predetermined route based on the information of the target object at the target perception trajectory point and the information of the projection point, and determining the virtual trajectory point of the target object when the first perception trajectory is interrupted, includes: Using the information of the target perception trajectory points as initial conditions, and based on the information of the projection points, the target object is simulated to move at a constant speed or uniform acceleration along the predetermined route to determine the virtual trajectory points of the target object when the first perception trajectory is interrupted. The information of the target sensing trajectory point includes the position and velocity information of the target sensing trajectory point, and the information of the projection point includes the progress information along the route.

3. The method according to claim 1, characterized in that, The determination of the first perceptual trajectory of the target object includes: Acquire sensing data collected by multiple sensors; The perceived data is time-aligned and correlated and fused to obtain multiple first perception trajectory points of the target object during its movement; The first perception trajectory of the target object is determined based on multiple perception trajectory points of the target object during its movement.

4. The method according to claim 3, characterized in that, After determining the first perceptual trajectory of the target object, the method further includes: If the interruption time of the valid sensing data corresponding to the target object exceeds a time threshold, the first sensing trajectory is determined to be interrupted; wherein, the valid sensing data is sensing data that has been continuously received for a duration exceeding a first duration.

5. The method according to claim 1, characterized in that, In the event of an interruption of the first sensing trajectory, before mapping the target sensing trajectory point to a predetermined route matching the first sensing trajectory and determining the information of the projection point corresponding to the target sensing trajectory point on the predetermined route, the method further includes: Obtain the route identifier or object identifier of the target object; Based on the route identifier or the object identifier, a predetermined route matching the first perceived trajectory is retrieved from the database.

6. The method according to claim 1, characterized in that, After obtaining the completed trajectory of the target object based on the virtual trajectory points and the residual sensing data of the target object when the first sensing trajectory is interrupted, the method further includes: When valid perception data corresponding to the target object is received again and the positional deviation between the target object and the completed trajectory is within the deviation range, the completed trajectory of the target object and the second perception trajectory are fused to obtain the final output trajectory of the target object. The second sensing trajectory is the sensing trajectory corresponding to the valid sensing data that is re-received after the first sensing trajectory is interrupted.

7. The method according to claim 6, characterized in that, The step of fusing the completed trajectory and the second perceived trajectory of the target object to obtain the final output trajectory of the target object includes: A gradual hybrid weighting strategy is used to perform weighted fusion of the completed trajectory and the second perceived trajectory to obtain the recovered segment trajectory of the target object; Based on the first perceived trajectory, the completed trajectory, and the recovered segment trajectory, the final output trajectory of the target object is obtained.

8. A multi-input fusion sensing accuracy and continuity enhancement device, characterized in that, The device includes: The trajectory determination module is used to determine the first perception trajectory of the target object, which includes multiple perception trajectory points of the target object during its movement. The matching and mapping module is used to map the target sensing trajectory point to a predetermined route matched by the first sensing trajectory when the first sensing trajectory is interrupted, and to determine the information of the projection point corresponding to the target sensing trajectory point on the predetermined route. The target sensing trajectory point is the last sensing trajectory point of the first sensing trajectory before the interruption. The virtual simulation module is used to perform kinematic simulation of the target object along the predetermined route based on the information of the target object at the target perception trajectory point and the information of the projection point, and to determine the virtual trajectory point of the target object when the first perception trajectory is interrupted. The trajectory completion module is used to obtain the completed trajectory of the target object based on the virtual trajectory points and the residual sensing data of the target object when the first sensing trajectory is interrupted.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images