Data processing method, device, server and storage medium

Abstract

The present invention discloses a data processing method, device, server and storage medium. The method includes: interpolating a vehicle data set obtained from a target vehicle to obtain a first vehicle data set corresponding to the target vehicle; matching the first vehicle data set with a perception data set obtained from a perception device, and determining target perception data and target vehicle data based on the matching results; determining the perception area of ​​each perception target based on the target perception data, and determining the circumscribed area of ​​the target vehicle based on the target vehicle data; when it is determined that the circumscribed area of ​​any target vehicle and the perception area of ​​any perception target intersect, determining the degree of overlap; and determining whether the perception target and the target vehicle correspond based on the degree of overlap. The above technical solution can accurately determine whether the perception target and the target vehicle correspond, providing a data basis for data deduplication.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of data processing technology, and in particular to a data processing method, device, server, and storage medium. Background Art

[0002] Building a real-time traffic model based on digital twin technology requires real-time traffic data. On intelligently renovated roads, sensory data can be acquired from sensing devices, and information such as the location, speed, direction, and size of the perceived target can be determined from this data. Alternatively, vehicle data can be acquired from the vehicle system, and information such as the location, speed, direction, and size of the vehicle can be determined from this data. Digital twin technology can then be used to build a real-time traffic model based on these sensory and vehicle data. When a vehicle corresponding to the vehicle system is within the sensing range of the sensory device, the perceived target determined based on the sensory data includes the vehicle corresponding to the vehicle system. In this case, the perceived target determined by the sensory data acquired by the server can also include the vehicle identified by the vehicle data acquired by the server. Building a real-time traffic model based on both sensory and vehicle data can easily lead to model redundancy.

[0003] In the prior art, the distance between the perception target determined by the perception data and the vehicle determined by the vehicle data is usually calculated to determine whether the perception target and the vehicle are the same target object, and the perception data is deduplicated after it is determined that the perception target and the vehicle are the same target object.

[0004] However, the accuracy of determining whether the perceived target and the vehicle are the same target object based on distance is not high, resulting in poor data deduplication effect. Summary of the Invention

[0005] The present invention provides a data processing method, device, server and storage medium to achieve data deduplication of perception data based on vehicle data, thereby reducing the redundancy of real-time traffic data obtained by fusing vehicle data and perception data.

[0006] In a first aspect, an embodiment of the present invention provides a data processing method, including:

[0007] Performing interpolation processing on the vehicle data set obtained from the target vehicle to obtain a first vehicle data set corresponding to the target vehicle;

[0008] matching the first vehicle data set with a perception data set acquired from a perception device, and determining target perception data and target vehicle data based on the matching result;

[0009] Determine the perception area of ​​each perception target based on the target perception data, and determine the circumscribed area of ​​the target vehicle based on the target vehicle data;

[0010] When it is determined that the circumscribed area of ​​any target vehicle and the sensing area of ​​any sensing target intersect, determining the degree of overlap;

[0011] It is determined whether the perceived target and the target vehicle correspond based on the degree of overlap.

[0012] The technical solution of an embodiment of the present invention provides a data processing method, including: interpolating a vehicle data set obtained from a target vehicle to obtain a first vehicle data set corresponding to the target vehicle; matching the first vehicle data set with a perception data set obtained from a perception device, and determining target perception data and target vehicle data based on the matching result; determining a perception area of ​​each perception target based on the target perception data, and determining a circumscribed area of ​​the target vehicle based on the target vehicle data; when it is determined that the circumscribed area of ​​any target vehicle and the perception area of ​​any perception target intersect, determining a degree of overlap; and determining whether the perception target and the target vehicle correspond based on the degree of overlap. The above technical solution obtains a vehicle dataset from the target vehicle, obtains a perception dataset from the perception device, and interpolates the vehicle dataset. The time interval of the obtained first vehicle dataset is consistent with the time interval of the perception dataset. After aligning and matching the first vehicle dataset and the perception dataset, the corresponding target vehicle data and target perception data can be obtained, thereby achieving matching between the vehicle data and the perception data. The circumscribed area corresponding to the target vehicle can be determined based on the target vehicle data, and the perception area corresponding to each perception target can be determined based on the target perception data. Based on coordinate operations and set operations, it can be determined whether the circumscribed area corresponding to each target vehicle and the perception area corresponding to each perception target intersect. When it is determined that the circumscribed area of ​​any target vehicle intersects the perception area of ​​any perception target, the degree of overlap between the circumscribed area and the perception area can be further determined. Based on the degree of overlap, it can be determined whether the perception target corresponds to the target vehicle. After determining that the perception target corresponds to the target vehicle and that the perception target and the target vehicle are the same target, the perception data corresponding to the perception target is deleted from the perception dataset. Data deduplication of the perception data is achieved based on the degree of overlap, thereby improving the accuracy of data deduplication and further reducing the redundancy of real-time traffic data obtained by fusing vehicle data and perception data.

[0013] Furthermore, the degree of overlap includes at least one of an area overlap ratio and an overlap area.

[0014] Furthermore, determining the perception area of ​​each perception target according to the target perception data includes:

[0015] Determining the position information, length information, and width information of each of the sensed targets based on the target sensing data;

[0016] Determining the center position information of each of the sensing targets according to the longitude and latitude included in the position information of each of the sensing targets;

[0017] The perception area of ​​each perception target is determined according to the center position information, the length information, and the width information of each perception target.

[0018] Furthermore, determining the circumscribed area of ​​the target vehicle according to the target vehicle data includes:

[0019] Determine the position information, length information and width information of the target vehicle based on the target vehicle data;

[0020] Determining the longitude and latitude included in the location information of the target vehicle as the center location information of the target vehicle;

[0021] The circumscribed area of ​​the target vehicle is determined according to the center position information, the length information, and the width information of the target vehicle.

[0022] Furthermore, interpolation processing is performed on the vehicle dataset acquired from the target vehicle to obtain a first vehicle dataset corresponding to the target vehicle, including:

[0023] Acquire the vehicle data set corresponding to the target vehicle from the target vehicle;

[0024] Determining an interpolation time of the vehicle dataset according to a first time interval corresponding to the vehicle dataset and a second time interval corresponding to the perception dataset, and determining interpolation data corresponding to each interpolation time according to each vehicle data included in the vehicle dataset;

[0025] The first vehicle dataset corresponding to the target vehicle is obtained according to the interpolation time, the interpolation data corresponding to the interpolation time, and the vehicle dataset.

[0026] Furthermore, the vehicle data includes position information of the target vehicle corresponding to the vehicle time, and the interpolation data includes position information of the target vehicle corresponding to the interpolation time. Accordingly, determining the interpolation data corresponding to each interpolation time according to each vehicle data included in the vehicle data set includes:

[0027] determining an interpolation time interval according to the first time interval and the second time interval;

[0028] Determining the position information of the target vehicle corresponding to each interpolation time according to the position information, vehicle speed and interpolation time interval of the target vehicle at each vehicle time included in each vehicle data;

[0029] The longitude and latitude included in the position information of the target vehicle corresponding to each of the interpolation times are determined as the interpolation data corresponding to each of the interpolation times.

[0030] Furthermore, matching the first vehicle data set with the perception data set acquired from the perception device, and determining target perception data and target vehicle data based on the matching result, includes:

[0031] determining a plurality of time points with equal time intervals, wherein the time interval between the plurality of time points is less than the time interval of the vehicle data set;

[0032] For any time point, determining the vehicle data corresponding to the vehicle time closest to the time point in the first vehicle data set, and determining the perception data corresponding to the perception time closest to the time point in the perception data set;

[0033] The vehicle data corresponding to the vehicle time closest to the time point is determined as the target vehicle data, and the perception data corresponding to the perception time closest to the time point is determined as the target perception data.

[0034] Furthermore, determining whether the perceived target and the target vehicle correspond based on the overlap degree includes:

[0035] If the degree of overlap is greater than a first preset threshold, determining that the sensed target corresponds to the target vehicle;

[0036] If the overlap degree is less than or equal to the first preset threshold and greater than a second preset threshold, updating the target perception data based on the previous perception data and / or the next perception data of the target perception data in the perception data set to obtain first target perception data;

[0037] If the degree of overlap between the first perception area corresponding to the first target perception data and the circumscribed area of ​​the target vehicle is greater than the first preset threshold, it is determined that the perception target corresponds to the target vehicle.

[0038] In a second aspect, an embodiment of the present invention further provides a data processing device, including:

[0039] a data acquisition module, configured to perform interpolation processing on a vehicle data set acquired from a target vehicle to obtain a first vehicle data set corresponding to the target vehicle;

[0040] a data matching module, configured to match the first vehicle data set with a perception data set acquired from a perception device, and determine target perception data and target vehicle data based on the matching result;

[0041] an area determination module, configured to determine a perception area of ​​each perception target based on the target perception data, and determine a circumscribed area of ​​the target vehicle based on the target vehicle data;

[0042] an overlap degree determination module, configured to determine the overlap degree when it is determined that the circumscribed area of ​​any target vehicle intersects with the sensing area of ​​any sensing target;

[0043] An execution module is used to determine whether the perception target and the target vehicle correspond based on the overlap degree.

[0044] In a third aspect, an embodiment of the present invention further provides a server, characterized in that the server comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the data processing method as described in any one of the first aspects.

[0045] In a fourth aspect, an embodiment of the present invention further provides a storage medium comprising computer-executable instructions, wherein the computer-executable instructions, when executed by a computer processor, are used to execute the data processing method as described in any one of the first aspects.

[0046] In a fifth aspect, the present application provides a computer program product, which includes computer instructions. When the computer instructions are run on a computer, the computer executes the data processing method provided in the first aspect.

[0047] It should be noted that the above-mentioned computer instructions may be stored in whole or in part on a computer-readable storage medium. The computer-readable storage medium may be packaged together with the processor of the data processing device or may be packaged separately from the processor of the data processing device, and this application does not limit this.

[0048] The descriptions of the second, third, fourth and fifth aspects of this application can refer to the detailed description of the first aspect; and the beneficial effects of the descriptions of the second, third, fourth and fifth aspects can refer to the analysis of the beneficial effects of the first aspect, which will not be repeated here.

[0049] In this application, the names of the aforementioned data processing devices do not limit the devices or functional modules themselves. In actual implementation, these devices or functional modules may appear with other names. As long as the functions of each device or functional module are similar to those of this application, they fall within the scope of the claims of this application and their equivalents.

[0050] These and other aspects of the present application will become more readily apparent from the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0052] Figure 1 A flowchart of a data processing method provided by an embodiment of the present invention;

[0053] Figure 2 A flowchart of another data processing method provided by an embodiment of the present invention;

[0054] Figure 3 A schematic diagram of determining interpolation time in another data processing method provided by an embodiment of the present invention;

[0055] Figure 4 A schematic diagram of determining interpolation data corresponding to an interpolation time in another data processing method provided by an embodiment of the present invention;

[0056] Figure 5 A schematic diagram of time alignment of a first vehicle dataset and a perception dataset based on isochronous pulses in another data processing method provided by an embodiment of the present invention;

[0057] Figure 6 A schematic diagram of determining optimized position information corresponding to a perception target in another data processing method provided by an embodiment of the present invention;

[0058] Figure 7 A schematic structural diagram of a data processing device provided by an embodiment of the present invention;

[0059] Figure 8 A schematic diagram of the structure of a server provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0060] The present invention will be further described in detail below with reference to the accompanying drawings and examples. It will be understood that the specific embodiments described herein are intended only to illustrate the present invention and are not intended to limit the present invention. It should also be noted that, for ease of description, the accompanying drawings only illustrate portions relevant to the present invention, not all structures.

[0061] The term "and / or" in this article is merely a description of the association relationship between associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0062] The terms "first" and "second" and the like in the specification and drawings of this application are used to distinguish different objects, or to distinguish different processing of the same object, rather than to describe a specific order of objects.

[0063] Furthermore, the terms "including," "having," and any variations thereof, as used in the description of this application are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or units is not limited to the listed steps or units but may optionally include other steps or units not listed, or may optionally include other steps or units inherent to the process, method, product, or apparatus.

[0064] It should be mentioned before discussing exemplary embodiments in more detail that some exemplary embodiments are described as processes or methods depicted as flow charts. Although flow charts describe various operations (or steps) as sequential processes, many operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of various operations can be rearranged. When its operation is completed, the process can be terminated, but can also have additional steps not included in the accompanying drawings. The process can correspond to methods, functions, procedures, subroutines, subprograms, etc. In addition, the features in the embodiments of the present invention and the embodiments can be combined with each other without conflict.

[0065] It should be noted that in the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be interpreted as being more preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0066] In the description of the present application, unless otherwise specified, “plurality” means two or more.

[0067] Digital twins leverage data from physical models, sensor updates, and operational history, integrating multidisciplinary, multi-physics, multi-scale, and multi-probability simulation processes to map the entire lifecycle of the corresponding physical equipment in a virtual space. To build a real-time traffic model, real-time traffic data is required. On intelligently transformed roads, sensor data can be acquired from sensing devices (e.g., cameras, millimeter-wave radars, lidars, etc.) deployed on light poles and similar structures. This data can be used to determine the location, speed, direction, size, and other information of perceived targets. Alternatively, vehicle data can be acquired from vehicle systems to determine the location, speed, direction, size, and other information of vehicles. This data can then be fused using artificial intelligence and deep learning algorithms. Specifically, real-time traffic data can be generated from these data. This real-time traffic data is then digitized and individualized, identifying the highly precise location, speed, direction, size, and other information of each target. This allows the construction of a real-time traffic model using digital twin technology based on these data.

[0068] As mentioned above, when the perception target determined by the perception data and the target vehicle represented by the vehicle data overlap, an algorithm can be used to deduplicate them, and finally output the fused one-to-one real-time traffic flow data. The existing technology based on the distance calculation method determines whether the perception target and the target vehicle are the same target object, but the accuracy is not high, resulting in poor data deduplication effect. Therefore, the present application provides a data processing method, which is based on the area calculation method to determine whether the perception target and the target vehicle are the same target object, so as to accurately determine whether the perception target and the target vehicle are the same target object. When it is determined that the perception target and the target vehicle are the same target object, the perception data is deduplicated based on the vehicle data, the data deduplication effect is optimized, and the efficiency of building a digital twin model is further improved.

[0069] The data processing method proposed in this application will be described in detail below with reference to diagrams and embodiments.

[0070] Figure 1 This is a flow chart of a data processing method provided by an embodiment of the present invention. This embodiment is applicable to situations where it is necessary to perform data deduplication on real-time traffic data consisting of sensor data and vehicle data. The method can be executed by a data processing device, such as Figure 1 As shown, the specific steps include:

[0071] Step 110: Perform interpolation processing on the vehicle dataset acquired from the target vehicle to obtain a first vehicle dataset corresponding to the target vehicle.

[0072] The server can obtain a vehicle dataset from the target vehicle at a first time interval and obtain a perception dataset from the perception device at a second time interval. Because the time intervals of the vehicle dataset and the perception dataset are inconsistent, in order to match the vehicle dataset and the perception dataset, interpolation processing must be performed on the dataset with the larger time interval. Specifically, the vehicle dataset must be interpolated to bring the time intervals of the vehicle dataset and the perception dataset into close proximity.

[0073] Typically, the first time interval is greater than the second time interval. The first time interval can be 200ms, and the second time interval can be 50ms. Because the first time interval is the vehicle reporting interval, its specific transmission time is subject to significant uncertainty. The second time interval can be the interception time of continuous sensing results, and therefore has relatively greater certainty.

[0074] Specifically, the interpolation time of the vehicle data set is determined according to the first time interval and the second time interval, and the interpolation data corresponding to each interpolation time is determined according to the vehicle data contained in the vehicle data set. Then, the interpolation data can be inserted into the vehicle data set according to the interpolation time to obtain the first vehicle data set corresponding to the target vehicle, thereby realizing the interpolation processing of the vehicle data set.

[0075] In the embodiment of the present invention, the first vehicle dataset is obtained by performing interpolation processing on the vehicle dataset, so that the time interval of the first vehicle dataset is close to the time interval of the perception dataset.

[0076] Step 120: Match the first vehicle data set with the perception data set obtained from the perception device, and determine target perception data and target vehicle data based on the matching result.

[0077] Specifically, multiple time points with equal time intervals can be determined, and the first vehicle data set and the perception data set can be matched according to each time point. Specifically, for any time point, the vehicle data corresponding to the vehicle time closest to the time point is determined in the first vehicle data set, and the vehicle data corresponding to the vehicle time closest to the time point is determined as the target vehicle data, the perception data corresponding to the perception time closest to the time point is determined in the perception data set, and the perception data corresponding to the perception time closest to the time point is determined as the target perception data.

[0078] In practical applications, an isochronous pulse generator can first be constructed to determine multiple time points with equal time intervals. The isochronous pulse generator can determine a time interval of 50 ms. Therefore, it can determine pulses with a time interval of 50 ms, that is, it can determine multiple time points with a time interval of 50 ms. The pulse time corresponding to each pulse is set as pti, where i represents the number of pulses. The first vehicle data corresponding to the first vehicle time in the first vehicle data set with the smallest time difference with any pulse time needs to be determined as the target vehicle data. The perception data corresponding to the perception time in the perception data set with the smallest time difference with any pulse time needs to be determined as the target perception data. Exemplarily, each pulse time is traversed to determine a first difference between the pulse time and the first vehicle time included in each first vehicle data in the first vehicle data set, and a second difference between the pulse time and the perception time included in each perception data in the perception data set. The first vehicle data corresponding to the first vehicle time with the smallest first difference is determined as the target vehicle data, and the perception data corresponding to the perception time with the smallest second difference is determined as the target perception data. The target perception data and target vehicle data are thus the aligned and matched perception data and vehicle data.

[0079] In an embodiment of the present invention, after obtaining a vehicle data set and a perception data set, the vehicle data set can be interpolated to obtain a first vehicle data set. The time interval of the first vehicle data set and the time interval of the perception data set can be consistent. The first vehicle data set and the perception data set can also be aligned and matched based on an isochronous pulse generator. By traversing each pulse emitted by the isochronous pulse generator, the perception time and the first vehicle time corresponding to any pulse with the smallest pulse time difference are determined. Then, the perception data corresponding to the perception time can be determined as the target perception data, and the first vehicle data corresponding to the first vehicle time can be determined as the target vehicle data, thereby achieving alignment and matching of the perception data and the vehicle data.

[0080] Step 130: Determine the perception area of ​​each perception target based on the target perception data, and determine the circumscribed area of ​​the target vehicle based on the target vehicle data.

[0081] Specifically, the target perception data is traversed to construct the perception area of ​​each perception target, that is, to construct the perception rectangle of each perception target. Specifically, the coordinates of the four vertices of the perception rectangle corresponding to each perception target can be determined based on the position information, length information, and width information of each perception target contained in the target perception data, and the perception area of ​​the perception target can be determined based on the coordinates of the four vertices. The coordinates of the four vertices of the target vehicle can also be determined based on the position information, length information, and width information of the target vehicle contained in the target vehicle data, and the circumscribed area of ​​the target vehicle can be determined based on the coordinates of the four vertices.

[0082] In an embodiment of the present invention, a perception area corresponding to each perception target within the perception range is constructed based on the perception data, and an external area corresponding to the vehicle data is also constructed, providing a data basis for determining whether the perception data and the vehicle data overlap.

[0083] Step 140: When it is determined that the circumscribed area of ​​any target vehicle intersects with the sensing area of ​​any sensing target, determine the degree of overlap.

[0084] Specifically, coordinate operations and set operations can be used to determine the intersection of each sensing area and each circumscribed area, and the intersection area can be calculated. After determining the sensing area of ​​the sensing area, the overlap ratio between the intersection area and the sensing area can be further determined. Based on the overlap ratio, the degree of overlap between the circumscribed area and the sensing area can be determined. Furthermore, the degree of overlap between the circumscribed area and the sensing area can be determined based on the intersection area. Furthermore, the degree of overlap between the circumscribed area and the sensing area can be determined based on the intersection area and the overlap ratio.

[0085] In an embodiment of the present invention, after determining that there is an intersection between the perception area and the external area, the intersection area can be determined, and the area overlap rate can be determined based on the intersection area and the perception area corresponding to the perception area, and then the degree of overlap between the external area and the perception area can be determined based on the intersection area and / or the area overlap rate. The degree of overlap can provide a data basis for determining whether the perception target corresponds to the target vehicle.

[0086] Step 150: Determine whether the perceived target and the target vehicle correspond based on the degree of overlap.

[0087] Because the far, middle, and near zones within the perception range experience varying degrees of occlusion, different first preset thresholds need to be set for the far, middle, and near zones. This allows for determining whether the perceived target corresponds to the target vehicle based on the first preset thresholds, thereby improving judgment accuracy. Alternatively, the same first preset threshold can be used for the far, middle, and near zones.

[0088] Specifically, based on the location information of the perception target and the location information of the perception device, the distance between the perception target and the perception device is determined based on image recognition and other technologies, and based on the distance, it is determined whether the perception target is in the far zone, the middle zone, or the near zone. After determining that the perception target is in the far zone, the degree of overlap is compared with the first preset threshold corresponding to the far zone. If the degree of overlap is greater than the first preset threshold corresponding to the far zone, it is determined that the perception target corresponds to the target vehicle; as mentioned above, after determining that the perception target is in the middle zone, the degree of overlap is compared with the first preset threshold corresponding to the middle zone. If the degree of overlap is greater than the first preset threshold corresponding to the middle zone, it is determined that the perception target corresponds to the target vehicle; after determining that the perception target is in the near zone, the degree of overlap is compared with the first preset threshold corresponding to the near zone. If the degree of overlap is greater than the first preset threshold corresponding to the near zone, it is determined that the perception target corresponds to the target vehicle. After determining that the perception target corresponds to the target vehicle, the perception data corresponding to the perception target can be deleted from the perception data set, thereby achieving deduplication of the perception data.

[0089] Of course, if the degree of overlap is less than the first preset threshold and greater than the second preset threshold, it is necessary to further determine whether the perceived target corresponds to the target vehicle; if the degree of overlap is less than the second preset threshold, it is determined that the perceived target does not correspond to the target vehicle.

[0090] In an embodiment of the present invention, whether the perception target and the target vehicle correspond can be determined based on the degree of overlap, and when it is determined that the perception target and the target vehicle correspond, it can be determined that the perception target and the target vehicle are the same target, and then the perception data corresponding to the perception target can be deleted in the perception data set to achieve deduplication of the perception data.

[0091] A data processing method provided by an embodiment of the present invention includes: interpolating a vehicle data set obtained from a target vehicle to obtain a first vehicle data set corresponding to the target vehicle; matching the first vehicle data set with a perception data set obtained from a perception device, and determining target perception data and target vehicle data based on the matching results; determining a perception area of ​​each perception target based on the target perception data, and determining an external area of ​​the target vehicle based on the target vehicle data; when it is determined that the external area of ​​any target vehicle and the perception area of ​​any perception target intersect, determining a degree of overlap; and determining whether the perception target and the target vehicle correspond based on the degree of overlap. The above technical solution obtains a vehicle dataset from the target vehicle, obtains a perception dataset from the perception device, and interpolates the vehicle dataset. The time interval of the obtained first vehicle dataset is consistent with the time interval of the perception dataset. After aligning and matching the first vehicle dataset and the perception dataset, the corresponding target vehicle data and target perception data can be obtained, thereby achieving matching of the vehicle data and the perception data. Then, the circumscribed area corresponding to the target vehicle can be determined based on the target vehicle data, and the perception area corresponding to each perception target can be determined based on the target perception data. Based on coordinate operations and set operations, it can be determined whether the circumscribed area corresponding to each target vehicle and the perception area corresponding to each perception target have an intersection. When it is determined that the circumscribed area of ​​any target vehicle and the perception area of ​​any perception target have an intersection, the degree of overlap between the circumscribed area and the perception area can be further determined. Based on the degree of overlap, it can be determined whether the perception target corresponds to the target vehicle. After determining whether the perception target corresponds to the target vehicle, the perception data corresponding to the perception target is deleted from the perception dataset. Data deduplication of the perception data is achieved based on the degree of overlap, thereby improving the accuracy of data deduplication and further reducing the redundancy of real-time traffic data obtained by fusing vehicle data and perception data.

[0092] Figure 2 This is a flow chart of another data processing method provided by an embodiment of the present invention. This embodiment is specific based on the above embodiment. Figure 2 As shown, in this embodiment, the method may further include:

[0093] Step 210: Acquire a vehicle data set corresponding to the target vehicle from the target vehicle, and perceive the data set from a perception device.

[0094] The server may obtain a vehicle dataset corresponding to the target vehicle from the target vehicle based on a first time interval, and may obtain a perception dataset from the perception device based on a second time interval. Because the target vehicle does not strictly send the vehicle dataset to the server based on the first time interval, and the perception device does not strictly send the perception dataset to the server based on the second time interval, the time intervals between when the server obtains the vehicle dataset and the perception dataset are not strictly consistent.

[0095] The first preset time interval is greater than the second preset time interval. The first time interval may be 200 ms, and the second time interval may be 50 ms.

[0096] Specifically, when a target vehicle connected to the server enters the perception range corresponding to the server's perception device, the server obtains a vehicle dataset vehSyncQue i = {vehpos 1, vehpos 2, ..., vehpos m} from the target vehicle based on a first preset time interval, where i represents the i-th target vehicle connected to the server and m represents the number of vehicle data sets obtained from the i-th target vehicle. The value of m is related to the first preset time interval. In actual applications, the server can obtain a vehicle dataset vehSyncQue = {vehSyncQue 1, vehSyncQue 2, ..., vehSyncQue n} from all target vehicles connected to the server, where n represents the number of target vehicles connected to the server. The server can also obtain a perception dataset perceptSyncQue = {perceptObjList 1, perceptObjList 2, ..., perceptObjListn p} from the perception device based on a second preset time interval, where p represents the number of perception data sets obtained from the perception device. The value of p is related to the second preset time interval. perceptObjListn p can be image data captured by a camera at a single point in time, which can include multiple target vehicles.

[0097] vehpos={vid,x,y,h,s,tm,vl,vw}, where vid is the unique ID of the target vehicle, x is the longitude, y is the latitude (WGS84 coordinate system), h is the heading angle, s is the speed (unit: m / s), tm is the time (usually the sending timestamp), vl is the length (unit: m), and vw is the width (unit: m). perceptObjList = {poleid, tm, {po1, po2, ... poi}}, where poleid is the id of the pole where the sensing device is located, tm is the time point (usually the sending timestamp), poi is the data of the i-th sensing target, poi = perceptObj = {pid, x, y, h, s, tm, szl, szw}, pid is the unique id of the sensing target, which remains unique within the sensing range, x is the longitude, y is the latitude (WGS84 coordinate system), h is the heading angle (the counterclockwise angle with the horizontal direction), s is the speed (unit: m / s), tm is the time (usually the sending timestamp), szw is the sensing width (unit: m), and szl is the sensing length (unit: m).

[0098] For real-time reported vehicle data, each time a set of vehicle data is received, it is appended to the end of vehSyncQue i corresponding to the vehicle ID of the target vehicle according to the vehicle ID of the target vehicle; for real-time reported perception data, each time a set of perception data is received, it is appended to the end of perceptSyncQue.

[0099] In addition, since the time interval for obtaining the vehicle dataset from the target vehicle data is different from the time interval for obtaining the perception dataset from the perception device, the vehicle dataset and the perception dataset do not match, and the accuracy of the perception data is lower than that of the vehicle data.

[0100] In an embodiment of the present invention, acquisition of vehicle data and perception data is achieved.

[0101] Step 211: determine the interpolation time of the vehicle dataset according to the first time interval corresponding to the vehicle dataset and the second time interval corresponding to the perception dataset, and determine the interpolation data corresponding to each interpolation time according to each vehicle data included in the vehicle dataset.

[0102] In one embodiment, determining the interpolation time of the vehicle dataset according to a first time interval corresponding to the vehicle dataset and a second time interval corresponding to the perception dataset includes:

[0103] An interpolation time interval is determined based on the first time interval and the second time interval; for a vehicle time contained in any vehicle data in the vehicle data set, an interpolation time between the vehicle time and the previous vehicle time is determined based on a time difference between the vehicle time and the previous vehicle time corresponding to the vehicle time and the interpolation time interval; and an interpolation time between the vehicle time and the next vehicle time corresponding to the vehicle time is determined based on an interpolation time closest to the vehicle time between the vehicle time and the previous vehicle time and the interpolation time interval.

[0104] Specifically, when the first time interval is 200ms and the second time interval is 50ms, the interpolation time interval can be determined to be 50ms. For the vehicle time t(i) contained in any vehicle data vehpos i in vehSyncQue i, the previous vehicle time t(i-1) corresponding to the vehicle data t(i) and the next vehicle time t(i+1) corresponding to t(i) can be determined. Next, the time difference dti=t(i)-t(i-1) between t(i) and t(i-1) can be calculated, and the number of interpolation times n=dti%STM between t(i) and t(i-1) can be calculated, where STM can be the second preset time interval of 50ms, and n is the number of equal time intervals of 50ms between t(i) and t(i-1). Figure 3 A schematic diagram of determining interpolation time in another data processing method provided by an embodiment of the present invention, such as Figure 3As shown, n = 4, and the interpolation time tl between t(i) and t(i-1) closest to t(i) = t(i) - n*STM = t(i) - 4*50. Since the time interval of the first vehicle data set obtained by interpolating the vehicle data set is 50 ms, it can be determined that the sum of the interpolation time tl between t(i) and t(i-1) closest to t(i) and the interpolation time tf between t(i) and t(i+1) closest to t(i) is 50 ms, that is, tl + tf = 50. Therefore, it can be determined that tf = 50 - tl. After determining tf, the interpolation time between t(i) and t(i+1) can be determined in turn.

[0105] In one embodiment, the vehicle data includes position information of the target vehicle corresponding to the vehicle time, and the interpolation data includes position information of the target vehicle corresponding to the interpolation time. Accordingly, determining the interpolation data corresponding to each interpolation time based on each vehicle data included in the vehicle data set includes:

[0106] An interpolation time interval is determined based on the first time interval and the second time interval; the position information corresponding to each interpolation time is determined based on the position information, vehicle speed and interpolation time interval of the target vehicle at each vehicle time contained in each vehicle data; and the longitude and latitude contained in the position information corresponding to each interpolation time are determined as the interpolation data corresponding to each interpolation time.

[0107] Specifically, Figure 4 A schematic diagram of determining interpolation data corresponding to an interpolation time in another data processing method provided by an embodiment of the present invention, such as Figure 4 As shown, any vehicle data vehpos i in vehSyncQue i can include vehicle time t(i) and the vehicle position (xi, yi) and vehicle speed vi of the target vehicle. When the vehicle position corresponding to t(i) is known to be (xi, yi) and the vehicle speed is vi, the interpolation time between t(i) and t(i+1) separated from t(i) by tf can be determined. That is, the vehicle position corresponding to the first interpolation time between t(i) and t(i+1) is (xi+vi*tf,yi+vi*tf). Based on the same calculation method, the vehicle position corresponding to the second interpolation time between t(i) and t(i+1) can be determined to be (xi+vi*(tf+50),yi+vi*(tf+50)), and thus the interpolation data corresponding to all interpolation times can be determined.

[0108] In the embodiment of the present invention, the interpolation time and interpolation data of the vehicle data set are determined.

[0109] Step 212: Obtain the first vehicle dataset corresponding to the target vehicle according to the interpolation time, the interpolation data corresponding to the interpolation time, and the vehicle dataset.

[0110] In one implementation, step 212 may specifically include:

[0111] The interpolation data is inserted into the vehicle dataset according to the interpolation time; after determining that the interpolation time corresponding to any of the interpolation data coincides with the vehicle time, the interpolation data is deleted; after determining that the time interval between any of the vehicle time and the interpolation times corresponding to two adjacent interpolation data is less than the second time interval, the vehicle data corresponding to the vehicle time is deleted to obtain the first vehicle dataset corresponding to the target vehicle.

[0112] Specifically, the vehicle data set includes vehicle data arranged in chronological order. Therefore, the position of the interpolation data in the vehicle data set can be determined based on the interpolation time contained in the interpolation data, so as to insert the interpolation data into the vehicle data set. Of course, when inserting the interpolation data into the vehicle data set, if the interpolation time contained in any interpolation data coincides with the vehicle time contained in any vehicle data in the vehicle data set, the interpolation data will be deleted; if the time interval between any vehicle time and the interpolation time contained in two adjacent interpolation data is less than a second preset time interval, such as Figure 3 As shown, if the time interval tl between t(i) and t(i-1) and the time interval tf between t(i) and t(i+1) are both less than 50ms, the vehicle data corresponding to the vehicle time is deleted to avoid data redundancy. After deleting the redundant interpolation data and / or vehicle data, the first vehicle data set vehSyncQue I = {vehpos1, vehpos2, ..., vehposN} corresponding to the target vehicle can be obtained.

[0113] In an embodiment of the present invention, the vehicle dataset is padded based on the interpolation time and the interpolation data to obtain a first vehicle dataset corresponding to the target vehicle, so that the time intervals of the first vehicle dataset and the perception dataset are consistent.

[0114] Step 213: Match the first vehicle data set and the perception data set, and determine target perception data and target vehicle data based on the matching result.

[0115] In one implementation, step 213 may specifically include:

[0116] Determine multiple time points with equal time intervals, where the time intervals of the multiple time points are smaller than the time interval of the vehicle data set; for any time point, determine the vehicle data corresponding to the vehicle time closest to the time point in the first vehicle data set, and determine the perception data corresponding to the perception time closest to the time point in the perception data set; determine the vehicle data corresponding to the vehicle time closest to the time point as the target vehicle data, and determine the perception data corresponding to the perception time closest to the time point as the target perception data.

[0117] In practical applications, the pulse time corresponding to each pulse in the isochronous pulse can be determined; each pulse time can be traversed to determine the first difference between any pulse time and the first vehicle time contained in each first vehicle data in the first vehicle data set, and the second difference between any pulse time and the perception time contained in each perception data in the perception data set; the first vehicle data corresponding to the first vehicle time corresponding to the smallest first difference is determined as the target vehicle data, and the perception data corresponding to the perception time corresponding to the smallest second difference is determined as the target perception data. The target perception data and the target vehicle data are the aligned and matched perception data and vehicle data.

[0118] Specifically, first, an isochronous pulse generator can be constructed. The time interval between pulses sent by the isochronous pulse generator is 50 ms, and the pulse time corresponding to each pulse is set as pti, where i represents the number of pulses. Figure 5 A schematic diagram of time alignment of a first vehicle dataset and a perception dataset based on isochronous pulses in another data processing method provided by an embodiment of the present invention, such as Figure 5 As shown, after the isochronous pulser emits a pulse (the pulse time is pti), the perception data set perceptSyncQue and the first vehicle data set vehSyncQue I corresponding to each target vehicle accessed by the server can be traversed from the head, and the first difference ptdiff1 between the vehicle data contained in each vehicle data in the first vehicle data set and pti is calculated. The second difference ptdiff2 between the perception time contained in each perception data in the perception data set perceptSyncQue and pti is calculated. If both the first difference and the second difference are less than 50ms, the first vehicle data vehpos a and the perception data perceptObjList b are placed in a matching set R = {{ptdiff1, vehpos a, ptdiff2, perceptObjList b}, ...}. Then, each first difference and each second difference in the matching set can be compared respectively, and the first vehicle data corresponding to the first vehicle time corresponding to the smallest first difference is determined as the target vehicle data vehpos pti, and the perception data corresponding to the perception time corresponding to the smallest second difference is determined as the target perception data perceptObjList pti.

[0119] In an embodiment of the present invention, by traversing each pulse emitted by the isochronous pulse generator, the first vehicle time and perception time corresponding to any pulse with the smallest pulse time difference are determined, and then the first vehicle data corresponding to the first vehicle time can be determined as the target vehicle data, and the perception data corresponding to the perception time can be determined as the target perception data, thereby realizing alignment and matching of the perception data and the vehicle data.

[0120] Step 214: Determine the perception area of ​​each perception target based on the target perception data, and determine the circumscribed area of ​​the target vehicle based on the target vehicle data.

[0121] In one embodiment, determining the perception area of ​​each perception target based on the target perception data includes:

[0122] Based on the target perception data, the position information, length information and width information of each perception target are determined; the center position information of each perception target is determined according to the longitude and latitude contained in the position information of each perception target; and the perception area of ​​each perception target is determined according to the center position information, the length information and the width information of each perception target.

[0123] Further, determining the center position information of each of the sensing targets according to the longitude and latitude included in the position information of each of the sensing targets includes:

[0124] The distance between each of the perception targets and the perception device is determined based on the position information of each of the perception targets and the position information of the perception device, and the position information optimization parameters and overlap rate optimization parameters of each of the perception targets are determined based on the distance; the position information of each of the perception targets is optimized based on the position information optimization parameters of each of the perception targets to obtain the optimized position information of each of the perception targets, wherein the optimized position information includes optimized longitude and optimized latitude; the optimized longitude and optimized latitude included in each of the optimized position information are determined as the center position information of each of the perception targets.

[0125] Specifically, each perception target in perceptObjList pti is traversed, and the distance between the perception target and the perception device is determined based on the location information of the perception target and the location information of the perception device. Furthermore, the perception target is determined to be in the far region perceptObjList pti RR, the middle region perceptObjList pti MR, or the near region perceptObjList pti NR based on the distance. Where perceptObjList pti xx = {poleid, tm, {po1, po2, ...po}}, poi = perceptObj = {pid, x, y, h, s, tm, szw, szl}. Furthermore, the position information optimization parameter AMPLIFY RATO and the overlap rate optimization parameter μ of the perception target can be determined according to whether the perception target is in the far zone, the middle zone or the near zone. For example, when the perception target is in the far zone, AMPLIFY RATO can be determined to be 145%, μ=1.1; when the perception target is in the middle zone, AMPLIFY RATO can be determined to be 125%, μ=1.05; when the perception target is in the near zone, AMPLIFY RATO can be determined to be 100%, μ=1.02.

[0126] Figure 6 A schematic diagram of determining optimized position information corresponding to a perception target in another data processing method provided by an embodiment of the present invention, such as Figure 6 As shown, after determining the position information optimization parameters corresponding to the perception target, the optimized position information (adjustment point) can be determined, that is, the optimized longitude x1 = x - (cos(h)*sqrt(x*x+y*y)*AMPLIFY_RATO) and the optimized latitude y1 = y - (sin(h)*sqrt(x*x+y*y)*AMPLIFY_RATO). Of course, if the angle is not in the first quadrant, the angle value is converted.

[0127] After determining the optimized location information corresponding to the perception target, each perception target in perceptObjList pti can be traversed to construct the perception area of ​​each perception target, that is, to construct the perception rectangle poRect i = {Li, Ti, Ri, Bi} corresponding to each perception target. When the longitude and latitude coordinates and the length meter conversion formula are set to DEGREE_2METER = 108000, it can be determined that: L = x1 - (szw / DEGREE_2METER) / 2, T = y1 + (szl / DEGREE_2METER) / 2, R = x1 + (szw / DEGREE_2METER) / 2, B = y1 - (szl / DEGREE_2METER) / 2.

[0128] In this embodiment, the perception areas of multiple perception targets can be determined from one target perception data perceptObjList pti. That is, when the perception data is a captured image, the perception areas of multiple perception targets (perception vehicles) can be determined from one image.

[0129] In one embodiment, determining the circumscribed area of ​​the target vehicle based on the target vehicle data includes:

[0130] Based on the target vehicle data, the position information, length information and width information of the target vehicle are determined; the longitude and latitude contained in the position information of the target vehicle are determined as the center position information of the target vehicle; and the circumscribed area of ​​the target vehicle is determined according to the center position information, the length information and the width information of the target vehicle.

[0131] Specifically, the bounding box of the target vehicle can be constructed, that is, the bounding box vehRect = {VL, VT, VR, VB} corresponding to the target vehicle can be constructed. As mentioned above, when the latitude and longitude coordinates and the length meter conversion formula are set to DEGREE_2METER = 108000, it can be determined that: VL = x1-(vw / DEGREE_2METER) / 2, VT = y1+(vl / DEGREE_2METER) / 2, VR = x1+(vw / DEGREE_2METER) / 2, VB = y1-(vl / DEGREE_2METER) / 2.

[0132] Of course, the aforementioned calculation process is all performed in the GIS coordinate system. During the calculation process, the perceived target and target vehicle can be converted to the GIS coordinate system.

[0133] In an embodiment of the present invention, the target perception data and the target vehicle data are calculated to construct the perception area corresponding to each perception target contained in the target perception data and the external area corresponding to the target vehicle corresponding to the target vehicle data, thereby realizing the construction of the perception area and the external area.

[0134] Step 215: When it is determined that the circumscribed area of ​​any target vehicle intersects with the sensing area of ​​any sensing target, determine the degree of overlap.

[0135] The degree of overlap may be an area overlap ratio between the intersection area and the sensing area or the circumscribed area.

[0136] Specifically, the intersection of poRect i corresponding to each perception target and vehRect corresponding to the target vehicle can be calculated. Based on the geographic coordinates and set operations, the intersection can be calculated as povehRect = {UL, UT, UR, UB}, and then the intersection area povehArea = (UR-UL)*(UT-UB) can be determined.

[0137] On the one hand, after determining the perception area of ​​the perception region, the area overlap ratio between the intersection area and the perception area can be further determined. Based on the area overlap ratio, the degree of overlap between the circumscribed area and the perception area can be determined. Specifically, after determining the perception area corresponding to the perception target as poArea = (RL) * (TB), the area overlap ratio between the intersection area and the perception area can be determined as povehCoin = povehArea / poArea based on the intersection area povehArea and the perception area poArea.

[0138] On the other hand, after determining the circumscribed area of ​​the circumscribed region, the overlap ratio between the intersection area and the circumscribed area can be further determined. Based on the overlap ratio, the degree of overlap between the circumscribed region and the sensing area can be determined. Specifically, after determining the circumscribed area of ​​the target vehicle as vehArea = (VR - VL) * (VT - VB), the overlap ratio between the intersection area and the circumscribed area can be determined based on the intersection area povehArea and the circumscribed area vehArea: povehCoin = povehArea / vehArea.

[0139] In an embodiment of the present invention, after determining that the perception area and the external area intersect, the intersection area can be determined, and the area overlap ratio can be determined based on the intersection area and the perception area corresponding to the perception area or the external area corresponding to the external area. Then, the degree of overlap between the external area and the perception area can be determined based on the area overlap ratio. The degree of overlap can provide a data basis for determining whether the perception target corresponds to the target vehicle.

[0140] Step 216: Determine whether the perceived target and the target vehicle correspond based on the degree of overlap.

[0141] In one implementation, step 216 may specifically include:

[0142] If the degree of overlap is greater than a first preset threshold, it is determined that the perceived target corresponds to the target vehicle; if the degree of overlap is less than or equal to the first preset threshold and greater than a second preset threshold, the target perception data is updated based on the previous perception data and / or the next perception data of the target perception data in the perception data set to obtain first target perception data; if the degree of overlap between the first perception area corresponding to the first target perception data and the external area of ​​the target vehicle is greater than the first preset threshold, it is determined that the perceived target corresponds to the target vehicle.

[0143] When the target is in the far zone, the first preset threshold COIN_RATO may be set to 0.7; when the target is in the middle zone, the first preset threshold COIN_RATO may be set to 0.8; when the target is in the near zone, the first preset threshold COIN_RATO may be set to 0.9. The second preset threshold may be 0.6.

[0144] Specifically, if povehCoin>COIN_RATO, it is determined that the perception target corresponds to the target vehicle. At this time, the perception data corresponding to the perception target can be deleted in the perception data set, and the element set deRet=(pid, vid, povehCoin) is recorded and added to the tail of the regression compensation queue; if 0.6<povehCoin<COIN_RATO, the element set deRet=(pid, vid, povehCoin) is recorded and added to the tail of the regression compensation queue. It is necessary to further determine whether the perception target and the target vehicle are the same target object.

[0145] Because the vehicle is positioned with high precision, the target vehicle data is accurate. The reason why the overlap falls below the first preset threshold is due to two factors: first, the detection algorithm is affected by external environmental interference, resulting in false detections (for example, sudden changes in light, obstructions such as leaves, etc.); second, the target perception data and target vehicle data are incorrectly determined.

[0146] For the second reason, the target perception data can be updated based on the previous perception data and / or the next perception data of the target perception data in the perception data set to obtain the first target perception data. For example, the previous perception data of the target perception data in the perception data set can be determined as the first target perception data, and then the overlap rate poCoin_pre of the first perception area corresponding to the first target perception data and the circumscribed area of ​​the target vehicle can be determined; the next perception data of the target perception data in the perception data set can be determined as the first target perception data, and then the overlap rate poCoin_next of the first perception area corresponding to the first target perception data and the circumscribed area of ​​the target vehicle can be determined. If poCoin_pre>COIN_RATO or poCoin_next>COIN_RATO, then poCoin is determined to be the larger value of poCoin_pre and poCoin_next, and then it can be determined that poCoin>COIN_RATO, which means that the perception target is determined to correspond to the target vehicle; otherwise, poCoin is determined to be 0, and then it can be determined that poCoin<0.6, which means that the perception target is determined not to correspond to the target vehicle.

[0147] In actual applications, the first and second area overlap ratios determined before determining the area overlap ratio are obtained. After determining that both the first and second area overlap ratios are greater than a first preset threshold, if poCoin_pre>COIN_RATO or poCoin_next>COIN_RATO, the sensed target is determined to correspond to the target vehicle. Determining that both the first and second area overlap ratios are greater than the first preset threshold ensures that the detection algorithm is correct.

[0148] For reason one, the overlap ratio can be optimized and compensated based on the overlap ratio optimization parameter μ determined in the previous steps. When the perceived target is in the far zone, μ can be determined to be 1.1; when the perceived target is in the middle zone, μ can be determined to be 1.05; and when the perceived target is in the near zone, μ can be determined to be 1.02. Therefore, the first and second area overlap ratios determined before determining the area overlap ratio are obtained. After determining that both the first and second area overlap ratios are greater than the first preset threshold, if poCoin_pre×μ>COIN_RATO or poCoin_next×μ>COIN_RATO, then it is determined that the perceived target corresponds to the target vehicle.

[0149] In an embodiment of the present invention, whether the perception target and the target vehicle correspond can be determined based on the degree of overlap, and when it is determined that the perception target and the target vehicle correspond, it can be determined that the perception target and the target vehicle are the same target, and then the perception data corresponding to the perception target can be deleted in the perception data set to achieve deduplication of the perception data.

[0150] The data processing method provided by an embodiment of the present invention includes: obtaining a vehicle data set corresponding to a target vehicle from a target vehicle, and a perception data set obtained from a perception device; determining an interpolation time of the vehicle data set based on a first time interval corresponding to the vehicle data set and a second time interval corresponding to the perception data set, and determining interpolation data corresponding to each interpolation time based on each vehicle data contained in the vehicle data set; obtaining the first vehicle data set corresponding to the target vehicle based on the interpolation time, the interpolation data corresponding to the interpolation time, and the vehicle data set; matching the first vehicle data set and the perception data set, and determining target perception data and target vehicle data based on the matching result; determining a perception area of ​​each perception target based on the target perception data, and determining an external area of ​​the target vehicle based on the target vehicle data; determining a degree of overlap when it is determined that the external area of ​​any target vehicle and the perception area of ​​any perception target intersect; and determining whether the perception target and the target vehicle correspond based on the degree of overlap. The above technical solution obtains a vehicle data set from the target vehicle, obtains a perception data set from the perception device, determines the interpolation time of the vehicle data set according to the first time interval corresponding to the vehicle data set and the second time interval corresponding to the perception data set, and then determines the interpolation data corresponding to each interpolation time according to each vehicle data contained in the vehicle data set, interpolates the vehicle data set based on the interpolation time and the interpolation data, and the time interval of the obtained first vehicle data set is consistent with the time interval of the perception data set. After aligning and matching the first vehicle data set and the perception data set, the corresponding target vehicle data and target perception data can be obtained, thereby achieving matching of the vehicle data and the perception data, and then the circumscribed area corresponding to the target vehicle can be determined according to the target vehicle data. The data determines the perception area corresponding to each perception target. Based on coordinate operations and set operations, it can be determined whether the circumscribed area corresponding to each target vehicle and the perception area corresponding to each perception target intersect. When it is determined that the circumscribed area of ​​any target vehicle intersects with the perception area of ​​any perception target, the degree of overlap between the circumscribed area and the perception area can be further determined. According to the degree of overlap, it is determined whether the perception target corresponds to the target vehicle. After determining that the perception target corresponds to the target vehicle and that the perception target and the target vehicle are the same target, the perception data corresponding to the perception target is deleted from the perception data set. Based on the degree of overlap, data deduplication of the perception data is achieved, the accuracy of data deduplication is improved, and the redundancy of the real-time traffic data obtained by fusing vehicle data and perception data is further reduced.

[0151] Figure 7 This is a schematic diagram of the structure of a data processing device provided in an embodiment of the present invention. This device is suitable for deduplicating real-time traffic data consisting of sensor data and vehicle data. The device can be implemented using software and / or hardware and is typically integrated into a server.

[0152] like Figure 7 As shown, the device includes:

[0153] The data acquisition module 710 is configured to perform interpolation processing on the vehicle dataset acquired from the target vehicle to obtain a first vehicle dataset corresponding to the target vehicle;

[0154] a data matching module 720 for matching the first vehicle data set with the perception data set acquired from the perception device, and determining target perception data and target vehicle data based on the matching result;

[0155] An area determination module 730 is configured to determine a perception area of ​​each perception target based on the target perception data, and to determine a circumscribed area of ​​the target vehicle based on the target vehicle data;

[0156] An overlap degree determination module 740 is configured to determine an overlap degree when it is determined that the circumscribed area of ​​any target vehicle intersects with the sensing area of ​​any sensing target;

[0157] The execution module 750 is configured to determine whether the perceived target and the target vehicle correspond to each other based on the degree of overlap.

[0158] The data processing device provided in this embodiment interpolates a vehicle data set obtained from a target vehicle to obtain a first vehicle data set corresponding to the target vehicle; matches the first vehicle data set with a perception data set obtained from a perception device, and determines target perception data and target vehicle data based on the matching results; determines a perception area of ​​each perception target based on the target perception data, and determines a circumscribed area of ​​the target vehicle based on the target vehicle data; when it is determined that the circumscribed area of ​​any target vehicle and the perception area of ​​any perception target intersect, determines a degree of overlap; and determines whether the perception target and the target vehicle correspond based on the degree of overlap. The above technical solution obtains a vehicle dataset from the target vehicle, obtains a perception dataset from the perception device, and interpolates the vehicle dataset. The time interval of the obtained first vehicle dataset is consistent with the time interval of the perception dataset. After aligning and matching the first vehicle dataset and the perception dataset, the corresponding target vehicle data and target perception data can be obtained, thereby achieving matching between the vehicle data and the perception data. The circumscribed area corresponding to the target vehicle can be determined based on the target vehicle data, and the perception area corresponding to each perception target can be determined based on the target perception data. Based on coordinate operations and set operations, it can be determined whether the circumscribed area corresponding to each target vehicle and the perception area corresponding to each perception target intersect. When it is determined that the circumscribed area of ​​any target vehicle intersects the perception area of ​​any perception target, the degree of overlap between the circumscribed area and the perception area can be further determined. Based on the degree of overlap, it can be determined whether the perception target corresponds to the target vehicle. After determining that the perception target corresponds to the target vehicle and that the perception target and the target vehicle are the same target, the perception data corresponding to the perception target is deleted from the perception dataset. Data deduplication of the perception data is achieved based on the degree of overlap, thereby improving the accuracy of data deduplication and further reducing the redundancy of real-time traffic data obtained by fusing vehicle data and perception data.

[0159] Based on the above embodiment, the degree of overlap includes at least one of an area overlap ratio and an overlap area.

[0160] Based on the above embodiment, the region determination module 730 is specifically configured to:

[0161] Determining the position information, length information, and width information of each of the perception targets based on the target perception data; determining the center position information of each of the perception targets based on the longitude and latitude included in the position information of each of the perception targets; and determining the perception area of ​​each of the perception targets based on the center position information, the length information, and the width information of each of the perception targets;

[0162] Based on the target vehicle data, the position information, length information and width information of the target vehicle are determined; the longitude and latitude contained in the position information of the target vehicle are determined as the center position information of the target vehicle; and the circumscribed area of ​​the target vehicle is determined according to the center position information, the length information and the width information of the target vehicle.

[0163] Based on the above embodiment, the data acquisition module 710 is specifically configured to:

[0164] The vehicle dataset corresponding to the target vehicle is obtained from the target vehicle; an interpolation time of the vehicle dataset is determined based on a first time interval corresponding to the vehicle dataset and a second time interval corresponding to the perception dataset, and interpolation data corresponding to each interpolation time is determined based on each vehicle data included in the vehicle dataset; and the first vehicle dataset corresponding to the target vehicle is obtained based on the interpolation time, the interpolation data corresponding to the interpolation time, and the vehicle dataset.

[0165] In one embodiment, the vehicle data includes position information of the target vehicle corresponding to the vehicle time, and the interpolation data includes position information of the target vehicle corresponding to the interpolation time. Accordingly, determining the interpolation data corresponding to each interpolation time based on each vehicle data included in the vehicle data set includes:

[0166] An interpolation time interval is determined based on the first time interval and the second time interval; the position information corresponding to each interpolation time is determined based on the position information, vehicle speed and interpolation time interval of the target vehicle at each vehicle time contained in each vehicle data; and the longitude and latitude contained in the position information corresponding to each interpolation time are determined as the interpolation data corresponding to each interpolation time.

[0167] Based on the above embodiment, the data matching module 720 is specifically configured to:

[0168] Determine multiple time points with equal time intervals, where the time intervals of the multiple time points are smaller than the time interval of the vehicle data set; for any time point, determine the vehicle data corresponding to the vehicle time closest to the time point in the first vehicle data set, and determine the perception data corresponding to the perception time closest to the time point in the perception data set; determine the vehicle data corresponding to the vehicle time closest to the time point as the target vehicle data, and determine the perception data corresponding to the perception time closest to the time point as the target perception data.

[0169] Based on the above embodiment, the execution module 750 is specifically configured to:

[0170] If the degree of overlap is greater than a first preset threshold, it is determined that the perceived target corresponds to the target vehicle; if the degree of overlap is less than or equal to the first preset threshold and greater than a second preset threshold, the target perception data is updated based on the previous perception data and / or the next perception data of the target perception data in the perception data set to obtain first target perception data; if the degree of overlap between the first perception area corresponding to the first target perception data and the external area of ​​the target vehicle is greater than the first preset threshold, it is determined that the perceived target corresponds to the target vehicle.

[0171] The data processing device provided by the embodiment of the present invention can execute the data processing method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0172] It is worth noting that in the embodiment of the above-mentioned data processing device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be realized; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0173] Figure 8 A schematic diagram of the structure of a server provided in an embodiment of the present invention. Figure 8 A block diagram of an exemplary server 8 suitable for use in implementing embodiments of the present invention is shown. Figure 8 The server 8 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0174] like Figure 8 As shown, server 8 is implemented as a general purpose computing electronic device. Components of server 8 may include, but are not limited to, one or more processors or processing units 16, system memory 28, and a bus 18 connecting various system components (including system memory 28 and processing unit 16).

[0175] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. Examples of these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0176] The server 8 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the server 8, including volatile and non-volatile media, removable and non-removable media.

[0177] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Server 8 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be configured to read and write non-removable, non-volatile magnetic media ( Figure 8 Not shown, often called a "hard drive"). Although Figure 8 Not shown, a magnetic disk drive for reading and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. System memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of various embodiments of the present invention.

[0178] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0179] The server 8 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), one or more devices that enable a user to interact with the server 8, and / or any device that enables the server 8 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may occur via an input / output (I / O) interface 22. Furthermore, the server 8 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 20. Figure 8 As shown, the network adapter 20 communicates with other modules of the server 8 via the bus 18. Figure 8Not shown, other hardware and / or software modules may be used in conjunction with server 8, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0180] The processing unit 16 executes various functional applications and page displays by running programs stored in the system memory 28, for example, implementing the data processing method provided in the embodiment of the present invention, which includes:

[0181] Performing interpolation processing on the vehicle data set obtained from the target vehicle to obtain a first vehicle data set corresponding to the target vehicle;

[0182] matching the first vehicle data set with a perception data set acquired from a perception device, and determining target perception data and target vehicle data based on the matching result;

[0183] Determine the perception area of ​​each perception target based on the target perception data, and determine the circumscribed area of ​​the target vehicle based on the target vehicle data;

[0184] When it is determined that the circumscribed area of ​​any target vehicle and the sensing area of ​​any sensing target intersect, determining the degree of overlap;

[0185] It is determined whether the perceived target and the target vehicle correspond based on the degree of overlap.

[0186] Of course, those skilled in the art will understand that the processor may also implement the technical solution of the data processing method provided by any embodiment of the present invention.

[0187] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the data processing method provided in the embodiment of the present invention is implemented, for example, and the method includes:

[0188] Performing interpolation processing on the vehicle data set obtained from the target vehicle to obtain a first vehicle data set corresponding to the target vehicle;

[0189] matching the first vehicle data set with a perception data set acquired from a perception device, and determining target perception data and target vehicle data based on the matching result;

[0190] Determine the perception area of ​​each perception target based on the target perception data, and determine the circumscribed area of ​​the target vehicle based on the target vehicle data;

[0191] When it is determined that the circumscribed area of ​​any target vehicle and the sensing area of ​​any sensing target intersect, determining the degree of overlap;

[0192] It is determined whether the perceived target and the target vehicle correspond based on the degree of overlap.

[0193] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device.

[0194] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0195] Program code embodied on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0196] Computer program code for performing the operations of the present invention may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0197] Those skilled in the art will appreciate that the modules or steps of the present invention described above can be implemented using a general-purpose computing device. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Alternatively, they can be implemented using program code executable by a computer device, which can then be stored in a storage device and executed by the computing device. Alternatively, they can be fabricated into separate integrated circuit modules, or multiple modules or steps can be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.

[0198] In addition, the acquisition, storage, use, and processing of data in the technical solution of the present invention comply with the relevant provisions of national laws and regulations.

[0199] Note that the above are only preferred embodiments of the present invention and the technical principles employed. Those skilled in the art will appreciate that the present invention is not limited to the specific embodiments herein, and that various obvious changes, readjustments, and substitutions are possible for those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments and may include many other equivalent embodiments without departing from the scope of the present invention. The scope of the present invention is determined by the scope of the appended claims.

Claims

1. A data processing method, characterized in that: include: Performing interpolation processing on the vehicle dataset obtained from the target vehicle to obtain a first vehicle dataset corresponding to the target vehicle, wherein a time interval of the first vehicle dataset is consistent with a time interval of the perception dataset obtained from the perception device; matching the first vehicle dataset and the perception dataset, and determining target perception data and target vehicle data according to the matching result; Determine the perception area of ​​each perception target based on the target perception data, and determine the circumscribed area of ​​the target vehicle based on the target vehicle data; When it is determined that the circumscribed area of ​​any target vehicle and the sensing area of ​​any sensing target intersect, determining the degree of overlap; If the degree of overlap is greater than a first preset threshold, it is determined that the perceived target corresponds to the target vehicle; if the degree of overlap is less than or equal to the first preset threshold and greater than a second preset threshold, the target perception data is updated based on the previous perception data and / or the next perception data of the target perception data in the perception data set to obtain first target perception data; if the degree of overlap between the first perception area corresponding to the first target perception data and the external area of ​​the target vehicle is greater than the first preset threshold, it is determined that the perceived target corresponds to the target vehicle.

2. The data processing method according to claim 1, wherein: The degree of overlap includes at least one of an area overlap ratio and an overlap area.

3. The data processing method according to claim 1, wherein: Determining a perception area of ​​each perception target according to the target perception data includes: Determining the position information, length information, and width information of each of the sensed targets based on the target sensing data; Determining the center position information of each of the sensing targets according to the longitude and latitude included in the position information of each of the sensing targets; The perception area of ​​each perception target is determined according to the center position information, the length information, and the width information of each perception target.

4. The data processing method according to claim 1, wherein: Determining a circumscribed area of ​​the target vehicle according to the target vehicle data includes: Determine the position information, length information and width information of the target vehicle based on the target vehicle data; Determining the longitude and latitude included in the location information of the target vehicle as the center location information of the target vehicle; The circumscribed area of ​​the target vehicle is determined according to the center position information, the length information, and the width information of the target vehicle.

5. The data processing method according to claim 1, wherein: Interpolating a vehicle dataset acquired from a target vehicle to obtain a first vehicle dataset corresponding to the target vehicle includes: Acquire the vehicle data set corresponding to the target vehicle from the target vehicle; Determining an interpolation time of the vehicle dataset according to a first time interval corresponding to the vehicle dataset and a second time interval corresponding to the perception dataset, and determining interpolation data corresponding to each interpolation time according to each vehicle data included in the vehicle dataset; The first vehicle dataset corresponding to the target vehicle is obtained according to the interpolation time, the interpolation data corresponding to the interpolation time, and the vehicle dataset.

6. The data processing method according to claim 5, characterized in that: The vehicle data includes the position information of the target vehicle corresponding to the vehicle time, and the interpolation data includes the position information of the target vehicle corresponding to the interpolation time. Accordingly, determining the interpolation data corresponding to each interpolation time according to each vehicle data included in the vehicle data set includes: determining an interpolation time interval according to the first time interval and the second time interval; Determining the position information of the target vehicle corresponding to each interpolation time according to the position information, vehicle speed and interpolation time interval of the target vehicle at each vehicle time included in each vehicle data; The longitude and latitude included in the position information of the target vehicle corresponding to each of the interpolation times are determined as the interpolation data corresponding to each of the interpolation times.

7. The data processing method according to claim 1, wherein: Matching the first vehicle data set with the perception data set obtained from the perception device, and determining target perception data and target vehicle data based on the matching result, including: determining a plurality of time points with equal time intervals, wherein the time interval between the plurality of time points is less than the time interval of the vehicle data set; For any time point, determining the vehicle data corresponding to the vehicle time closest to the time point in the first vehicle data set, and determining the perception data corresponding to the perception time closest to the time point in the perception data set; The vehicle data corresponding to the vehicle time closest to the time point is determined as the target vehicle data, and the perception data corresponding to the perception time closest to the time point is determined as the target perception data.

8. A data processing device, characterized in that: include: a data acquisition module, configured to interpolate a vehicle dataset acquired from a target vehicle to obtain a first vehicle dataset corresponding to the target vehicle, wherein a time interval of the first vehicle dataset is consistent with a time interval of a perception dataset acquired from a perception device; a data matching module, configured to match the first vehicle dataset with the perception dataset, and determine target perception data and target vehicle data based on the matching result; an area determination module, configured to determine a perception area of ​​each perception target based on the target perception data, and determine a circumscribed area of ​​the target vehicle based on the target vehicle data; an overlap degree determination module, configured to determine the overlap degree when it is determined that the circumscribed area of ​​any target vehicle intersects with the sensing area of ​​any sensing target; An execution module is used to determine that the perceived target corresponds to the target vehicle if the degree of overlap is greater than a first preset threshold; if the degree of overlap is less than or equal to the first preset threshold and greater than a second preset threshold, it is used to update the target perception data based on the previous perception data and / or the next perception data of the target perception data in the perception data set to obtain first target perception data; if the degree of overlap between the first perception area corresponding to the first target perception data and the circumscribed area of ​​the target vehicle is greater than the first preset threshold, it is used to determine that the perceived target corresponds to the target vehicle.

9. A server, characterized in that: The server includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the data processing method according to any one of claims 1 to 7.

10. A storage medium comprising computer-executable instructions, wherein the computer-executable instructions are used to perform the data processing method according to any one of claims 1 to 7 when executed by a computer processor.

Images