Object positioning method, device, equipment and storage medium

Abstract

The present invention relates to an object positioning method, device, equipment and storage medium. The method includes obtaining a plurality of first position information obtained based on a vehicle-mounted camera and a plurality of second position information obtained based on a roadside sensing device, matching each first position information with each second position information to obtain a plurality of successfully matched groups of matching combinations; determining a plurality of target objects corresponding to the plurality of matching combinations; inputting the first matching position information and the second matching position information in each matching combination in the plurality of matching combinations into a position prediction model, performing position prediction processing, and obtaining a plurality of target position information of a plurality of target objects. The present invention does not require the installation of a sensing device on a vehicle, thus reducing the cost of the vehicle, and by matching the determined position information of the vehicle-mounted camera and the roadside sensing device, and performing a prediction process of the target position of the target object based on the matched position information, the positioning accuracy of the target position is improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an object positioning method, device, equipment and storage medium. Background Art

[0002] In recent years, automobile companies and Internet companies have started the research and development of intelligent connected vehicles, among which the core technology is autonomous driving technology. With the rapid development of technologies such as sensors, computing platforms, and big data, as well as the continuous improvement of intelligent communications and road facilities, driverless cars, as the ultimate development stage of intelligent connected vehicles, will surely enter real life in the near future and change the existing traffic mode. Object perception and positioning in autonomous driving technology is a crucial link and is the guarantee of the safety and intelligence of intelligent connected vehicles.

[0003] At present, the main method is to install the sensing device on the car together with the on-board camera to sense and locate the object, which increases the cost of the vehicle. However, after removing the sensing device, the accuracy of object sensing and positioning will be greatly reduced. Therefore, it is necessary to provide a technical solution to solve the problem that the cost and accuracy of object sensing and positioning in the prior art have a great influence on each other. Summary of the invention

[0004] The technical problem to be solved by the present invention is that during driving, the cost and accuracy of sensing and positioning objects that interfere with the driving of the vehicle have a significant impact on each other.

[0005] In order to solve the above technical problems, the present invention discloses an object positioning method, device, equipment and storage medium.

[0006] According to one aspect of the present application, a method for locating an object is disclosed, the method comprising: acquiring a plurality of first position information and a plurality of second position information, the first position information being obtained based on a vehicle-mounted camera, and the second position information being obtained based on a roadside sensing device;

[0007] Performing position information matching on each first position information in the plurality of first position information and each second position information in the plurality of second position information to obtain a plurality of groups of matching combinations with successful matching, each group of matching combinations including first matching position information and second matching position information, the first matching position information being one of the plurality of first position information, and the second matching position information being second position information in the plurality of second position information that matches the first matching position information;

[0008] Determine a plurality of target objects corresponding to the plurality of matching combinations, wherein the target object corresponding to each group of matching combinations is the object corresponding to the first matching position information in each group of matching combinations;

[0009] The first matching position information and the second matching position information in a plurality of matching combinations are input into a position prediction model, and position prediction processing is performed to obtain a plurality of target position information corresponding to the plurality of target objects.

[0010] Further, performing position information matching on each first position information in the plurality of first position information with each second position information in the plurality of second position information to obtain a plurality of groups of matching combinations that are successfully matched includes: determining the current first position information to be matched in the plurality of first position information;

[0011] Performing position information matching on the current first position information to be matched with each of the plurality of second position information to obtain a current matching combination that is successfully matched;

[0012] Each of the plurality of first position information is traversed to obtain a plurality of groups of matching combinations that are successfully matched.

[0013] Furthermore, performing position information matching on the current first position information to be matched with each of the plurality of second position information to obtain a current matching combination that is successfully matched includes:

[0014] Determine matching distance information between the current first position information to be matched and each of the plurality of second position information to obtain a plurality of matching distance information;

[0015] Determine target matching distance information among the multiple matching distance information, wherein the target matching distance information is the minimum matching distance information among the multiple matching distance information;

[0016] When the target matching distance information is less than a preset distance threshold, determining that the current first position information to be matched successfully matches the second position information corresponding to the target matching distance information;

[0017] The first position information and the second position information to be matched that have been matched successfully are respectively determined as the first matching position information and the second matching position information; and a matching combination is determined according to the first matching position information and the second matching position information. Further, after the first position information and the second position information to be matched that have been matched successfully are respectively determined as the first matching position information and the second matching position information, the method further includes:

[0018] If the second matching position information has been marked, obtain the previous matching distance information and the previous matching combination of the second matching position information, wherein the previous matching distance information is the minimum matching distance between the previous first matching position information and the second matching position information, the previous first matching position information is the first position information among the multiple first position information that is previously matched with the second matching position information, and the previous matching combination is the matching combination previously composed of the previous first matching position information and the second matching position information;

[0019] If the target matching distance information is smaller than the prior matching distance information, obtaining the concession matching distance information of the prior first matching position information, wherein the concession matching distance information is the first distance information greater than the prior target matching distance information among the plurality of prior matching distance information; determining the prior second position information corresponding to the concession matching distance information;

[0020] The previous first matching position information and the previous second position information are reassembled into a previous matching combination.

[0021] Furthermore, the method further comprises:

[0022] determining remaining first position information that is not matched among the plurality of first position information and remaining objects corresponding to the remaining first position information,

[0023] and determining remaining second position information that is not matched among the plurality of second position information and remaining objects corresponding to the remaining second position information;

[0024] taking the remaining objects corresponding to the remaining first position information or the remaining objects corresponding to the remaining second position information as target objects;

[0025] The remaining first position information or the remaining second position information is used as the remaining target position.

[0026] In one possible implementation, the position prediction model is a model based on a Kalman filter algorithm.

[0027] In one possible implementation, the roadside sensing device includes any one of a laser radar, a millimeter wave radar, and a radio frequency identification sensor.

[0028] According to another aspect of the present application, an object positioning device is also disclosed, the device comprising:

[0029] A location acquisition module, which acquires a plurality of first location information and a plurality of second location information, wherein the first location information is obtained based on a vehicle-mounted camera, and the second location information is obtained based on a roadside sensing device;

[0030] a matching combination determination module, configured to perform position information matching on each first position information in the plurality of first position information and each second position information in the plurality of second position information, so as to obtain a plurality of groups of matching combinations that are successfully matched, each group of matching combinations comprising first matching position information and second matching position information, the first matching position information being one of the plurality of first position information, and the second matching position information being second position information in the plurality of second position information that matches the first matching position information;

[0031] A target object determination module, used to determine a plurality of target objects corresponding to the plurality of matching combinations, wherein the target object corresponding to each group of matching combinations is the object corresponding to the first matching position information in each group of matching combinations;

[0032] The target position determination module is used to input the first matching position information and the second matching position information in multiple matching combinations into a position prediction model, perform position prediction processing, and obtain multiple target position information corresponding to the multiple target objects.

[0033] According to another aspect of the present application, an electronic device is also disclosed, including: a processor;

[0034] a memory for storing instructions executable by the processor;

[0035] The processor is configured to execute the instructions to implement the object positioning method as described above.

[0036] According to another aspect of the present application, a computer-readable storage medium is also disclosed. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can execute the object positioning method as described above.

[0037] The object positioning method of the present invention first obtains a plurality of first position information obtained based on the vehicle-mounted camera and a plurality of second position information obtained based on the roadside sensing device; thus, the sensing device can be set on the roadside without being installed on the vehicle, thereby reducing the vehicle cost. Further, each of the plurality of first position information is matched with each of the plurality of second position information to obtain a plurality of successfully matched combinations; the object corresponding to the first matching position information in each matching combination is used as the target object corresponding to each matching combination; the first matching position information and the second matching position information in each matching combination are input into the position prediction model, and position prediction processing is performed to obtain a plurality of target position information of the plurality of target objects. By matching the determined position information of the vehicle-mounted camera and the roadside sensing device, and performing the target position prediction processing of the target object based on the matched position information, the positioning accuracy of the target position is improved. Further, by fusing the positions detected by the vehicle-mounted camera and the roadside sensing device, the defect of perception failure caused by perception blind spots at intersections, obstacles, etc., which is only based on the perception of the vehicle-mounted camera, is overcome. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] 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.

[0039] Figure 1 It is a schematic diagram of an implementation environment of an object positioning method provided in an embodiment of the present application;

[0040] Figure 2 is a flow chart of an object positioning method provided by an embodiment of the present application;

[0041] Figure 3 is a flowchart of matching each first location information in a plurality of first location information with each first location information in a plurality of second location information provided by this embodiment;

[0042] 4 is a flowchart of matching the current first position information to be matched with each second position information in a plurality of second position information provided by an embodiment of the present application;

[0043] Figure 5 is a flow chart of another object positioning method provided by an embodiment of the present application;

[0044] Figure 6 is a flow chart of another object positioning method provided by an embodiment of the present application;

[0045] Figure 7 is a structural block diagram of an object positioning device provided in an embodiment of the present application;

[0046] Figure 8 It is a block diagram of an electronic device for object positioning provided in an embodiment of the present application. DETAILED DESCRIPTION

[0047] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.

[0048] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0049] Please refer to Figure 1, which is a schematic diagram of an implementation environment of an object positioning method provided in an embodiment of the present application. The application environment may include a vehicle 01, a vehicle-mounted camera 02 set on the vehicle 01, a body controller 03 set on the vehicle, and a roadside sensing device 04 set on the roadside.

[0050] In an optional embodiment, the on-board camera 02 on the vehicle 01 can be used to obtain image data of multiple objects around the vehicle 01, where the objects can be pedestrians, other vehicles other than the vehicle, roadside railings and other obstacles that interfere with the driving of the vehicle, and the image data of the objects can be expressed as information such as the object's position information, posture information, speed information, etc.

[0051] In an optional embodiment, the roadside sensing device 04 is installed on the roadside. The roadside sensing device 04 can be used to collect point cloud data of multiple objects around the vehicle and vehicle identification information. The point cloud data of each object can be used to determine a second position information of the object. Further, the roadside sensing device 04 can upload the collected point cloud data to the body controller 03 of the vehicle corresponding to the vehicle identification information based on the vehicle identification information.

[0052] In an optional embodiment, the vehicle body controller 03 can communicate with the vehicle camera 02 via a controller area network CAN bus. The roadside sensing device 04 can upload the acquired point cloud data to the vehicle body controller 03 via vehicle to X (V2X) wireless communication technology.

[0053] The following describes an object positioning method provided by the present application. FIG2 is a flow chart of an object positioning method provided by an embodiment of the present application, the method comprising:

[0054] S100. Acquire multiple first position information and multiple second position information, where the first position information is obtained based on a vehicle-mounted camera, and the second position information is obtained based on a roadside sensing device.

[0055] Specifically, the vehicle-mounted camera can capture images around the vehicle, and the images can include multiple objects. After capturing images around the vehicle, the vehicle-mounted camera can upload the captured images to the body controller. The body controller can convert the positions corresponding to the multiple objects in the image captured by the vehicle-mounted camera from the position information in the camera coordinate system to the position information in the world coordinate system based on the conversion relationship between the camera coordinate system and the world coordinate system, so as to obtain multiple first position information based on the vehicle-mounted camera, wherein each object in the image corresponds to one first position information. It can be understood that the conversion process from the camera coordinate system to the world coordinate system is a prior art and will not be repeated here.

[0056] Furthermore, the roadside sensing device may be any one of a laser radar, a millimeter wave radar, and a radio frequency identification sensor. The roadside sensing device may obtain point cloud data of multiple objects around the vehicle, and the point cloud data of each object may be used to determine a second position information of the object. It is understandable that the object determined based on the vehicle-mounted camera may be the same as or different from the object determined based on the roadside sensing device.

[0057] S102: Perform position information matching on each piece of first position information among the plurality of first position information and each piece of second position information among the plurality of second position information to obtain a plurality of groups of successful matching combinations.

[0058] Each matching combination includes first matching position information and second matching position information, the first matching position information is one of a plurality of first position information, and the second matching position information is second position information matching the first matching position information among a plurality of second position information.

[0059] Specifically, the location information of each first location information in the plurality of first location information is matched with each second location information in the plurality of second location information, and the location point data corresponding to each first location information in the plurality of first location information is compared with the location point data corresponding to each second location information in the plurality of second location information, so as to obtain mutually matching first matching location information and second matching location information. Specifically, as shown in FIG. 3, Figure 3 FIG. 3 is a flowchart of matching each first location information in a plurality of first location information with each first location information in a plurality of second location information provided by this embodiment. As shown in FIG. 3 , the steps may include:

[0060] S200: Determine current first position information to be matched among multiple first position information.

[0061] Specifically, the first position information currently required to be matched may be determined from multiple pieces of first position information as the current first position information to be matched.

[0062] S202: Perform position information matching on the first position information to be matched and each of the plurality of second position information to obtain a current matching combination that is successfully matched.

[0063] Specifically, the current first position information to be matched can be matched with each of the multiple second position information respectively, so that when there is second position information in the multiple second position information that can match the current first position information to be matched, it is determined that the current first position information to be matched is matched successfully, and the current first position information to be matched is combined with the second position information in the multiple second position information that matches the current first position information to be matched to obtain a current matching combination that is successfully matched.

[0064] S204: traverse each first position information in the plurality of first position information to obtain a plurality of groups of matching combinations that are successfully matched.

[0065] Specifically, after the matching of the current first position information is completed, the process can return to step S200 to traverse each of the multiple first position information until each of the multiple first position information is determined as the current first position information to be matched once, thereby determining multiple matching combinations.

[0066] Further, the specific matching process of the current first position information to be matched with each of the plurality of second position information is specifically described below in conjunction with FIG4. As shown in FIG4, this step includes:

[0067] S300: Determine matching distance information between the current first position information to be matched and each second position information in a plurality of second position information to obtain a plurality of matching distance information.

[0068] Specifically, the matching distance information between the current first position information to be matched and each second position information in the multiple second position information can be determined based on the distance calculation formula between the spatial coordinate points to determine multiple matching distance information. Exemplarily, the multiple first position information can be the first position information corresponding to the four points a, b, c, and d, and the current first position information to be matched can be the first position information corresponding to point a. The multiple second position information can be the second position information corresponding to the four points A, B, C, and D. After the distance calculation is performed between the current first position information to be matched and each second position information in the multiple second position information, the matching distance information between the current first position information to be matched and each second position information as shown in Table 1 is obtained, and then multiple matching distance information is obtained.

[0069] Table 1

[0070]

[0071] S302: Determine target matching distance information among multiple matching distance information, where the target matching distance information is the minimum matching distance information among the multiple matching distance information.

[0072] Specifically, the minimum matching distance information is found among the multiple matching distance information, and the minimum matching distance information is used as the target matching distance information. For example, as shown in Table 1 above, the matching distance information between the current first position information to be matched corresponding to point a and the second position information corresponding to point D among the multiple second position information is the smallest. At this time, the second position information corresponding to point D can be used as the target matching distance information.

[0073] S304: When the target matching distance information is less than a preset distance threshold, determine that the current first position information to be matched successfully matches the second position information corresponding to the target matching distance information.

[0074] Specifically, the preset distance threshold may be 30mm, 50mm, 70mm, etc., which can be set according to actual needs and is not specifically limited here. When the target matching distance information is less than the preset distance threshold, it means that the current first position information to be matched and the second position information corresponding to the target matching distance information determine the same object, then it is determined that the current first position information to be matched and the second position information corresponding to the target matching distance information are matched successfully. Exemplarily, in this specification, the preset distance threshold may be 30mm. As can be seen from the above results, the target matching distance is 21mm, which is less than the preset distance threshold. At this time, it can be considered that the current first position information to be matched corresponding to point a and the second position information corresponding to point D are matched successfully, that is, the current first position information to be matched and the second position information corresponding to the target matching distance information are matched successfully.

[0075] S306, determining the successfully matched current first position information and the second position information to be matched as the first matching position information and the second matching position information respectively. It can be understood that if the currently matched first position information and the second position information corresponding to the target matching distance information are successfully matched, the currently matched first position information and the second position information corresponding to the target matching distance information can be marked respectively, for example, the successfully matched current first position information and the second position information to be matched are marked as the first matching position information and the second matching position information respectively.

[0076] S308: Determine a matching combination according to the first matching position information and the second matching position information.

[0077] Specifically, the first matching position information and the second matching position information that match each other are determined as a matching combination.

[0078] It can be understood that by taking each of the multiple first position information as the current position information to be matched, each of the multiple first position information can be traversed, avoiding missing the target object, thereby improving the vehicle's perception accuracy of surrounding objects and avoiding the missed target objects from affecting the normal driving of the vehicle.

[0079] S104: Determine multiple target objects corresponding to multiple matching combinations.

[0080] The target object corresponding to each matching combination is the object corresponding to the first matching position information in each matching combination.

[0081] Specifically, each of the multiple matching combinations corresponds to a target object. The vehicle body controller can also determine the type and object identification information of the object corresponding to each first position information in the image based on the image taken by the vehicle-mounted camera. Therefore, the object corresponding to the first matching position information in each group of matching combinations can be determined based on the object identification information corresponding to the first matching position information, and the object is used as the target object of the matching combination, and multiple target objects corresponding to multiple matching combinations can be further determined.

[0082] S106: Input the first matching position information and the second matching position information in the multiple matching combinations into a position prediction model, perform position prediction processing, and obtain multiple target position information of multiple target objects.

[0083] Specifically, the position prediction model may refer to a model for implementing the Kalman filter algorithm. When the first matching position information and the second matching position information are input into the position prediction model, the first matching position information and the second matching position information are respectively used as two measurement values. The position prediction model finally outputs an estimated value based on the input first matching position information and the second matching position information, and uses the estimated value as the target position of the target object corresponding to the first matching position information. It can be understood that each of the multiple target objects determined above will correspond to a target position, thereby determining multiple target position information corresponding to the multiple target objects.

[0084] In the present invention, a plurality of first position information obtained based on the vehicle-mounted camera and a plurality of second position information obtained based on the roadside sensing device are first obtained; thus, the sensing device can be set on the roadside without being installed on the vehicle, thereby reducing the vehicle cost. Furthermore, each first position information in the plurality of first position information is matched with each second position information in the plurality of second position information to obtain a plurality of successfully matched combinations; the object corresponding to the first matching position information in each matching combination is used as the target object corresponding to each matching combination; the first matching position information and the second matching position information in each matching combination are input into the position prediction model, and position prediction processing is performed to obtain a plurality of target position information of a plurality of target objects, and the positioning accuracy of the target position is improved by matching the determined position information of the vehicle-mounted camera and the roadside sensing device, and performing prediction processing of the target position of the target object based on the matched position information.

[0085] Further, the above-mentioned comparison of the position point data corresponding to each first position information in the plurality of first position information with the position point data corresponding to each second position information in the plurality of second position information to obtain mutually matching first matching position information and second matching position information is only a preferred implementation. In a specific implementation, the position point data corresponding to each second position information in the plurality of second position information may be compared with the position point data corresponding to each first position information in the plurality of first position information to obtain mutually matching first matching positions and second matching positions. In this process, the above-mentioned step S104 is repeated. The difference is that when the roadside perception device obtains information about objects around the vehicle, it can also obtain the correspondence between the identification information of the object and the second position information. Since the process is based on the comparison between the second position information and each first position information, after determining the second matching position information, the object corresponding to the second matching position information can be determined based on the identification information corresponding to the second matching position information, and the object can be used as the target object of the matching combination. The rest of the specific matching process and matching principles can refer to the steps and principles introduced above for comparing the position point data corresponding to each first position information in multiple first position information with the position point data corresponding to each second position information in multiple second position information, which will not be repeated here.

[0086] Further, as shown in FIG5 , another flow chart of the object positioning method is provided. The steps shown in FIG5 are specifically implemented after step S306 . As shown in FIG5 , the steps include: S400 , if the second matching position information has been marked, obtaining the prior matching distance information and the prior matching combination of the second matching position information.

[0087] Among them, the prior matching distance information is the minimum matching distance between the prior first matching position information and the second matching position information, the prior first matching position information is the first position information among multiple first position information that is prior matched with the second matching position information, and the prior matching combination is the matching combination prior composed of the prior first matching position information and the second matching position information.

[0088] Specifically, since each of the plurality of first position information is matched with each of the plurality of second position information, if the second matching position information has been marked, it means that the second matching position information has been matched previously. At this time, the previous matching distance information and the previous matching combination of the second matching position information can be obtained, and based on the obtained previous matching distance information and the previous matching combination of the second matching position information, the previous first matching position information in the previous matching combination, and the minimum matching distance between the previous first matching position information and the second matching position information are determined. And the size between the previous matching distance information and the target matching distance information is compared.

[0089] S402: If the target matching distance information is smaller than the previous matching distance information, obtain the concession matching distance information of the previous first matching position information.

[0090] The concession matching distance information is the distance information that is first greater than the previous target matching distance information among the multiple previous distance information.

[0091] Specifically, if the target matching distance information is smaller than the prior matching distance information, it means that the second matching position information is closer to the position information between the first position information to be matched, and the prior second position information corresponding to the concession matching distance information can be determined. Specifically, the concession matching distance information is the first distance information greater than the prior target matching distance information among multiple prior matching distance information. Exemplarily, if the prior target matching distance information is 20mm, and multiple prior matching distance information are 20mm, 23mm, 27mm, and 30mm respectively, then the first distance information greater than the prior target matching distance information is 23mm. At this time, 23mm is the concession matching distance information, and the second position information corresponding to the concession matching distance information is the prior second matching position information.

[0092] S404: Recompose the previous first matching position information and the previous second position information into a previous matching combination.

[0093] Specifically, after determining the previous first matching position information and the previous second position information, the previous first matching position information and the previous second position information may be recombined into a matching combination, and the recombined matching combination may be determined as the previous matching combination.

[0094] It can be understood that in the process of traversing the matching, by comparing the current target matching distance with the previous target matching distance, when it is determined that the currently determined minimum matching distance is less than the minimum matching distance of the previously completed matching, the previously determined matching combination is updated to improve the matching accuracy between the first matching position and the second matching position.

[0095] Further, as shown in FIG6 , a flow chart of another object positioning method of the present application is shown. As shown in FIG6 , the method includes:

[0096] S500, determining remaining first location information that is not matched among multiple first location information and remaining objects corresponding to the remaining first location information;

[0097] And, determining the remaining second position information that is not matched in the plurality of second positions and the remaining objects corresponding to the remaining second position information.

[0098] It can be understood that since the number of objects in the image taken by the vehicle-mounted camera is different from the number of objects around the vehicle acquired by the roadside perception device, or there may be objects not involved in the image taken by the vehicle-mounted camera that are detected by the roadside perception device, or there may be objects involved in the image taken by the vehicle-mounted camera that are not detected by the roadside perception device, therefore, there may be unmatched first position information in the multiple first position information, and there may be unmatched second position information in the multiple second position information. Therefore, it is necessary to determine the remaining unmatched first position information in the multiple first position information and the remaining objects corresponding to the remaining first position information, as well as to determine the remaining unmatched second position information in the multiple second positions and the remaining objects corresponding to the remaining second position information.

[0099] S502: Use the remaining objects corresponding to the remaining first position information or the remaining objects corresponding to the remaining second position information as target objects.

[0100] S504: Use the remaining first position information or the remaining second position information as the remaining target position.

[0101] By directly determining the remaining first position information and / or the remaining second position information as the target position information in the above steps S500 to S504, the target position information of the target object can be directly determined based on the remaining first position information and / or the remaining second position information, thereby reducing the impact of the inability to confirm the target position information due to the absence of matching position information on the normal driving of the vehicle. Further, based on the same inventive concept as the above method, as shown in FIG7 , the present application also discloses a structural block diagram of an object positioning device, as shown in FIG7 , the device includes:

[0102] A position acquisition module, for acquiring a plurality of first position information and a plurality of second position information, wherein the first position information is obtained based on a vehicle-mounted camera, and the second position information is obtained based on a roadside sensing device; a matching combination determination module, for matching each first position information in the plurality of first position information with each second position information in the plurality of second position information, so as to obtain a plurality of groups of matching combinations that are successfully matched, wherein each group of matching combinations includes a first matching position information and a second matching position information, wherein the first matching position information is one of the plurality of first position information, and the second matching position information is the second position information in the plurality of second position information that matches the first matching position information; a target object determination module, for determining a plurality of target objects corresponding to the plurality of matching combinations, wherein the target object corresponding to each group of matching combinations is the object corresponding to the first matching position information in each group of matching combinations;

[0103] The target position determination module is used to input the first matching position information and the second matching position information into a position prediction model, perform position prediction processing, and obtain multiple target position information corresponding to multiple target objects.

[0104] The implementation scheme of each module in an object positioning device in this embodiment refers to the processing steps of the above method, which will not be repeated here.

[0105] FIG8 is a block diagram of an electronic device for object positioning according to an exemplary embodiment. The electronic device may be a server, and its internal structure diagram may be as shown in FIG8 . The electronic device includes a processor, a memory, and a network interface connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for request processing is implemented.

[0106] Those skilled in the art can understand that the structure shown in FIG8 is only a block diagram of a part of the structure related to the scheme of the present disclosure, and does not constitute a limitation on the electronic device to which the scheme of the present disclosure is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components. In an exemplary embodiment, an electronic device is also provided, including: a processor; a memory for storing executable instructions of the processor; wherein the processor is configured to execute the instructions to implement a request processing method as in the embodiment of the present disclosure.

[0107] In an exemplary embodiment, a computer-readable storage medium is also provided, and when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the request processing method in the embodiment of the present disclosure. The computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0108] In an exemplary embodiment, a computer program product containing instructions is also provided. When the computer program product is executed on a computer, the computer is caused to execute the request processing method in the embodiment of the present disclosure.

[0109] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0110] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and examples are considered to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims. It should be understood that the present disclosure is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the present disclosure is limited only by the appended claims.

[0111] According to another aspect of the present application, a computer-readable storage medium is also disclosed. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can execute the object positioning method as claimed in the above claims.

[0112] It is worth noting that in the above-mentioned device and terminal embodiments, the modules and units 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 achieved; in addition, the specific names of the modules and units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0113] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the terminal embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of modules or units, which can be electrical, mechanical or other forms.

[0114] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An object positioning method, characterized in that: The method comprises: Acquire multiple first location information and multiple second location information, wherein the first location information is obtained based on a vehicle-mounted camera, and the second location information is obtained based on a roadside sensing device; Performing position information matching on each first position information in the plurality of first position information and each second position information in the plurality of second position information to obtain a plurality of groups of matching combinations with successful matching, each group of matching combinations comprising first matching position information and second matching position information, the first matching position information being one of the plurality of first position information, the second matching position information being second position information in the plurality of second position information that matches the first matching position information; the first matching position information and the second matching position information are determined based on the first position information and the second position information to be matched that have successfully matched; If the second matching position information has been marked, obtain the previous matching distance information and the previous matching combination of the second matching position information, wherein the previous matching distance information is the minimum matching distance between the previous first matching position information and the second matching position information, the previous first matching position information is the first position information among the multiple first position information that is previously matched with the second matching position information, and the previous matching combination is the matching combination previously composed of the previous first matching position information and the second matching position information; determine the matching distance information between the current first position information to be matched and each second position information among the multiple second position information to obtain multiple matching distance information; the multiple matching distance information is determined based on the matching distance information between the current first position information to be matched and each second position information among the multiple second position information; Determine target matching distance information among the multiple matching distance information, wherein the target matching distance information is the minimum matching distance information among the multiple matching distance information; If the target matching distance information is smaller than the previous matching distance information, obtaining the concession matching distance information of the previous first matching position information, wherein the concession matching distance information is the first distance information greater than the previous target matching distance information among the multiple previous matching distance information; Determine the previous second position information corresponding to the concession matching distance information; Recombining the previous first matching position information and the previous second position information into a previous matching combination; Determine a plurality of target objects corresponding to the plurality of matching combinations, wherein the target object corresponding to each group of matching combinations is the object corresponding to the first matching position information in each group of matching combinations; The first matching position information and the second matching position information in a plurality of matching combinations are input into a position prediction model, and position prediction processing is performed to obtain a plurality of target position information corresponding to the plurality of target objects.

2. The object positioning method according to claim 1, characterized in that: The performing position information matching of each first position information in the plurality of first position information with each second position information in the plurality of second position information to obtain a plurality of groups of matching combinations with successful matching includes: Determine the current first position information to be matched among the multiple first position information; Performing position information matching on the current first position information to be matched with each of the plurality of second position information to obtain a current matching combination that is successfully matched; Each of the plurality of first position information is traversed to obtain a plurality of groups of matching combinations that are successfully matched.

3. The object positioning method according to claim 2, characterized in that: The performing position information matching of the current first position information to be matched with each of the plurality of second position information to obtain a current matching combination with successful matching includes: Determine matching distance information between the current first position information to be matched and each of the plurality of second position information to obtain a plurality of matching distance information; Determine target matching distance information among the multiple matching distance information, wherein the target matching distance information is the minimum matching distance information among the multiple matching distance information; When the target matching distance information is less than a preset distance threshold, determining that the current first position information to be matched successfully matches the second position information corresponding to the target matching distance information; Determine the successfully matched current first position information and the second position information to be matched as the first matching position information and the second matching position information respectively; A matching combination is determined according to the first matching position information and the second matching position information.

4. The object positioning method according to claim 1, characterized in that: The method further includes: determining remaining first position information that is not matched among the plurality of first position information and remaining objects corresponding to the remaining first position information, and determining remaining second position information that is not matched among the plurality of second position information and remaining objects corresponding to the remaining second position information; taking the remaining objects corresponding to the remaining first position information or the remaining objects corresponding to the remaining second position information as target objects; The remaining first position information or the remaining second position information is used as the remaining target position.

5. The object positioning method according to claim 1, characterized in that: The position prediction model is a model based on the Kalman filter algorithm.

6. The object positioning method according to claim 1, characterized in that: The roadside sensing device includes any one of a laser radar, a millimeter wave radar and a radio frequency identification sensor.

7. An object positioning device, characterized in that: include: A location acquisition module, which acquires a plurality of first location information and a plurality of second location information, wherein the first location information is obtained based on a vehicle-mounted camera, and the second location information is obtained based on a roadside sensing device; A matching combination determination module, used to match each first position information in the multiple first position information with each second position information in the multiple second position information to obtain multiple groups of matching combinations with successful matches, each group of matching combinations including first matching position information and second matching position information, the first matching position information is one of the multiple first position information, and the second matching position information is the second position information in the multiple second position information that matches the first matching position information; the first matching position information and the second matching position information are determined based on the current first position information and the second position information to be matched that have successfully matched; if the second matching position information has been marked, obtain the previous matching distance information and the previous matching combination of the second matching position information, the previous matching distance information is the previous first matching distance information. The minimum matching distance between the position information and the second matching position information, the prior first matching position information is the first position information among the multiple first position information that is previously matched with the second matching position information, and the prior matching combination is the matching combination previously composed of the prior first matching position information and the second matching position information; determining the matching distance information between the current first position information to be matched and each second position information among the multiple second position information to obtain multiple matching distance information; the multiple matching distance information is determined based on the matching distance information between the current first position information to be matched and each second position information among the multiple second position information; determining the target matching distance information among the multiple matching distance information, and the target matching distance information is the minimum matching distance information among the multiple matching distance information; If the target matching distance information is smaller than the previous matching distance information, obtaining the concession matching distance information of the previous first matching position information, wherein the concession matching distance information is the first distance information greater than the previous target matching distance information among the multiple previous matching distance information; Determine the previous second position information corresponding to the concession matching distance information; re-form the previous first matching position information and the previous second position information into a previous matching combination; A target object determination module, used to determine a plurality of target objects corresponding to the plurality of matching combinations, wherein the target object corresponding to each group of matching combinations is the object corresponding to the first matching position information in each group of matching combinations; The target position determination module is used to input the first matching position information and the second matching position information in multiple matching combinations into a position prediction model, perform position prediction processing, and obtain multiple target position information corresponding to the multiple target objects.

8. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the object positioning method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the object positioning method according to any one of claims 1 to 6.

Images