Method for improving positioning accuracy executed by vehicle positioning system and vehicle positioning system

Abstract

The invention discloses a method for improving positioning accuracy executed by a vehicle positioning system and the vehicle positioning system. An exemplary method includes identifying a first encoded mark around an entrance space in a parking facility to generate encoded mark identification information; estimating a position and an orientation of the identified encoded mark based on the encoded mark identification information and a parameter of the at least one camera, obtaining information about a second encoded mark having the same ID as the identified encoded mark from a mark database, the mark database contains information about an ID, a position, an orientation, and a size of each of a plurality of encoded marks installed in the parking facility, calculates an error based on the encoded mark identification information and information about a second encoded mark, and performs calibration based on the error when the error is greater than or equal to a preset threshold value.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of Korean Patent Application No. 10-2023-0113261, filed on August 29, 2023, which is hereby incorporated by reference in its entirety. Technical Field

[0003] The present disclosure relates to a method and apparatus for positioning using AVPS markers. More specifically, the present disclosure relates to a method and apparatus for improving the accuracy of positioning of an autonomous vehicle using AVPS markers. Background Art

[0004] The following description merely provides background information related to the present disclosure and does not constitute prior art.

[0005] In order to facilitate parking, an automatic valet parking system (AVPS) is being developed. When the driver gets off the vehicle at the drop-off area in the parking facility, the AVPS automatically operates the vehicle so that the vehicle moves to an empty parking space and parks. In addition, the AVPS automatically moves the parked vehicle to the pick-up area according to the driver's request to allow the driver to get on the vehicle.

[0006] For safe and reliable AVPS, level 4 or higher autonomous driving is required. AVPS must not only identify other objects to prevent collisions, but also determine empty parking spaces and driving routes and automatically move, park, and drive out of the vehicle. To this end, positioning technology for estimating the current position of the subject vehicle is important.

[0007] AVPS adopts vision-based positioning using high-definition maps and cameras as positioning technology. AVPS uses coded markers specified in ISO23374 for positioning. Coded markers are a type of fiducial marker and can be installed in parking facilities and recognized by vehicles. A fiducial marker is an artificial marker that is an object placed in the field of view of an imaging system that appears in the generated image and is used as a reference point or measurement. The high-definition map may include information about the identification (ID), location, orientation, etc. of the coded markers installed in the parking facility. The accuracy of coded marker recognition affects the vehicle positioning performance in AVPS.

[0008] Related technologies for fiducial marker detection include methods for detecting ArUco markers using general image processing techniques or deep learning. However, related technologies have the following problems: small markers may not be detected, markers may be detected incorrectly, or the marker recognition rate for highly distorted images may be very low.

[0009] Vehicles that have applied AVPS use high-definition maps and cameras to perform positioning. In other words, the accuracy of positioning is determined by the angle or position of the camera installation. When the angle or position of the camera installation changes from the information previously input into the vehicle due to a collision or other reasons, the accuracy of positioning may decrease.

[0010] Therefore, the camera needs to be calibrated to ensure the accuracy of positioning. Summary of the invention

[0011] An embodiment of the present invention provides a calibration method for ensuring positioning accuracy.

[0012] The embodiments of the present disclosure are not limited to the above-mentioned embodiments, and other embodiments not mentioned above will be clearly understood by a person of ordinary skill in the art through the following description.

[0013] At least one embodiment of the present disclosure provides a method for improving the positioning accuracy performed by a vehicle positioning system, comprising: identifying a first coded marker around an entrance space in a parking facility to generate coded marker identification information including an ID, a bounding box, and a corner point of the identified coded marker, estimating a position and orientation of the identified coded marker based on the coded marker identification information and parameters of at least one camera, obtaining information about a second coded marker having the same ID as the identified coded marker from a marker database, the marker database containing information about the ID, position, orientation, and size of each of a plurality of coded markers installed in the parking facility, calculating an error based on the coded marker identification information and the information about the second coded marker, and in response to the error being greater than or equal to a preset threshold, performing calibration based on the error.

[0014] Another embodiment of the present disclosure provides a vehicle positioning system set in a vehicle, including: a marker recognition unit, configured to recognize a coded marker in a parking facility and generate coded marker recognition information including an ID, a bounding box and a corner point of the recognized coded marker; a marker position estimation unit, configured to estimate the position and orientation of the recognized coded marker based on the coded marker recognition information and parameters of at least one camera; and a vehicle positioning unit, configured to obtain a current position of the vehicle in the parking facility, wherein the vehicle positioning unit includes: an error calculation unit, configured to calculate an error based on the coded marker recognition information and information about a second coded marker having the same ID as the recognized coded marker from a marker database, the marker database containing information about the ID, position, orientation and size of each of a plurality of coded markers installed in the parking facility; and a calibration unit, configured to perform calibration based on the error in response to the error being greater than or equal to a preset threshold.

[0015] According to an embodiment of the present disclosure, a calibration method may be provided for ensuring the accuracy of positioning by measuring an error using the position and orientation of a specific encoding mark and performing calibration using the error.

[0016] The effects of the present disclosure are not limited to the above-mentioned effects, and other effects not mentioned will be clearly understood from the following description by those skilled in the art. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a configuration diagram of a vehicle positioning system using an AVPS tag according to an embodiment of the present disclosure.

[0018] Figure 2 is a schematic block diagram showing a vehicle positioning unit according to an embodiment of the present disclosure.

[0019] Figure 3 is a diagram illustrating a parking facility according to an embodiment of the present disclosure.

[0020] Figure 4 Detailed description is a flowchart illustrating a process of performing calibration by a vehicle positioning system according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0021] Hereinafter, some embodiments of the present disclosure will be described in detail with reference to the attached illustrative drawings. In the following description, the same reference numerals preferably represent the same elements, although these elements are shown in different drawings. In addition, in the following description of some embodiments, for the purpose of clarity and brevity, detailed descriptions of related known components and functions will be omitted when it is considered to obscure the subject matter of the embodiments of the present disclosure.

[0022] Various ordinal numbers or letter codes such as first, second, i), ii), a), b), etc. are only added as prefixes to distinguish one component from another, and do not imply or suggest the substance, order or sequence of the components. Throughout this specification, when a component "includes" or "comprises" a component, the component is intended to also include other components, and these components are not excluded unless specifically stated to the contrary. Terms such as "unit", "module", etc. refer to one or more units for processing at least one function or operation, which can be implemented by hardware, software or a combination thereof.

[0023] The following description of the embodiments of the present disclosure in conjunction with the accompanying drawings is intended to describe exemplary embodiments of the present disclosure, and is not intended to represent only embodiments in which the technical concept of the present disclosure can be practiced.

[0024] In this specification, the term "AVPS tag" may be used interchangeably with the term "coding tag" and may be simply referred to as the term "tag".

[0025] A vehicle positioning system using an AVPS tag (hereinafter, referred to as a “vehicle positioning system”) according to an embodiment of the present disclosure will first be described.

[0026] refer to Figure 1 , the vehicle positioning system 10 according to the embodiment of the present disclosure obtains the current position of the vehicle. The vehicle positioning system 10 can recognize the coded marker in the image, estimate the position of the coded marker using the coded marker recognition information and the mileage information of the vehicle, and then perform map matching based on the estimated position of the coded marker and the AVPS parking facility marking information 30 to obtain the current position of the vehicle. To this end, the vehicle positioning system 10 includes all or some of the marker recognition unit 100, the mileage extraction unit 120, the marker position estimation unit 140, and the vehicle positioning unit 160.

[0027] The marker recognition unit 100 recognizes a coded marker in a parking facility based on images obtained by photographing the front, left, right, and rear sides of a vehicle using a plurality of cameras 20a, 20b, 20c, and 20d. The marker recognition unit 100 outputs coded marker recognition information including an ID, a bounding box, and corner points of the coded marker in the image.

[0028] To this end, the marker recognition unit 100 may perform marker detection, marker classification, and marker tracking. Marker detection is the process of simultaneously detecting the bounding box and corner points of an object belonging to a category corresponding to a coding marker in each input image frame, and a deep learning network trained by multi-task learning may be used, but the present disclosure is not limited thereto. Marker classification is the process of extracting a region of interest (ROI) corresponding to a coding marker in each image frame using the detection result and identifying the ID of the coding marker by performing decoding on the ROI. Marker tracking is the process of tracking the position change of a coding marker within a series of image frames, and coding marker tracking may be performed by additionally utilizing the ID information of the identified coding marker.

[0029] The mileage extraction unit 120 periodically calculates the longitudinal and lateral movement distances of the vehicle over time by wheel odometry and stores the longitudinal and lateral movement distances in a buffer. Wheel odometry refers to estimating the change in the position of the vehicle over time using vehicle specification information and vehicle sensor information. The vehicle specification information may include wheelbase, number of gear teeth, wheel size, etc. The vehicle sensor information may include wheel speed signals, wheel pulse signals, and steering angle signals received through a chassis controller area network (CAN).

[0030] The marker position estimation unit 140 estimates the position and orientation of the coded marker based on the center of the vehicle (hereinafter referred to as "vehicle-based coded marker position"). Here, "vehicle-based" means indicating the relative position and orientation of the coded marker with the center of the vehicle as a reference point. First, the camera-based coded marker position and orientation can be obtained using the coded marker identification information, the actual size of the coded marker, and the internal / external parameters of the camera. Here, "camera-based" means indicating the relative position and orientation of the coded marker with the camera as a reference point. Then, by using the vehicle specifications and the installation position of the camera, the reference point of the camera-based coded marker position and orientation is moved to the center of the vehicle, and the vehicle-based coded marker position can be estimated.

[0031] Meanwhile, a delay occurs from time t1 when the marker recognition unit 100 receives the image to time t2 when the marker recognition unit 100 outputs the coded marker recognition information. When the delay is long, the accuracy of the vehicle-based coded marker position estimation based on the coded marker recognition information may deteriorate due to the movement of the vehicle. Therefore, the marker position estimation unit 140 may use the buffer data stored by the mileage extraction unit 120 to obtain the longitudinal and lateral movement distances of the vehicle between time t1 and time t2, and use the obtained movement distances to correct the estimation result of the vehicle-based coded marker position.

[0032] The vehicle positioning unit 160 obtains the current position of the vehicle in the parking facility based on the coded marker identification information (the ID of the coded marker and the information about the vehicle-based coded marker position) and the AVPS parking facility marker information 30. The vehicle positioning unit 160 can find the marker ID that is the same as the ID of the recognized coded marker from the AVPS parking facility marker information 30, and obtain the current position of the vehicle in the parking facility using the vehicle-based coded marker position.

[0033] For example, it is assumed that a marker with ID 45 is installed at a position of 100 m in the longitudinal direction and 50 m in the lateral direction relative to the entry point of the parking facility. When the ID of the identified coded marker is 45 and the vehicle-based coded marker position is estimated to be 3 m in the longitudinal direction and -1 m in the lateral direction, by searching the AVPS parking facility marker information 30 for the marker corresponding to ID 45, based on the absolute position (100, 50) of the marker in the parking facility and the vehicle-based coded marker position (3, -1), it can be seen that the position of the vehicle in the parking facility is (103, 49).

[0034] The AVPS parking facility marking information 30 includes information about the ID, location, orientation, size, etc. of each of a plurality of coded markings installed in the parking facility. When a vehicle enters the parking facility, the AVPS parking facility marking information 30 may be included in a high-definition map transmitted from a parking facility control center. Here, the parking facility control center may be an R subsystem specified in ISO23374, but is not limited thereto.

[0035] The vehicle positioning system 10 uses a plurality of cameras to identify a coding marker. The vehicle positioning system 10 performs positioning by estimating the position of the identified coding marker and correcting the estimated position of the coding marker using the position or orientation of the camera when it was installed. However, due to impact, etc., the position or orientation of at least one of the plurality of cameras may be different from the position or orientation when it was installed. When the position or orientation of the camera changes from the position or orientation when the camera was installed, an error may occur in the position or orientation of the vehicle-based coding marker estimated by the marker position estimation unit 140. Due to the error in the position or orientation of the vehicle-based coding marker, an error may occur in the current position of the vehicle obtained by the vehicle positioning unit 160.

[0036] To eliminate errors in the position or orientation of the camera, the vehicle positioning unit 160 may perform calibration.

[0037] Figure 2 is a schematic block diagram showing a vehicle positioning unit according to an embodiment of the present disclosure.

[0038] refer to Figure 2 The vehicle positioning unit 160 includes an error calculation unit 210 and a calibration unit 220. Figure 2 The components shown in the figure represent functionally divided elements, and in an actual physical environment, at least one or more components may be implemented in an integrated form. Figure 2 The components shown in FIG. 1 are only one embodiment, and the vehicle positioning unit 160 may also include Figure 2 Other components than those shown in the figure may be included, or some components may be omitted.

[0039] According to an embodiment of the present disclosure, the error calculation unit 210 compares the vehicle-based coded mark position with the position of the actual coded mark included in the AVPS parking facility mark information 30, and calculates the position error. Here, the actual coded mark has the same ID as the vehicle-based coded mark. Here, the position error is the difference between the vehicle-based coded mark position and the actual coded mark position.

[0040] According to another embodiment of the present disclosure, the error calculation unit 210 compares the orientation of the vehicle-based coded marker with the orientation of the actual coded marker included in the AVPS parking facility marking information 30, and calculates the orientation error. Here, the actual coded marker has the same ID as the identified vehicle-based coded marker. Here, the orientation error is the difference between the vehicle-based coded marker orientation and the actual coded marker orientation.

[0041] The calibration unit 220 compares the calculated error with a preset threshold. When the calculated error is less than the preset threshold, the calibration unit 220 determines that the calibration is completed. For example, when the calculated position error is less than the position threshold, the calibration unit 220 may determine that the calibration is completed. As another embodiment, when the calculated orientation error is less than the orientation threshold, the calibration unit 220 may determine that the calibration is completed. Here, the position threshold is a threshold for determining whether the calibration of the position error is completed. The orientation threshold is a threshold for determining whether the calibration of the orientation error is completed.

[0042] When the calculated error is equal to or greater than a preset threshold, the calibration unit 220 may perform calibration. That is, when the position error is equal to or greater than the position threshold, or the orientation error is equal to or greater than the orientation threshold, the calibration unit 220 may perform calibration. For example, the calibration unit 220 may correct the internal and / or external parameters of at least one of the cameras 20a, 20b, 20c, and 20d. The calibration unit 220 may correct the internal and / or external parameters of at least one of the cameras 20a, 20b, 20c, and 20d based on the position error and / or the orientation error. The calibration unit 220 may correct the data of the installation position of at least one of the cameras 20a, 20b, 20c, and 20d based on the position error and / or the orientation error.

[0043] Calibration unit 220 may store the number of times calibration has been performed. If calibration has been performed more than a preset number of times, calibration unit 220 may send a "calibration failure" signal to the parking facility control center without performing calibration.

[0044] Figure 3 is a diagram illustrating a parking facility according to an embodiment of the present disclosure.

[0045] Reference Figure 3 , the vehicle 330 performs automatic parking by moving from the drop-off area 300 to the parking space 310. The vehicle 330 moves from the drop-off area 300 to the parking space 310 through the entrance space 320. Here, the entrance space 320 refers to a space or passage connecting the drop-off area 300 to the parking space 310.

[0046] Because the entrance space 320 is a designated location independent of the location of the vehicle 330, each coded marker around the entrance space 320 has its ID, location, and orientation designated. Therefore, when the vehicle 330 is located in the entrance space 320, the vehicle positioning system 10 can perform calibration with reference to the designated coded markers.

[0047] When the vehicle 330 is located in the entrance space 320, the vehicle 330 may be aligned based on the parking line of the entrance space 320. For example, the vehicle 330 may be aligned by using an e-corner system so that the parking line and the vehicle 330 are parallel. Here, the fact that the parking line is parallel to the vehicle means that the longitudinal direction of the vehicle is parallel to the parking line. The vehicle positioning system 10 may accurately identify the position and orientation of the coded marker by aligning the vehicle 330 based on the parking line.

[0048] Figure 4 Detailed description is a flowchart illustrating a process of performing calibration by a vehicle positioning system according to an embodiment of the present disclosure.

[0049] Reference Figure 4 , the marker recognition unit 100 may recognize the coded markers around the entrance space 320. The marker recognition unit 100 generates coded marker recognition information including an ID of each coded marker and a plurality of corner points (S400).

[0050] The marker position estimation unit 140 estimates the vehicle-based coded marker position for each coded marker around the entrance space 320. The marker position estimation unit 140 may estimate the camera-based coded marker position and orientation by using, for example, coded marker identification information, an actual size of the coded marker, and internal / external parameters of at least one of the cameras 20a, 20b, 20c, and 20d. The marker position estimation unit 140 may estimate the vehicle-based coded marker position and orientation from the camera-based coded marker position and orientation by using vehicle specifications and an installation position of at least one of the cameras 20a, 20b, 20c, and 20d (S410).

[0051] The error calculation unit 210 obtains information about an actual coded marker having the same ID as the vehicle-based coded marker from the AVPS parking facility marker information 30 including information about the ID, position, orientation, and size of each of a plurality of coded markers installed in a parking facility (S420).

[0052] The error calculation unit 210 may calculate a position error by comparing the vehicle-based coded marker position with the actual coded marker position (S430). The error calculation unit 210 may calculate an orientation error by comparing the vehicle-based coded marker orientation with the actual coded marker orientation (S430).

[0053] The calibration unit 220 may compare the position error and / or orientation error with a preset threshold value (S440). The calibration unit 220 may compare the position error with the position threshold value. The calibration unit 220 may compare the orientation error with the orientation threshold value.

[0054] When the position error is equal to or greater than a preset position threshold, the calibration unit 220 performs calibration. When the orientation error is equal to or greater than a preset orientation threshold, the calibration unit 220 performs calibration. The calibration unit 220 stores the number of times calibration has been performed. The calibration unit 220 determines whether the number of times calibration has been performed exceeds a preset number of times (S450). When the number of times calibration has been performed exceeds the preset number of times, the calibration unit 220 sends a "calibration failure" signal to the parking facility control center without performing calibration (S460).

[0055] When the calibration has been performed no more than the preset number of times, the calibration unit 220 performs calibration using the position error and / or orientation error (S470). As an embodiment, the calibration unit 220 may correct the internal and / or external parameters of at least one of the cameras 20a, 20b, 20c, and 20d based on the position error and / or orientation error. As another embodiment, the calibration unit 220 may correct the data of the installation position of at least one of the cameras 20a, 20b, 20c, and 20d based on the position error and / or orientation error.

[0056] After the calibration unit 220 performs calibration, the vehicle positioning system 10 estimates the vehicle-based coded marker position and / or the vehicle-based coded marker orientation again, that is, repeating steps S410 to S440.

[0057] When the position error is less than the preset position threshold and the orientation error is less than the preset orientation threshold, the calibration unit 220 determines that the calibration has been completed (S480).

[0058] Each component of the device or method according to the embodiment of the present disclosure can be implemented in hardware, software or a combination of hardware and software. In addition, the function of each component can be implemented as software, and the microprocessor can be implemented to execute the software function corresponding to each component.

[0059] Various implementations of the systems and techniques described herein may include digital electronic circuits, integrated circuits, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations with one or more computer programs that can be executed on a programmable system. A programmable system includes at least one programmable processor (which may be a special purpose processor or a general purpose processor) combined to receive data and instructions from a storage system and to send data and instructions to the storage system, at least one input device, and at least one output device. A computer program (also referred to as a program, software, software application, or code) includes instructions for a programmable processor and stored in a "computer-readable storage medium."

[0060] Computer-readable storage media include all kinds of storage devices that store data that can be read by a computer system. Computer-readable storage media may include non-volatile or non-temporary media (such as ROM, CD-ROM, magnetic tape, floppy disk, memory card, hard disk, magneto-optical disk, and storage device), and further include temporary media (such as data transmission media). In addition, computer-readable storage media can be distributed in computer systems connected via a network, and computer-readable codes can be stored and executed in a distributed manner.

[0061] In the flowcharts in this specification, each process is described to occur sequentially, but this is only an example of the technology of the embodiments of the present disclosure. In other words, a person skilled in the art of the embodiments of the present disclosure can make various modifications and changes by changing the order described in the flowcharts in this specification or by going through one or more processes in parallel within the basic features of the embodiments of the present disclosure, so the flowcharts in this specification are not limited to the time series order.

[0062] Although exemplary embodiments of the present disclosure have been described for illustrative purposes, those skilled in the art will recognize that various modifications, additions, and substitutions are possible without departing from the concept and scope of the claimed invention. Therefore, for the sake of brevity and clarity, exemplary embodiments of the present disclosure have been described. The scope of the technical concept of the embodiments of the present disclosure is not limited by the diagrams. Therefore, those of ordinary skill will understand that the scope of the claimed invention is not limited by the embodiments explicitly described above, but by the claims and their equivalents.

Claims

1. A method for improving the accuracy of positioning performed by a vehicle positioning system, the method comprising: identifying a first coded marker around an entrance space in a parking facility to generate coded marker identification information including an identification (ID), a bounding box, and corner points of the identified coded marker; estimating a position and an orientation of the identified coded marker based on the coded marker identification information and parameters of at least one camera; obtaining information about a second coded marker having the same ID as the identified coded marker from a marker database, the marker database containing information including an ID, a location, an orientation, and a size of each of a plurality of coded markers installed in the parking facility; calculating an error based on the coded mark identification information and information about the second coded mark; as well as In response to the error being greater than or equal to a preset threshold, calibration is performed based on the error.

2. The method according to claim 1, wherein: Calculating the error includes calculating a position error by comparing the estimated position of the identified encoded marker with the position of the second encoded marker.

3. The method according to claim 1, wherein: Calculating the error includes calculating an orientation error by comparing the estimated orientation of the identified encoding marker with the orientation of the second encoding marker.

4. The method according to claim 1, wherein: Performing the calibration includes sending a calibration failure signal to a parking facility control center without performing the calibration when the calibration has been performed a number of times greater than a preset number of times.

5. The method according to claim 1, further comprising: The vehicle is aligned based on at least one parking line in the entrance space.

6. The method according to claim 1, wherein: Performing the calibration includes correcting data regarding an installation position of the at least one camera based on the error.

7. The method according to claim 1, wherein: Performing the calibration includes correcting at least one of an intrinsic parameter and an extrinsic parameter of the at least one camera based on the error.

8. The method according to claim 1, wherein: Performing the calibration includes determining that the calibration is completed when the position error is less than a preset position threshold and the orientation error is less than a preset orientation threshold.

9. A vehicle positioning system, arranged in a vehicle, the system comprising: a marker recognition unit configured to recognize a first coded marker in the parking facility and generate coded marker recognition information including an identification (ID), a bounding box, and corner points of the recognized coded marker; a marker position estimation unit configured to estimate the position and orientation of the identified coded marker based on the coded marker identification information and parameters of at least one camera; as well as a vehicle positioning unit configured to obtain a current position of the vehicle in the parking facility, Wherein, the vehicle positioning unit comprises: an error calculation unit configured to calculate an error based on the coded marker identification information and information about a second coded marker having the same ID as the identified coded marker from a marker database, the marker database including information about an ID, a position, an orientation, and a size of each of a plurality of coded markers installed in the parking facility, and The calibration unit is configured to perform calibration based on the error when the error is greater than or equal to a preset threshold.

10. The vehicle positioning system according to claim 9, wherein: The error calculation unit is configured to calculate a position error by comparing the estimated position of the identified encoded marker with the position of the second encoded marker.

11. The vehicle positioning system according to claim 9, wherein: The error calculation unit is configured to calculate an orientation error by comparing the estimated orientation of the identified encoding mark with the orientation of the second encoding mark.

12. The vehicle positioning system according to claim 9, wherein: The calibration unit is configured to correct data regarding an installation position of the at least one camera based on the error.

13. The vehicle positioning system according to claim 9, wherein: The calibration unit is configured to correct at least one of an intrinsic parameter and an extrinsic parameter of the at least one camera based on the error.

14. The vehicle positioning system according to claim 9, wherein: The calibration unit is configured to determine that the calibration is completed when the position error is smaller than a preset position threshold and the orientation error is smaller than a preset orientation threshold.

Images