Verification method of signboard recognition result and related device

Abstract

The application relates to a verification method and related device for a signboard recognition result. The method first acquires a to-be-recognized image containing a target signboard through an image acquisition device; secondly, the target signboard in the to-be-recognized image is recognized and calculated to obtain a recognition result, the recognition result at least including a recognition size of the target signboard and a recognition distance of the target signboard to the image acquisition device; then, a calibration distance corresponding to the recognition distance is queried from a calibration data set to obtain a calibration size corresponding to the target signboard; then, the recognition size and the calibration size are compared to obtain a comparison result; finally, the accuracy of the recognition result is verified based on the comparison result. Through the application, a deterministic result can be used to verify an indeterminate problem, the accuracy of the signboard recognition result can be verified, and the objectivity of the verification result of the accuracy of the signboard recognition result is ensured.

Description

Technical Field

[0001] This application relates to the field of high-precision map surveying technology, and in particular to a method and related apparatus for verifying road sign recognition results. Background Technology

[0002] With the development of technologies such as artificial intelligence and autonomous driving, building intelligent transportation has become a research hotspot, and high-precision maps are an indispensable part of intelligent transportation data construction. High-precision maps can include various traffic signs, such as ground features like lane lines, stop lines, and pedestrian crossings, as well as aerial features like road signs and traffic lights, to provide data support for navigation in applications such as autonomous driving. Road signs, as information carriers of urban geographic entities, possess navigation functions including place names, routes, distances, and directions. Furthermore, as infrastructure distributed at urban road intersections, they have unique spatial characteristics and serve as excellent carriers for the city's basic Internet of Things (IoT). Therefore, accurate and efficient identification of traffic road signs is crucial for the creation of high-precision maps.

[0003] However, in related technologies, the verification of the accuracy of road sign recognition results usually requires human intervention to label reliable data. However, manual labeling is prone to errors, so the objectivity of the verification results of the road sign recognition accuracy cannot be guaranteed. Summary of the Invention

[0004] To overcome the problems existing in the related technologies, this application provides a method and related apparatus for verifying road sign recognition results, which can verify the accuracy of road sign recognition results and ensure the objectivity of the verification results of the accuracy of road sign recognition results.

[0005] The first aspect of this application provides a method for verifying road sign recognition results, including:

[0006] The image to be identified is acquired using an image acquisition device;

[0007] The target road sign in the image to be identified is identified and calculated to obtain the identification result, which includes at least the identification size of the target road sign and the identification distance from the target road sign to the image acquisition device;

[0008] Query the calibration distance corresponding to the recognition distance from the calibration dataset to obtain the calibration size corresponding to the target road sign;

[0009] The identification size and the calibration size are compared to obtain the comparison result;

[0010] The accuracy of the identification result is verified based on the comparison results.

[0011] A second aspect of this application provides a verification device for road sign recognition results, comprising:

[0012] The image acquisition module is used to acquire images of the target road sign to be identified through an image acquisition device;

[0013] The target road sign recognition module is used to recognize the target road sign in the image to be recognized and obtain the recognition result. The recognition result includes at least the recognition size of the target road sign and the recognition distance from the target road sign to the image acquisition device.

[0014] The query module is used to query the calibration distance corresponding to the recognition distance from the calibration dataset to obtain the calibration size corresponding to the target road sign;

[0015] The comparison module is used to compare the identified size and the calibrated size to obtain the comparison result;

[0016] The verification module is used to verify the accuracy of the identification result based on the comparison result.

[0017] A third aspect of this application provides an electronic device, comprising:

[0018] Processor; and

[0019] The memory stores executable code, which, when executed by the processor, causes the processor to perform the road sign recognition result verification method as described above.

[0020] A fourth aspect of this application provides a non-transitory machine-readable storage medium having executable code stored thereon, which, when executed by a processor of an electronic device, causes the processor to perform a method for verifying road sign recognition results as described above.

[0021] The technical solution provided in this application can include the following beneficial effects: First, an image containing the target road sign is acquired using an image acquisition device; second, the target road sign in the image is identified and calculated to obtain a recognition result, which includes at least the recognition size of the target road sign and the recognition distance from the target road sign to the image acquisition device; then, the calibration distance corresponding to the recognition distance is queried from the calibration dataset to obtain the calibration size corresponding to the target road sign; next, the recognition size and the calibration size are compared to obtain a comparison result; finally, the accuracy of the recognition result is verified based on the comparison result. This application uses deterministic results to verify uncertainties, enabling the verification of the accuracy of the road sign recognition result and ensuring the objectivity of the verification result regarding the accuracy of the road sign recognition result.

[0022] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0023] The above and other objects, features and advantages of this application will become more apparent from the more detailed description of exemplary embodiments thereof in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments thereof.

[0024] Figure 1 This is a flowchart illustrating the method for verifying road sign recognition results according to an embodiment of this application;

[0025] Figure 2 This is a schematic diagram of an image taken at a relatively close distance to the target road sign, as shown in an embodiment of this application.

[0026] Figure 3 This is a schematic diagram of an image taken at a distance from the target road sign, as shown in an embodiment of this application.

[0027] Figure 4 This is a schematic diagram of the structure of the verification device for road sign recognition results shown in the embodiments of this application;

[0028] Figure 5 This is a schematic diagram of the structure of an electronic device shown in an embodiment of this application. Detailed Implementation

[0029] Preferred embodiments of the present application will now be described in more detail with reference to the accompanying drawings. While preferred embodiments of the present application are shown in the drawings, it should be understood that the present application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.

[0030] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0031] It should be understood that although the terms "first," "second," "third," etc., may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0032] In view of the problems existing in the related technologies, the embodiments of this application provide a method and related device for verifying road sign recognition results, which can verify the accuracy of road sign recognition results and ensure the objectivity of the verification results of the accuracy of road sign recognition results.

[0033] The technical solutions of the embodiments of this application are described in detail below with reference to the accompanying drawings.

[0034] Figure 1 This is a flowchart illustrating the method for verifying road sign recognition results according to an embodiment of this application. See also... Figure 1 This application provides a method for verifying road sign recognition results, which specifically includes the following steps:

[0035] S10: Acquire an image of the target road sign using an image acquisition device.

[0036] It should be noted that the execution entity of the road sign recognition result verification method provided in this embodiment of the invention is a road sign recognition result verification device. The road sign recognition result verification device can be a central processing unit (CPU) built into the vehicle, or a development board based on a CPU, for information processing and program execution.

[0037] Specifically, in step S10, the image acquisition device can be a monocular camera installed on the autonomous vehicle. The road sign recognition result verification device receives images captured in real time by the camera installed on the autonomous vehicle as images to be recognized, and these images contain the target road sign. The target road sign contained in the image to be recognized is not limited to one; it can be a road sign corresponding to multiple traffic signs. The road signs corresponding to traffic signs are usually regular shapes, and this embodiment of the invention does not specifically limit this. For example, the shape of the road sign corresponding to a traffic sign can be square or circular, etc. It should be noted that in this embodiment, the image to be recognized containing the target road sign is obtained by the image acquisition device on the autonomous vehicle at any location.

[0038] S11: Identify and calculate the target road sign in the image to be identified, and obtain the identification result. The identification result includes at least the identification size of the target road sign and the identification distance from the target road sign to the image acquisition device.

[0039] The process of identifying target road signs in the image to be identified is based on sample road sign images and parameters labeled with the corresponding sample road sign images.

[0040] The process of identifying and calculating the target road sign in the image to be identified to obtain the identification result specifically includes: acquiring the location information of the target road sign and the location information of the image acquisition device; calculating the distance based on the location information of the target road sign and the location information of the image acquisition device to obtain the identification distance d from the target road sign to the image acquisition device; and identifying the target road sign in the image to be identified using a road sign recognition algorithm to obtain the identification size size of the target road sign.

[0041] Specifically, in step S11, the step of identifying the target road sign in the image to be identified using a road sign recognition algorithm to obtain the recognition size of the target road sign includes: identifying and calculating the target road sign in the image to be identified using SLAM algorithm and deep learning to obtain the recognition size of the target road sign.

[0042] It should be noted that the road sign recognition algorithm uses a pre-trained deep learning model to identify the size of the target road sign, and calculates the distance between the target road sign and the image acquisition device based on the location information of the target road sign and the location information of the image acquisition device.

[0043] S12: Query the calibration distance corresponding to the recognition distance from the calibration dataset to obtain the calibration size corresponding to the target road sign.

[0044] In a specific embodiment, it is necessary to first calibrate the known set of images containing the target road sign to obtain a calibration dataset. This calibration dataset includes: the location information of the target road sign, the location information of the image acquisition device, the calibration distance between the target road sign and the image acquisition device, and the calibration size of the target road sign. In this specific embodiment, for the target road sign to be identified, multiple sets of images containing the target road sign are captured at different locations by the image acquisition device, and then the images are calibrated according to the location information of the target road sign. i Location information of image acquisition device (cp) i And the size of the target road sign corresponding to the shooting location. i To mark the target road signs. Calculate the distance d between the target road signs and the image acquisition device sequentially. i Then, the calibration parameters and the calculated distance d are used. i According to distance d iStore the corresponding data for the key, and then obtain the calibration dataset (containing the location information rp of the target road sign). i Location information of image acquisition device (cp) i and the size of the target road sign i It should be noted that when an image acquisition device captures images of the same target road sign from different locations, the size of the target road sign in the resulting images will vary. Figure 2 and Figure 3 As shown, Figure 2 The image was taken from a position relatively close to the target road sign. Figure 3 It is an image taken from a distance from the target road sign.

[0045] Specifically, the calibration process of the calibration dataset includes: receiving a calibration operation instruction; calibrating the target road sign in the image to be identified according to the calibration operation instruction to obtain calibration parameters, the calibration parameters including: the location information of the target road sign, the location information of the image acquisition device, and the calibration size of the target road sign; calculating the distance based on the location information of the target road sign and the location information of the image acquisition device to obtain the calibration distance from the target road sign to the image acquisition device; and storing the calibration parameters and the calibration distance as keywords to obtain the calibration dataset. It should be noted that the calibration dataset can be stored in various formats, and the storage format is not specifically limited here.

[0046] Specifically, in step S12, the calibration distance corresponding to the recognition distance is queried from the calibration dataset to obtain the calibration size corresponding to the target road sign. i It should be noted that if no calibration distance corresponding to the recognition distance is found in the calibration dataset, the method also needs to: calculate the distance difference between the recognition distance and all calibration distances in turn; and query the calibration distance corresponding to the smallest distance difference to obtain the calibration size corresponding to the target road sign. i .

[0047] S13: Compare the identified size with the calibrated size to obtain the comparison result.

[0048] Specifically, in step S13, the recognition size and calibration size corresponding to the target road sign are... i By comparing the identification size and the calibration size of the target road sign, the deviation value can be obtained.

[0049] S14: Verify the accuracy of the identification results based on the comparison results.

[0050] Specifically, in step S14, the accuracy of the target road sign recognition result is verified based on the comparison result. It should be noted that the smaller the deviation value, the higher the accuracy of the target road sign recognition result. The magnitude of the deviation value can be determined according to the actual required accuracy, as long as the accuracy requirement is met, and no specific limitation is made here.

[0051] This application provides a method for verifying road sign recognition results. First, an image containing the target road sign is acquired using an image acquisition device. Second, the target road sign in the image is identified and calculated to obtain a recognition result, which includes at least the recognition size of the target road sign and the recognition distance from the target road sign to the image acquisition device. Then, the calibration distance corresponding to the recognition distance is queried from a calibration dataset to obtain the calibration size corresponding to the target road sign. Next, the recognition size and the calibration size are compared to obtain a comparison result. Finally, the accuracy of the recognition result is verified based on the comparison result. This application uses deterministic results to verify uncertainties, enabling the verification of the accuracy of road sign recognition results and ensuring the objectivity of the verification results.

[0052] Corresponding to the aforementioned application function implementation method embodiments, this application also provides a road sign recognition result verification device, electronic device, and corresponding embodiments.

[0053] Figure 4 This is a schematic diagram of the structure of a road sign recognition result verification device shown in an embodiment of this application. See also... Figure 4 This application provides a verification device for road sign recognition results. The device specifically includes: an image acquisition module 40, a target road sign recognition module 41, a query module 42, a comparison module 43, and a verification module 44, wherein:

[0054] The image acquisition module 40 is used to acquire an image containing a target road sign through an image acquisition device; the target road sign recognition module 41 is used to recognize the target road sign in the image to be recognized and obtain a recognition result, the recognition result including at least the recognition size of the target road sign and the recognition distance from the target road sign to the image acquisition device; the query module 42 is used to query the calibration distance corresponding to the recognition distance from the calibration dataset and obtain the calibration size corresponding to the target road sign; the comparison module 43 is used to compare the recognition size and the calibration size and obtain a comparison result; the verification module 44 is used to verify the accuracy of the recognition result based on the comparison result.

[0055] Furthermore, in a specific embodiment, the target road sign recognition module 41 includes:

[0056] The acquisition unit is used to acquire the location information of the target road sign and the location information of the image acquisition device;

[0057] The calculation unit is used to perform distance calculation based on the location information of the target road sign and the location information of the image acquisition device to obtain the recognition distance from the target road sign to the image acquisition device;

[0058] The target road sign recognition unit is used to recognize the target road sign in the image to be recognized by using a road sign recognition algorithm, and to obtain the recognition size of the target road sign.

[0059] Furthermore, in a specific embodiment, the target road sign recognition unit is specifically used for:

[0060] The target road sign in the image to be identified is identified and calculated using the SLAM algorithm and deep learning to obtain the identification size of the target road sign.

[0061] This application provides a verification device for road sign recognition results. First, an image acquisition module acquires an image containing the target road sign through an image acquisition device. Second, a target road sign recognition module identifies and calculates the target road sign in the image to be recognized, obtaining a recognition result. This recognition result includes at least the recognition size of the target road sign and the recognition distance from the target road sign to the image acquisition device. Then, a query module queries the calibration distance corresponding to the recognition distance from a calibration dataset to obtain the calibration size corresponding to the target road sign. Next, a comparison module compares the recognition size and the calibration size to obtain a comparison result. Finally, a verification module verifies the accuracy of the recognition result based on the comparison result. This application uses deterministic results to verify uncertainties, enabling the verification of the accuracy of road sign recognition results and ensuring the objectivity of the verification results regarding the accuracy of road sign recognition.

[0062] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated further here.

[0063] Figure 5 This is a schematic diagram of the structure of an electronic device shown in an embodiment of this application.

[0064] See Figure 5 The electronic device 500 includes a memory 510 and a processor 520.

[0065] The processor 520 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0066] Memory 510 may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage devices. ROM may store static data or instructions required by the processor 520 or other modules of the computer. Permanent storage devices may be read-write storage devices. Permanent storage devices may be non-volatile storage devices that retain stored instructions and data even when the computer is powered off. In some embodiments, permanent storage devices use mass storage devices (e.g., magnetic or optical disks, flash memory) as permanent storage devices. In other embodiments, permanent storage devices may be removable storage devices (e.g., floppy disks, optical drives). System memory may be a read-write storage device or a volatile read-write storage device, such as dynamic random access memory. System memory may store some or all of the instructions and data required by the processor during operation. Furthermore, memory 510 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and disks and / or optical disks may also be used. In some embodiments, memory 510 may include a removable storage device that is readable and / or writable, such as a laser disc (CD), a read-only digital multifunction optical disc (e.g., DVD-ROM, dual-layer DVD-ROM), a read-only Blu-ray disc, an ultra-high-density optical disc, a flash memory card (e.g., SD card, mini SD card, Micro-SD card, etc.), a magnetic floppy disk, etc. Computer-readable storage media do not contain carrier waves or transient electronic signals transmitted wirelessly or via wired connections.

[0067] The memory 510 stores executable code, which, when processed by the processor 520, can cause the processor 520 to execute part or all of the methods described above.

[0068] The solution of this application has been described in detail above with reference to the accompanying drawings. In the above embodiments, the descriptions of each embodiment have different emphases; parts not described in detail in a certain embodiment can be referred to in the relevant descriptions of other embodiments. Those skilled in the art should also understand that the actions and modules involved in the specification are not necessarily essential to this application. Furthermore, it is understood that the steps in the method of this application embodiment can be adjusted, combined, and deleted according to actual needs, and the modules in the device of this application embodiment can be combined, divided, and deleted according to actual needs.

[0069] Furthermore, the method according to this application can also be implemented as a computer program or computer program product, which includes computer program code instructions for performing some or all of the steps in the method described above.

[0070] Alternatively, this application may be implemented as a non-transitory machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) storing executable code (or computer program, or computer instruction code) that, when executed by a processor of an electronic device (or electronic device, server, etc.), causes the processor to perform some or all of the steps of the methods described above according to this application.

[0071] Those skilled in the art will also understand that the various exemplary logic blocks, modules, circuits, and algorithm steps described in connection with the present application can be implemented as electronic hardware, computer software, or a combination of both.

[0072] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems and methods according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0073] The various embodiments of this application have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or improvement of the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for verifying road sign recognition results, characterized in that, include: The image to be identified is acquired using an image acquisition device; The target road sign in the image to be identified is identified and calculated to obtain the identification result, which includes at least the identification size of the target road sign and the identification distance from the target road sign to the image acquisition device; Query the calibration distance corresponding to the recognition distance from the calibration dataset to obtain the calibration size corresponding to the target road sign; The calibration process of the calibration dataset includes: receiving a calibration operation instruction; calibrating the target road sign in the image to be identified according to the calibration operation instruction to obtain calibration parameters, the calibration parameters including: the location information of the target road sign, the location information of the image acquisition device, and the calibration size of the target road sign; calculating the distance based on the location information of the target road sign and the location information of the image acquisition device to obtain the calibration distance from the target road sign to the image acquisition device; and storing the calibration parameters and the calibration distance as keywords to obtain the calibration dataset. The identification size and the calibration size are compared to obtain the comparison result; The accuracy of the identification result is verified based on the comparison results.

2. The method according to claim 1, characterized in that, The process of identifying and calculating the target road sign in the image to be identified, and obtaining the identification result, includes: Obtain the location information of the target road sign and the location information of the image acquisition device; The distance from the target road sign to the image acquisition device is calculated based on the location information of the target road sign and the location information of the image acquisition device. The target road sign in the image to be identified is identified using a road sign recognition algorithm, and the recognition size of the target road sign is obtained.

3. The method according to claim 2, characterized in that, The step of identifying the target road sign in the image to be identified using a road sign recognition algorithm to obtain the recognition size of the target road sign includes: The target road sign in the image to be identified is identified and calculated using the SLAM algorithm and deep learning to obtain the identification size of the target road sign.

4. The method according to claim 1, characterized in that, If no calibration distance corresponding to the recognition distance is found in the calibration dataset, the method further includes: Calculate the distance difference between the recognition distance and all calibration distances sequentially; The calibration size of the target road sign is obtained by querying the calibration distance corresponding to the smallest distance difference.

5. A device for verifying road sign recognition results, characterized in that, include: The image acquisition module is used to acquire images of the target road sign to be identified through an image acquisition device; The target road sign recognition module is used to recognize the target road sign in the image to be recognized and obtain the recognition result. The recognition result includes at least the recognition size of the target road sign and the recognition distance from the target road sign to the image acquisition device. The query module is used to query the calibration distance corresponding to the recognition distance from the calibration dataset to obtain the calibration size corresponding to the target road sign; The calibration process of the calibration dataset includes: receiving a calibration operation instruction; calibrating the target road sign in the image to be identified according to the calibration operation instruction to obtain calibration parameters, the calibration parameters including: the location information of the target road sign, the location information of the image acquisition device, and the calibration size of the target road sign; calculating the distance based on the location information of the target road sign and the location information of the image acquisition device to obtain the calibration distance from the target road sign to the image acquisition device; and storing the calibration parameters and the calibration distance as keywords to obtain the calibration dataset. The comparison module is used to compare the identified size and the calibrated size to obtain the comparison result; The verification module is used to verify the accuracy of the identification result based on the comparison result.

6. The apparatus according to claim 5, characterized in that, The target road sign recognition module includes: The acquisition unit is used to acquire the location information of the target road sign and the location information of the image acquisition device; The calculation unit is used to perform distance calculation based on the location information of the target road sign and the location information of the image acquisition device to obtain the recognition distance from the target road sign to the image acquisition device; The target road sign recognition unit is used to recognize the target road sign in the image to be recognized by using a road sign recognition algorithm, and to obtain the recognition size of the target road sign.

7. The apparatus according to claim 6, characterized in that, The target road sign recognition unit is specifically used for: The target road sign in the image to be identified is identified and calculated using the SLAM algorithm and deep learning to obtain the identification size of the target road sign.

8. An electronic device, characterized in that, include: processor; as well as A memory storing executable code, which, when executed by the processor, causes the processor to perform a method for verifying the road sign recognition results as described in any one of claims 1-4.

9. A non-transitory machine-readable storage medium, characterized in that, It stores executable code, which, when executed by the processor of the electronic device, causes the processor to perform the verification method for the road sign recognition result as described in any one of claims 1-4.

Images