CN114898063A - High-precision map abnormal data processing method, device, equipment and storage medium - Google Patents

Abstract

The application relates to a high-precision map abnormal data processing method, device, equipment and storage medium. The method comprises the following steps: acquiring a plurality of data extracted by an image about a certain road element, and importing the plurality of data into the same array; and when the array meets the preset screening condition, removing abnormal data in the array according to a preset filtering rule until the array does not meet the preset screening condition any more, and taking the current array as a target array, wherein the abnormal data is the data with the maximum deviation degree from the current array. By locking the data with the maximum deviation from the current array and removing the abnormal data from the current array, the data in the target array can keep the accuracy, so that the manufacturing accuracy of the high-precision map can be well kept when the high-precision map is built by using the data in the target array subsequently.

Description

High-precision map abnormal data processing method, device, equipment and storage medium

technical field

The present application relates to the technical field of high-precision maps, and in particular, to a method, device, device, and storage medium for processing abnormal data of high-precision maps.

Background technique

The high-precision map is a reconstruction of the road environment. The high-precision map contains a large number of road elements, such as lane lines, traffic lights, and traffic signs. High-precision map formation is an accurate three-dimensional representation of the road network, and technologies such as unmanned driving, vehicle positioning, path planning, and vehicle control all rely heavily on high-precision maps.

In the related art, in order to improve the production accuracy of the high-precision map as much as possible, N photos taken by the vehicle-mounted camera are identified and analyzed, and multiple data for constructing a certain road element are extracted from the N photos. However, due to reasons such as mismatching, recognition accuracy, and parsing algorithms, some of the extracted data may deviate greatly from the rest of the data. If such abnormal data is subsequently introduced into the construction of road elements, it will inevitably affect the production accuracy of high-precision maps.

SUMMARY OF THE INVENTION

In order to solve or partially solve the problems existing in the related art, the present application provides a method, device, equipment and storage medium for processing abnormal data of a high-precision map, which can improve the production accuracy of a high-precision map.

A first aspect of the present application provides a method for processing abnormal data in a high-precision map, including:

Acquiring a plurality of data extracted from an image about a certain road element, and importing a plurality of the data into the same array;

When the array satisfies the preset filtering conditions, remove abnormal data in the array according to the preset filtering rules, and use the current array as the target array until the array no longer meets the preset filtering conditions , wherein the abnormal data is the data with the largest deviation from the current array.

Preferably, before the said array satisfies the preset filtering conditions, it further includes:

Count the array length of the array, and calculate the array mean and array variance corresponding to the array;

The preset filter conditions include:

The array length corresponding to the array is greater than a preset length value; and

The array variance corresponding to the array is greater than a preset variance threshold.

Preferably, removing abnormal data in the array according to preset filtering rules includes:

Calculate the difference between each of the data in the array and the mean value of the array corresponding to the array to obtain a number of differences;

Sort the absolute values of several of the differences, and filter out abnormal data to be removed based on the sorting results.

Preferably, sorting the absolute values of several of the differences, and filtering out abnormal data that needs to be removed based on the sorting results, including:

Sort the absolute values of a number of the difference values in ascending order, lock the data corresponding to the absolute value of the largest difference value as abnormal data, and remove the abnormal data from the array.

Preferably, a plurality of data extracted from the acquired image about a certain road element include:

Obtain the image with respect to the extracted multiple data of the traffic sign.

A second aspect of the present application provides a high-precision map abnormal data processing device, including:

an acquisition module, used for acquiring multiple data extracted from the image about a certain road element, and importing the multiple data into the same array;

The filtering module is used to remove abnormal data in the array according to the preset filtering rules when the array satisfies the preset filtering conditions, until the array no longer meets the preset filtering conditions, the current all The array is used as the target array, wherein the abnormal data is the data with the largest deviation from the current array.

Preferably, the filtering module is further configured to count the array length of the array, and calculate the array mean and array variance corresponding to the array;

The preset filter conditions include:

The array length corresponding to the array is greater than a preset length value; and

The array variance corresponding to the array is greater than a preset variance threshold.

Preferably, the filtering module removes abnormal data in the array according to preset filtering rules, including:

Calculate the difference between each of the data in the array and the mean value of the array corresponding to the array to obtain a number of differences;

Sort the absolute values of several of the differences, and filter out abnormal data to be removed based on the sorting results.

A third aspect of the present application provides an electronic device, comprising:

processor; and

The memory has executable codes stored thereon, and when the executable codes are executed by the processor, causes the processor to execute the above-mentioned method for processing abnormal data of a high-precision map.

A fourth aspect of the present application provides a computer-readable storage medium on which executable codes are stored, and when the executable codes are executed by a processor of an electronic device, the processor is caused to execute the above-mentioned high-level functions. The method of processing abnormal data of precise map.

The technical solution provided by this application can include the following beneficial effects:

The technical solution of the present application is to obtain multiple data extracted from an image about a certain road element, and import the multiple data into the same array; when the array satisfies the preset filtering conditions, the anomalies in the array are removed according to the preset filtering rules Data until the array no longer meets the preset filter conditions, the current array is used as the target array, and the abnormal data is the data with the largest deviation from the current array. By locking the data with the largest deviation from the current array, and removing abnormal data from the current array, the data in the target array can be kept accurate, so that when the data in the target array is used to build a high-precision map later, It can also well maintain the production accuracy of high-precision maps.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not limiting of the present application.

Description of drawings

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

1 shows a schematic flowchart of a method for processing abnormal data of a high-precision map in an embodiment of the present application;

FIG. 2 shows a schematic flowchart of a method for processing abnormal data of a high-precision map in another embodiment of the present application;

3 shows a flowchart of a method for processing abnormal data of a high-precision map in an embodiment of the present application;

FIG. 4 shows a schematic structural diagram of an apparatus for processing abnormal data of a high-precision map in an embodiment of the present application;

FIG. 5 shows a schematic structural diagram of an apparatus for processing abnormal data of a high-precision map in another embodiment of the present application;

FIG. 6 is a schematic structural diagram of an electronic device shown in an embodiment of the present application.

Detailed ways

Embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although 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 by the embodiments set forth herein. Rather, these embodiments are provided so that this application will be thorough and complete, and will fully convey the scope of this application to those skilled in the art.

The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to limit the application. As used in this application and the appended claims, the singular forms "a," "the," and "the" are intended to include the plural forms as well, unless the context clearly dictates otherwise. It will also be understood that the term "and/or" as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

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

At present, in related technologies, due to reasons such as mismatching, recognition accuracy, parsing algorithm, etc., some data extracted from images may deviate greatly from the rest of the data. If such abnormal data is subsequently introduced into the construction of road elements, it will inevitably affect high-precision The precision of the map.

Therefore, in order to solve the above technical problems, the present application provides a method, device, device and storage medium for processing abnormal data of a high-precision map, which can improve the production accuracy of a high-precision map.

The technical principles of the present application will be described in detail below with reference to the accompanying drawings.

FIG. 1 shows a schematic flowchart of a method for processing abnormal data of a high-precision map in an embodiment of the present application.

Please refer to Figure 1, a method for processing abnormal data of high-precision map, including the following steps:

Step S111: Acquire multiple pieces of data extracted from the image about road elements, and import the multiple pieces of data into the same array.

The image is a photo taken by a vehicle-mounted camera, and the image contains a large number of road elements, such as traffic signs (street signs), lane lines, and stop lines. Import multiple data of the same dimension of a certain road element from the acquired image into the same array, and the array is a collection of multiple data in a certain road element. For an array, the array has the characteristic of length, and the length of the array is the number of data contained in the current array.

Step S112, when the array satisfies the preset filtering conditions, remove the abnormal data in the array according to the preset filtering rules, until the array no longer meets the preset filtering conditions, take the current array as the target array, wherein the abnormal data is the same as the current array. The data with the largest deviation in the array.

Due to mismatches, recognition accuracy, parsing algorithms, etc., each data in the array may not reflect road elements very accurately. The specific performance is that each data contained in the array has its own corresponding value, and each data has a certain degree of deviation from the array. In order to ensure the accuracy of building road elements using the data in the array subsequently. The abnormal data in the array is removed from the array that meets the preset filter conditions according to the preset filter rules. That is, for data with a large deviation from the array (such data is called abnormal data), such abnormal data is filtered out in the array, so that there is no obvious deviation between the filtered array data and the data.

The technical solution of this embodiment can maintain the accuracy of the data in the target array by locking the data with the largest deviation from the current array and removing the abnormal data from the current array, so that the data in the target array can be used to construct the When using high-precision maps, the production accuracy of high-precision maps can also be well maintained.

FIG. 2 shows a schematic flowchart of a method for processing abnormal data of a high-precision map in another embodiment of the present application. Compared with FIG. 1 , FIG. 2 illustrates the preset filtering conditions and the preset filtering rules in detail.

Please refer to Figure 2, a method for processing abnormal data of high-precision map, including the following steps:

Step S211: Acquire multiple pieces of data extracted from the image about a certain road element, and import the multiple pieces of data into the same array.

The image is a photo taken by a vehicle-mounted camera, and the image contains a large number of road elements, such as traffic signs (street signs), lane lines, and stop lines. Import multiple data of a certain road element from the acquired image into the same array, and the array is a collection of multiple data in a certain road element. For an array, the array has the characteristic of length, and the length of the array is the number of data contained in the current array.

Step S212: Count the array lengths of the arrays, and calculate the array mean value and the array variance corresponding to the arrays. When it is satisfied that the array length corresponding to the array is greater than the preset length value and the array variance corresponding to the array is greater than the preset variance threshold, filter according to the preset The rule removes abnormal data in the array until the array no longer satisfies that the array length corresponding to the array is greater than the preset length value or the array variance corresponding to the array is less than the preset variance threshold, the current array is used as the target array, where the abnormal data is the same as the target array. The data with the largest deviation in the current array.

It should be noted that the array length of the array is the number of data contained in the data, and because the data contained in the array has its own value, the array mean and array variance corresponding to the array can be calculated.

The formula for calculating the mean of an array is as follows:

Among them, mean represents the mean of the array, X _i represents the ith data in the array, and N is the length of the array.

The formula for calculating the variance of an array is as follows:

Among them, std represents the variance of the array, X _i represents the ith data in the array, mean represents the mean of the array, and N is the length of the array.

Through formula (1) and formula (2), the numerical mean and array variance corresponding to the array can be calculated.

Determine whether the array satisfies the preset filter conditions. When the array length N corresponding to the satisfied array is greater than the preset length value len and the array variance std corresponding to the array is greater than the preset variance threshold STD, it is determined that the array meets the preset filter conditions. data is filtered.

Remove abnormal data in the array according to preset filtering rules, wherein the preset filtering rules include: calculating the difference between each data in the array and the mean value of the array corresponding to the array to obtain several differences; sorting the absolute values of several differences , based on the sorting results to filter out the abnormal data that needs to be removed. For example, the absolute values of several differences can be sorted in ascending order, the data corresponding to the absolute value of the largest difference can be locked as abnormal data, and the abnormal data can be removed from the array.

Through the above process, the abnormal data in the array can be quickly locked, the abnormal data can be filtered (that is, the locked abnormal data can be removed from the array), and the array can be updated. And based on the updated array, the array length, array mean, and array variance of the array will be counted and calculated again. Until the array no longer satisfies that the array length corresponding to the array is greater than the preset length value or the array variance corresponding to the array is less than the preset variance threshold, the current array is used as the target array. The target array obtained at this time is the array with the exception data removed.

The technical solution of this embodiment can maintain the accuracy of the data in the target array by locking the data with the largest deviation from the current array and removing the abnormal data from the current array, so that the data in the target array can be used to construct the When using high-precision maps, the production accuracy of high-precision maps can also be well maintained.

FIG. 3 shows a flowchart of a method for processing abnormal data of a high-precision map in an embodiment of the present application. Figure 3 expands on the application scenario of processing road elements—traffic signs.

Please refer to Figure 3, a high-precision map exception handling method, including the following steps:

Step S311, import multiple data X _i about the traffic sign into the array data, and go to step S312.

In step S312, the array length N corresponding to the array data is counted, and the array mean mean and the array variance std corresponding to the array data are calculated, and the process proceeds to step S313.

Step S313: Determine whether the array length N is greater than the preset length value len and whether the array variance std is greater than the preset variance threshold SRTD, if yes, go to step S314; if not, go to step S317.

Step S314: Calculate the difference between each data in the array data and the mean value of the array to obtain several difference values D _i , and then go to step S315.

Step S315, sort the absolute values of several differences Di in ascending order, lock the data X _i corresponding to the absolute value of the largest difference as the abnormal data X _error , and move the abnormal data X _error from the array data. remove, and proceed to step S316.

Step S316, update the array data, and return to step S313.

Step S317, taking the current array data as the target array data.

Through the above steps, the data with the largest deviation from the current array is quickly locked based on the variance of the array, and the abnormal data is removed from the current array, so that the data in the target array can maintain the accuracy, so that the data in the target array can be used subsequently. When building a high-precision map, the production accuracy of the high-precision map can also be well maintained.

Corresponding to the foregoing functional method embodiments, the present application further provides a high-precision map abnormal data processing apparatus and corresponding embodiments.

FIG. 4 shows a schematic structural diagram of an apparatus for processing abnormal data of a high-precision map in an embodiment of the present application.

Referring to FIG. 4 , a high-precision map abnormal data processing apparatus 40 includes an acquisition module 410 and a filtering module 420 .

The acquiring module 410 is used for acquiring multiple data extracted from the image about a certain road element, and importing the multiple data into the same array.

The image is a photo taken by a vehicle-mounted camera, and the image contains a large number of road elements, such as traffic signs (street signs), lane lines, and stop lines. Import multiple data of the same dimension of a certain road element from the acquired image into the same array, and the array is a collection of multiple data in a certain road element. For an array, the array has the characteristic of length, and the length of the array is the number of data contained in the current array.

The filtering module 420 is used to remove the abnormal data in the array according to the preset filtering rules when the array satisfies the preset filtering conditions, until the array no longer meets the preset filtering conditions, and the current array is used as the target array, wherein the abnormal data is the same as the target array. The data with the largest deviation in the current array.

Due to mismatches, recognition accuracy, parsing algorithms, etc., each data in the array may not reflect road elements very accurately. The specific performance is that each data contained in the array has its own corresponding value, and each data has a certain degree of deviation from the array. In order to ensure the accuracy of building road elements using the data in the array subsequently. The abnormal data in the array is removed from the array that meets the preset filter conditions according to the preset filter rules. That is, for data with a large deviation from the array (such data is called abnormal data), such abnormal data is filtered out in the array, so that there is no obvious deviation between the filtered array data and the data.

In the device of this embodiment, the acquiring module 410 acquires multiple data extracted from the image about a certain road element, and imports the multiple data into the same array; the filtering module 420, when the array satisfies the preset filtering conditions, follows the preset filtering rules Remove the abnormal data in the array until the array no longer meets the preset filter conditions, and use the current array as the target array, where the abnormal data is the data with the largest deviation from the current array. By locking the data with the largest deviation from the current array, and removing abnormal data from the current array, the data in the target array can be kept accurate, so that when the data in the target array is used to build a high-precision map later, It can also well maintain the production accuracy of high-precision maps.

FIG. 5 shows a schematic structural diagram of an apparatus for processing abnormal data of a high-precision map in another embodiment of the present application.

Referring to FIG. 5 , a high-precision map abnormal data processing apparatus 50 includes an acquisition module 510 and a filtering module 520 .

For details of the functions of the acquiring module 510 and the filtering module 520, please refer to the relevant description in FIG. 4, and details are not repeated here.

The filtering module 520 is also used to count the array length of the array, and calculate the array mean and the array variance corresponding to the array.

Correspondingly, the preset screening conditions include: the array length corresponding to the array is greater than the preset length value; and the array variance corresponding to the array is greater than the preset variance threshold.

Correspondingly, the filtering module 520 removes abnormal data in the array according to the preset filtering rules, including: calculating the difference between each data in the array and the mean value of the array corresponding to the array to obtain several differences; Sort, filter out the abnormal data that needs to be removed based on the sorting results.

Regarding the apparatus in the above-mentioned embodiment, the specific manner in which each module and unit performs operations has been described in detail in the method embodiment corresponding to the apparatus, and will not be described in detail here.

Referring to FIG. 6 , the electronic device 600 includes a processor 610 and a memory 620 .

The processor 610 may be a central processing unit (Central Processing Unit, CPU), other general-purpose processors, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field-available processor Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

Memory 620 may include various types of storage units, such as system memory, read only memory (ROM), and persistent storage. The ROM may store static data or instructions required by the processor 610 or other modules of the computer. Persistent storage devices may be readable and writable storage devices. Permanent storage may be a non-volatile storage device that does not lose stored instructions and data even if the computer is powered off. In some embodiments, persistent storage devices employ mass storage devices (eg, magnetic or optical disks, flash memory) as persistent storage devices. In other embodiments, persistent storage may be a removable storage device (eg, a floppy disk, an optical drive). System memory can be a readable and writable storage device or a volatile readable and writable storage device, such as dynamic random access memory. System memory can store some or all of the instructions and data that the processor needs at runtime. Additionally, memory 620 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (eg, DRAM, SRAM, SDRAM, flash memory, programmable read only memory), and magnetic and/or optical disks may also be employed. Executable codes are stored on the memory 620, and when the executable codes are processed by the processor 610, the processor 610 can be caused to execute some or all of the above-mentioned methods.

Furthermore, the method according to the present application can also be implemented as a computer program or computer program product comprising computer program code instructions for performing some or all of the steps in the above method of the present application.

Alternatively, the present application can also be implemented as a computer-readable storage medium (or a non-transitory machine-readable storage medium or a machine-readable storage medium) on which executable codes (or computer programs or computer instruction codes) are stored, When the executable code (or computer program or computer instruction code) is executed by the processor of the electronic device (or server, etc.), the processor is caused to perform some or all of the steps of the above method according to the present application.

Various embodiments of the present application have been described above, and the foregoing descriptions are exemplary, not exhaustive, and not limiting of the disclosed embodiments. Numerous modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein was chosen to best explain the principles of the embodiments, the practical application or improvement over the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

Claims (10)

1. a high-precision map abnormal data processing method, is characterized in that, comprises: Acquiring a plurality of data extracted from an image about a certain road element, and importing a plurality of the data into the same array; When the array satisfies the preset filtering conditions, remove abnormal data in the array according to the preset filtering rules, and use the current array as the target array until the array no longer meets the preset filtering conditions , wherein the abnormal data is the data with the largest deviation from the current array. 2. The abnormal data processing method for high-precision maps according to claim 1, wherein, before the array satisfies a preset screening condition, the method further comprises: Count the array length of the array, and calculate the array mean and array variance corresponding to the array; The preset filter conditions include: The array length corresponding to the array is greater than a preset length value; and The array variance corresponding to the array is greater than a preset variance threshold. 3. The method for processing abnormal data in high-precision maps according to claim 2, wherein the abnormal data in the array is removed according to a preset filtering rule, comprising: Calculate the difference between each of the data in the array and the mean value of the array corresponding to the array to obtain a number of differences; Sort the absolute values of several of the differences, and filter out abnormal data to be removed based on the sorting results. 4. The method for processing abnormal data in a high-precision map according to claim 3, wherein the absolute values of some of the differences are sorted, and the abnormal data that needs to be removed is filtered out based on the sorting result, comprising: Sorting the absolute values of a plurality of the difference values in ascending order, locking the data corresponding to the absolute value of the largest difference value as abnormal data, and removing the abnormal data from the array. 5. The method for processing abnormal data in a high-precision map according to any one of claims 1 to 4, wherein the acquired image is about a plurality of data extracted from a certain road element, comprising: Obtain the image with respect to the extracted multiple data of the traffic sign. 6. A high-precision map abnormal data processing device, characterized in that, comprising: an acquisition module, used for acquiring multiple data extracted from the image about a certain road element, and importing the multiple data into the same array; The filtering module is used to remove abnormal data in the array according to the preset filtering rules when the array satisfies the preset filtering conditions, until the array no longer meets the preset filtering conditions, the current all The array is used as the target array, wherein the abnormal data is the data with the largest deviation from the current array. 7. The high-precision map abnormal data processing device according to claim 6, wherein the filtering module is also used to count the array length of the array, and calculate the array mean and the array variance corresponding to the array; The preset filter conditions include: The array length corresponding to the array is greater than a preset length value; and The array variance corresponding to the array is greater than a preset variance threshold. 8. The high-precision map abnormal data processing device according to claim 7, wherein the filtering module removes abnormal data in the array according to preset filtering rules, comprising: Calculate the difference between each of the data in the array and the mean value of the array corresponding to the array to obtain a number of differences; Sort the absolute values of several of the differences, and filter out abnormal data to be removed based on the sorting results. 9. An electronic device, characterized in that, comprising: processor; and A memory having executable codes stored thereon, and when the executable codes are executed by the processor, the processor is caused to execute the abnormal data processing method for a high-precision map according to any one of claims 1 to 5 . 10. A computer-readable storage medium on which executable codes are stored, and when the executable codes are executed by a processor of an electronic device, the processor is caused to execute as claimed in any one of claims 1 to 5. The abnormal data processing method of the high-precision map described above.

Images