CN116563837A - High-precision map guideboard graphic data resolving method, device, equipment and storage medium - Google Patents
High-precision map guideboard graphic data resolving method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN116563837A CN116563837A CN202310430143.5A CN202310430143A CN116563837A CN 116563837 A CN116563837 A CN 116563837A CN 202310430143 A CN202310430143 A CN 202310430143A CN 116563837 A CN116563837 A CN 116563837A
- Authority
- CN
- China
- Prior art keywords
- image
- guideboard
- images
- resolved
- target image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000003860 storage Methods 0.000 title claims description 23
- 238000012216 screening Methods 0.000 claims abstract description 113
- 238000004422 calculation algorithm Methods 0.000 claims description 22
- 238000001914 filtration Methods 0.000 claims description 21
- 238000001514 detection method Methods 0.000 claims description 17
- 238000003708 edge detection Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 description 12
- 230000006870 function Effects 0.000 description 11
- 238000012545 processing Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 230000002085 persistent effect Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 230000006872 improvement Effects 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 230000002829 reductive effect Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000000670 limiting effect Effects 0.000 description 2
- 238000010845 search algorithm Methods 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 125000003275 alpha amino acid group Chemical group 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 239000002355 dual-layer Substances 0.000 description 1
- 238000013209 evaluation strategy Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/63—Scene text, e.g. street names
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/587—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Library & Information Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Image Processing (AREA)
Abstract
The method comprises the steps of firstly receiving a plurality of guideboard images to be resolved, screening the guideboard images to be resolved based on screening rules to obtain an image set comprising a first target image, taking one image with the largest pixel area of the first target image in the image set as an initial image, selecting a second target image from the image set based on the initial image, resolving the pose of the guideboard based on the second target image, screening unqualified images due to the fact that the image set of the first target image is obtained through the screening rules, then selecting the second target image according to preset acquisition intervals, resolving the second target image as a guideboard standard image, not directly resolving all images, solving the problems of distortion, inaccurate size of a recognition frame and the like in the images, and further improving resolving precision.
Description
Technical Field
The present disclosure relates to the field of graphics data reading and processing technologies, and in particular, to a method, an apparatus, a device, and a storage medium for resolving graphics data of a high-precision map guideboard.
Background
The high-precision map is also called as a high-precision map, and is used as a key technology in automatic driving, and very high requirements are put forward on the precision of the high-precision map, so that the resolution of the guideboard is an important link for manufacturing the high-precision map in the process of drawing. Therefore, the resolution of graphic data such as a guideboard is also an important premise for improving the drawing accuracy.
In the related art, although the improvement of the resolution accuracy can be achieved by improving the resolution algorithm when processing the graphic data, because the improvement is that the resolution algorithm is itself, when the resolution object is a complex guideboard image, there is still a situation that the feature point matching is inaccurate, so that the guideboard image is misidentified, and the resolution accuracy of the guideboard is not high enough.
Disclosure of Invention
In order to overcome the problems in the related art, the application provides a high-precision map guideboard graphic data resolving method, which is used for optimizing and screening guideboard images according to a preset acquisition distance and a preset acquisition quantity on the basis of screening the guideboard images under the condition that a resolving algorithm is not changed, so that unnecessary interference is removed, the accuracy of identification is improved, the calculated amount of the algorithm is reduced, and the efficiency of guideboard identification is improved.
The first aspect of the application provides a high-precision map guideboard graphic data resolving method, which comprises the following steps:
receiving a plurality of guideboard images to be resolved;
screening from the plurality of guideboard images to be resolved based on a screening rule to obtain an image set comprising a first target image; the first number of first target images in the image set is at least greater than a preset identification number; the preset identification quantity is used for representing the minimum quantity capable of calculating the pose of the guideboard; the screening rule is used for reserving images meeting the identification conditions;
taking one image with the largest pixel area of a first target image in the image set as an initial image, and selecting a second target image from the image set based on the initial image, wherein the acquisition interval between the first target image and the second target image is a preset distance, and the acquisition interval between two adjacent second target images is the preset distance;
and resolving the pose of the guideboard based on the second target image.
Optionally, the filtering based on the filtering rule performs filtering from the plurality of guideboard images to be resolved, including:
identifying the plurality of guideboard images to be resolved to obtain an identification result;
Determining a corresponding screening rule according to the identification result;
and determining an image set of the first target image from the plurality of guideboard images to be resolved based on the corresponding screening rules.
Optionally, the screening rule includes:
confidence screening rules, recognition shape screening rules, recognition area screening rules, and/or recognition frame ratio screening rules.
Optionally, the filtering rule includes a confidence filtering rule, and determining the first target image from the plurality of guideboard images to be resolved includes:
receiving a guideboard image to be resolved;
extracting characteristic information of the guideboard image to be resolved;
calculating the confidence coefficient of the characteristic information to obtain current confidence coefficient data;
comparing the current confidence coefficient data with preset confidence coefficient data, and determining that the guideboard image to be resolved, of which the current confidence coefficient data is larger than the preset confidence coefficient data, is the first target image;
and/or, the filtering rule comprises a shape identifying filtering rule, and determining a first target image in the plurality of guideboard images to be resolved comprises:
receiving a guideboard image to be resolved;
detecting the guideboard image to be resolved based on an edge detection algorithm to obtain a detection result;
Determining a guideboard image to be resolved, which is rectangular in shape, in the detection result as a first target image;
and/or, the screening rule includes an area identifying screening rule, and determining a first target image from the plurality of guideboard images to be resolved includes:
receiving a guideboard image to be resolved;
calculating the pixel area of the guideboard in the guideboard image to be calculated to obtain the current guideboard area;
comparing the current guideboard area with a preset area to obtain a comparison result;
determining a guideboard image to be solved, of which the current guideboard area is larger than the preset area, in the comparison result as a first target image;
and/or, the screening rule includes an identification frame screening rule, and determining a first target image in the plurality of guideboard images to be resolved includes:
receiving a guideboard image to be resolved;
identifying the outline of the guideboard in the guideboard image to be solved based on an outline detection algorithm, and calculating to obtain the outline pixel area of the guideboard;
calculating the ratio of the area of the outline pixel to the circumscribed rectangle of the guideboard image to be calculated to obtain a ratio result;
and determining the guideboard image to be solved, which is larger than the preset ratio, in the ratio result as a first target image.
Optionally, the method further comprises:
receiving a guideboard image to be resolved;
reading distortion parameters in the guideboard image to be resolved;
and de-distorting the guideboard image to be resolved based on an iterative de-distorting algorithm to obtain an undistorted guideboard image.
Optionally, the selecting a second target image from the image set based on the initial image includes:
acquiring the initial image;
determining a first target image with the initial image as a collection interval as a second target image based on the initial image;
setting the second target image as an initial image, returning to determining the first target image which is the acquisition interval with the initial image as the second target image based on the initial image, and terminating the selection until a termination condition is met;
wherein the termination condition includes reaching a preset target number of pickups.
Optionally, the process of determining the acquisition interval includes:
receiving the first target image;
inquiring the information of the track points of the acquired vehicle of the first target image to obtain the acquisition time point of the first target image;
determining the longitude and latitude of a target corresponding to the acquisition time point;
and calculating the acquisition interval of the two first target images according to the target longitude and latitude.
A second aspect of the present application provides a high-precision map guideboard graphic data solver, comprising:
the receiving module is used for receiving a plurality of guideboard images to be resolved;
the screening module is used for screening from the plurality of guideboard images to be resolved based on screening rules to obtain an image set comprising a first target image; the first number of first target images in the image set is at least greater than a preset identification number; the preset identification quantity is used for representing the minimum quantity capable of calculating the pose of the guideboard; the screening rule is used for reserving images meeting the identification conditions;
the acquisition module takes one image with the largest pixel area of a first target image in the image set as an initial image, and selects a second target image from the image set based on the initial image, wherein the acquisition interval between the first target image and the second target image is a preset distance, and the acquisition interval between two adjacent second target images is the preset distance;
and the resolving module is used for resolving the pose of the guideboard based on the second target image.
A third aspect of the present application provides an electronic device, comprising:
a processor; and
a memory having executable code stored thereon which, when executed by the processor, causes the processor to perform the method as described above.
A fourth aspect of the present application provides a non-transitory machine-readable storage medium having stored thereon executable code, which when executed by a processor of an electronic device, causes the processor to perform the method as described above.
Therefore, the method, the device, the equipment and the storage medium for calculating the high-precision map guideboard graphic data are characterized in that a plurality of guideboard images to be calculated are received, screening is conducted from the plurality of guideboard images to be calculated based on screening rules, an image set comprising a first target image is obtained, the first number of the first target images in the image set is at least larger than the preset identification number, the preset identification number is used for representing the minimum number capable of calculating the guideboard pose, the screening rules are used for reserving images meeting identification conditions, one image with the largest pixel area of the first target image in the image set is used as an initial image, a second target image is selected from the image set based on the initial image, the acquisition distance between the first target image and the second target image is the preset distance, and the acquisition distance between two adjacent second target images is the preset distance, and based on the pose of the second target image, the first target image is obtained through the screening rules, unqualified images are selected, the second target image is taken as the initial image, the second target image is taken as the image to be directly used for calculating the guideboard, and the distortion is not solved, and the problems such as the accurate resolving of the image are solved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The foregoing and other objects, features and advantages of the application will be apparent from the following more particular descriptions of exemplary embodiments of the application as illustrated in the accompanying drawings wherein like reference numbers generally represent like parts throughout the exemplary embodiments of the application.
Fig. 1 is a flow chart of a high-precision map guideboard graphic data resolving method according to an embodiment of the present application.
Fig. 2 is a schematic structural view of a rectangular traffic sign guideboard shown in an embodiment of the present application.
Fig. 3 is a schematic structural view of a high-precision map guideboard graphic data solver according to an embodiment of the present application.
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
Preferred embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While the preferred embodiments of the present application are shown in the drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or 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 herein to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first message may also be referred to as a second message, and similarly, a second message may also be referred to as a first message, without departing from the scope of the present application. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
The embodiment of the application is mainly applied to scenes of high-precision maps, and particularly relates to a method, a device, equipment and a storage medium for resolving high-precision map guideboard graphic data. The high-precision map contains rich road information, including guideboards, lane lines, traffic signs and the like, wherein the guideboard information is particularly important for an automatic driving system, because the guideboard information can provide important navigation, traffic rules, road speed limit and the like. Therefore, the accuracy of the guideboard resolution accuracy in the high-accuracy map is very critical. In the related art, the improvement of the resolution accuracy of the guideboard is realized by improving the resolution algorithm, but as all acquired guideboard images are taken as guideboard images to be resolved, the problems of influence accuracy and false recognition caused by distortion and the like still exist in the images, and the resolution accuracy of the guideboard is not high enough.
Based on this, in the embodiment of the application, the guideboard image to be resolved is firstly screened through the screening rule, the obtained first target image is selected according to the preset distance, and the obtained second target image is used as the guideboard standard image to resolve, so that the accuracy of guideboard resolving is improved.
Referring to fig. 1, fig. 1 is a flow chart illustrating a high-precision map guideboard graphic data resolving method according to an embodiment of the present application. The application discloses a high-precision map guideboard graphic data resolving method, which comprises the following steps:
s10, receiving a plurality of guideboard images to be resolved.
In the embodiment of the application, the guideboard image can be understood as an image acquired by the acquisition vehicle in the process of making the high-precision map, wherein the image comprises at least one guideboard image and an environment image of a non-guideboard.
In this embodiment of the present application, the collected images are grouped according to the guideboard at each actual coordinate position, and the images in the same group all include the images of the guideboard, where the images including the same guideboard collected under the conditions of different distances, different angles or different light rays may be.
It can be understood that the received plurality of guideboard images to be resolved belong to the same group for pose resolving of the subsequent guideboard.
S20, screening from the plurality of guideboard images to be resolved based on screening rules to obtain an image set comprising a first target image; the first number of first target images in the image set is at least greater than a preset identification number; the preset identification quantity is used for representing the minimum quantity capable of calculating the pose of the guideboard; the screening rule is used for reserving images meeting the identification conditions.
In the embodiment of the application, the screening rule can perform preliminary screening on a plurality of guideboard images to be resolved, and the images meeting the standard in the guideboard images to be resolved are reserved as the first target images according to the preset standard. The first target image obtained after screening is more beneficial to subsequent processing and analysis, so that the accuracy and reliability of pose calculation of the guideboard are improved.
In actual use, a plurality of guideboard image categories to be resolved in the group are identified, the identification result is screened according to the screening rule, the guideboard image to be resolved which accords with the screening rule is taken as a first target image, and a new image set is constructed. For example, when recognizing the images in the speed-limiting guideboard group, the numbers in the guideboards are first character-recognized, and the numbers may be automatically recognized by OCR, or manually recognized. And counting the recognized numbers, calculating the occurrence frequency of each number, screening, and if the number 30 is the largest, selecting the number on the speed-limiting guideboard to be 30.
It is understood that the preset recognition number refers to the minimum number of images capable of calculating the pose of the guideboard, and the first number of the screened image sets needs to be at least greater than the preset recognition number so as to meet the requirement of the number of images in the subsequent step.
S30, taking one image with the largest pixel area of a first target image in the image set as an initial image, and selecting a second target image from the image set based on the initial image, wherein the acquisition interval between the first target image and the second target image is a preset distance, and the acquisition interval between two adjacent second target images is the preset distance.
In this embodiment of the present application, the pixel area refers to the pixel area of a guideboard recognition frame in the first target image, where the guideboard recognition frame may locate a portion of the guideboard image in the image, and use the guideboard recognition frame to frame the guideboard, where the guideboard recognition frame may be a rectangular recognition frame, and the area of the rectangular recognition frame may be a minimum area including all the guideboards.
In the embodiment of the application, the pixel area of the first target image in the image set is calculated, and the pixel area can be obtained by calculating the width and the height of the rectangular frame.
Comparing pixel areas of all first target images in the image set, wherein one image with the largest pixel area is taken as an initial image, and a pixel area calculation formula is defined as follows:
（1）
in the formula (1), the components are as follows,representing the number of gray levels or color levels contained in a pixel of a guideboard image, which may also be referred to as the bit depth or color depth of the image,/for example >Representing the resolution of the image in the horizontal direction, i.e. the number of pixels in the horizontal direction, +.>The resolution in the vertical direction of the image, i.e., the number of pixels in the vertical direction, is represented. Wherein (1)>Representing the actual area of each pixel.
In the embodiment of the application, the collection distance is the actual coordinate distance between two guideboard images when the actual collection vehicle collects the guideboard images. And determining the GPS longitude and latitude of the two points before and after the time stamp of each guideboard image collected in the group. Searching and collecting GPS longitude and latitude of front and rear points of a guideboard image time stamp based on a dichotomy, and converting longitude and latitude coordinates corresponding to the guideboard image time stamp according to the GPS longitude and latitude time deviation proportion of the guideboard image time stamp at the front and rear points and the GPS longitude and latitude of the front and rear points.
On the basis of the embodiment, metric distances of the two guideboard images can be calculated according to longitude and latitude coordinates of at least two guideboard images.
And S40, resolving the pose of the guideboard based on the second target image.
In the embodiment of the application, the first target image is obtained through the screening rule, the unqualified image is screened, the second target image is selected through the preset acquisition interval, the second target image is used as the standard image of the guideboard to be resolved, all the images are not directly resolved, the problems of distortion, inaccurate size of the identification frame and the like in the images are solved, and further the resolving precision is improved.
In the above embodiments, the process of selecting and selecting the guideboard image in the high-precision map making process is described, and the embodiment of the present application will describe the selecting process in detail.
In this embodiment of the present application, screening from the plurality of guideboard images to be resolved based on a screening rule includes:
s201, identifying the plurality of guideboard images to be resolved to obtain an identification result;
in the embodiment of the application, the guideboard image to be resolved is input into the guideboard recognition model, the target guideboard image in the guideboard image to be resolved can be recognized, the guideboard is marked by using the guideboard recognition frame, and the guideboard image in the guideboard image to be resolved can be marked accurately and efficiently.
The guideboard recognition model can be established by adopting a convolutional neural network, machine learning and other methods.
S202, determining a corresponding screening rule according to the identification result;
in the embodiment of the application, the recognition result can determine the category of the guideboard through the guideboard identification content, for example, the traffic forbidden guideboard, the traffic speed limiting guideboard and the like, and can also determine the category of the guideboard through the shape of the guideboard, for example, the guideboard is rectangular, the guideboard is circular and the like.
And selecting a corresponding screening rule based on the category of the guideboard to screen, for example, in the screening process, the identification result is rectangular, the identification content of the guideboard is a road indication mark, and the guideboard type can be determined to be the rectangular traffic road indication mark guideboard, so that the screening rule corresponding to the rectangular traffic road indication mark guideboard is called to screen.
S203, determining an image set of the first target image from the plurality of guideboard images to be resolved based on the corresponding screening rules.
In the embodiment of the application, the type of the guideboard image to be resolved is confirmed according to the identification result, the corresponding screening rule is selected for screening, and the image set of the first target image is obtained to remove the guideboard image which is mistakenly identified in the guideboard image to be resolved, so that the influence on the resolution precision of the guideboard caused by resolving the mistakenly identified guideboard image in the subsequent resolving process is avoided.
In order to further improve accuracy of selecting the corresponding screening rule, in the embodiment of the present application, the screening rule in the foregoing embodiment is further defined.
The screening rules include:
confidence screening rules, recognition shape screening rules, recognition area screening rules, and/or recognition frame ratio screening rules.
In the above embodiment, four screening rules are described, and a screening method of the four screening rules is described in detail below.
In this embodiment of the present application, when determining that the filtering rule is a confidence filtering rule, determining a first target image in the plurality of guideboard images to be resolved includes:
and receiving the guideboard image to be resolved.
And extracting the characteristic information of the guideboard image to be resolved.
And calculating the confidence coefficient of the characteristic information to obtain current confidence coefficient data.
Comparing the current confidence coefficient data with preset confidence coefficient data, and determining that the guideboard image to be resolved, of which the current confidence coefficient data is larger than the preset confidence coefficient data, is the first target image.
In the embodiment of the application, the confidence level screening rule refers to a guideboard image to be resolved, wherein the confidence level of the guideboard identification is greater than a certain threshold value.
In the embodiment of the application, the guideboard image is input into a feature extraction model, wherein the feature extraction model can be a target detection model of YOLOv5, and features of the guideboard image can be extracted through a convolutional neural network.
In the embodiment of the application, the characteristic information of the guideboard image is input into a classifier connected with the model, wherein the classifier classifies the characteristic information of the guideboard image and outputs the probability score of each class.
Typically, the probability score output by the classifier can be converted into a probability distribution using a soft max function, and the sum of probabilities can be ensured to be 1.
On the basis of the above embodiment, for the probability distribution output by the classifier, the category with the highest probability may be selected as the classification result by using the maximum probability method, and the probability may be used as the current confidence data.
In the embodiment of the application, the current confidence coefficient data is compared with the preset confidence coefficient data, the guideboard image with the current confidence coefficient data larger than the preset confidence coefficient data is reserved, namely the guideboard image with the correct image is judged, and the guideboard image reserved after screening is used as the first target image.
Therefore, after the guideboard is screened by the confidence level screening rule, the misrecognized guideboard can be removed, and the accuracy of the subsequent guideboard calculation is improved.
In this embodiment of the present application, when determining that the filtering rule is an identifying shape filtering rule, determining a first target image in the plurality of guideboard images to be resolved includes:
and receiving the guideboard image to be resolved.
And detecting the guideboard image to be resolved based on an edge detection algorithm to obtain a detection result.
And determining the guideboard image to be resolved in the rectangular shape in the detection result as a first target image.
In the embodiment of the application, the recognition shape screening rule refers to screening a guideboard image to be resolved, wherein the guideboard recognition shape of the guideboard image is rectangular.
In the embodiment of the application, the shape of the road sign image is detected, the outline of the road sign image can be obtained through an edge detection algorithm, and the judgment can be carried out by judging the pixel coordinates of four corner points.
In the embodiment of the application, whether the processed guideboard image accords with the rectangular feature is judged, the guideboard image in the detection result is reserved to be the guideboard image in the rectangular shape, and the guideboard image reserved after screening is used as the first target image.
Referring to fig. 2, fig. 2 is a schematic structural view of a rectangular traffic sign guideboard according to an embodiment of the present application.
In actual use, the guideboard image to be solved is a rectangular traffic sign guideboard image, the rectangular traffic sign guideboard image can be optimized by using the HRNET, and the pixel coordinates of the rectangular traffic sign guideboard image are determined, wherein the pixel coordinates are the pixel coordinates of four corner points of the upper left, the upper right, the lower left and the lower right of the rectangular traffic sign guideboard image. And judging the shape formed by the four corner pixel coordinates, wherein the four corner pixel coordinates are formed into a rectangular shape as shown in a graph x, and reserving the guideboard image as a first target image.
Therefore, after screening through the identification shape screening rule, the misrecognized guideboard can be removed, and the accuracy of the subsequent guideboard calculation is improved.
In this embodiment of the present application, when determining that the screening rule is an identification area screening rule, determining a first target image in the plurality of guideboard images to be resolved includes:
And receiving the guideboard image to be resolved.
Calculating the pixel area of the guideboard in the guideboard image to be calculated to obtain the current guideboard area;
and comparing the current guideboard area with a preset area to obtain a comparison result.
And determining that the guideboard image to be solved, of which the current guideboard area is larger than the preset area, in the comparison result is a first target image.
In the embodiment of the application, the identification area screening rule refers to screening of guideboard images with identification areas larger than a certain threshold.
In the embodiment of the application, calculating the pixel area of the guideboard in the guideboard image may use a contour detection algorithm and an image processing function in the Open CV library.
In actual use, the received guideboard image to be resolved is subjected to gray scale processing, and the gray scale image is subjected to binarization processing, so that a binarized guideboard image is obtained. Contour detection is carried out through a find objects function in the Open CV library, contour information of all guideboard images is obtained, pixel areas of all Contours are calculated, the pixel areas are compared with a preset area threshold value, and the guideboard image to be solved, of which the current guideboard area is larger than the preset area, in the comparison result is determined to be a first target image.
Therefore, after screening by the identification area screening rule, the reserved pixel area of the guideboard image to be resolved is larger, so that more characteristic points of the guideboard can be extracted, and the accuracy of subsequent resolving work is improved.
In this embodiment of the present application, when determining that the screening rule is an identification frame screening rule, determining a first target image in the plurality of guideboard images to be resolved includes:
and receiving the guideboard image to be resolved.
And identifying the outline of the guideboard in the guideboard image to be solved based on an outline detection algorithm, and calculating to obtain the outline pixel area of the guideboard.
And calculating the ratio of the area of the outline pixel to the circumscribed rectangle of the guideboard image to be calculated to obtain a ratio result.
And determining the guideboard image to be solved, which is larger than the preset ratio, in the ratio result as a first target image.
In the embodiment of the application, the identification frame screening rule refers to that the ratio of the outline area of the screening guideboard identification frame to the circumscribed rectangle of the guideboard identification frame is larger than a certain threshold value.
In the embodiment of the application, the outline of the guideboard image to be resolved can be identified through an outline detection algorithm.
In the embodiment of the application, in order to evaluate the proportion of the size of the guideboard outline relative to the whole guideboard image, the pixel area of the guideboard outline can be processed to the pixel area of the circumscribed rectangle of the guideboard image to be solved.
In this embodiment of the present application, the preset ratio may be set according to actual requirements and scenes. And when the ratio result of the guideboard image to be calculated is larger than the preset ratio, determining the image as a first target image.
In the embodiment of the application, the identification frame screening rule is set to keep the image of the road board image in the road board image to be resolved, so that the condition that the external rectangle of the road board identification frame is too large, the content of the road board image is too small, and the resolving precision is influenced is avoided.
In this embodiment of the present application, further includes:
and receiving the guideboard image to be resolved.
And reading distortion parameters in the guideboard image to be resolved.
And de-distorting the guideboard image to be resolved based on an iterative de-distorting algorithm to obtain an undistorted guideboard image.
In the embodiment of the application, the distortion parameters generally include radial distortion and tangential distortion, and the distortion parameters in the image of the guideboard to be resolved refer to radial distortion.
It can be understood that, because a plurality of images of the same guideboard at different positions and different angles are acquired, and most of the images are not located at the center of the whole image, in the radial distortion, the pixel position of the center of the image is more accurate, but the distortion condition of the pixel position farther from the center is more serious, so that the radial distortion of part of the images is more serious, and the resolving precision of the subsequent guideboard images is very affected.
In the embodiment of the present application, the method for de-distorting the guideboard image to be resolved may use a CV2. Undistitortpints function in the Open CV library, i.e. an iterative de-distorting algorithm.
In actual use, converting a guideboard image into a gray image by using a cv2.cvtColor function, detecting checkerboard corner points in the gray image by using a cv2.final color corner function to obtain an original first point coordinate array, de-distorting second point coordinate data by using a cv2.undistitcher points function to obtain de-distorted second point coordinate data, drawing the second point coordinate data on the original gray image, and observing a de-distorting effect.
In this embodiment of the present application, the selecting, based on the initial image, a second target image from the image set includes:
acquiring the initial image;
determining a first target image with the initial image as a collection interval as a second target image based on the initial image;
setting the second target image as an initial image, returning to determining the first target image which is the acquisition interval with the initial image as the second target image based on the initial image, and terminating the selection until a termination condition is met;
wherein the termination condition includes reaching a preset target number of pickups.
In the embodiment of the present application, an initial image is taken as a selected starting point, and a second target image is selected from the first target image according to a preset acquisition interval.
The first target images may be ordered according to the order of the positions of the collection vehicles when the images are collected, so that the collection space substantially refers to the distance that the collection vehicles move between the two images.
In this embodiment of the present application, the acquisition interval refers to a distance that is taken from the initial image to the first target image.
In actual use, the image with the largest pixel area of the guideboard recognition frame is taken as an initial image, 1 first target image is selected forward at intervals of 1m to serve as a second target image, the second target image is taken as the initial image, 1 first target image is selected in the same direction to serve as the second target image, and the operation is repeated until the number of selected images meets 7.
On the basis, if the number of selected images is less than 7, the interval is reduced to 0.8 times of the original interval, namely, 1 first target image is selected forward at the interval of 0.8m to serve as a second target image, and 1 first target image is selected in the same direction to serve as a second target image by taking the second target image as an initial image, and the operation is repeated until the number of selected images is 7.
On the basis, if the number of the selected images still does not meet 7, repeatedly reducing the interval to be 0.8 times of the original interval, and iterating 8 times at most until the selected interval is 0.2m at minimum, namely 0.8 7 =0.2m。
On the basis, if the number of the selected images still does not meet 7, converting the direction of the selected images into backward 1 first target image to be used as a second target image, and selecting the second target image as an initial image to be used as 1 first target image to be used as a second target image according to the same direction, and repeating the operation until the number of the selected images meets 7.
On the basis, if the number of the selected images still does not meet 7, repeatedly reducing the interval to be 0.8 times of the original interval, and iterating 8 times at most until the selected interval is 0.2m at minimum, namely 0.8 7 =0.2m。
On the basis, if the number of the selected images still does not meet 7, converting the direction of the selected images into forward selection until the images do not meet the minimum spacing distance of 0.2m, and then backward selecting the rest images until 7 images are met.
In this embodiment of the present application, the optimal collection interval may be 1m, if the collection interval is larger, errors may occur in the later stage feature point matching link, because the position difference of the guideboard in the two images is larger, the number of matched feature points may be reduced, thereby causing larger errors of the rotation matrix and the translation matrix.
In addition, because the acquisition interval is larger, the shape and texture of the guideboard in different images can also have larger difference, and further the characteristic point matching is adversely affected.
And when the acquisition interval is smaller, the error of the characteristic point matching link can be reduced, but due to the interference of factors such as pixel errors, camera errors and the like, the error of solving the road-license pose through triangulation can be increased when the road-license pose is solved.
In addition, if the image interval is too small, the rotation matrix and the translation matrix of the two images are also changed less, so that the accuracy of road-license pose calculation is not high enough.
In the embodiment of the application, in the drawing process of the high-precision map, the guideboard needs to be identified and positioned, and the pose of the guideboard needs to be determined through a plurality of images. A BA optimization method may be used to improve the accuracy of pose estimation in general. I.e. using two consecutive images to estimate the pose of the guideboard.
The estimated guideboard pose can be evaluated by error comparison, and the effect can also be evaluated by other evaluation strategies, for example, by guideboard back projection error comparison, namely, the pose of the guideboard is back projected onto two images, and the error between the projection point of the guideboard on the images and the actual guideboard position is calculated. And determining the road-license pose with the best effect by comparing the error sizes of different road-license poses.
In the above embodiment, 7 pieces are selected as the best guideboard images to determine the pose of the guideboard.
In this embodiment of the present application, a process for determining an acquisition interval includes:
the first target image is received.
Inquiring the information of the track points of the acquisition vehicle of the first target image to obtain the acquisition time point of the first target image.
And determining the longitude and latitude of the target corresponding to the acquisition time point.
And calculating the acquisition interval of the two first target images according to the target longitude and latitude.
In the embodiment of the application, the information of the track points of the acquired vehicles can be longitude and latitude coordinates where each guideboard image is located when the guideboard image is acquired, and a time point when the guideboard image is acquired.
In the embodiment of the application, longitude and latitude coordinates of the front point and the rear point of the time stamp of the acquired guideboard image are acquired based on a binary search algorithm. And calculating the time difference between the two time stamps, and calculating according to the time difference and longitude and latitude coordinates of the two points to obtain the longitude and latitude coordinates of the first target image. And respectively calculating longitude and latitude coordinates of the two first target images, and calculating metric distances of the two first target images according to a distance formula.
In actual use, based on a binary search algorithm, the distance guideboard image time is foundFirst timestamp of the last timestamp tAnd a second timestamp->Wherein->、/>Satisfy->. Determining a first timestamp from acquisition of vehicle track point information And a second timestamp->Corresponding first coordinate->And second coordinates->. And estimating the longitude and latitude of the guideboard image according to the first distance formula.
Wherein the first distance formula is defined as
（2）
In the formula (2), the amino acid sequence of the compound,for timestamp->Is the english abbreviation of longitude. Wherein (1)>Longitude value of the first coordinate, +.>Longitude value of the second coordinate, +.>Representation->Relative to->Time difference of->Representing the total length of the time difference. Thus (S)>The ratio representing the time difference represents the ratio of occurrence of the longitude value within the time period. Multiplying the ratio by +.>Representing the variation of longitude values over a period of time, finally adding the starting longitude +.>Obtaining time->Longitude values at that time. />
And calculating metric distances of the two guideboard images according to longitude and latitude coordinates of the two guideboard images.
Corresponding to the embodiment of the application function implementation method, the application also provides an embodiment of the high-precision map guideboard graphic data calculating device.
Referring to fig. 3, fig. 3 is a schematic structural diagram of a high-precision map guideboard graphic data solver according to an embodiment of the present application.
The embodiment of the application shows a high-precision map guideboard graphic data calculating device, which comprises:
the receiving module 1 is used for receiving a plurality of guideboard images to be resolved;
The screening module 2 is used for screening from the plurality of guideboard images to be resolved based on screening rules to obtain an image set comprising a first target image; the first number of first target images in the image set is at least greater than a preset identification number; the preset identification quantity is used for representing the minimum quantity capable of calculating the pose of the guideboard; the screening rule is used for reserving images meeting the identification conditions;
the acquisition module 3 takes one image with the largest pixel area of a first target image in the image set as an initial image, and selects a second target image from the image set based on the initial image, wherein the acquisition interval between the first target image and the second target image is a preset distance, and the acquisition interval between two adjacent second target images is the preset distance;
and a resolving module 4 for resolving the pose of the guideboard based on the second target image.
In this embodiment of the present application, the filtering based on the filtering rule includes:
identifying the plurality of guideboard images to be resolved to obtain an identification result;
determining a corresponding screening rule according to the identification result;
And determining an image set of the first target image from the plurality of guideboard images to be resolved based on the corresponding screening rules.
In this embodiment of the present application, the screening rule includes:
confidence screening rules, recognition shape screening rules, recognition area screening rules, and/or recognition frame ratio screening rules.
In this embodiment of the present application, the filtering rule includes a confidence level filtering rule, and determining a first target image from the plurality of guideboard images to be resolved includes:
receiving a guideboard image to be resolved;
extracting characteristic information of the guideboard image to be resolved;
calculating the confidence coefficient of the characteristic information to obtain current confidence coefficient data;
comparing the current confidence coefficient data with preset confidence coefficient data, and determining that the guideboard image to be resolved, of which the current confidence coefficient data is larger than the preset confidence coefficient data, is the first target image;
and/or, the filtering rule comprises a shape identifying filtering rule, and determining a first target image in the plurality of guideboard images to be resolved comprises:
receiving a guideboard image to be resolved;
detecting the guideboard image to be resolved based on an edge detection algorithm to obtain a first detection result;
Determining a guideboard image to be resolved, which is rectangular in shape, in the detection result as a first target image;
and/or, the screening rule includes an area identifying screening rule, and determining a first target image from the plurality of guideboard images to be resolved includes:
receiving a guideboard image to be resolved;
calculating the pixel area of the guideboard in the guideboard image to be calculated to obtain the current guideboard area;
comparing the current guideboard area with a preset area to obtain a comparison result;
determining a guideboard image to be solved, of which the current guideboard area is larger than the preset area, in the comparison result as a first target image;
and/or, the screening rule includes an identification frame screening rule, and determining a first target image in the plurality of guideboard images to be resolved includes:
receiving a guideboard image to be resolved;
identifying the outline of the guideboard in the guideboard image to be solved based on an outline detection algorithm, and calculating to obtain the outline pixel area of the guideboard;
calculating the ratio of the area of the outline pixel to the circumscribed rectangle of the guideboard image to be calculated to obtain a ratio result;
and determining the guideboard image to be solved, which is larger than the preset ratio, in the ratio result as a first target image.
In this embodiment of the present application, further includes:
receiving a guideboard image to be resolved;
reading distortion parameters in the guideboard image to be resolved;
and de-distorting the guideboard image to be resolved based on an iterative de-distorting algorithm to obtain an undistorted guideboard image.
In this embodiment of the present application, the selecting, based on the initial image, a second target image from the image set includes:
acquiring the initial image;
determining a first target image with the initial image as a collection interval as a second target image based on the initial image;
setting the second target image as an initial image, returning to determining the first target image which is the acquisition interval with the initial image as the second target image based on the initial image, and ending picking until a termination condition is met;
the termination condition comprises the preset iteration times of picking, the preset distance of picking or the preset target number of picking.
In this embodiment, the process for determining the acquisition interval includes:
receiving the first target image;
inquiring the information of the track points of the acquired vehicle of the first target image to obtain the acquisition time point of the first target image;
Determining the longitude and latitude of a target corresponding to the acquisition time point;
and calculating the acquisition interval of the two first target images according to the target longitude and latitude.
In the embodiment of the application, the device can screen a plurality of guideboard images to be resolved based on a screening rule in the drawing process of the high-precision map, screen unqualified images, select a second target image according to a preset acquisition interval, and resolve the second target image as a guideboard standard image. Because the plurality of guideboard images to be resolved are screened to remove the guideboard images which are mistakenly identified, and then the second target image is selected according to the preset acquisition interval, the matching of the characteristic points of the two adjacent guideboard images is more accurate, and the accuracy of subsequent resolving is ensured.
Referring to fig. 4, fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application, and the electronic device 500 includes a memory 510 and a processor 520.
The processor 520 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Memory 510 may include various types of storage units, such as system memory, read Only Memory (ROM), and persistent storage. Where the ROM may store static data or instructions that are required by the processor 520 or other modules of the computer. The persistent storage may be a readable and writable storage. The persistent storage may be a non-volatile memory device that does not lose stored instructions and data even after the computer is powered down. In some embodiments, the persistent storage device employs a mass storage device (e.g., magnetic or optical disk, flash memory) as the persistent storage device. In other embodiments, the persistent storage may be a removable storage device (e.g., diskette, optical drive). The system memory may be a read-write memory device or a volatile read-write memory device, such as dynamic random access memory. The system memory may store instructions and data that are required by some or all of the processors at runtime. 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), magnetic disks, and/or optical disks may also be employed. In some embodiments, memory 510 may include a readable and/or writable removable storage device such as a Compact Disc (CD), a read-only digital versatile disc (e.g., DVD-ROM, dual layer DVD-ROM), a read-only blu-ray disc, an ultra-dense disc, a flash memory card (e.g., SD card, min SD card, micro-SD card, etc.), a magnetic floppy disk, and the like. The computer readable storage medium does not contain a carrier wave or an instantaneous electronic signal transmitted by wireless or wired transmission.
The memory 510 has stored thereon executable code that, when processed by the processor 520, causes the processor 520 to perform some or all of the methods described above.
The aspects of the present application have been described in detail hereinabove with reference to the accompanying drawings. In the foregoing embodiments, the descriptions of the embodiments are focused on, and for those portions of one embodiment that are not described in detail, reference may be made to the related descriptions of other embodiments. Those skilled in the art will also appreciate that the acts and modules referred to in the specification are not necessarily required in the present application. In addition, it can be understood that the steps in the method of the embodiment of the present application may be sequentially adjusted, combined and pruned according to actual needs, and the modules in the apparatus of the embodiment of the present application may be combined, divided and pruned according to actual needs.
Furthermore, the method according to the present application may also be implemented as a computer program or computer program product comprising computer program code instructions for performing part or all of the steps of the above-described method of the present application.
Alternatively, the present application may also be embodied as a non-transitory machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) having stored thereon executable code (or a 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 above-described methods according to the present application.
Those of skill would further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the application herein may be implemented as electronic hardware, computer software, or combinations of both.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems and methods according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The embodiments of the present application have been described above, the foregoing description is exemplary, not exhaustive, and not limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the improvement of 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 guideboard graphic data resolving method, characterized by comprising:
receiving a plurality of guideboard images to be resolved;
screening from the plurality of guideboard images to be resolved based on a screening rule to obtain an image set comprising a first target image; the first number of first target images in the image set is at least greater than a preset identification number; the preset identification quantity is used for representing the minimum quantity capable of calculating the pose of the guideboard; the screening rule is used for reserving images meeting the identification conditions;
taking one image with the largest pixel area of a first target image in the image set as an initial image, and selecting a second target image from the image set based on the initial image, wherein the acquisition interval between the first target image and the second target image is a preset distance, and the acquisition interval between two adjacent second target images is the preset distance;
And resolving the pose of the guideboard based on the second target image.
2. The method according to claim 1, wherein the filtering from the plurality of guideboard images to be resolved based on the filtering rule comprises:
identifying the plurality of guideboard images to be resolved to obtain an identification result;
determining a corresponding screening rule according to the identification result;
and determining an image set of the first target image from the plurality of guideboard images to be resolved based on the corresponding screening rules.
3. A method of resolving according to claim 2, wherein the screening rules comprise:
confidence screening rules, recognition shape screening rules, recognition area screening rules, and/or recognition frame ratio screening rules.
4. A method of resolving according to claim 3, wherein the screening rules include confidence level screening rules, and determining a first target image from the plurality of guideboard images to be resolved comprises:
receiving a guideboard image to be resolved;
extracting characteristic information of the guideboard image to be resolved;
calculating the confidence coefficient of the characteristic information to obtain current confidence coefficient data;
comparing the current confidence coefficient data with preset confidence coefficient data, and determining that the guideboard image to be resolved, of which the current confidence coefficient data is larger than the preset confidence coefficient data, is the first target image;
And/or, the filtering rule comprises a shape identifying filtering rule, and determining a first target image in the plurality of guideboard images to be resolved comprises:
receiving a guideboard image to be resolved;
detecting the guideboard image to be resolved based on an edge detection algorithm to obtain a detection result;
determining a guideboard image to be resolved, which is rectangular in shape, in the detection result as a first target image;
and/or, the screening rule includes an area identifying screening rule, and determining a first target image from the plurality of guideboard images to be resolved includes:
receiving a guideboard image to be resolved;
calculating the pixel area of the guideboard in the guideboard image to be calculated to obtain the current guideboard area;
comparing the current guideboard area with a preset area to obtain a comparison result;
determining a guideboard image to be solved, of which the current guideboard area is larger than the preset area, in the comparison result as a first target image;
and/or, the screening rule includes an identification frame screening rule, and determining a first target image in the plurality of guideboard images to be resolved includes:
receiving a guideboard image to be resolved;
identifying the outline of the guideboard in the guideboard image to be solved based on an outline detection algorithm, and calculating to obtain the outline pixel area of the guideboard;
Calculating the ratio of the area of the outline pixel to the circumscribed rectangle of the guideboard image to be calculated to obtain a ratio result;
and determining the guideboard image to be solved, which is larger than the preset ratio, in the ratio result as a first target image.
5. A method of resolving according to claim 1, further comprising:
receiving a guideboard image to be resolved;
reading distortion parameters in the guideboard image to be resolved;
and de-distorting the guideboard image to be resolved based on an iterative de-distorting algorithm to obtain an undistorted guideboard image.
6. A method of resolving according to claim 1, wherein the selecting a second target image from the set of images based on the initial image comprises:
acquiring the initial image;
determining a first target image with the initial image as a collection interval as a second target image based on the initial image;
setting the second target image as an initial image, returning to determining the first target image which is the acquisition interval with the initial image as the second target image based on the initial image, and terminating the selection until a termination condition is met;
wherein the termination condition includes reaching a preset target number of pickups.
7. A method of resolving according to claim 6, wherein determining the acquisition pitch comprises:
receiving the first target image;
inquiring the information of the track points of the acquired vehicle of the first target image to obtain the acquisition time point of the first target image;
determining the longitude and latitude of a target corresponding to the acquisition time point;
and calculating the acquisition interval of the two first target images according to the target longitude and latitude.
8. A high-precision map guideboard graphic data solver, comprising:
the receiving module is used for receiving a plurality of guideboard images to be resolved;
the screening module is used for screening from the plurality of guideboard images to be resolved based on screening rules to obtain an image set comprising a first target image; the first number of first target images in the image set is at least greater than a preset identification number; the preset identification quantity is used for representing the minimum quantity capable of calculating the pose of the guideboard; the screening rule is used for reserving images meeting the identification conditions;
the acquisition module takes one image with the largest pixel area of a first target image in the image set as an initial image, and selects a second target image from the image set based on the initial image, wherein the acquisition interval between the first target image and the second target image is a preset distance, and the acquisition interval between two adjacent second target images is the preset distance;
And the resolving module is used for resolving the pose of the guideboard based on the second target image.
9. An electronic device, comprising:
a processor; and
a memory having executable code stored thereon, which when executed by the processor, causes the processor to perform the method of any of claims 1-7.
10. A computer readable storage medium having stored thereon executable code which when executed by a processor of an electronic device causes the processor to perform the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310430143.5A CN116563837A (en) | 2023-04-21 | 2023-04-21 | High-precision map guideboard graphic data resolving method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310430143.5A CN116563837A (en) | 2023-04-21 | 2023-04-21 | High-precision map guideboard graphic data resolving method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116563837A true CN116563837A (en) | 2023-08-08 |
Family
ID=87487097
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310430143.5A Pending CN116563837A (en) | 2023-04-21 | 2023-04-21 | High-precision map guideboard graphic data resolving method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116563837A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117216301A (en) * | 2023-11-08 | 2023-12-12 | 高德软件有限公司 | Image data recommendation method and device, electronic equipment and storage medium |
-
2023
- 2023-04-21 CN CN202310430143.5A patent/CN116563837A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117216301A (en) * | 2023-11-08 | 2023-12-12 | 高德软件有限公司 | Image data recommendation method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111695486B (en) | High-precision direction signboard target extraction method based on point cloud | |
| CN111179152B (en) | Road identification recognition method and device, medium and terminal | |
| CN111652230B (en) | License plate recognition method, electronic device and storage medium | |
| CN111027546B (en) | Character segmentation method, device and computer readable storage medium | |
| CN112085022B (en) | Method, system and equipment for recognizing characters | |
| CN114332513B (en) | New energy automobile abnormal parking amplification data detection method for smart city | |
| CN110276295B (en) | Vehicle identification number detection and identification method and device | |
| CN108509950B (en) | Railway contact net support number plate detection and identification method based on probability feature weighted fusion | |
| CN116563837A (en) | High-precision map guideboard graphic data resolving method, device, equipment and storage medium | |
| CN113781391A (en) | Image defect detection method and related equipment | |
| CN110991437B (en) | Character recognition method and device, training method and device for character recognition model | |
| CN111507332A (en) | Vehicle VIN code detection method and equipment | |
| US20230065041A1 (en) | Geometric pattern matching method and device for performing the method | |
| CN111598104A (en) | License plate character recognition method and system | |
| CN110866931A (en) | Image segmentation model training method and classification-based enhanced image segmentation method | |
| CN110765963A (en) | Vehicle brake detection method, device, equipment and computer readable storage medium | |
| CN114155285A (en) | Image registration method based on gray level histogram | |
| CN111027601B (en) | Plane detection method and device based on laser sensor | |
| CN111797832A (en) | Automatic generation method and system of image interesting region and image processing method | |
| CN115713750A (en) | Lane line detection method and device, electronic equipment and storage medium | |
| CN113191351B (en) | Reading identification method and device of digital electric meter and model training method and device | |
| US6351560B1 (en) | Apparatus, method, and program for locating an objective on a form and a recording medium for recording the program for locating the objective on the form | |
| CN112598088B (en) | Method for acquiring visual multi-target robust template of industrial component | |
| CN111626299A (en) | Outline-based digital character recognition method | |
| CN115661787A (en) | Square board identification method and device, electronic equipment and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |