CN115100617A - Map evaluating method and device - Google Patents
Map evaluating method and device Download PDFInfo
- Publication number
- CN115100617A CN115100617A CN202210731420.1A CN202210731420A CN115100617A CN 115100617 A CN115100617 A CN 115100617A CN 202210731420 A CN202210731420 A CN 202210731420A CN 115100617 A CN115100617 A CN 115100617A
- Authority
- CN
- China
- Prior art keywords
- map
- evaluated
- elements
- deviation information
- precision
- 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 57
- 238000011156 evaluation Methods 0.000 claims abstract description 119
- 238000004590 computer program Methods 0.000 claims description 11
- 238000009432 framing Methods 0.000 claims description 11
- 238000012937 correction Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 description 25
- 238000009499 grossing Methods 0.000 description 17
- 238000004458 analytical method Methods 0.000 description 13
- 238000001914 filtration Methods 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000007499 fusion processing Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000007781 pre-processing Methods 0.000 description 5
- 230000011218 segmentation Effects 0.000 description 5
- 238000012795 verification Methods 0.000 description 5
- 230000004927 fusion Effects 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 238000007670 refining Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000008676 import Effects 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
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/05—Geographic models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Geometry (AREA)
- Remote Sensing (AREA)
- Computer Graphics (AREA)
- Processing Or Creating Images (AREA)
Abstract
The present disclosure provides a map evaluating method and device, including: determining first deviation information of a map to be evaluated and a high-precision map in the dimension of a road edge element, and modifying the map to be evaluated according to the first deviation information to obtain a modified map to be evaluated, wherein the map to be evaluated and the high-precision map are maps describing geographic features of the same area, and determining second deviation information of the high-precision map and the modified map to be evaluated in the dimension of other map elements, wherein the other map elements are at least one of the map elements except the road edge element, and generating an evaluation result of the map to be evaluated according to the second deviation information, so that the efficiency of map evaluation is improved, and the accuracy and the reliability of map evaluation are improved.
Description
Technical Field
The disclosure relates to the technical field of high-precision maps, in particular to a map evaluating method and device.
Background
The map elements are important contents for drawing the high-precision map, and can be evaluated in order to improve the effectiveness and the reliability of the high-precision map.
For example, the map elements may be evaluated manually, for example, a true value is made manually, and the map elements are compared with the true value, so as to evaluate the map elements.
However, the efficiency of manually making truth values is low, the method is not suitable for scenes with large data volume of map elements, and is easily influenced by human subjective factors, so that the technical problem of low evaluation accuracy is caused.
Disclosure of Invention
The disclosure provides a map evaluation method and a map evaluation device, which are used for improving the accuracy and effectiveness of map evaluation.
In a first aspect, an embodiment of the present disclosure provides a map evaluating method, including:
determining first deviation information of a map to be evaluated and a high-precision map in the road edge element dimension, and correcting the map to be evaluated according to the first deviation information to obtain a corrected map to be evaluated, wherein the map to be evaluated and the high-precision map are maps describing geographic features of the same area;
determining second deviation information of the high-precision map and the corrected map to be evaluated in other map element dimensions, wherein the other map elements are at least one of the map elements except the road edge elements;
and generating an evaluation result of the map to be evaluated according to the second deviation information.
In one embodiment of the present disclosure, the map elements have a type attribute for distinguishing different types of map elements; the determining of the first deviation information of the to-be-evaluated map and the high-precision map in the road edge element dimension comprises the following steps:
acquiring road edge elements from the map to be evaluated based on the type attributes, and acquiring the road edge elements from the high-precision map based on the type attributes;
determining a first corresponding relation between road edge elements in the map to be evaluated and road edge elements in the high-precision map, wherein the road edge elements in the map to be evaluated and the road edge elements in the high-precision map with the first corresponding relation represent the same object in an actual road scene;
and calculating the difference value between the coordinates of the road edge elements in the to-be-evaluated map with the first corresponding relation and the coordinates of the road edge elements in the high-precision map to obtain the first deviation information.
In an embodiment of the present disclosure, the determining second deviation information of the high-precision map and the corrected map to be evaluated in other map element dimensions includes:
determining a second corresponding relation between other map elements in the high-precision map and other map elements in the corrected map to be evaluated, wherein the other map elements in the high-precision map having the second corresponding relation and the other map elements in the corrected map to be evaluated represent the same object in an actual road scene;
and calculating the difference value between the coordinates of other map elements in the high-precision map with the second corresponding relation and the coordinates of other map elements in the corrected map to be evaluated to obtain the second deviation information.
In one embodiment of the present disclosure, the map element has a directional attribute including a longitudinal attribute for characterizing a cross section perpendicular to a road on which the map element is located, or a lateral attribute for characterizing a parallel to the cross section; the calculating a difference between the coordinates of the other map elements in the high-precision map having the second corresponding relationship and the coordinates of the other map elements in the corrected map to be evaluated to obtain the second deviation information includes:
if the direction attributes of the other map elements with the second corresponding relationship are transverse attributes, calculating a transverse coordinate difference value between the high-precision map and the corrected map to be evaluated of the map element with the second corresponding relationship to obtain transverse deviation information;
if the direction attributes of the other map elements with the second corresponding relationship are longitudinal attributes, calculating a longitudinal coordinate difference value between the high-precision map and the corrected map to be evaluated of the other map elements with the second corresponding relationship to obtain longitudinal deviation information;
wherein the second deviation information comprises the lateral deviation information and/or the longitudinal deviation information.
In an embodiment of the present disclosure, the generating an evaluation result of the map to be evaluated according to the second deviation information includes:
repositioning the map to be evaluated according to the second deviation information to obtain a repositioned map to be evaluated;
determining a third corresponding relation between other map elements in the high-precision map and other map elements in the relocated map to be evaluated, wherein the other map elements in the high-precision map and the other map elements in the relocated map to be evaluated having the third corresponding relation represent the same object in an actual road scene;
and determining the evaluation result according to the third corresponding relation.
In an embodiment of the present disclosure, the determining the evaluation result according to the third corresponding relationship includes:
and calculating the difference value between the coordinates of other map elements in the high-precision map with the third corresponding relation and the coordinates of other map elements in the relocated map to be evaluated to obtain third deviation information, and determining the evaluation result according to the third deviation information.
In one embodiment of the present disclosure, the method further comprises:
acquiring a road surface surrounding frame of a road described by a preset map, and acquiring an identification area surrounding frame of a road where a vehicle runs, wherein the preset map comprises the high-precision map;
determining an intersection surrounding frame of the road surface surrounding frame and the identification area surrounding frame, and determining the intersection surrounding frame as an evaluation area;
and calculating a difference value between the coordinates of the other map elements in the high-precision map with the third corresponding relation and the coordinates of the other map elements in the relocated map to be evaluated to obtain third deviation information, wherein the third deviation information comprises: and calculating other map elements with the third corresponding relation, and obtaining the third deviation information by calculating the difference between the coordinate in the relocated map to be evaluated in the evaluation area and the coordinate in the high-precision map in the evaluation area.
In an embodiment of the present disclosure, the obtaining of the road surface surrounding frame of the road of the preset map includes:
acquiring roads and lane lines in the preset map, and generating a bounding box for framing the road surface comprising the roads and the lane lines;
and according to the acquired track of the vehicle running on the road, acquiring a road surface surrounding frame for framing the track from the surrounding frames.
In an embodiment of the disclosure, the map to be evaluated includes a segmented map to be evaluated corresponding to each track segment, and each track segment is obtained by segmenting an acquired track of a road described by the map to be evaluated, where the road is driven by a vehicle, based on a preset interval mileage length.
In one embodiment of the present disclosure, the method further comprises:
acquiring a single-frame map generated based on point cloud data and/or images acquired by a vehicle running on a road;
determining an object represented by the map element represented by the single-frame map in an actual road scene, and acquiring other frame maps comprising the map element representing the object;
and carrying out fusion processing on the single-frame map and the other frame maps to obtain the map to be evaluated.
In an embodiment of the present disclosure, the fusing the single-frame map and the other-frame maps to obtain the map to be evaluated includes:
clustering the single-frame map and the other frame maps to obtain a clustered map;
constructing a topological relation and a distance relation between map elements representing objects in an actual road scene according to the single-frame map and the other-frame maps;
and preprocessing the clustering map according to the topological relation and the distance relation to obtain the map to be evaluated.
In an embodiment of the present disclosure, the preprocessing the clustering map according to the topological relation and the distance relation to obtain the to-be-evaluated map includes:
according to the topological relation and the distance relation, filtering the clustering map to obtain a filtered clustering map;
fitting according to the filtered clustering map to obtain a map element model comprising map elements, and smoothing the map element model to obtain a smoothed map element model;
and verifying the correctness of the map elements in the map element model after the smoothing treatment according to the track of the vehicle running on the road, and determining the map element model passing the verification as a map to be evaluated.
In a second aspect, an embodiment of the present disclosure provides a map evaluating apparatus, including:
the system comprises a first determining unit, a second determining unit and a third determining unit, wherein the first determining unit is used for determining first deviation information of a to-be-evaluated map and a high-precision map in the road edge element dimension, and the to-be-evaluated map and the high-precision map are maps describing geographic features of the same area;
the correction unit is used for correcting the map to be evaluated according to the first deviation information to obtain a corrected map to be evaluated;
the second determining unit is used for determining second deviation information of the high-precision map and the corrected map to be evaluated in other map element dimensions, wherein the other map elements are at least one of the map elements except the road edge elements;
and the generating unit is used for generating an evaluation result of the map to be evaluated according to the second deviation information.
In one embodiment of the present disclosure, the map elements have a type attribute for distinguishing different types of map elements; the first determination unit includes:
the obtaining subunit is used for obtaining road edge elements from the map to be evaluated based on the type attributes, and obtaining the road edge elements from the high-precision map based on the type attributes;
the first determining subunit is configured to determine a first correspondence between road edge elements in the map to be evaluated and road edge elements in the high-precision map, where the road edge elements in the map to be evaluated and the road edge elements in the high-precision map having the first correspondence represent a same object in an actual road scene;
and the first calculating subunit is configured to calculate a difference between the coordinates of the road edge element in the to-be-evaluated map having the first corresponding relationship and the coordinates of the road edge element in the high-precision map, so as to obtain the first deviation information.
In one embodiment of the present disclosure, the second determining unit includes:
a second determining subunit, configured to determine a second correspondence between other map elements in the high-precision map and other map elements in the corrected map to be evaluated, where the other map elements in the high-precision map and the other map elements in the corrected map to be evaluated that have the second correspondence represent the same object in an actual road scene;
and the second calculating subunit is used for calculating a difference value between the coordinates of the other map elements in the high-precision map with the second corresponding relation and the coordinates of the other map elements in the corrected map to be evaluated to obtain the second deviation information.
In one embodiment of the present disclosure, the map element has a directional attribute including a longitudinal attribute for characterizing a cross section perpendicular to a road on which the map element is located, or a lateral attribute for characterizing a parallel to the cross section; the second calculating subunit is configured to, if the direction attribute of the other map element having the second correspondence is a lateral attribute, calculate a lateral coordinate difference between the high-precision map and the corrected map to be evaluated of the map element having the second correspondence, and obtain lateral deviation information;
the second calculating subunit is configured to, if the direction attribute of the other map element having the second correspondence is a longitudinal attribute, calculate a longitudinal coordinate difference between the high-precision map and the corrected map to be evaluated of the other map element having the second correspondence, and obtain longitudinal deviation information;
wherein the second deviation information includes the lateral deviation information and/or the longitudinal deviation information.
In one embodiment of the present disclosure, the generating unit includes:
the repositioning subunit is used for repositioning the map to be evaluated according to the second deviation information to obtain a repositioned map to be evaluated;
a third determining subunit, configured to determine a third correspondence between other map elements in the high-precision map and other map elements in the relocated map to be evaluated, where the other map elements in the high-precision map and the other map elements in the relocated map to be evaluated that have the third correspondence characterize the same object in an actual road scene;
and the fourth determining subunit is used for determining the evaluation result according to the third corresponding relation.
In one embodiment of the present disclosure, the fourth determining subunit includes:
the calculation module is used for calculating the difference value between the coordinates of other map elements in the high-precision map with the third corresponding relation and the coordinates of other map elements in the relocated map to be evaluated to obtain third deviation information;
and the first determining module is used for determining the evaluation result according to the third deviation information.
In an embodiment of the present disclosure, the fourth determining subunit further includes:
the acquisition module is used for acquiring a road surface surrounding frame of a road described by a preset map and acquiring an identification area surrounding frame of the road where a vehicle runs, wherein the preset map comprises the high-precision map;
the second determination module is used for determining an intersection surrounding frame of the road surface surrounding frame and the identification area surrounding frame and determining the intersection surrounding frame as an evaluation area;
and the calculation module is used for calculating other map elements with the third corresponding relation, and obtaining the third deviation information by calculating the difference between the coordinate in the relocated map to be evaluated in the evaluation area and the coordinate in the high-precision map in the evaluation area.
In one embodiment of the present disclosure, the obtaining module includes:
the first obtaining submodule is used for obtaining the roads and the lane lines in the preset map;
a generation submodule for generating a bounding box for framing a road surface including the road and the lane line;
and the second acquisition sub-module is used for acquiring a road surface surrounding frame for framing the track from the surrounding frames according to the acquired track of the vehicle running on the road.
In an embodiment of the disclosure, the map to be evaluated includes a segmented map to be evaluated corresponding to each track segment, and each track segment is obtained by segmenting an acquired track of a road described by the map to be evaluated, where the road is driven by a vehicle, based on a preset interval mileage length.
In one embodiment of the present disclosure, the apparatus further includes:
the system comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for acquiring a single-frame map generated based on point cloud data and/or images acquired by a vehicle running on a road;
a third determining unit, configured to determine an object represented in an actual road scene by the map element represented by the single-frame map;
a second acquisition unit configured to acquire another frame map including a map element representing the object;
and the fusion unit is used for carrying out fusion processing on the single-frame map and the other-frame maps to obtain the map to be evaluated.
In one embodiment of the present disclosure, the fusion unit includes:
the clustering subunit is used for clustering the single-frame map and the other-frame maps to obtain a clustered map;
the construction subunit is used for constructing a topological relation and a distance relation between map elements representing objects in an actual road scene according to the single-frame map and the other-frame maps;
and the processing subunit is used for preprocessing the clustering map according to the topological relation and the distance relation to obtain the map to be evaluated.
In one embodiment of the present disclosure, the processing subunit includes:
the filtering module is used for filtering the clustering map according to the topological relation and the distance relation to obtain a filtered clustering map;
the fitting module is used for fitting according to the filtered clustering map to obtain a map element model comprising map elements;
the smoothing module is used for smoothing the map element model to obtain a smoothed map element model;
the verification module is used for verifying the correctness of the map elements in the map element model after the smoothing processing according to the track of the vehicle running on the road;
and the third determining module is used for determining the verified map element model as the map to be evaluated.
In a third aspect, an embodiment of the present disclosure provides an electronic device, including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the electronic device to perform the method of any one of the first aspect of the disclosure.
In a fourth aspect, the disclosed embodiments provide a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the method of any one of the first aspects of the disclosure.
In a fifth aspect, the embodiments of the present disclosure provide a computer program product comprising a computer program that, when executed by a processor, implements the method of any one of the first aspects of the present disclosure.
The embodiment of the disclosure provides a map evaluating method and device, comprising the following steps: determining first deviation information of a map to be evaluated and a high-precision map in the dimension of a road edge element, and correcting the map to be evaluated according to the first deviation information to obtain a corrected map to be evaluated, wherein the map to be evaluated and the high-precision map are maps describing geographic features of the same area, determining second deviation information of the high-precision map and the corrected map to be evaluated in the dimension of other map elements, wherein the other map elements are at least one of the map elements except the road edge element, generating an evaluation result of the map to be evaluated according to the second deviation information, wherein the characteristic of the first deviation information is determined to be equivalent to the characteristic of a subordinate road level, roughly matching the map to be evaluated and the high-precision map, the characteristic of the second deviation information is determined to be equivalent to the map element in the subordinate road, namely finely matching the corrected map to be evaluated and the high-precision map, by adopting the mode of 'rough matching + fine matching' to evaluate the map, the defects of low efficiency and accuracy caused by adopting a manual mode to evaluate in the example, low reliability caused by real-time evaluation in the example and limited scene and data quantity caused by evaluating by taking the region as a unit in the example can be avoided, the efficiency of evaluating the map is improved, and the accuracy and reliability of evaluating the map are improved.
Drawings
In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present disclosure, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a flowchart of a map evaluating method according to an embodiment of the present disclosure;
fig. 2 is a flowchart of a map evaluating method according to another embodiment of the present disclosure;
FIG. 3 is a schematic view of a road edge element of an embodiment of the disclosure;
fig. 4 is a schematic diagram of a map evaluating apparatus according to an embodiment of the present disclosure;
fig. 5 is a schematic diagram of a map evaluating apparatus according to another embodiment of the present disclosure;
fig. 6 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present disclosure.
With the foregoing drawings in mind, certain embodiments of the disclosure have been shown and described in more detail below. These drawings and written description are not intended to limit the scope of the disclosed concepts in any way, but rather to illustrate the concepts of the disclosure to those skilled in the art by reference to specific embodiments.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present disclosure more clear, the technical solutions of the embodiments of the present disclosure will be described clearly and completely with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are some, but not all embodiments of the present disclosure. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.
The terms "first," "second," "third," and the like in the description and in the claims of the present disclosure and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein.
Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
To facilitate a reading of the present disclosure, at least some of the terms of the present disclosure are now explained as follows:
the High-precision map is also called a High definition map (HD map), and refers to a map for automatic driving assistance, the relative precision is in centimeter level, and the High-precision map has rich lane lines, road signs, traffic lights, lane curvature, gradient and lane-level real-time traffic dynamic information, and is mainly used for judgment, decision, control and the like of the automatic driving environment of a machine.
The high-precision base map is used for abstracting and describing geographic entities and virtual elements by using semantic information extracted from images and laser point clouds.
Map elements in a high-precision map for characterizing objects in an actual road scene. Map elements have type attributes such as traffic signs, rods, guardrails, curbs, and the like. The map elements have directional attributes, such as a landscape attribute and a portrait attribute.
Map elements may be divided into road edge elements and other map elements based on whether the map elements are objects that characterize the edges of roads in an actual road scene. The road edge elements are used for representing objects at the edge of a road in an actual road scene, such as guardrails and curbs. The other map elements are map elements except for road edge elements, that is, map elements used for representing objects except for edges of roads in an actual road scene, such as traffic signs, rods, lane lines and the like.
The map evaluation refers to quality evaluation of map elements, namely, evaluation of recall rate and/or accuracy and the like of the map elements. The evaluation dimensions may include recall information of relative truth values of map elements, recall accuracy information, absolute and relative precisions of map elements, and the like. As will be understood from the above explanation of the terms of the map elements, the evaluation objects may specifically include lane lines, road edges, ground road components (ground characters, arrows, etc.), non-ground road components (traffic signs, traffic lights, etc.), and the like, which are not listed here.
Lane lines are short for lane boundaries, and are traffic markings used to separate traffic flows traveling in the same direction, typically white, solid, or yellow.
The traffic sign is a traffic sign or traffic sign for short, and is a facility for transmitting specific information by using graphic symbols and characters to manage traffic and indicate driving direction to ensure smooth road and driving safety, and is mainly applicable to highways, urban roads and special highways, and vehicles and pedestrians need to abide by.
The traffic light is a signal light composed of red, yellow and green (green is blue green) lights for directing traffic.
The map elements are important contents for drawing high-precision maps, and with the development of the automatic driving technology, the attention of users to the safety and reliability of the automatic driving technology is higher and higher. In the map element production process, namely when vectorization processing is carried out on the collected point cloud and/or image, the map element obtained through vectorization processing needs to be evaluated to check the accuracy, precision condition and the like of the map element so as to ensure the quality of the map element, so that the high-precision map has high quality, and the safety and reliability of the vehicle in automatic driving based on the high-precision map are improved.
In some embodiments, the map elements may be evaluated manually. If a true value is made manually, the value of the map element (such as the coordinate of the map element) is compared with the true value, so as to evaluate the map element.
However, the efficiency of manually making truth values is low, the method is not suitable for scenes with large data volume of map elements, and is easily influenced by human subjective factors, so that the technical problem of low evaluation accuracy is caused.
In other embodiments, a real-time trajectory of the collection vehicle, such as a real-time position (e.g., coordinates), a real-time velocity, a real-time acceleration, etc., of the collection vehicle, may be obtained, and the map elements may be evaluated based on the real-time trajectory.
However, the error precision and reliability of the real-time trajectory are relatively poor, and the precision, recall and the like of map elements generated by evaluating in real time are poor, so that the evaluation reliability is low.
In still other embodiments, map elements within a region may be evaluated in units of the region. However, the evaluation scenario is limited, and the evaluation data volume is limited.
In order to avoid at least one of the above technical problems, the inventors of the present disclosure have made creative efforts to obtain the inventive concept of the present disclosure: and evaluating by adopting a mode of 'rough matching + fine matching', wherein the 'rough matching' can be road-level matching between a map to be evaluated and a high-precision map determined based on the dimension of road edge elements, the map to be evaluated is corrected based on a result obtained by the matching, and the 'fine matching' can be matching between other map elements in the high-precision map and other map elements in the modified map to be evaluated, and an evaluation result is determined based on deviation information of the other map elements determined by the matching result between the high-precision map and the modified map to be evaluated.
Hereinafter, the technical solution of the present disclosure will be described in detail by specific examples. It should be noted that the following specific embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.
Referring to fig. 1, fig. 1 is a flowchart illustrating a map evaluating method according to an embodiment of the disclosure. As shown in fig. 1, the method includes:
s101: determining first deviation information of the map to be evaluated and the high-precision map in the road edge element dimension, and correcting the map to be evaluated according to the first deviation information to obtain a corrected map to be evaluated.
The to-be-evaluated map and the high-precision map are maps describing geographic features of the same area.
For example, an execution main body of the map evaluating method according to the embodiment of the present disclosure may be a map evaluating device, where the map evaluating device may be a server (such as a cloud server, or a local server, or a server cluster), may also be a computer, may also be a terminal device, may also be a processor, may also be a chip, and the like, and this is not listed here any more.
The embodiment does not limit the manner of obtaining the map to be evaluated and the high-precision map. Taking the obtaining of a map to be evaluated (or a high-precision map) as an example, the method can be implemented in the following manner:
in one example, the map evaluating device may be connected to the data transmission device and receive a map to be evaluated (or a high-precision map) transmitted by the data transmission device.
In another example, the map evaluating apparatus may provide a tool for loading a map to be evaluated (or a high-precision map), and the user may transmit the map to be evaluated (or the high-precision map) to the map evaluating apparatus through the tool for loading the map to be evaluated (or the high-precision map).
The tool for loading the map (or high-precision map) to be evaluated can be an interface for connecting with external equipment, such as an interface for connecting with other storage equipment, and the map (or high-precision map) to be evaluated transmitted by the external equipment is acquired through the interface; the tool for loading the map (or high-precision map) to be evaluated can also be a display device, for example, the map evaluating device can input an interface with the function of loading the map (or high-precision map) to be evaluated on the display device, a user can import the map (or high-precision map) to be evaluated into the evaluating device through the interface, and the map evaluating device acquires the imported map (or high-precision map) to be evaluated.
The method for obtaining the to-be-evaluated map and the high-precision map may be the same or different, and this embodiment is not limited.
The first deviation information can be understood as deviation information between the map to be evaluated and the high-precision map determined from the dimension of the road edge element, and the deviation information can be deviation information on coordinates.
Illustratively, in conjunction with the above analysis, the road edge element is one of map elements and is used to characterize objects, such as guardrails and curbs, at the edge of the road in the actual road scene.
Correspondingly, the map to be evaluated comprises road edge elements, so that the road edge elements are used for representing the objects at the edge of the road in the actual road scene. For the sake of distinction, the road edge element on the map to be evaluated is referred to as a first road edge element.
Similarly, the high-precision map includes road edge elements, so as to characterize the objects at the edge of the road in the actual road scene based on the road edge elements. For the sake of distinction, the road edge element in the high-precision map is referred to as a second road edge element.
The difference information between the first road edge element and the second road edge element, which may be referred to as first deviation information, may be determined by means of matching, such as coordinate matching.
That is to say, the first deviation information represents the deviation between the map to be evaluated and the high-precision map from the road edge element dimension, that is, the high-precision map is used as a reference, and the map to be evaluated deviates from the position information of the high-precision map in the road edge element dimension.
In order to improve the accuracy and reliability of the map to be evaluated, the map to be evaluated can be corrected based on the first deviation information.
The correction processing may be understood as adjusting the map to be evaluated based on the first deviation information, for example, adjusting coordinates of map elements in the map to be evaluated to correct the deviation of the map to be evaluated.
S102: and determining second deviation information of the high-precision map and the corrected map to be evaluated in other map element dimensions.
Wherein, the other map elements are at least one of the map elements except the road edge elements.
In combination with the above analysis, the other map element is one of the map elements and is used to represent other objects in the actual road scene, such as traffic signs, besides the objects at the edge of the road.
Correspondingly, the to-be-evaluated map comprises other map elements, so that other objects except for the object at the edge of the road in the actual road scene can be represented based on the other map elements. For the sake of distinction, the other map elements in the map to be evaluated are referred to as first other map elements.
Similarly, other map elements are included in the high-precision map so as to represent other places in the actual road scene except for the objects at the edges of the road based on the other map elements. For the sake of distinction, the other map elements in the high-precision map are referred to as second other map elements.
The difference information between the first further map element and the second further map element, which may be referred to as second deviation information, may be determined by means of matching, such as coordinate matching.
That is to say, the second deviation information represents the deviation between the high-precision map and the corrected map to be evaluated from the dimensions of other map elements, that is, the corrected map to be evaluated deviates from the information of the high-precision map in the dimensions of other map elements by taking the high-precision map as a reference.
It is worth to be noted that by determining the first deviation information and correcting the map to be evaluated based on the first deviation information, the deviation between the corrected map to be evaluated and the high-precision map can be relatively reduced, and the second deviation information is further determined on the basis, so that the error of the determined second deviation information can be avoided as much as possible, and the accuracy and the reliability of the second deviation information are improved.
S103: and generating an evaluation result of the map to be evaluated according to the second deviation information.
Based on the above analysis, the present disclosure provides a map evaluating method, including: determining first deviation information of a map to be evaluated and a high-precision map in the dimension of a road edge element, and performing correction processing on the map to be evaluated according to the first deviation information to obtain a corrected map to be evaluated, wherein the map to be evaluated and the high-precision map are maps describing geographic features of the same area, determining second deviation information of the high-precision map and the corrected map to be evaluated in the dimension of other map elements, wherein the other map elements are at least one of the map elements except the road edge element, generating an evaluation result of the map to be evaluated according to the second deviation information, in the embodiment, determining the feature of the first deviation information to be equivalent to the feature of a road level, performing rough matching on the map to be evaluated and the high-precision map, determining the feature of the second deviation information to be equivalent to the map element of the road, namely the lane level, the corrected map to be evaluated and the high-precision map are subjected to 'fine matching', and the map is evaluated by adopting a 'coarse matching + fine matching' mode, so that the defects of low efficiency and accuracy caused by evaluation by adopting a manual mode in the example, low reliability caused by real-time evaluation in the example and the defects of limited scene and data quantity caused by evaluation by taking the region as a unit in the example can be avoided, the efficiency of map evaluation is improved, and the accuracy and reliability of map evaluation are improved.
For the reader to more deeply understand the implementation principle of the present disclosure, the implementation principle of the present disclosure will now be explained in more detail with reference to fig. 2. Fig. 2 is a flowchart of a map evaluating method according to another embodiment of the present disclosure. As shown in fig. 2, the method includes:
s201: and acquiring a map to be evaluated and a high-precision map corresponding to the map to be evaluated.
It should be understood that, in order to avoid cumbersome statements, the present embodiment will not be described again with respect to the same technical features as those in the above embodiments.
Wherein, the high-precision base map comprises a high-precision map. For example, the high-precision map can be a map which is acquired from a high-precision base map and corresponds to a map to be evaluated. The term "corresponding" herein may be understood as a correspondence of regions. Namely, the to-be-evaluated map and the high-precision map are maps describing the geographic features of the same area.
In some embodiments, obtaining the map to be evaluated may include the following steps:
the first step is as follows: a single-frame map generated based on point cloud data and/or images acquired when a vehicle runs on a road is acquired.
Exemplarily, the following is exemplarily illustrated by taking an image as an example: and acquiring a current frame image, and performing vectorization processing on the current frame image to obtain a single-frame map.
The second step is as follows: an object represented by a map element in the single-frame map in the actual road scene is determined, and other frame maps including the map element representing the object are obtained.
For example, if the object represented by the map element in the single-frame map in the actual road scene is a traffic sign, the other-frame map including the map element for representing the traffic sign is acquired.
In some embodiments, the single-frame map has attribute information, the attribute information is used for identifying whether other frame maps representing the same object as the single-frame map in an actual road scene exist, if so, the other frame maps are obtained, and if not, the map to be evaluated can be the single-frame map.
The third step: and carrying out fusion processing on the single-frame map and other frame maps to obtain a map to be evaluated.
Correspondingly, if other frame maps which represent the same object with the map elements in the single frame map in the actual road scene exist, the single frame map and the other frame maps are subjected to fusion processing to obtain the map to be evaluated. That is, the map to be evaluated may be obtained by performing a multi-frame map fusion process on map elements included in the actual road scene and representing the same object.
In this embodiment, a single-frame map and other-frame maps representing map elements of the same object in an actual road scene are fused to obtain a map to be evaluated, so that the map to be evaluated has high comprehensiveness, and the accuracy and reliability of evaluation are improved.
In some embodiments, the third step may comprise the sub-steps of:
the first substep: and clustering the single-frame map and other frame maps to obtain a clustered map.
The Clustering process may be understood as dividing a data set including a single frame map and other frame maps into different classes or clusters, so that the similarity of data objects in the same cluster is as large as possible, and the difference of data objects not in the same cluster is also as large as possible. That is, after the clustering process, the data of the same class are gathered together as much as possible, and the data of different classes are separated as much as possible.
In this embodiment, the clustering method is not limited, and for example, a Partition-based clustering method (Partition-based Methods) may be used for clustering, a Density-based clustering method (Density-based Methods) may be used for clustering, a Hierarchical clustering method (Hierarchical Methods) may be used for clustering, and the like.
The second sub-step: and constructing a topological relation and a distance relation between map elements representing the objects in the actual road scene according to the single-frame map and other frame maps.
For example, an object in an actual road scene may be represented by a plurality of map elements, and there is a certain association relationship between the map elements, such as an association relationship on a topological structure (which may be understood as an association relationship on a position), and an association relationship on a distance.
The third substep: and preprocessing the clustering map according to the topological relation and the distance relation to obtain a map to be evaluated.
Illustratively, based on the topological relation and the distance relation, the noise removal processing can be performed on the map elements in the clustering map, so as to obtain the map to be evaluated. And smoothing map elements in the clustering map based on the topological relation and the distance relation to obtain a map to be evaluated, and the like.
In the embodiment, the map to be evaluated is obtained by combining the clustering and preprocessing modes, so that redundant data and noise data of the map to be evaluated can be avoided, the effectiveness of the map to be evaluated is improved, and the accuracy of map evaluation is further improved.
In some embodiments, the third substep may comprise the following refinement steps:
a first thinning step: and filtering map elements in the clustering map according to the topological relation and the distance relation to obtain the filtered clustering map.
Illustratively, according to the topological relation and the distance relation, noise map elements and redundant map elements in the clustering map are filtered out, and the filtered clustering map is obtained.
A second refining step: and fitting according to the filtered clustering map to obtain a map element model comprising map elements, and smoothing the map element model to obtain the smoothed map element model.
The map element model can be understood as a curve equation obtained based on filtered clustering map fitting. Accordingly, smoothing may be understood as smoothing the curve equation to remove noise data in the curve equation, so that the curve equation is smoother.
A third refining step: and verifying the correctness of the map elements in the map element model after the smoothing treatment according to the track of the vehicle running on the road, and determining the map element model passing the verification as the map to be evaluated.
Illustratively, when a vehicle runs on a road to acquire point cloud data and/or images, tracks can be formed, such as the speed, position, direction, elevation, acceleration and the like of the vehicle, the map elements in the map element model after the smoothing processing can be verified based on at least one of the tracks to verify the correctness of the map elements in the map element model after the smoothing processing, and if the verification result is incorrect, the incorrect map elements are removed from the map element model after the smoothing processing, so that a map to be evaluated is obtained.
In the embodiment, by combining the processing of filtering, smoothing and verifying, redundant data and noise data in the map to be evaluated can be reduced as much as possible, so that the correctness of map elements in the map to be evaluated can be improved as much as possible, the accuracy and the effectiveness of the map to be evaluated can be improved, and the reliability of evaluation can be further improved.
S202: and acquiring road edge elements from the map to be evaluated based on the type attributes, and acquiring the road edge elements from the high-precision map based on the type attributes.
Wherein the map elements have a type attribute, the type attribute being used to distinguish between different types of map elements.
In conjunction with the above analysis, the map elements may be divided into road edge elements and other map elements based on whether the elements are used to characterize the road edges in the actual road scene, and therefore, the type attribute may include the type of the road edge element and the types of the other map elements.
Alternatively, in conjunction with the above analysis, the type attribute of the map element includes, for example, a traffic sign type, a shaft type, a guardrail type, a curb type, etc.
In this embodiment, the road edge element with the type attribute as the type of the road edge element may be obtained from the to-be-evaluated map, or the road edge element with the type attribute as the type of the road edge element may be obtained from the high-precision map. For example, curbs and/or road borders and the like can be acquired from the map to be evaluated and the high-precision map respectively.
S203: and determining a first corresponding relation between the road edge elements in the map to be evaluated and the road edge elements in the high-precision map.
The road edge elements in the to-be-evaluated map and the road edge elements in the high-precision map with the first corresponding relation represent the same object in an actual road scene.
For example, since the collected data may have errors, on one hand, the number of road edge elements in the map to be evaluated may be greater than that in the high-precision map, for example, the number of road edge elements in the map to be evaluated includes curbs and road borders, while the number of road edge elements in the high-precision map includes only road borders.
On the other hand, the road edge elements in the to-be-evaluated map and the high-precision map are both road edges, but the number of the road edges in the to-be-evaluated map is more than that in the high-precision map.
This step may be understood as constructing a correspondence (i.e., a first correspondence) between the road edge element in the map to be evaluated and the road edge element in the high-precision map, which characterize the same object, in the actual road scene.
Illustratively, as shown in fig. 3, a road in the map to be evaluated is marked as a road 1, and the road 1 includes a road boundary 11 and a road boundary 12. The road in the high-precision map is labeled as road 2, and the road 2 includes a road edge 21 and a road edge 22. In combination with the above analysis, it can be seen that road 1 and road 2 represent the same road in an actual road scene.
If the road edge 11 and the road edge 21 represent the same road edge in the actual road scene, a first corresponding relationship between the road edge 11 and the road edge 21 is established. If the road edge 12 and the road edge 22 represent the same road edge in the actual road scene, a first corresponding relationship between the road edge 12 and the road edge 22 is established.
In some embodiments, the first correspondence may be determined based on a "global residual minimization principle," which is exemplary:
calculating a deviation between the set edge line 11 and the set edge line 21, such as a distance between the set edge line 11 and the set edge line 21 (for the sake of distinction, the distance is referred to as a first distance); calculating a deviation between the set edge line 12 and the set edge line 22, such as a distance between the set edge line 12 and the set edge line 22 (for the sake of distinction, the distance is referred to as a second distance); the sum of the first distance and the second distance is calculated.
Calculating a deviation between the set edge line 11 and the edge line 22, such as a distance between the set edge line 11 and the edge line 22 (for the sake of distinction, this distance is referred to as a third distance); calculating a deviation between the set border line 12 and the road border line 21, such as a distance between the set border line 12 and the road border line 21 (for the sake of distinction, the distance is referred to as a fourth distance); the sum of the third distance and the fourth distance is calculated.
If the first distance + the second distance > the third distance + the fourth distance, a first correspondence between the roadside line 11 and the roadside line 21 and a first correspondence between the roadside line 12 and the roadside line 22 are established.
If the first distance + the second distance < the third distance + the fourth distance, a first correspondence between the road edge 11 and the road edge 22 and a first correspondence between the road edge 12 and the road edge 21 are established.
S204: and calculating the difference value between the coordinates of the road edge elements in the to-be-evaluated map with the first corresponding relation and the coordinates of the road edge elements in the high-precision map to obtain first deviation information.
For example, in combination with the above analysis, if there is a first corresponding relationship between the roadside 11 and the roadside 21 and there is a first corresponding relationship between the roadside 12 and the roadside 22, then the deviation distance from the roadside 11 to the roadside 21 may be calculated according to the coordinates of the roadside 11 and the coordinates of the roadside 21 to obtain the first deviation information.
Alternatively, the deviation distance from the roadside 12 to the roadside 22 may be calculated according to the coordinates of the roadside 12 and the coordinates of the roadside 22 to obtain the first deviation information.
Alternatively, after calculating the deviation distance from the road edge 11 to the road edge 21 and the deviation distance from the road edge 12 to the road edge 22, the average of the two calculated deviation distances is determined as the first deviation information.
In this embodiment, the first deviation information is obtained by determining road edge elements representing road edges in an actual scene, which correspond to the map to be evaluated and the high-precision map respectively, and determining a first corresponding relationship representing road edge elements of the same object in the actual road scene, and calculating a coordinate difference between the road edge elements having the first corresponding relationship, so that the first deviation information can be more accurately represented in the actual road scene to represent the deviation condition of the road edges of the same object between the map to be evaluated and the high-precision map.
S205: and according to the first deviation information, correcting the map to be evaluated to obtain a corrected map to be evaluated.
Illustratively, the first deviation information is added on the basis of the high-precision map to correct the map to be evaluated, so that the corrected map to be evaluated is obtained. Or, the first deviation information is subtracted on the basis of the high-precision map so as to modify the map to be evaluated, and the modified map to be evaluated is obtained.
S206: and determining a second corresponding relation between other map elements in the high-precision map and other map elements in the corrected map to be evaluated.
Wherein, the other map elements are at least one of the map elements except the road edge elements. And the other map elements in the high-precision map with the second corresponding relation and the other map elements in the corrected map to be evaluated represent the same object in the actual road scene.
For example, the other map elements in the high-precision map may include at least one of a lane line, a traffic sign, a traffic light, and the like, and the other map elements in the modified map to be evaluated may also include at least one of a lane line, a traffic sign, a traffic light, and the like.
Similarly, the types of other map elements in the high-precision map may be more than the types of other map elements of the corrected map to be evaluated, may also be less than the types of other map elements of the corrected map to be evaluated, and may also be equal to the types of other map elements of the corrected map to be evaluated.
In addition, in terms of quantity, other map elements in the high-precision map may be more than other map elements of the corrected map to be evaluated, may also be less than other map elements of the corrected map to be evaluated, and may also be equal to other map elements of the corrected map to be evaluated.
The step can be understood as comparing other map elements in the high-precision map with other map elements in the corrected map to be evaluated to determine other map elements in the high-precision map and other map elements in the corrected map to be evaluated, which represent the same object in the actual road scene.
In combination with the above analysis, the map elements have type attributes, and accordingly, in some embodiments, the high-precision map and the other map elements with the same type attributes in the revised map to be evaluated may be determined based on the type attributes, and then, based on the "distance minimization principle", the other map elements characterizing the same object in the actual road scene may be determined from the other map elements with the same type, that is, the second correspondence may be determined.
The "distance minimization principle" may be understood as that, if the number of other map elements including the same type attribute in the high-precision map and the corrected map to be evaluated is multiple, coordinate differences of other map elements of any same type attribute in the high-precision map and the corrected map to be evaluated are calculated, and the other map elements in the high-precision map corresponding to the minimum coordinate difference in the coordinate differences and the other map elements in the corrected map to be evaluated are determined as the other map elements having the second correspondence.
Illustratively, taking the traffic sign as an example, the traffic sign is obtained from a high-precision map, the traffic sign is obtained from a corrected map to be evaluated, and if the number of the traffic signs in the high-precision map is two, the traffic signs are a first traffic sign and a second traffic sign. The number of the traffic cards in the corrected map to be evaluated is two, namely a third traffic card and a fourth traffic card.
And if the distance between the first traffic board and the third traffic board is less than the distance between the first traffic board and the fourth traffic board, determining that the first traffic board and the third traffic board are traffic boards with a second corresponding relationship.
S207: and calculating the difference value between the coordinates of other map elements in the high-precision map with the second corresponding relation and the coordinates of other map elements in the corrected map to be evaluated to obtain second deviation information.
Illustratively, the first traffic sign in the high-precision map and the third traffic sign in the corrected map to be evaluated have a second corresponding relationship, that is, the first traffic sign and the third traffic sign represent the same traffic sign in the actual road scene, and then the second deviation information is determined according to the coordinate of the first traffic sign and the coordinate of the third traffic sign.
Similarly, in this embodiment, the second deviation information is obtained by determining the second corresponding relationship representing the other map elements in the actual scene, which correspond to the corrected map to be evaluated and the other map elements in the high-precision map, and determining the second corresponding relationship representing the other map elements of the same object in the actual road scene, and calculating the coordinate difference between the other map elements having the second corresponding relationship, so that the second deviation information can be more accurately reflected in the actual road scene to represent the deviation condition of the other map elements of the same object between the map to be evaluated and the high-precision map.
In some embodiments, the map element has directional properties including a longitudinal property for characterizing a cross-plane perpendicular to a road on which the map element is located, or a transverse property for characterizing a parallel and cross-plane; s207 may include:
and if the direction attribute of the other map elements with the second corresponding relation is the transverse attribute, calculating the transverse coordinate difference value between the high-precision map and the corrected map to be evaluated of the other map elements with the second corresponding relation to obtain transverse deviation information.
And if the direction attributes of the other map elements with the second corresponding relationship are longitudinal attributes, calculating the longitudinal coordinate difference value between the high-precision map and the corrected map to be evaluated of the other map elements with the second corresponding relationship to obtain longitudinal deviation information.
Wherein the second deviation information includes lateral deviation information and/or longitudinal deviation information.
Illustratively, the difference value between the transverse coordinate of the lane line with the second corresponding relation in the high-precision map and the transverse coordinate of the corrected map to be evaluated is calculated to obtain the transverse deviation information.
And calculating the difference value between the longitudinal coordinate of the traffic board with the second corresponding relation in the corrected to-be-evaluated map and the longitudinal coordinate of the high-precision map to obtain longitudinal deviation information. For example, the longitudinal deviation information may be determined based on four corner points of the traffic sign.
In this embodiment, the second deviation information is determined from the two dimensions of the horizontal dimension and the vertical dimension by combining the horizontal attribute and the vertical attribute of other map elements, so that the diversity and the integrity of the second deviation information can be improved, and the accuracy and the reliability of map evaluation can be improved.
In some embodiments, other map elements have a weight attribute, such as a lane line having a weight attribute and a traffic sign also having a weight attribute, and the weight attribute of the lane line and the weight attribute of the traffic sign may be the same or different.
Accordingly, based on the above analysis, the map elements having the second correspondence relationship may be multiple, for example, the first traffic card and the third traffic card have the second correspondence relationship, and the second traffic card and the fourth traffic card have the second correspondence relationship. The map elements having the second correspondence relationship may also be various, such as the first traffic sign and the third traffic sign having the second correspondence relationship, the first lane line and the second lane line having the second correspondence relationship, and so on.
Accordingly, the lateral deviation information may be determined in combination with the weight ratio attribute of the lane line, and if the weight ratio attribute of the lane line represents that the weight ratio of the lane line is 1 in a scene of another map element in which only the lane line is the lateral attribute.
If the longitudinal deviation information can be determined by combining the weight ratio attributes corresponding to the traffic sign and the traffic light in the scene where the other map elements of the longitudinal attribute include the traffic light and the traffic sign, for example, the weight ratio attribute of the traffic sign indicates that the weight ratio of the traffic sign is 0.8, and the weight ratio attribute of the traffic light indicates that the weight ratio of the traffic light is 0.2, after the respective longitudinal deviation information is determined from the traffic sign and the traffic light, the final longitudinal deviation information can be determined by combining the weight ratio of the traffic sign and the traffic light and the respective longitudinal deviation information.
The weight ratio of the weight ratio attribute representation can be determined based on the precision of other map elements, and relatively, the higher the precision of other map elements is, the larger the weight ratio of the weight ratio attribute representation of the other map elements is, whereas the lower the precision of the other map elements is, the smaller the weight ratio of the weight ratio attribute representation of the other map elements is.
In some embodiments, the above operations of correcting the map to be evaluated and determining the second deviation information may be iterated to improve the accuracy and reliability of the determined second deviation information, such as obtaining the optimal second deviation information. The number of iterations may be determined based on a requirement, a history record, a test, and the like, or the second deviation information of the current iteration may be determined as the final second deviation information if the deviation value of the second deviation information of the current iteration is smaller than a preset threshold (similarly, the deviation value may be determined based on the requirement, the history record, the test, and the like).
S208: and repositioning the corrected map to be evaluated according to the second deviation information to obtain the repositioned map to be evaluated.
For example, this step may be understood as calculating coordinates of other map elements in the corrected map to be evaluated according to the second deviation information, and determining the calculated coordinates of other map elements as coordinates of other map elements in the relocated map to be evaluated.
For example, the coordinates of other map elements in the relocated map to be evaluated can be obtained by taking the coordinates of other map elements in the high-precision map as a reference and adding or subtracting the deviation value represented by the second deviation information.
And combining the analysis, if the map elements in the high-precision map and the other map elements in the corrected map to be evaluated possibly have a second corresponding relationship, repositioning the coordinates of the other map elements in the corrected map to be evaluated based on the second corresponding relationship, thereby obtaining the repositioned map to be evaluated.
For example, if the first traffic card in the high-precision map and the third traffic card in the map to be evaluated have the second corresponding relationship, the coordinates of the third traffic card are determined based on the second deviation information and the coordinates of the first traffic card.
S209: and determining a third corresponding relation between other map elements in the high-precision map and other map elements in the relocated map to be evaluated.
And the other map elements in the high-precision map with the third corresponding relation and the other map elements in the relocated map to be evaluated represent the same object in the actual road scene.
Illustratively, the high-precision map includes lane lines, the relocated map to be evaluated includes lane lines, and the lane lines are characterized by the same lane line in the actual road scene, so that it is determined that the two lane lines have the third corresponding relationship.
S210: and determining an evaluation result according to the third corresponding relation.
In this embodiment, the other map elements in the high-precision map having the third correspondence and the other map elements in the relocated map to be evaluated are represented by the same object in the actual road scene, and when the relocated map to be evaluated is evaluated based on the third correspondence, the evaluation can have a more reliable evaluation criterion, so that the evaluation accuracy and reliability are improved.
In some embodiments, S210 may include the steps of:
the first step is as follows: and calculating the difference value between the coordinates of other map elements in the high-precision map with the third corresponding relation and the coordinates of other map elements in the relocated map to be evaluated to obtain third deviation information.
In some embodiments, to further improve the validity and reliability of the third deviation information, an evaluation area may be determined first to determine the third deviation information within the evaluation area.
For example, determining the evaluation area may include the following steps:
the first step is as follows: and acquiring a road surface surrounding frame of a road described by a preset map. Wherein the preset map comprises a high-precision map.
For example, the road-side bounding box may be determined based on the association information of the roads and the lane lines in the preset map.
In some embodiments, the first step may comprise the sub-steps of:
the first substep: the method comprises the steps of obtaining roads and lane lines in a preset map, and generating an enclosure frame for framing the road surface of the selected road according to the roads and the lane lines.
The second substep: and acquiring a road surface surrounding frame for framing the track from the surrounding frames according to the acquired track of the vehicle running on the road.
By way of example, this embodiment may be understood as first determining bounding boxes from a large extent (i.e., bounding boxes for bounding a roadway surface), and then within the large extent bounding boxes, determining relatively more accurate bounding boxes of a small extent (i.e., bounding boxes for bounding a roadway surface).
That is to say, the road surrounding frame is the area covered by the track, namely the area where the vehicle actually runs, and the road surrounding frame is determined by adopting a large-range and small-range mode, so that the effectiveness of the road surrounding frame can be improved, and the effectiveness and the efficiency of evaluation are improved.
The second step is as follows: an identification area enclosure frame of a road on which a vehicle is traveling is acquired.
The identification area enclosure frame can be understood as an enclosure frame corresponding to the effective identification range. For example, the device for capturing an image on the vehicle is an image collector (such as a camera, etc.), the image collector has an identification range, for example, if the identification range is determined based on the field angle of the image collector, an area within the identification range is an effective identification area, and accordingly, a bounding box for framing the effective identification area may be referred to as an identification area bounding box.
The third step: and determining an intersection surrounding frame of the road surface surrounding frame and the identification area surrounding frame, and determining the intersection surrounding frame as an evaluation area.
By combining the above understanding of the road surface surrounding frame and the identification region surrounding frame, the evaluation region is the region where the track is located and is the identification effective region, and therefore, the intersection surrounding frame of the road surface surrounding frame and the identification region surrounding frame is determined as the evaluation region, so that the evaluation region has high effectiveness and reliability.
Correspondingly, calculating a difference value between the coordinates of other map elements in the high-precision map with the third corresponding relation and the coordinates of other map elements in the relocated map to be evaluated to obtain third deviation information, wherein the third deviation information can be replaced by: and calculating a map element with a third corresponding relation, and obtaining third deviation information according to a difference value between the coordinate in the relocated map to be evaluated in the evaluation area and the coordinate in the high-precision map in the evaluation area.
The evaluation area has higher effectiveness and reliability, so that the third deviation information determined based on the third corresponding relation has higher effectiveness and reliability in the evaluation area.
In some embodiments, the relocated map to be evaluated of the evaluation area may be further subjected to filtering processing based on the trajectory, so as to filter out abnormal other map elements in the relocated map to be evaluated, other map elements which are not acted on the evaluation area, and the like.
For example, the map to be evaluated after the relocation of the evaluation area may be filtered based on the direction, the elevation, and the like in the track, so as to determine the deviation between other map elements in the map to be evaluated after the filtering in the evaluation area and other map elements in the high-precision map in the evaluation area according to the third correspondence, thereby improving the efficiency and reliability of determining the third deviation information.
In combination with the above analysis, the map element has a directional attribute, and accordingly, the third deviation information includes lateral deviation information determined based on the other map elements having the third correspondence relationship of the lateral attribute and longitudinal deviation information determined based on the other map elements having the third correspondence relationship of the longitudinal attribute.
For example, the high-precision map in the evaluation area includes a lane line and a traffic sign, the relocated map to be evaluated in the evaluation area includes a lane line and a traffic sign, the lane line in the high-precision map in the evaluation area and the lane line in the relocated map to be evaluated in the evaluation area have a third corresponding relationship, and the traffic sign in the high-precision map in the evaluation area and the relocated map to be evaluated in the evaluation area have a third corresponding relationship.
Correspondingly, calculating the difference between the coordinate in the relocated map to be evaluated in the evaluation area and the coordinate in the high-precision map in the evaluation area by using other map elements having the third corresponding relationship, may include:
and calculating a difference value between the coordinates of the lane lines in the relocated map to be evaluated in the evaluation area and the coordinates of the lane lines in the high-precision map in the evaluation area, and determining the difference value as transverse deviation information.
And calculating the difference between the coordinates of the traffic board in the relocated map to be evaluated in the evaluation area and the coordinates of the traffic board in the high-precision map in the evaluation area, and determining the difference as longitudinal deviation information.
The calculation of the lateral deviation information may be understood as generating a relationship between a characteristic lane line in the relocated to-be-evaluated map in the evaluation area and a point-to-line relationship between lane lines in the high-precision map in the evaluation area, for example, determining a distance between a vertical direction of the lane line and the lane line in the high-precision map in the evaluation area for the lane line in the relocated to-be-evaluated map in the evaluation area, and determining the distance as the lateral deviation information.
The calculation of the longitudinal deviation information can be understood as calculating three-dimensional coordinate deviation between the traffic sign corner points in the relocated map to be evaluated in the evaluation area and the traffic sign corner points in the high-precision map in the evaluation area, and determining the three-dimensional coordinate deviation as the longitudinal deviation information.
The longitudinal deviation information obtained by calculation can also be understood as that three-dimensional coordinate deviation between the traffic sign central point in the relocated map to be evaluated in the evaluation area and the traffic sign central point in the high-precision map in the area to be evaluated is calculated, and the three-dimensional coordinate deviation can be determined as the longitudinal deviation information.
That is, the longitudinal deviation information may be determined based on the corner points of the traffic sign, or may be determined based on the center point of the traffic sign, which is not limited in this embodiment.
The second step: and determining an evaluation result according to the third deviation information.
For example, the evaluation result may include two dimensions of content, such as a recall dimension and an accuracy dimension.
In some embodiments, the evaluation result of the map to be evaluated may be generated based on a preset evaluation index and the third deviation information. Wherein, the evaluation index can be that the recall rate reaches 85%, the precision reaches 95%, and the like.
In conjunction with the above analysis, the third deviation information may include lateral deviation information determined based on other map elements of the lateral attributes, such as lateral deviation information determined based on the lane lines having the third correspondence relationship.
Accordingly, recall rate and accuracy may be determined based on the mileage and lateral deviation information, and in the case of recall rate, the evaluation result may indicate that the recall rate within the XX mileage is Y%. Recall and accuracy may be determined based on the number and vertical deviation information.
Based on the above analysis, in some embodiments, the map to be evaluated may be taken as a whole to combine the whole with the high-precision map corresponding to the whole to determine the evaluation result, and in other embodiments, a partial evaluation result of a partial map to be evaluated may be determined first, and the evaluation result of the map to be evaluated may be determined by combining the partial evaluation results.
Illustratively, the map to be evaluated comprises a segmented map to be evaluated corresponding to each track segment, and each track segment is obtained by segmenting the acquired track of the road where the vehicle runs on the basis of the preset interval mileage length.
The length of the interval mileage can be determined based on the needs, history, tests, and the like, which is not limited in this embodiment. If the track can be segmented according to the interval mileage length, N (N is a positive integer greater than 1) track segments are obtained, the map to be evaluated in each track segment is a segmented map to be evaluated, namely the map to be evaluated comprises N segmented maps to be evaluated.
In some embodiments, for each track segment, a three-dimensional coordinate enclosure frame may be generated according to track coordinates of the track segment, and a map within the three-dimensional coordinate enclosure frame is extracted from a map to be evaluated to determine the map to be evaluated as the segmented map of the track segment.
Correspondingly, aiming at each segmented map to be evaluated, the segmented high-precision map corresponding to the segmented map to be evaluated is obtained from the high-precision map. And determining a segmentation evaluation result according to the segmentation to-be-evaluated map and the segmentation high-precision map so as to obtain N segmentation evaluation results, and further determining the evaluation result of the to-be-evaluated map according to the N segmentation evaluation results.
In this embodiment, the segment evaluation result of each segment is determined in a segment manner, so that each segment evaluation result can relatively accurately represent the evaluation result corresponding to the map to be evaluated, and thus, when the evaluation result of the map to be evaluated is obtained by combining the segment evaluation results, the accuracy and reliability of the determined evaluation result can be improved.
Referring to fig. 4, fig. 4 is a schematic diagram of a map evaluating apparatus according to an embodiment of the present disclosure, as shown in fig. 4, the map evaluating apparatus 400 includes:
the first determining unit 401 is configured to determine first deviation information of a to-be-evaluated map and a high-precision map in a road edge element dimension, where the to-be-evaluated map and the high-precision map are maps describing geographic features of the same area.
And a correcting unit 402, configured to perform correction processing on the map to be evaluated according to the first deviation information, so as to obtain a corrected map to be evaluated.
A second determining unit 403, configured to determine second deviation information of the high-precision map and the corrected map to be evaluated in other map element dimensions, where the other map elements are at least one of map elements except the road edge element.
And the generating unit 404 is configured to generate an evaluation result of the map to be evaluated according to the second deviation information.
Referring to fig. 5, fig. 5 is a schematic diagram of a map evaluating apparatus according to another embodiment of the present disclosure, as shown in fig. 5, the map evaluating apparatus 500 includes:
the first acquiring unit 501 is configured to acquire a single-frame map generated based on point cloud data and/or an image acquired by a vehicle traveling on a road.
A third determining unit 502, configured to determine an object of the map element represented by the single-frame map in the actual road scene.
A second obtaining unit 503, configured to obtain another frame map including a map element representing the object.
And the fusion unit 504 is configured to perform fusion processing on the single-frame map and the other-frame maps to obtain the map to be evaluated.
In some embodiments, as can be seen in fig. 5, the fusion unit 504 includes:
a clustering subunit 5041, configured to perform clustering processing on the single-frame map and the other-frame maps to obtain a clustered map;
a constructing subunit 5042, configured to construct, according to the single-frame map and the other-frame maps, a topological relationship and a distance relationship between map elements representing objects in an actual road scene;
and the processing subunit 5043 is configured to pre-process the cluster map according to the topological relation and the distance relation, so as to obtain the to-be-evaluated map.
In some embodiments, processing subunit 5043, includes:
and the filtering module is used for filtering the clustering map according to the topological relation and the distance relation to obtain the filtered clustering map.
And the fitting module is used for fitting according to the filtered clustering map to obtain a map element model comprising map elements.
And the smoothing module is used for smoothing the map element model to obtain the smoothed map element model.
And the verification module is used for verifying the correctness of the map elements in the map element model after the smoothing processing according to the track of the vehicle running on the road.
And the third determining module is used for determining the verified map element model as the map to be evaluated.
The first determining unit 505 is configured to determine first deviation information of a to-be-evaluated map and a high-precision map in a road edge element dimension, where the to-be-evaluated map and the high-precision map are maps describing geographic features of the same area.
In some embodiments, the map elements have a type attribute that is used to distinguish between different types of map elements. As can be seen from fig. 5, the first determining unit 505 includes:
an obtaining sub-unit 5051 is configured to obtain a road edge element from the map to be evaluated based on the type attribute, and obtain a road edge element from the high-precision map based on the type attribute.
A first determining subunit 5052 is configured to determine a first corresponding relationship between a road edge element in the map to be evaluated and a road edge element in the high-precision map, where the road edge element in the map to be evaluated and the road edge element in the high-precision map having the first corresponding relationship characterize the same object in an actual road scene.
A first calculating sub-unit 5053, configured to calculate a difference between the coordinates of the road edge element in the map to be evaluated having the first corresponding relationship and the coordinates of the road edge element in the high-precision map, so as to obtain the first deviation information.
And the correcting unit 506 is configured to correct the map to be evaluated according to the first deviation information, so as to obtain a corrected map to be evaluated.
A second determining unit 507, configured to determine second deviation information of the high-precision map and the corrected map to be evaluated in other map element dimensions, where the other map elements are at least one of map elements except the road edge element.
In some embodiments, as may be seen in fig. 5, the second determining unit 507 includes:
a second determining subunit 5071, configured to determine a second correspondence between other map elements in the high-precision map and other map elements in the corrected map to be evaluated, where the other map elements in the high-precision map and the other map elements in the corrected map to be evaluated having the second correspondence characterize the same object in an actual road scene.
A second calculating subunit 5072, configured to calculate a difference between the coordinates of the other map elements in the high-precision map with the second correspondence and the coordinates of the other map elements in the corrected map to be evaluated, so as to obtain the second deviation information.
In some embodiments, the map element has directional properties including a longitudinal property characterizing a cross-section perpendicular to a road on which the map element is located, or a lateral property characterizing a parallel to the cross-section; the second calculating subunit 5072 is configured to, if the direction attribute of the other map element having the second corresponding relationship is a horizontal attribute, calculate a horizontal coordinate difference between the high-precision map and the corrected map to be evaluated of the map element having the second corresponding relationship, and obtain horizontal deviation information.
The second calculating subunit 5072 is configured to, if the direction attribute of the other map element having the second correspondence is a longitudinal attribute, calculate a longitudinal coordinate difference between the high-precision map and the corrected map to be evaluated of the other map element having the second correspondence, and obtain longitudinal deviation information.
Wherein the second deviation information includes the lateral deviation information and/or the longitudinal deviation information.
And the generating unit 508 is configured to generate an evaluation result of the map to be evaluated according to the second deviation information.
In some embodiments, as can be seen in fig. 5, the generating unit 508 includes:
and the repositioning subunit 5081 is configured to perform repositioning processing on the map to be evaluated according to the second deviation information, so as to obtain a repositioned map to be evaluated.
A third determining subunit 5082, configured to determine a third correspondence between other map elements in the high-precision map and other map elements in the relocated map to be evaluated, where the other map elements in the high-precision map and the other map elements in the relocated map to be evaluated having the third correspondence characterize the same object in an actual road scene.
A fourth determining subunit 5083, configured to determine the evaluation result according to the third correspondence.
In some embodiments, the fourth determining subunit 5083 includes:
and the calculation module is used for calculating the difference value between the coordinates of other map elements in the high-precision map with the third corresponding relation and the coordinates of other map elements in the relocated map to be evaluated to obtain third deviation information.
And the first determining module is used for determining the evaluation result according to the third deviation information.
In some embodiments, the fourth determining subunit 5083 further includes:
the acquisition module is used for acquiring a road surface surrounding frame of a road described by a preset map and acquiring an identification area surrounding frame of the road where a vehicle runs, wherein the preset map comprises the high-precision map;
and the second determination module is used for determining an intersection surrounding frame of the road surface surrounding frame and the identification area surrounding frame and determining the intersection surrounding frame as an evaluation area.
In some embodiments, the obtaining module includes:
and the first acquisition submodule is used for acquiring the roads and the lane lines in the preset map.
A generation submodule for generating a bounding box for framing a road surface including the road and the lane line.
And the second acquisition sub-module is used for acquiring a road surface surrounding frame for framing the track from the surrounding frames according to the acquired track of the vehicle running on the road.
And the calculation module is used for calculating other map elements with the third corresponding relation, and obtaining the third deviation information according to the difference value between the coordinate in the relocated map to be evaluated in the evaluation area and the coordinate in the high-precision map in the evaluation area.
In some embodiments, the map to be evaluated comprises a segmented map to be evaluated corresponding to each track segment, and each track segment is obtained by segmenting the acquired track of a road described by the map to be evaluated, wherein the track is driven by the vehicle based on a preset interval mileage length.
Fig. 6 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present disclosure. As shown in fig. 6, an electronic device 600 of an embodiment of the present disclosure may include: at least one processor 601 (only one processor is shown in FIG. 6); and a memory 602 communicatively coupled to the at least one processor. The memory 602 stores instructions executable by the at least one processor 601, and the instructions are executed by the at least one processor 601, so that the electronic device 600 can execute the technical solutions in any of the foregoing method embodiments.
Alternatively, the memory 602 may be separate or integrated with the processor 601.
When the memory 602 is a separate device from the processor 601, the electronic device 600 further comprises: a bus 603 for connecting the memory 602 and the processor 601.
The electronic device provided by the embodiment of the present disclosure may execute the technical solution of any one of the foregoing method embodiments, and the implementation principle and the technical effect are similar, which are not described herein again.
The embodiment of the present disclosure further provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the computer program is used to implement the technical solution in any of the foregoing method embodiments.
The embodiment of the present disclosure provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the computer program implements the technical solution in any of the foregoing method embodiments.
The embodiment of the present disclosure further provides a chip, including: a processing module and a communication interface, wherein the processing module can execute the technical scheme in the method embodiment.
Further, the chip further includes a storage module (e.g., a memory), the storage module is configured to store instructions, the processing module is configured to execute the instructions stored in the storage module, and the execution of the instructions stored in the storage module causes the processing module to execute the technical solution in the foregoing method embodiment.
It should be understood that the Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor, or in a combination of the hardware and software modules within the processor.
The memory may comprise a high speed RAM memory, and may further comprise a non-volatile storage NVM, such as at least one magnetic disk memory, and may also be a usb disk, a removable hard disk, a read-only memory, a magnetic or optical disk, or the like.
The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, the buses in the figures of the present disclosure are not limited to only one bus or one type of bus.
The storage medium may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.
An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be integral to the processor. The processor and the storage medium may reside in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the storage medium may reside as discrete components in an electronic device.
Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present disclosure, and not for limiting the same; while the present disclosure has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art will understand that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present disclosure.
Claims (12)
1. A map evaluating method is characterized by comprising the following steps:
determining first deviation information of a map to be evaluated and a high-precision map in the road edge element dimension, and correcting the map to be evaluated according to the first deviation information to obtain a corrected map to be evaluated, wherein the map to be evaluated and the high-precision map are maps describing geographic features of the same area;
determining second deviation information of the high-precision map and the corrected map to be evaluated in other map element dimensions, wherein the other map elements are at least one of the map elements except the road edge elements;
and generating an evaluation result of the map to be evaluated according to the second deviation information.
2. The method of claim 1, wherein the map elements have a type attribute for distinguishing between different types of map elements; the determining of the first deviation information of the to-be-evaluated map and the high-precision map in the road edge element dimension comprises the following steps:
acquiring road edge elements from the map to be evaluated based on the type attributes, and acquiring the road edge elements from the high-precision map based on the type attributes;
determining a first corresponding relation between road edge elements in the map to be evaluated and road edge elements in the high-precision map, wherein the road edge elements in the map to be evaluated and the road edge elements in the high-precision map with the first corresponding relation represent the same object in an actual road scene;
and calculating the difference value between the coordinates of the road edge elements in the to-be-evaluated map with the first corresponding relation and the coordinates of the road edge elements in the high-precision map to obtain the first deviation information.
3. The method according to claim 1 or 2, wherein the determining second deviation information of the high-precision map and the corrected map to be evaluated in other map element dimensions comprises:
determining a second corresponding relation between other map elements in the high-precision map and other map elements in the corrected map to be evaluated, wherein the other map elements in the high-precision map having the second corresponding relation and the other map elements in the corrected map to be evaluated represent the same object in an actual road scene;
and calculating the difference value between the coordinates of other map elements in the high-precision map with the second corresponding relation and the coordinates of other map elements in the corrected map to be evaluated to obtain the second deviation information.
4. The method of claim 3, wherein the map element has a directional property comprising a longitudinal property characterizing a cross-section perpendicular to a road on which the map element is located, or a transverse property characterizing a parallel to the cross-section; the calculating a difference between the coordinates of the other map elements in the high-precision map having the second corresponding relationship and the coordinates of the other map elements in the corrected map to be evaluated to obtain the second deviation information includes:
if the direction attributes of the other map elements with the second corresponding relationship are transverse attributes, calculating a transverse coordinate difference value between the high-precision map and the corrected map to be evaluated of the map element with the second corresponding relationship to obtain transverse deviation information;
if the direction attributes of the other map elements with the second corresponding relationship are longitudinal attributes, calculating a longitudinal coordinate difference value between the high-precision map and the corrected map to be evaluated of the other map elements with the second corresponding relationship to obtain longitudinal deviation information;
wherein the second deviation information includes the lateral deviation information and/or the longitudinal deviation information.
5. The method according to any one of claims 1 to 4, wherein the generating of the evaluation result of the map to be evaluated according to the second deviation information comprises:
repositioning the map to be evaluated according to the second deviation information to obtain a repositioned map to be evaluated;
determining a third corresponding relation between other map elements in the high-precision map and other map elements in the relocated map to be evaluated, wherein the other map elements in the high-precision map and the other map elements in the relocated map to be evaluated have the third corresponding relation, and the same object is represented in an actual road scene;
and determining the evaluation result according to the third corresponding relation.
6. The method according to claim 5, wherein said determining said evaluation result according to said third correspondence comprises:
and calculating the difference value between the coordinates of other map elements in the high-precision map with the third corresponding relation and the coordinates of other map elements in the relocated map to be evaluated to obtain third deviation information, and determining the evaluation result according to the third deviation information.
7. The method of claim 6, further comprising:
acquiring a road surface surrounding frame of a road described by a preset map, and acquiring an identification area surrounding frame of the road where a vehicle runs, wherein the preset map comprises the high-precision map;
determining an intersection surrounding frame of the road surface surrounding frame and the identification area surrounding frame, and determining the intersection surrounding frame as an evaluation area;
and calculating a difference value between the coordinates of the other map elements in the high-precision map with the third corresponding relation and the coordinates of the other map elements in the relocated map to be evaluated to obtain third deviation information, wherein the third deviation information comprises: and calculating other map elements with the third corresponding relation, and obtaining the third deviation information by calculating the difference between the coordinate in the relocated map to be evaluated in the evaluation area and the coordinate in the high-precision map in the evaluation area.
8. The method according to claim 7, wherein the obtaining of the road surface surrounding frame of the road of the preset map comprises:
acquiring roads and lane lines in the preset map, and generating a bounding box for framing the road surface comprising the roads and the lane lines;
and acquiring a road surface surrounding frame for framing the track from the surrounding frames according to the acquired track of the vehicle running on the road.
9. The method according to any one of claims 1 to 8, wherein the map to be evaluated comprises a segmented map to be evaluated corresponding to each track segment, and each track segment is obtained by segmenting the acquired track of the road described by the map to be evaluated, wherein the track is driven by the vehicle, based on a preset interval mileage length.
10. A map evaluating apparatus comprising:
the system comprises a first determining unit, a second determining unit and a third determining unit, wherein the first determining unit is used for determining first deviation information of a to-be-evaluated map and a high-precision map in the road edge element dimension, and the to-be-evaluated map and the high-precision map are maps describing geographic features of the same area;
the correction unit is used for correcting the map to be evaluated according to the first deviation information to obtain a corrected map to be evaluated;
the second determining unit is used for determining second deviation information of the high-precision map and the corrected map to be evaluated in other map element dimensions, wherein the other map elements are at least one of the map elements except the road edge elements;
and the generating unit is used for generating an evaluation result of the map to be evaluated according to the second deviation information.
11. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the electronic device to perform the method of any of claims 1-9.
12. A computer-readable storage medium, characterized in that a computer program is stored thereon which, when being executed by a processor, carries out the method of any one of claims 1-9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210731420.1A CN115100617A (en) | 2022-06-24 | 2022-06-24 | Map evaluating method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210731420.1A CN115100617A (en) | 2022-06-24 | 2022-06-24 | Map evaluating method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115100617A true CN115100617A (en) | 2022-09-23 |
Family
ID=83293488
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210731420.1A Pending CN115100617A (en) | 2022-06-24 | 2022-06-24 | Map evaluating method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115100617A (en) |
-
2022
- 2022-06-24 CN CN202210731420.1A patent/CN115100617A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111179152A (en) | Road sign identification method and device, medium and terminal | |
CN112154446B (en) | Stereo lane line determining method and device and electronic equipment | |
CN110088766B (en) | Lane line recognition method, lane line recognition device, and nonvolatile storage medium | |
CN115690773B (en) | DEM partitioning and rebuilding method, computing device and storage medium | |
CN113221750A (en) | Vehicle tracking method, device, equipment and storage medium | |
CN113255578A (en) | Traffic identification recognition method and device, electronic equipment and storage medium | |
CN112432650A (en) | Acquisition method of high-precision map data, vehicle control method and device | |
CN114763999A (en) | Map generation device, map generation method, and computer program for map generation | |
Hu | Intelligent road sign inventory (IRSI) with image recognition and attribute computation from video log | |
CN117351511A (en) | High-precision map detection method, device and equipment | |
CN115131761B (en) | Road boundary identification method, drawing method and drawing device | |
CN115100617A (en) | Map evaluating method and device | |
CN117058912A (en) | Method and device for detecting abnormal parking of inspection vehicle, storage medium and electronic equipment | |
CN113989765A (en) | Detection method and detection device for rail obstacle and readable storage medium | |
CN113392170A (en) | High-precision map data generation method and device and server | |
CN116721396A (en) | Lane line detection method, device and storage medium | |
CN112651417A (en) | License plate recognition method, device, equipment and storage medium | |
CN110539748A (en) | congestion car following system and terminal based on look around | |
CN115497036A (en) | Waterlogging depth calculation method and system and readable storage medium | |
CN117011481A (en) | Method and device for constructing three-dimensional map, electronic equipment and storage medium | |
CN113688259B (en) | Labeling method and device for navigation target, electronic equipment and computer readable medium | |
CN115795626B (en) | Digital road model analysis method, device, computing equipment and storage medium | |
CN116152761B (en) | Lane line detection method and device | |
CN115238119B (en) | Method and device for analyzing position information of oblique photography photo | |
CN112000757B (en) | Road boundary processing method and electronic equipment |
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 |