CN116295513A

CN116295513A - Electronic navigation map quality detection method and device

Info

Publication number: CN116295513A
Application number: CN202310001847.0A
Authority: CN
Inventors: 侯政华; 杜志颖; 韩永根
Original assignee: Beijing Chusudu Technology Co ltd
Current assignee: Beijing Chusudu Technology Co ltd
Priority date: 2019-08-22
Filing date: 2019-08-22
Publication date: 2023-06-23
Also published as: CN112414430B; CN112414430A

Abstract

The embodiment of the invention discloses a method and a device for detecting the quality of an electronic navigation map, wherein the method comprises the following steps: obtaining an electronic navigation map to be detected; acquiring a plurality of pose information and corresponding positioning moments of the pose information in the running process of a scene corresponding to the electronic navigation map; obtaining perception data determined in the running process of the vehicle, wherein the corresponding relation exists between the acquisition time corresponding to each road image and the positioning time corresponding to each pose information; for each pose information, determining map semantic data corresponding to the pose information from an electronic navigation map; and determining a quality detection result of the electronic navigation map based on map position information of map semantic data corresponding to the pose information in the electronic navigation map and/or observation position information of perception data corresponding to the pose information in the corresponding road image aiming at each pose information so as to realize detection of quality problems of the electronic navigation map.

Description

Electronic navigation map quality detection method and device

The application is divided application with application number 201910778638.0 and name of an electronic navigation map quality detection method and device, and the application date of the mother application is 2019, 08 and 22.

Technical Field

The invention relates to the technical field of intelligent transportation, in particular to a method and a device for detecting the quality of an electronic navigation map.

Background

In the unmanned field, the decision and planning technology for the driving route of a vehicle often depends on an electronic navigation map used by the vehicle. In particular, for positioning of an unmanned vehicle, the positional accuracy of an electronic navigation map determines, to some extent, the accuracy of the positioning result of the unmanned vehicle.

In the related art, in the process of creating an electronic navigation map, quality problems often occur in the electronic navigation map, such as bending, breaking, shaking of the elevation of the lane line, and tilting of the lamp post in the electronic navigation map. The quality problem affects the accuracy of the positioning result of the vehicle in the running process to a certain extent.

Then, the detection of quality problems of the electronic navigation map is a key problem for obtaining a high-quality electronic navigation map.

Disclosure of Invention

The invention provides a method and a device for detecting the quality of an electronic navigation map, which are used for detecting the quality problem of the electronic navigation map. The specific technical scheme is as follows:

In a first aspect, an embodiment of the present invention provides a method for detecting quality of an electronic navigation map, including:

obtaining an electronic navigation map to be detected;

obtaining track information of a vehicle in a scene running process corresponding to the electronic navigation map, wherein the track information comprises a plurality of pose information and positioning time corresponding to each pose information;

obtaining the perception data determined by the vehicle in the driving process, wherein each perception data is: the method comprises the steps that data detected from road images acquired by image acquisition equipment of a vehicle are acquired, and the corresponding relation exists between the acquisition time corresponding to each road image and the positioning time corresponding to each pose information;

for each pose information, determining map semantic data corresponding to the pose information from the electronic navigation map;

and determining a quality detection result of the electronic navigation map according to the map position information of the map semantic data corresponding to the pose information in the electronic navigation map and/or the observation position information of the perception data corresponding to the pose information in the corresponding road image aiming at each pose information.

Optionally, the quality detection result includes a detection result of a position deviation condition of each map semantic data;

The step of determining the quality detection result of the electronic navigation map based on the map position information of the map semantic data corresponding to the pose information in the electronic navigation map and/or the observation position information of the perception data corresponding to the pose information in the corresponding road image according to each pose information comprises the following steps:

for each piece of pose information, determining projection position information of map semantic data in a road image corresponding to the pose information based on the map position information of the map semantic data corresponding to the pose information in the electronic navigation map and the pose information;

determining a position deviation value between the map semantic data and the corresponding perception data based on projection position information of the map semantic data in the road image corresponding to the pose information and observation position information of the perception data corresponding to the map semantic data in the road image;

judging whether the position deviation value exceeds a preset distance threshold value or not;

and if the judgment result is that the position deviation value exceeds the preset distance threshold, determining that the map semantic data in the electronic navigation map has position deviation.

Optionally, the perceived data includes perceived lane lines, and the map semantic data includes map lane lines; the quality detection result comprises a detection result of position deviation of the map lane line in the elevation direction;

for each piece of pose information, determining the mapping position information of the map lane line in a vehicle body coordinate system corresponding to the pose information based on the map position information of the map lane line in the electronic navigation map in the map semantic data corresponding to the pose information and the pose information;

for each piece of pose information, determining mapping position information of a sensing lane line in a vehicle body coordinate system corresponding to the pose information based on observation position information of the sensing lane line in a corresponding road image in sensing data corresponding to the pose information, the pose information and a projection matrix corresponding to the image acquisition equipment;

Determining whether a position deviation condition exists in the transverse axis direction and the longitudinal axis direction of each map lane line corresponding to each pose information based on the mapping position information of the map lane line in a vehicle body coordinate system corresponding to the pose information and the mapping position information of a sensing lane line corresponding to the map lane line in the vehicle body coordinate system corresponding to the pose information;

if the situation that the position deviation exists in the horizontal axis direction and the vertical axis direction of the vehicle body coordinate system of the map lane line is determined, for each piece of pose information, determining the projection position information of the map lane line in the road image corresponding to the pose information based on the map position information of the map lane line in the electronic navigation map in the map semantic data corresponding to the pose information and the pose information;

and determining whether the map lane line has position deviation in the elevation direction according to the projection position information of the map lane line in the road image corresponding to the pose information and the observation position information of the perception lane line in the road image in the perception data corresponding to the map lane line aiming at each map lane line corresponding to each pose information.

Optionally, the perceived data includes perceived lane lines, and the map semantic data includes map lane lines; the quality detection result comprises a detection result of the bending condition and/or the breaking condition of the map lane line;

if the quality detection result includes a detection result of a curve condition of a map lane line, the step of determining the quality detection result of the electronic navigation map based on map position information of map semantic data corresponding to the pose information in the electronic navigation map and/or observation position information of perception data corresponding to the pose information in a corresponding road image for each pose information includes:

for each piece of pose information, determining mapping position information of a map lane line in a vehicle body coordinate system corresponding to the pose information based on the map position information of the map lane line in the electronic navigation map in map semantic data corresponding to the pose information and the pose information, wherein each piece of mapping position information comprises: mapping position information of a plurality of discrete points corresponding to the corresponding map lane lines;

aiming at each map lane line corresponding to each pose information, fitting to obtain a lane line fitting line corresponding to the map lane line based on mapping position information of a plurality of discrete points corresponding to the map lane line and a preset fitting algorithm;

Determining a distance variance corresponding to each map lane line according to each map lane line corresponding to each pose information, based on a lane line fitting line corresponding to the map lane line and mapping position information of a plurality of discrete points corresponding to the map lane line;

if the distance variance exceeds a preset variance threshold, determining that a lane line bending condition exists in the map lane line;

and/or, if the quality detection result includes a detection result of a map lane line break condition, determining, for each pose information, a quality detection result of the electronic navigation map based on map position information of map semantic data corresponding to the pose information in the electronic navigation map and/or observation position information of perception data corresponding to the pose information in a corresponding road image, where the step includes:

for each pose information, determining conversion position information of a map lane line in a vehicle body coordinate system or a road image corresponding to the pose information based on map position information of the map lane line in the electronic navigation map in map semantic data corresponding to the pose information and the pose information, wherein each conversion position information comprises: conversion position information of a plurality of discrete points corresponding to the corresponding map lane lines;

Calculating the distance between every two adjacent discrete points according to the conversion position information of a plurality of discrete points corresponding to each map lane line corresponding to each pose information;

if the difference value between the distance between two adjacent discrete points and the distance between two other adjacent discrete points exceeds the preset difference value in a plurality of discrete points corresponding to the map lane line, determining that the map lane line has a lane line break condition.

Optionally, the sensing data comprises a sensing light pole, and the map semantic data comprises a map light pole; the quality detection result comprises a detection result of the inclination condition of the map lamp post;

for each pose information, determining projection position information of a map light pole in a road image corresponding to the pose information based on the map position information of the map light pole in the electronic navigation map in the map semantic data corresponding to the pose information and the pose information;

And determining whether the map lamp post has an inclination condition or not according to the projection position information of the map lamp post in the road image corresponding to the pose information and the observation position information of the perception lamp post in the corresponding road image in the perception data corresponding to the map lamp post aiming at each map lamp post corresponding to the pose information.

Optionally, the perceived data includes perceived traffic signs, and the map semantic data includes map traffic signs; the quality detection result comprises a detection result of the turning condition of the map traffic sign board;

for each pose information, determining the mapping position information of the map traffic signpost in a vehicle body coordinate system corresponding to the pose information based on the map position information of the map traffic signpost in the electronic navigation map in the map semantic data corresponding to the pose information and the pose information;

For each piece of pose information, determining mapping position information of a perceived traffic sign in a vehicle body coordinate system corresponding to the pose information based on observation position information of the perceived traffic sign in a corresponding road image in perceived data corresponding to the pose information, the pose information and a projection matrix corresponding to the image acquisition equipment;

and determining whether the map traffic signpost has a turnover condition or not according to the map traffic signpost corresponding to each pose information and the mapping position information of the sensing traffic signpost corresponding to the map traffic signpost in the vehicle body coordinate system corresponding to the pose information.

Optionally, the step of determining whether the map traffic sign has a turnover condition based on the mapping position information of the map traffic sign in the vehicle body coordinate system corresponding to the pose information and the mapping position information of the perceived traffic sign corresponding to the map traffic sign in the vehicle body coordinate system corresponding to the pose information includes:

fitting to obtain a first fitting surface corresponding to the map traffic sign based on the mapping position information of the map traffic sign in a vehicle body coordinate system corresponding to the pose information and a preset plane fitting algorithm;

Fitting to obtain a second fitting surface corresponding to the perceived traffic sign board corresponding to the map traffic sign board based on the mapping position information of the perceived traffic sign board corresponding to the map traffic sign board in the vehicle body coordinate system corresponding to the pose information and the preset plane fitting algorithm;

calculating an included angle between a normal vector corresponding to the first fitting surface and a normal vector corresponding to the second fitting surface;

and if the included angle exceeds a preset angle, determining that the map traffic sign board has a turning condition.

Optionally, after the step of determining, for each pose information, a quality detection result of the electronic navigation map based on map position information of map semantic data corresponding to the pose information in the electronic navigation map and/or observation position information of perception data corresponding to the pose information in the corresponding road image, the method further includes:

if the quality detection result of the electronic navigation map indicates that the electronic navigation map has a quality problem, storing an abnormal statistical document and abnormal image information corresponding to the electronic navigation map, wherein the abnormal statistical document at least comprises: the identification of map semantic data with quality problems in the electronic navigation map, the quality types of the map semantic data with quality problems in the electronic navigation map and map position information in the electronic navigation map, and the abnormal image information comprises: image information corresponding to map semantic data having a quality problem.

In a second aspect, an embodiment of the present invention provides an electronic navigation map quality detection apparatus, including:

the first acquisition module is configured to acquire an electronic navigation map to be detected;

the second obtaining module is configured to obtain track information of the vehicle in the running process of the scene corresponding to the electronic navigation map, wherein the track information comprises a plurality of pose information and positioning time corresponding to each pose information;

the third obtaining module is configured to obtain perception data determined by the vehicle in the driving process, wherein each perception data is: the method comprises the steps that data detected from road images acquired by image acquisition equipment of a vehicle are acquired, and the corresponding relation exists between the acquisition time corresponding to each road image and the positioning time corresponding to each pose information;

the first determining module is configured to determine map semantic data corresponding to the pose information from the electronic navigation map according to each piece of pose information;

the second determining module is configured to determine a quality detection result of the electronic navigation map according to the map position information of the map semantic data corresponding to the pose information in the electronic navigation map and/or the observation position information of the perception data corresponding to the pose information in the corresponding road image aiming at each pose information.

the second determining module is specifically configured to determine, for each piece of pose information, projection position information of map semantic data corresponding to the pose information in a road image corresponding to the pose information based on map position information of the map semantic data corresponding to the pose information in the electronic navigation map and the pose information;

The second determining module is specifically configured to determine, for each piece of pose information, mapping position information of a map lane line in a vehicle body coordinate system corresponding to the pose information based on map position information of the map lane line in the electronic navigation map in map semantic data corresponding to the pose information and the pose information;

if the quality detection result includes a detection result of a bending condition of a map lane line, the second determining module is specifically configured to determine, for each pose information, map position information of the map lane line in a vehicle body coordinate system corresponding to the pose information based on map position information of the map lane line in the electronic navigation map in map semantic data corresponding to the pose information and the pose information, where each map position information includes: mapping position information of a plurality of discrete points corresponding to the corresponding map lane lines;

and/or, if the quality detection result includes a detection result of a map lane line breaking situation, the second determining module is specifically configured to determine, for each pose information, conversion position information of the map lane line in a vehicle body coordinate system or a road image corresponding to the pose information based on map position information of the map lane line in the electronic navigation map and the pose information in map semantic data corresponding to the pose information, where each conversion position information includes: conversion position information of a plurality of discrete points corresponding to the corresponding map lane lines;

the second determining module is specifically configured to determine, for each piece of pose information, projection position information of a map light pole in a road image corresponding to the pose information based on map position information of the map light pole in the electronic navigation map in map semantic data corresponding to the pose information and the pose information;

the second determining module is specifically configured to determine, for each piece of pose information, mapping position information of the map traffic sign in a vehicle body coordinate system corresponding to the pose information based on map position information of the map traffic sign in the electronic navigation map in map semantic data corresponding to the pose information and the pose information;

Optionally, the second determining module is specifically configured to obtain a first fitting surface corresponding to the map traffic sign board through fitting based on mapping position information of the map traffic sign board in a vehicle body coordinate system corresponding to the pose information and a preset plane fitting algorithm;

Optionally, the apparatus further includes:

the storage module is configured to store an abnormal statistical document and abnormal image information corresponding to the electronic navigation map after determining a quality detection result of the electronic navigation map based on map position information of map semantic data corresponding to the pose information in the electronic navigation map and/or observation position information of perception data corresponding to the pose information in a corresponding road image for each pose information, wherein the abnormal statistical document at least comprises: the identification of map semantic data with quality problems in the electronic navigation map, the quality types of the map semantic data with quality problems in the electronic navigation map and map position information in the electronic navigation map, and the abnormal image information comprises: image information corresponding to map semantic data having a quality problem.

As can be seen from the above, the method and apparatus for detecting quality of an electronic navigation map according to the embodiments of the present invention can obtain an electronic navigation map to be detected; obtaining track information of a vehicle in a scene running process corresponding to an electronic navigation map, wherein the track information comprises a plurality of pose information and positioning time corresponding to each pose information; obtaining the sensing data determined in the running process of the vehicle, wherein each sensing data is as follows: the method comprises the steps that data identified from road images acquired by image acquisition equipment of a vehicle are corresponding to acquisition time corresponding to each road image and positioning time corresponding to each pose information; for each pose information, determining map semantic data corresponding to the pose information from an electronic navigation map; and determining a quality detection result of the electronic navigation map according to the map position information of the map semantic data corresponding to the pose information in the electronic navigation map and/or the observation position information of the perception data corresponding to the pose information in the corresponding road image aiming at each pose information.

By applying the embodiment of the invention, the map semantic data and the perception data in the electronic navigation map corresponding to each other can be determined based on the positioning moment corresponding to the pose information in the track information of the vehicle in the scene driving process corresponding to the electronic navigation map, and further, each pose information is determined based on the map position information of the map semantic data corresponding to the pose information in the electronic navigation map and/or the observation position information of the perception data corresponding to the pose information in the corresponding road image, so that the quality detection result of the electronic navigation map is determined, and the quality problem of the electronic navigation map is detected. Of course, it is not necessary for any one product or method of practicing the invention to achieve all of the advantages set forth above at the same time.

The innovation points of the embodiment of the invention include:

1. map semantic data and perception data in the electronic navigation map corresponding to each other can be determined based on the positioning moment corresponding to the pose information in the track information of the vehicle in the scene driving process corresponding to the electronic navigation map, and further, each pose information is determined based on the map position information of the map semantic data corresponding to the pose information in the electronic navigation map and/or the observation position information of the perception data corresponding to the pose information in the corresponding road image, so that the quality detection result of the electronic navigation map is determined, and the quality problem of the electronic navigation map is detected.

2. Based on the projection position information of each map semantic data in the electronic navigation map in the corresponding image and the observation position information of the corresponding perception data in the road image, whether the position of each map semantic data in the electronic navigation map has deviation can be determined.

3. If the sensing data contains sensing lane lines, mapping the map lane lines from the electronic navigation map to a vehicle body coordinate system of the vehicle, mapping the sensing lane lines corresponding to the map lane lines from the road image to the vehicle body coordinate system of the vehicle, and further determining whether the map lane lines have position deviation from different angles based on the mapping position information of the map lane lines in the vehicle body coordinate system and the mapping position information of the sensing lane lines corresponding to the map lane lines in the vehicle body coordinate system, so as to realize the detection of the position deviation condition of the map lane lines in a refined manner.

4. If a sensing lane line exists in the sensing data, mapping the map lane line from the electronic navigation map to a vehicle body coordinate system of the vehicle, fitting to obtain a lane line fitting line corresponding to the map lane line based on mapping position information of a plurality of discrete points corresponding to the map lane line, determining a distance variance corresponding to the map lane line based on the mapping position information of the plurality of discrete points corresponding to the map lane line and the lane line fitting line, determining whether the map lane line has a lane line bending condition based on the distance variance, and/or calculating the distance between every two adjacent discrete points based on conversion position information of the plurality of discrete points corresponding to the map lane line in the vehicle body coordinate system or a road image, and determining whether the map lane line has a lane line breaking condition based on the distance between every two adjacent discrete points, thereby realizing the detection of the lane line bending condition and/or the lane line breaking condition of the map lane line in the electronic navigation map.

5. If the sensing data comprises the sensing lamp post, projecting the map lamp post into an image corresponding to the sensing lamp post corresponding to the map lamp post, and detecting the inclination condition of the map lamp post in the electronic navigation map based on the projection position information of the map lamp post in the road image and the observation position information of the sensing lamp post corresponding to the map lamp post in the road image.

6. If the sensing data comprises the sensing traffic signboards, mapping the map traffic signboards in the map semantic data into a vehicle body coordinate system of the vehicle, and mapping the sensing traffic signboards corresponding to the map traffic signboards into the vehicle body coordinate system, and further, based on the mapping position information of the map traffic signboards in the vehicle body coordinate system and the mapping position information of the sensing traffic signboards corresponding to the map traffic signboards in the vehicle body coordinate system, detecting the turning condition of the map traffic signboards in the electronic navigation map.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It is apparent that the drawings in the following description are only some embodiments of the invention. Other figures may be derived from these figures without inventive effort for a person of ordinary skill in the art.

Fig. 1 is a schematic flow chart of a method for detecting quality of an electronic navigation map according to an embodiment of the present invention;

fig. 2 is a schematic flow chart of another method for detecting quality of an electronic navigation map according to an embodiment of the present invention;

Fig. 3 is a schematic structural diagram of an electronic navigation map quality detection device according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without any inventive effort, are intended to be within the scope of the invention.

It should be noted that the terms "comprising" and "having" and any variations thereof in the embodiments of the present invention and the accompanying drawings are intended to cover non-exclusive inclusions. A process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed but may alternatively include other steps or elements not listed or inherent to such process, method, article, or apparatus.

The invention provides a method and a device for detecting the quality of an electronic navigation map, which are used for detecting the quality problem of the electronic navigation map. The following describes embodiments of the present invention in detail.

Fig. 1 is a schematic flow chart of a method for detecting quality of an electronic navigation map according to an embodiment of the present invention. The method may comprise the steps of:

s101: and obtaining the electronic navigation map to be detected.

In the embodiment of the invention, the method can be applied to any type of electronic equipment with computing capability, and the electronic equipment can be a server or terminal equipment. The electronic device may be mounted in the vehicle, may be an in-vehicle device, or may not be mounted in the vehicle, and may be an off-vehicle device.

In this step, the electronic device may obtain an electronic navigation map to be detected, where the electronic navigation map may be any type of electronic map, and the electronic navigation map includes map semantic data, where the map semantic data may include: representing semantic information of lane lines, lamp posts, traffic signs and the like included in a scene corresponding to the electronic navigation map, wherein the semantic information can be: and the information representing the shapes, the sizes and the types of the corresponding lane lines, the lamp poles and the traffic signs and the positions of the traffic signs in the scenes corresponding to the electronic navigation map.

In the embodiment of the invention, the semantic information representing the lane lines included in the scene corresponding to the electronic navigation map and included in the map semantic data can be called as map lane lines, the semantic information representing the street lamp poles included in the scene corresponding to the electronic navigation map can be called as map street lamp poles, and the semantic information representing the traffic signboards included in the scene corresponding to the electronic navigation map can be called as map traffic signboards. The electronic navigation map further comprises map identifications corresponding to the semantic data of each map, wherein the map identifications can be identified through serial numbers or letters, and the electronic navigation map has uniqueness, so that workers can accurately position the semantic data of each map in the electronic navigation map.

S102: and obtaining track information of the vehicle in the running process of the scene corresponding to the electronic navigation map.

The track information comprises a plurality of pose information and positioning time corresponding to each pose information.

In the embodiment of the invention, the electronic navigation map quality detection flow provided by the embodiment of the invention can be executed after the vehicle runs correspondingly in the scene corresponding to the electronic navigation map. The track information obtained by the electronic device may be: track information generated in the whole or partial running process of the vehicle in the corresponding scene of the electronic navigation map. The track information includes: and the pose information of the vehicle is acquired at each moment in the whole or partial running process of the vehicle in the corresponding scene of the electronic navigation map.

The electronic navigation map quality detection flow provided by the embodiment of the invention may be executed when the vehicle is traveling in a scene corresponding to the electronic navigation map, and at this time, the track information may be track information generated at a time before a current time in the scene traveling corresponding to the electronic navigation map, that is, the track information includes: pose information of the vehicle, which is generated at a time before the current time in the running process of the scene corresponding to the electronic navigation map, is generated by the vehicle.

In one implementation manner, the plurality of pose information may be pose information measured by pose determining devices such as an inertial navigation system, a global positioning system and/or a high-precision inertial navigation device, which are provided by a vehicle, and the embodiment of the invention does not limit the obtaining manner of the plurality of pose information included in the track information of the vehicle in the driving process of the scene corresponding to the electronic navigation map, and any obtaining manner of the plurality of pose information included in the track information of the vehicle in the driving process of the scene corresponding to the electronic navigation map in the related art may be applied to the embodiment of the invention. Among them, the high-precision inertial navigation device includes high-precision inertial navigation devices such as a fiber optic gyroscope, an acceleration sensor, and the like.

S103: and obtaining the perception data determined by the vehicle in the driving process.

Wherein each perceived data is: the corresponding relation exists between the acquisition time corresponding to each road image and the positioning time corresponding to each pose information of the data detected from the road image acquired by the image acquisition equipment of the vehicle.

In this step, in the driving process of the scene corresponding to the electronic navigation map, the image acquisition device set by the vehicle may capture the environment where the vehicle is located in the driving process, acquire road images, and further, may detect the perception data in each road image through a target detection model based on deep learning, where the perception data may include information such as a shape, a type, and a size of a target included in the representation road image, and the target may include a lane line, a light pole, a traffic sign board, and the like. The target detection model may be a model obtained by training based on a sample image labeled with a target, wherein the training process of the model may be referred to as a model training process in the related art, and will not be described herein.

In the embodiment of the invention, the electronic equipment can directly obtain the perceived data identified by other equipment from the road image; or the electronic equipment can directly obtain road images acquired by the image acquisition equipment of the vehicle in the running process of the scene corresponding to the electronic navigation map, and further detect the perception data in each road image based on the target detection model of the deep learning, which is all possible.

The information of the lane lines in the representation image included in the perception data detected from the road image can be called as the perception lane lines, and the information of the lamp posts in the representation image included in the perception data detected from the road image can be called as the perception lamp posts; the information representing the traffic sign in the image included in the perceived data detected from the road image is referred to as perceived traffic sign.

S104: and determining map semantic data corresponding to the pose information from the electronic navigation map according to each piece of pose information.

It can be understood that each piece of pose information of the vehicle in the running process of the scene corresponding to the electronic navigation map can represent the position and the pose of the vehicle in the scene corresponding to the electronic navigation map, and correspondingly, each piece of pose information corresponds to a position and a pose in the electronic navigation map. The electronic equipment can determine the map area of the electronic navigation map corresponding to the pose information from the electronic navigation map through each pose information, and further, for each pose information, the map semantic data corresponding to the pose information is determined based on the map area corresponding to the pose information.

S105: for each pose information, determining a quality detection result of the electronic navigation map based on map position information of map semantic data corresponding to the pose information in the electronic navigation map and/or observation position information of perception data corresponding to the pose information in a corresponding road image.

In this step, for each pose information, corresponding perception data and corresponding map semantic data in the electronic navigation map may be determined, where a correspondence exists between the perception data and the map semantic data. Based on the observation position information of the perception data with the corresponding relation in the road image corresponding to the pose information and/or the map position information of the map semantic data in the electronic navigation map, determining the detection result of the map semantic data in the electronic navigation map, and based on the detection result of the map semantic data in the electronic navigation map, determining the quality detection result of the electronic navigation map. For the sake of clarity of layout, a detailed description will be given of a process of determining a quality detection result of the electronic navigation map.

In the embodiment of the invention, after the quality detection result of the electronic navigation map is determined, the quality detection result can be stored so as to facilitate the subsequent staff to check the quality detection result of the electronic navigation map and correct the electronic navigation map based on the quality detection result.

By applying the embodiment of the invention, the map semantic data and the perception data in the electronic navigation map corresponding to each other can be determined based on the positioning moment corresponding to the pose information in the track information of the vehicle in the scene driving process corresponding to the electronic navigation map, and further, each pose information is determined based on the map position information of the map semantic data corresponding to the pose information in the electronic navigation map and/or the observation position information of the perception data corresponding to the pose information in the corresponding road image, so that the quality detection result of the electronic navigation map is determined, and the quality problem of the electronic navigation map is detected.

In another embodiment of the present invention, the quality detection result includes a detection result of a position deviation condition of each map semantic data; as shown in fig. 2, the step S105 may include:

s201: and determining projection position information of the map semantic data in the road image corresponding to the pose information according to the map position information of the map semantic data corresponding to the pose information in the electronic navigation map and the pose information aiming at each piece of pose information.

S202: and determining a position deviation value between the map semantic data and the corresponding perception data based on the projection position information of the map semantic data in the road image corresponding to the pose information and the observation position information of the perception data corresponding to the map semantic data in the road image.

S203: and judging whether the position deviation value exceeds a preset distance threshold value.

S204: if the judgment result is that the position deviation value exceeds the preset distance threshold, determining that the position deviation condition exists in the map semantic data in the electronic navigation map.

In the embodiment of the invention, whether the position information of each map semantic data in the electronic navigation map is accurate can be detected, and the quality detection result of the electronic navigation map is determined based on the accurate detection result of the position information of each map semantic data.

The electronic device can determine whether map position information of map semantic data corresponding to pose information in the electronic navigation map is accurate according to each pose information, wherein for convenience of description, the map position information of the map semantic data in the electronic navigation map can be called as map position information, and the position information of perception data in a corresponding road image can be called as perception position information.

In one implementation manner, for each piece of pose information, the electronic device may determine, according to the pose information and the pose information preceding the pose information, a pose change between the pose information and the pose information preceding the pose information; obtaining position information of perception data corresponding to the pose information in a road image corresponding to the pose information before the pose information; and determining depth information of the perceived data based on the pose change between the pose information and the pose information before the pose information and the position information of the perceived data corresponding to the pose information in the road image corresponding to the pose information before the pose information by using a triangulation algorithm, and obtaining the depth information of the perceived data, namely the depth information of the map semantic data corresponding to the perceived data. The depth information represents distance information between the sensing data and the image acquisition device of the vehicle, and can be considered as distance information between the sensing data and the vehicle, namely, distance information between map semantic data corresponding to the sensing data and the image acquisition device of the vehicle, and can be considered as distance information between map semantic data corresponding to the sensing data and the vehicle. And the electronic equipment calculates the projection position information of the map semantic data in the road image corresponding to the pose information based on the pose information, the map position information of the map semantic data corresponding to the pose information in the electronic navigation map and the depth information of the map semantic data.

Alternatively, it may be: the vehicle is provided with a laser sensor, depth information of map semantic data corresponding to sensing data, namely sensing data, can be acquired through the laser sensor, the electronic equipment obtains the depth information of the map semantic data corresponding to the sensing data acquired by the laser sensor, and projection position information of the map semantic data in a road image corresponding to the pose information is calculated based on the pose information, map position information of the map semantic data corresponding to the pose information in an electronic navigation map and the depth information of the map semantic data.

The process of calculating the projection position information of the map semantic data in the road image corresponding to the pose information based on the pose information, the map position information of the map semantic data corresponding to the pose information in the electronic navigation map and the depth information of the map semantic data may be: converting map semantic data corresponding to pose information from a map coordinate system to an equipment coordinate system based on a first conversion relation between the map coordinate system corresponding to the electronic navigation map and the equipment coordinate system of the image acquisition equipment corresponding to the road image corresponding to the pose information, namely determining the position information of the map semantic data corresponding to the pose information in the equipment coordinate system based on the first conversion relation and the map position information of the map semantic data corresponding to the pose information in the electronic navigation map; and determining and obtaining projection position information of the map semantic data corresponding to the pose information in the road image corresponding to the pose information based on the position information of the map semantic data corresponding to the pose information in the equipment coordinate system, the depth information of the map semantic data and a second conversion relation between the image coordinate system corresponding to the road image corresponding to the pose information and the equipment coordinate system.

The second conversion relation between the image coordinate system corresponding to the road image and the equipment coordinate system is as follows: the conversion relation calibrated for the image acquisition equipment is determined in advance, and the second conversion relation is determined. The first conversion relationship may be determined by the pose information based on a first conversion relationship between a map coordinate system corresponding to the electronic navigation map and a device coordinate system of an image acquisition device corresponding to a road image corresponding to the pose information.

In this case, the above-mentioned pose information is determined by the pose determining device of the vehicle, and the pose information is pose information describing the pose determining device of the vehicle, that is, in the embodiment of the present invention, the pose information describing the pose of the pose determining device of the vehicle is taken as the pose information describing the vehicle. In order to improve accuracy of quality detection results of the electronic navigation map to a certain extent, before S201, pose information of the image acquisition devices can be determined based on a conversion relation between a coordinate system where the pose determination devices are located and a device coordinate system of the image acquisition devices and pose information of the pose determination devices, and then, for the pose information of each image acquisition device, projection position information of map semantic data in a road image corresponding to the pose information of the image acquisition devices is determined based on map position information of map semantic data corresponding to the pose information of the image acquisition devices in the electronic navigation map and the pose information of the image acquisition devices; and performs the subsequent steps.

When the image acquisition device is arranged in the vehicle, the relative position relation between the image acquisition device and the vehicle and the relative position relation between the image acquisition device and the pose determining device arranged in the vehicle can be fixed, and the relative position relation between the image acquisition device and the vehicle and the relative position relation between the image acquisition device and the pose determining device arranged in the vehicle can be obtained through calibration by a position relation calibration mode in the related technology.

In one case, the map semantic data corresponding to each pose information may include at least one map semantic data, for example, may include at least one map lane line, at least one map light pole, and/or at least one map traffic sign, etc.; the sensory data corresponding to the pose information may include a plurality of at least one sensory data, for example, may include at least one sensory lane line, at least one sensory light pole, and/or at least one sensory traffic sign, etc. For each pose information, each map semantic data has a one-to-one correspondence with the perception data. Correspondingly, the electronic device may calculate, for each map semantic data corresponding to each pose information, a distance corresponding to the map semantic data and the corresponding perception data based on projection position information of the map semantic data in the road image corresponding to the pose information and observation position information of the perception data corresponding to the map semantic data in the road image, where the distance is a position deviation value between the map semantic data and the corresponding perception data.

And comparing the position deviation value between the map semantic data and the corresponding sensing target with a preset distance threshold value for each map semantic data corresponding to each pose information, judging whether the position deviation value between the map semantic data and the corresponding sensing data exceeds the preset distance threshold value, if so, determining that the projection position information of the map semantic data in the road image corresponding to the pose information is too large in distance from the observation position information of the corresponding sensing data in the road image, and further determining that the position deviation condition exists in the position of the map semantic data in the electronic navigation map.

In this case, when it is determined that there is a position deviation in the position of at least one map semantic data in the electronic navigation map for each map semantic data corresponding to each pose information, it may be further determined that the electronic navigation map has a quality problem. The quality detection result corresponding to the electronic navigation map includes information representing that the map semantic data has a position deviation, wherein it can be understood that, in order to ensure that a worker can quickly locate which map lane lines in the electronic navigation map have problems, a map identifier corresponding to the map semantic data with the position deviation and map position information of the map semantic data in the electronic navigation map can be recorded correspondingly.

In another implementation manner of the present invention, if the determination result is that the position deviation values corresponding to all map semantic data in the electronic navigation map do not exceed the preset distance threshold, it may be determined that the map semantic data in the electronic navigation map has no position deviation.

In another embodiment of the invention, the perceived data comprises perceived lane lines and the map semantic data comprises map lane lines; the quality detection result comprises a detection result of position deviation of the map lane line in the elevation direction; the S105 may include: for each piece of pose information, determining the mapping position information of the map lane line in a vehicle body coordinate system corresponding to the pose information based on the map position information of the map lane line in the electronic navigation map in the map semantic data corresponding to the pose information and the pose information;

for each piece of pose information, determining mapping position information of a sensing lane line in a vehicle body coordinate system corresponding to the pose information based on observation position information of the sensing lane line in a corresponding road image in sensing data corresponding to the pose information, the pose information and a projection matrix corresponding to image acquisition equipment; wherein the projection matrix is the second conversion relation;

Determining whether a position deviation condition exists in the transverse axis direction and the longitudinal axis direction of the vehicle body coordinate system of each map lane line corresponding to each pose information based on the mapping position information of the map lane line in the vehicle body coordinate system corresponding to the pose information and the mapping position information of the sensing lane line corresponding to the map lane line in the vehicle body coordinate system corresponding to the pose information;

Wherein, the car body coordinate system: the wheel speed coordinate system is also called as a wheel speed coordinate system, and can take the midpoint of the connecting line of the centers of the two rear wheels of the vehicle as the center, namely the origin; observing in the direction from the tail to the head, wherein the direction from left to right is the direction of the transverse axis of a vehicle body coordinate system; the direction from back to front is the direction of the longitudinal axis of the vehicle body coordinate system; from bottom to top is the direction of the vertical axis of the vehicle body coordinate system. The elevation direction may be referred to as a vertical axis direction of a vehicle body coordinate system, a horizontal axis direction of the vehicle body coordinate system may be referred to as a left-right direction of the vehicle, and a vertical axis direction of the vehicle body coordinate system may be referred to as a front-rear direction of the vehicle.

In the implementation manner, the sensing data comprises the sensing lane lines, and under the condition that the map semantic data comprises the map lane lines, whether the map lane lines in the electronic navigation map have position deviation conditions or not can be determined in a finer mode, and the position deviation conditions in which direction are determined, so that quality detection results with finer results are obtained, and subsequent correction of the electronic navigation map by workers is facilitated.

Aiming at each pose information, the electronic equipment determines a vehicle body coordinate system corresponding to the pose information based on the pose information; further, determining a conversion relation between a vehicle body coordinate system corresponding to the pose information and the electronic navigation map as a third conversion relation; and determining the mapping position information of the map lane lines in the map semantic data corresponding to the pose information in a vehicle body coordinate system corresponding to the pose information based on the third conversion relation and the map position information of the map lane lines in the map semantic data corresponding to the pose information in the electronic navigation map.

Determining, for each piece of pose information, pose change between the pose information and the previous pose information of the pose information according to the pose information and the previous pose information of the pose information; obtaining the position information of a perceived lane line corresponding to the pose information in a road image corresponding to the pose information before the pose information; and determining depth information of the perceived lane line based on the pose change between the pose information and the pose information before the pose information and the position information of the perceived lane line corresponding to the pose information in the road image corresponding to the pose information before the pose information by using a triangulation algorithm. Alternatively, it may be: the vehicle is provided with a laser sensor, the depth information of the sensing lane line can be acquired through the laser sensor, and the electronic equipment obtains the depth information of the sensing lane line acquired by the laser sensor.

The depth information characterizes distance information between the perceived lane and the image acquisition device of the vehicle, and can also be regarded as distance information between the perceived lane and the vehicle.

The electronic equipment calculates equipment position information of an equipment coordinate system corresponding to the road image corresponding to the pose information based on the pose information, the observation position information of the perception lane line corresponding to the pose information in the corresponding road image and the depth information of the perception data. And determining mapping position information of the perceived lane line in the vehicle body coordinate system corresponding to the pose information based on the conversion relation between the device coordinate system corresponding to the road image corresponding to the pose information and the vehicle body coordinate system and the device position information of the perceived lane line in the device coordinate system corresponding to the road image corresponding to the pose information.

In one implementation, each map lane line in each map semantic data in the electronic navigation map may include a series of discrete points, and the mapping position information of each map lane line in the vehicle body coordinate system corresponding to the pose information includes: mapping position information of a plurality of discrete points corresponding to the map lane lines.

Correspondingly, the electronic device may calculate, for each discrete point included in each map lane line corresponding to each pose information, an error sub-vector between the discrete point and a perceived lane line corresponding to the map lane line based on mapping position information of the discrete point and mapping position information of the perceived lane line corresponding to the map lane line in a vehicle body coordinate system corresponding to the pose information, where a magnitude of a modulus of the error sub-vector between the discrete point and the perceived lane line corresponding to the map lane line: and the direction of the error sub-vector between the discrete point and the sensing lane line corresponding to the map lane line points to the discrete point.

Subsequently, the electronic device determines an error vector between each map lane line corresponding to each pose information and a perceived lane line corresponding to the map lane line based on an error sub-vector between each discrete point included in each map lane line corresponding to each pose information and the perceived lane line corresponding to the map lane line, and the error vector is used as the error vector corresponding to each map lane line.

Wherein, each pose information corresponds to the magnitude of the modulus of the error vector between each map lane line and the perception lane line corresponding to the map lane line: the average value of the modes of the error sub-vectors between each discrete point included in the map lane line and the sensing lane line corresponding to the map lane line is equal to the average value of the modes of the error sub-vectors between each map lane line and the sensing lane line corresponding to the map lane line, and the direction of the error vector between each map lane line and the sensing lane line corresponding to the map lane line is as follows: the direction of any one of the error sub-vectors between each discrete point included in the map lane line and the perceived lane line corresponding to the map lane line is specified. The specified error sub-vector may be an error sub-vector corresponding to a discrete point located at a middle position included in the map lane line.

The electronic equipment determines an error vector component of the error vector corresponding to the map lane line in the transverse axis direction of the vehicle body coordinate system corresponding to the pose information and an error vector component of the error vector corresponding to the pose information in the longitudinal axis direction of the vehicle body coordinate system corresponding to the pose information according to each map lane line corresponding to each pose information based on the error vector corresponding to the map lane line; and respectively calculating the modulus of the error vector component of the error vector corresponding to the map lane line in the transverse axis direction of the vehicle body coordinate system corresponding to the pose information and the modulus of the error vector component in the longitudinal axis direction of the vehicle body coordinate system corresponding to the pose information.

Judging whether the modulus of the error vector component of the error vector corresponding to the map lane line in the transverse axis direction of the vehicle body coordinate system corresponding to the pose information exceeds a first numerical value, if the modulus of the error vector component of the error vector corresponding to the map lane line in the transverse axis direction of the vehicle body coordinate system corresponding to the pose information does not exceed first data, determining that the map lane line has no position deviation in the transverse axis direction of the vehicle body coordinate system, otherwise, if the modulus of the error vector component of the error vector corresponding to the map lane line in the transverse axis direction of the vehicle body coordinate system corresponding to the pose information exceeds first data, determining that the map lane line has position deviation in the transverse axis direction of the vehicle body coordinate system.

Judging whether the modulus of the error vector component of the error vector corresponding to the map lane line in the longitudinal axis direction of the vehicle body coordinate system corresponding to the pose information exceeds a second numerical value, if the modulus of the error vector component of the error vector corresponding to the map lane line in the longitudinal axis direction of the vehicle body coordinate system corresponding to the pose information does not exceed second data, determining that the map lane line has no position deviation in the longitudinal axis direction of the vehicle body coordinate system, otherwise, if the modulus of the error vector component of the error vector corresponding to the map lane line in the longitudinal axis direction of the vehicle body coordinate system corresponding to the pose information exceeds first data, determining that the map lane line has position deviation in the longitudinal axis direction of the vehicle body coordinate system.

The first value and the second value may be values set according to actual conditions, and may be equal or different.

The electronic equipment can continue to project the map lane line in the map semantic data corresponding to the pose information into the road image corresponding to the pose information according to each pose information when determining that the map lane line does not have position deviation in the directions of the horizontal axis and the vertical axis of the vehicle body coordinate system, namely, based on the map position information and the pose information of the map lane line in the map semantic data corresponding to the pose information in the electronic navigation map, determining the projection position information of the map lane line in the road image corresponding to the pose information, and further, for each map lane line corresponding to each pose information, determining whether the map lane line has position deviation in the elevation direction based on the projection position information of the map lane line in the road image corresponding to the pose information and the observation position information of the perception lane line in the perception data corresponding to the map lane line in the road image.

In one implementation, after determining that the map lane line has a position deviation in the horizontal axis direction and/or the vertical axis direction of the vehicle body coordinate system, the electronic device may not perform the subsequent step of determining whether the map lane line has a position deviation in the vertical axis direction, that is, the elevation direction of the vehicle body coordinate system.

In one case, the mapping position information of the perceived lane line corresponding to each map lane line in the vehicle body coordinate system corresponding to the pose information may include mapping position information of a plurality of discrete points corresponding to the perceived lane line. Correspondingly, the process of calculating the error sub-vector between each discrete point and the perceived lane corresponding to the map lane by the electronic device according to the mapping position information of the discrete point and the mapping position information of the perceived lane corresponding to the map lane in the vehicle body coordinate system corresponding to the pose information, for each discrete point included in each map lane corresponding to each pose information, may be:

traversing projection points of a plurality of discrete points contained in a sensing lane line corresponding to a map lane line in a vehicle body coordinate system corresponding to the pose information, determining two projection points closest to the discrete point from projection points of the plurality of discrete points contained in the sensing lane line corresponding to the map lane line in the vehicle body coordinate system corresponding to the pose information, calculating an error sub-vector between the discrete point and a connecting line of the two projection points closest to the discrete point, and taking the error sub-vector between the discrete point and the connecting line of the two projection points closest to the discrete point as the error sub-vector between the discrete point and the sensing lane line corresponding to the map lane line.

Furthermore, the quality detection result corresponding to the electronic navigation map includes information indicating that the map lane has a position deviation condition in the elevation direction or a position deviation condition in the left-right direction of the vehicle or a position deviation condition in the front-rear direction of the vehicle, where it can be understood that, in order to ensure that a worker can quickly locate which map lane in the electronic navigation map has a problem, a map identifier corresponding to the map lane having the problem and map position information of the map lane in the electronic navigation map can be recorded correspondingly.

In another embodiment of the invention, the perceived data comprises perceived lane lines and the map semantic data comprises map lane lines; the quality detection results comprise detection results of the bending condition and/or the breaking condition of the map lane lines.

In one implementation manner, if the quality detection result includes a detection result of a curve condition of the map lane line, the step S105 may include:

for each piece of pose information, based on the map position information of the map lane line in the electronic navigation map in the map semantic data corresponding to the pose information and the pose information, determining the map position information of the map lane line in a vehicle body coordinate system corresponding to the pose information, wherein each piece of map position information comprises: mapping position information of a plurality of discrete points corresponding to the corresponding map lane lines;

and if the distance variance exceeds a preset variance threshold, determining that the lane line of the map has a lane line bending condition.

The embodiment of the invention can also detect whether the lane line in the electronic navigation map is bent or not, and the quality detection result comprises a detection result of the lane line bending condition.

In one implementation, each map lane line in each map semantic data in the electronic navigation map may include a series of discrete points, theoretically, uniformly distributed among the series of discrete points included in each map lane line and distributed along a straight line. In the embodiment of the invention, the electronic equipment can map a series of discrete points included in the map lane line into a vehicle body coordinate system corresponding to pose information for each map lane line corresponding to the pose information to obtain the mapping position information of the series of discrete points included in the map lane line in the vehicle body coordinate system corresponding to the pose information, and fit the map lane line into a lane line fitting line corresponding to the map lane line in the vehicle body coordinate system corresponding to the pose information based on the mapping position information of the series of discrete points included in each map lane line in the vehicle body coordinate system corresponding to the pose information and a preset fitting algorithm. The preset fitting algorithm may be any type of linear fitting method such as a least square linear fitting method.

In theory, how each map lane line does not have a bending condition, the distance variance between a series of discrete points included in each map lane line and a lane line fitting line corresponding to the map lane line in a vehicle body coordinate system corresponding to the pose information is not large.

In view of this, the electronic device calculates, for each map lane corresponding to each pose information, the square of the distance between each discrete point corresponding to the map lane and the lane fitting line corresponding to the map lane based on the lane fitting line corresponding to the map lane and the mapping position information of the plurality of discrete points corresponding to the map lane, respectively, and further calculates the sum of the squares of the distances between each discrete point corresponding to the map lane and the lane fitting line corresponding to the map lane as the distance variance corresponding to the map lane, and determines whether the distance variance exceeds the preset variance threshold, and if the distance variance exceeds the preset variance threshold, determines that the map lane has a lane bending condition. And if the distance variance does not exceed the preset variance threshold, determining that the lane line bending condition of the map lane line does not exist. The preset variance threshold is a value set according to the situation.

In one implementation manner, if the quality detection result includes a detection result of a map lane line break condition, the step S105 may include: for each pose information, determining conversion position information of a map lane line in a vehicle body coordinate system or a road image corresponding to the pose information based on the map position information of the map lane line in the electronic navigation map in map semantic data corresponding to the pose information and the pose information, wherein each conversion position information comprises: conversion position information of a plurality of discrete points corresponding to the corresponding map lane lines;

In one implementation, each map lane line in each map semantic data in the electronic navigation map may include a series of discrete points, theoretically, uniformly distributed among the series of discrete points included in each map lane line and distributed along a straight line. In one case, the electronic device may map, for each map lane line corresponding to each pose information, a series of discrete points included in the map lane line to a vehicle body coordinate system corresponding to the pose information, so as to obtain mapping position information of the series of discrete points included in the map lane line in the vehicle body coordinate system corresponding to the pose information. Or, the electronic device may project, for each map lane line corresponding to each pose information, a series of discrete points included in the map lane line into a road image corresponding to the pose information, so as to obtain projection position information of the series of discrete points included in the map lane line in the road image corresponding to the pose information. In the embodiment of the invention, the mapping position information of a series of discrete points included in the map lane line in the vehicle body coordinate system corresponding to the pose information and the projection position information of a series of discrete points included in the map lane line in the road image corresponding to the pose information can be called as conversion position information.

Furthermore, the electronic device calculates the distance between every two adjacent discrete points based on the conversion position information of the plurality of discrete points corresponding to the map lane lines for each map lane line corresponding to each pose information, and compares the distance between every two adjacent discrete points. In view of this, if the difference between the distance between two adjacent discrete points and the distance between two other adjacent discrete points exceeds the preset difference in the plurality of discrete points corresponding to the map lane line, it may be determined that the series of discrete points included in the map lane line in the electronic navigation map are unevenly distributed, and further, it is determined that the map lane line has a lane line break condition.

Furthermore, the quality detection result corresponding to the electronic navigation map includes information representing the situation that the map lane line has a broken lane line, wherein it can be understood that, in order to ensure that a worker can quickly locate which map lane lines in the electronic navigation map have problems, the map identifier corresponding to the map lane line with the broken lane line and the map position information of the map lane line in the electronic navigation map can be recorded correspondingly.

In another embodiment of the invention, the perceived data comprises perceived light poles and the map semantic data comprises map light poles; the quality detection result comprises a detection result of the inclination condition of the map lamp post; the S105 may include:

In this implementation, if the perceived data includes a perceived light pole, the map semantic data includes a map light pole, and the electronic device needs to detect whether the map light pole has a tilting condition. In the detection process, the electronic equipment can project the map light pole in the map semantic data corresponding to the pose information into the road image corresponding to the pose information according to each pose information, namely, based on the map position information of the map light pole in the map semantic data corresponding to the pose information in the electronic navigation map and the pose information, the projection position information of the map light pole in the road image corresponding to the pose information is determined; and determining the observation position information of the perceived lamp post corresponding to each map lamp post in the corresponding road image, namely the road image corresponding to the pose information, aiming at each map lamp post corresponding to each pose information, calculating an included angle between the map lamp post and the perceived lamp post based on the projection position information of the map lamp post in the road image corresponding to the pose information and the observation position information of the perceived lamp post corresponding to the map lamp post in the road image corresponding to the pose information, and determining whether the map lamp post has an inclination condition based on the included angle.

In one case, the electronic device may determine, for each map light pole corresponding to each pose information, whether an included angle between the map light pole and the sensing light pole exceeds a preset included angle, determine that the map light pole has a tilting condition if the determined result is that the included angle exceeds the preset included angle, and determine that the map light pole does not have the tilting condition if the determined result is that the included angle does not exceed the preset included angle.

And if the inclination condition of the map lamp post is determined, the quality detection result corresponding to the electronic navigation map comprises information representing the inclination condition of the map lamp post. It can be understood that, in order to ensure that a worker can quickly locate which map lamp posts in the electronic navigation map have problems, a map identifier corresponding to the map lamp post with an inclined condition and map position information of the map lamp post in the electronic navigation map can be correspondingly recorded.

In another embodiment of the invention, the perceived data comprises perceived traffic signs and the map semantic data comprises map traffic signs; the quality detection result comprises a detection result of the turning condition of the map traffic sign board;

The S105 may include: for each pose information, determining the mapping position information of the map traffic signpost in a vehicle body coordinate system corresponding to the pose information based on the map position information of the map traffic signpost in the electronic navigation map in the map semantic data corresponding to the pose information and the pose information;

for each piece of pose information, determining mapping position information of a perceived traffic sign in a vehicle body coordinate system corresponding to the pose information based on observation position information of the perceived traffic sign in a corresponding road image in perceived data corresponding to the pose information, the pose information and a projection matrix corresponding to image acquisition equipment;

In this implementation, if the perceived data includes a perceived traffic sign, the map semantic data includes a map traffic sign, and the electronic device needs to detect whether the map traffic sign has a rollover condition. In the detection process, the electronic equipment maps map traffic signboards in the electronic navigation map and perceived map traffic signboards corresponding to the map traffic signboards into a vehicle body coordinate system so as to determine whether the map traffic signboards are overturned or not through a space coordinate system.

Specifically, for each pose information, the electronic equipment maps the map traffic signpost to a vehicle body coordinate system corresponding to the pose information based on the map position information of the map traffic signpost in the electronic navigation map in the map semantic data corresponding to the pose information and the pose information, and determines the mapping position information of the map traffic signpost in the vehicle body coordinate system corresponding to the pose information; for each pose information, mapping the perceived traffic signpost corresponding to the map traffic signpost to a vehicle body coordinate system corresponding to the pose information based on the observed position information of the perceived traffic signpost in the corresponding road image in the perceived data corresponding to the pose information, the pose information and a projection matrix corresponding to the image acquisition equipment, and determining the mapping position information of the perceived traffic signpost in the vehicle body coordinate system corresponding to the pose information; the projection matrix corresponding to the image acquisition device is the second conversion relation. Further, based on the map traffic sign corresponding to each pose information, whether the map traffic sign has a turning condition is determined based on the mapping position information of the map traffic sign in the vehicle body coordinate system corresponding to the pose information and the mapping position information of the perceived traffic sign corresponding to the map traffic sign in the vehicle body coordinate system corresponding to the pose information.

The process of mapping the map traffic sign to the vehicle body coordinate system corresponding to the pose information may refer to the process of mapping the map lane line to the vehicle body coordinate system corresponding to the pose information, and the process of mapping the perceived traffic sign corresponding to the map traffic sign to the vehicle body coordinate system corresponding to the pose information may refer to the process of mapping the perceived lane line corresponding to the map lane line to the vehicle body coordinate system corresponding to the pose information, which will not be described herein.

In an embodiment of the present invention, the step of determining whether the map traffic sign has a rollover condition based on the mapping position information of the map traffic sign in the vehicle body coordinate system corresponding to the pose information and the mapping position information of the perceived traffic sign corresponding to the map traffic sign in the vehicle body coordinate system corresponding to the pose information may include:

fitting to obtain a second fitting surface corresponding to the perceived traffic sign board corresponding to the map traffic sign board based on the mapping position information of the perceived traffic sign board corresponding to the map traffic sign board in the vehicle body coordinate system corresponding to the pose information and a preset plane fitting algorithm;

if the included angle exceeds the preset angle, determining that the map traffic sign board has a turnover condition.

In this implementation manner, the electronic device may obtain, by fitting, a first fitting surface corresponding to the map traffic sign board based on mapping position information of the map traffic sign board in a vehicle body coordinate system corresponding to the pose information and a preset plane fitting algorithm, and obtain, by fitting, a second fitting surface corresponding to the perceived traffic sign board corresponding to the map traffic sign board based on mapping position information of the perceived traffic sign board corresponding to the map traffic sign board in the vehicle body coordinate system corresponding to the pose information and the preset plane fitting algorithm. Further, determining normal vectors of the first fitting surface and normal vectors of the second fitting surface, and calculating an included angle between the normal vectors corresponding to the first fitting surface and the normal vectors corresponding to the second fitting surface; comparing the included angle between the normal vector corresponding to the first fitting surface and the normal vector corresponding to the second fitting surface with a preset angle, and determining that the map traffic sign board has a turnover condition if the included angle between the normal vector corresponding to the first fitting surface and the normal vector corresponding to the second fitting surface exceeds the preset angle; if the included angle between the normal vector corresponding to the first fitting surface and the normal vector corresponding to the second fitting surface does not exceed the preset angle, determining that the map traffic sign board does not have the overturning condition.

In one case, the traffic sign is generally a plane, and the preset plane fitting algorithm may be any type of algorithm in related technologies such as a plane fitting algorithm based on a least square method, and the plane fitting algorithm may be an algorithm that can obtain a plane of a series of space points based on the series of space points.

And determining that the map traffic sign has a turnover condition, wherein the quality detection result corresponding to the electronic navigation map comprises information representing the turnover condition of the map traffic sign. It can be understood that, in order to ensure that a worker can quickly locate which map traffic signboards in the electronic navigation map have problems, a map identifier corresponding to the map traffic signboards with turning conditions and map position information of the map traffic signboards in the electronic navigation map can be correspondingly recorded.

In another embodiment of the present invention, after the step S105, the method may further include:

if the quality detection result of the electronic navigation map indicates that the electronic navigation map has a quality problem, storing an abnormal statistical document and abnormal image information corresponding to the electronic navigation map, wherein the abnormal statistical document at least comprises: the identification of map semantic data with quality problems in the electronic navigation map, the quality type of the problems, and map position information in the electronic navigation map, and the abnormal image information comprises: image information corresponding to map semantic data having a quality problem.

If the quality detection result of the electronic navigation map indicates that the electronic navigation map has a quality problem, that is, at least one map semantic data in the electronic navigation map has a quality problem, the quality problem existing in the map semantic data may be classified, where the quality types of the problems obtained by classifying the quality problem existing in the map semantic data may include, but are not limited to: position deviation condition, map lane line bending condition, breaking condition, lamp pole inclination condition and map traffic sign board overturning condition. In particular, classification can also be performed more finely, for example: when the map lane line has a position deviation, namely the quality type of the problem corresponding to the map lane line is the position deviation, the map lane line can be further specifically subdivided into: there are some problems such as a positional deviation in the elevation direction, a positional deviation in the lateral direction of the vehicle, and a positional deviation in the longitudinal direction of the vehicle.

In one case, for each map semantic data in the electronic navigation map, in the driving process of the vehicle in the scene corresponding to the electronic navigation map, the image acquisition device of the vehicle can observe the real target corresponding to the map semantic data for a plurality of times, namely, each map semantic data can correspond to a plurality of pose information, and correspondingly, for different pose information, the electronic device can determine the detection results of one position deviation condition of the map semantic data, one position deviation condition in the elevation direction, one breaking condition of the bending condition of the map lane line, one inclination condition of the map lamp post and/or one turning condition of the map traffic sign board. The map semantic data corresponding error conditions can be called as position deviation conditions, position deviation conditions in the elevation direction, map lane line bending conditions, map lane line breaking conditions, map light pole inclination conditions, map traffic sign board overturning conditions and the like.

At this time, for each map semantic data, from the error conditions corresponding to the map semantic data in each problem quality type, determining the error condition indicating that the map semantic data has the largest error, and adding the largest error condition corresponding to each map semantic data to the abnormal statistical document.

The error condition that the map semantic data has the largest position deviation is characterized by: the error condition with the largest corresponding error value. For example: when the error condition is a position deviation condition, the error value may be a position deviation value; when the error condition is a position deviation condition in the elevation direction, the error value is a position deviation value in the elevation direction; when the error condition is the curve condition of the map lane line, the error value is the distance variance corresponding to the map lane line; when the error condition is a map lane line break condition, the error value is the difference value between the distance between two adjacent discrete points corresponding to the map lane line and the distance between other two adjacent discrete points; when the error condition is the inclination condition of the map lamp post, the error value is the included angle between the map lamp post and the corresponding perceived lamp post; when the error condition is the turning condition of the map traffic sign, the error value is the included angle between the map traffic sign and the corresponding perception traffic sign.

Wherein, the abnormal image information may be: road images containing projected points of map semantic data having quality problems, and the like. The abnormal image information reflects the comparison result between the map semantic data with the corresponding relation and the perception data, and can be used for analyzing the map semantic data with quality problems in the electronic navigation map.

In one implementation manner, the method comprises the steps of firstly detecting the position deviation condition of a map lane line in the map semantic data in an electronic navigation map in the elevation direction, then detecting the lane line bending condition and the lane line breaking condition of the map lane line in the map semantic data, then detecting the map light pole inclination condition of the map light pole in the map semantic data, then detecting the map traffic sign turning condition of the map traffic sign in the map semantic data, and finally detecting the position accuracy of the map semantic data, namely detecting the position deviation condition of the map semantic data. It should be understood that the foregoing is merely an example of an execution sequence of the detection aspect, and is not limited to the execution sequence of the detection aspect provided by the embodiment of the present invention.

Corresponding to the above method embodiment, an embodiment of the present invention provides an electronic navigation map quality detection apparatus, as shown in fig. 3, may include:

a first obtaining module 310 configured to obtain an electronic navigation map to be detected;

a second obtaining module 320, configured to obtain track information of the vehicle during the driving process of the scene corresponding to the electronic navigation map, where the track information includes a plurality of pose information and a positioning time corresponding to each pose information;

a third obtaining module 330, configured to obtain the perceived data determined by the vehicle during the driving process, where each perceived data is: the method comprises the steps that data detected from road images acquired by image acquisition equipment of a vehicle are acquired, and the corresponding relation exists between the acquisition time corresponding to each road image and the positioning time corresponding to each pose information;

a first determining module 340, configured to determine, for each pose information, map semantic data corresponding to the pose information from the electronic navigation map;

the second determining module 350 is configured to determine, for each pose information, a quality detection result of the electronic navigation map based on map position information of map semantic data corresponding to the pose information in the electronic navigation map and/or observation position information of perception data corresponding to the pose information in the corresponding road image.

In another embodiment of the invention, the perceived data includes perceived lane lines and the map semantic data includes map lane lines; the quality detection result comprises a detection result of position deviation of the map lane line in the elevation direction;

the second determining module 350 is specifically configured to determine, for each pose information, mapping position information of a map lane line in a vehicle body coordinate system corresponding to the pose information based on map position information of the map lane line in the map semantic data corresponding to the pose information and the pose information of the electronic navigation map;

In another embodiment of the invention, the perceived data includes perceived lane lines and the map semantic data includes map lane lines; the quality detection result comprises a detection result of the bending condition and/or the breaking condition of the map lane line;

if the quality detection result includes a detection result of a curve condition of a map lane line, the second determining module 350 is specifically configured to determine, for each pose information, map position information of the map lane line in a vehicle body coordinate system corresponding to the pose information based on map position information of the map lane line in the electronic navigation map in map semantic data corresponding to the pose information and the pose information, where each map position information includes: mapping position information of a plurality of discrete points corresponding to the corresponding map lane lines;

and/or, if the quality detection result includes a detection result of a map lane line break condition, the second determining module 350 is specifically configured to determine, for each pose information, conversion position information of the map lane line in a vehicle body coordinate system or a road image corresponding to the pose information based on map position information of the map lane line in the electronic navigation map and the pose information in map semantic data corresponding to the pose information, where each conversion position information includes: conversion position information of a plurality of discrete points corresponding to the corresponding map lane lines;

In another embodiment of the invention, the sensory data comprises sensory light poles and the map semantic data comprises map light poles; the quality detection result comprises a detection result of the inclination condition of the map lamp post;

the second determining module 350 is specifically configured to determine, for each pose information, projection position information of a map light pole in a road image corresponding to the pose information based on map position information of the map light pole in the electronic navigation map in map semantic data corresponding to the pose information and the pose information;

In another embodiment of the invention, the sensory data comprises sensory traffic signboards and the map semantic data comprises map traffic signboards; the quality detection result comprises a detection result of the turning condition of the map traffic sign board;

the second determining module 350 is specifically configured to determine, for each pose information, mapping position information of the map traffic sign in a vehicle body coordinate system corresponding to the pose information based on map position information of the map traffic sign in the electronic navigation map in the map semantic data corresponding to the pose information and the pose information;

In another embodiment of the present invention, the second determining module 350 is specifically configured to obtain, based on the mapping position information of the map traffic sign in the vehicle body coordinate system corresponding to the pose information and a preset plane fitting algorithm, a first fitting surface corresponding to the map traffic sign;

In another embodiment of the present invention, the apparatus further comprises:

The device and system embodiments correspond to the method embodiments, and have the same technical effects as the method embodiments, and specific description refers to the method embodiments. The apparatus embodiments are based on the method embodiments, and specific descriptions may be referred to in the method embodiment section, which is not repeated herein.

Those of ordinary skill in the art will appreciate that: the drawing is a schematic diagram of one embodiment and the modules or flows in the drawing are not necessarily required to practice the invention.

Those of ordinary skill in the art will appreciate that: the modules in the apparatus of the embodiments may be distributed in the apparatus of the embodiments according to the description of the embodiments, or may be located in one or more apparatuses different from the present embodiments with corresponding changes. The modules of the above embodiments may be combined into one module, or may be further split into a plurality of sub-modules.

Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. The method for detecting the quality of the electronic navigation map is characterized by comprising the following steps of:

obtaining an electronic navigation map to be detected;

for each pose information, determining a quality detection result of the electronic navigation map based on map position information of map semantic data corresponding to the pose information in the electronic navigation map and/or observation position information of perception data corresponding to the pose information in a corresponding road image;

the perception data comprises perception lane lines, and the map semantic data comprises map lane lines; the quality detection result comprises a detection result of the bending condition and/or the breaking condition of the map lane line;

2. The method of claim 1, wherein the quality detection result includes a detection result of a position deviation condition of each map semantic data;

3. The method of claim 1, wherein the perceived data comprises perceived lane lines and the map semantic data comprises map lane lines; the quality detection result comprises a detection result of position deviation of the map lane line in the elevation direction;

4. The method of claim 3, wherein the map lane line includes a plurality of discrete points, and the map lane line mapping position information in the vehicle body coordinate system corresponding to the pose information includes: mapping position information of a plurality of discrete points corresponding to the map lane lines;

for each map lane line corresponding to each pose information, determining whether a position deviation condition exists in the transverse axis direction and the longitudinal axis direction of the vehicle body coordinate system of the map lane line based on the mapping position information of the map lane line in the vehicle body coordinate system corresponding to the pose information and the mapping position information of the sensing lane line corresponding to the map lane line in the vehicle body coordinate system corresponding to the pose information, including:

calculating an error sub-vector between each discrete point and a perceived lane corresponding to each map lane according to the mapping position information of the discrete point and the mapping position information of the perceived lane corresponding to the map lane in a vehicle body coordinate system corresponding to the pose information;

determining an error vector between each map lane line and a perceived lane line corresponding to the map lane line corresponding to each pose information based on the error sub-vector between each discrete point included in each map lane line and the perceived lane line corresponding to the map lane line corresponding to each pose information, and taking the error vector as the error vector corresponding to each map lane line;

For each map lane line corresponding to each pose information, determining an error vector component of the error vector corresponding to the map lane line in the transverse axis direction of a vehicle body coordinate system corresponding to the pose information and an error vector component of the error vector component in the longitudinal axis direction of the vehicle body coordinate system corresponding to the pose information based on the error vector corresponding to the map lane line, and respectively calculating a modulus of the error vector component of the error vector corresponding to the map lane line in the transverse axis direction of the vehicle body coordinate system corresponding to the pose information and a modulus of the error vector component in the longitudinal axis direction of the vehicle body coordinate system corresponding to the pose information;

judging whether the modulus of the error vector component of the error vector corresponding to the map lane line in the transverse axis direction of the vehicle body coordinate system corresponding to the pose information exceeds a first numerical value, if the modulus of the error vector component of the error vector corresponding to the map lane line in the transverse axis direction of the vehicle body coordinate system corresponding to the pose information does not exceed first data, determining that the map lane line has no position deviation in the transverse axis direction of the vehicle body coordinate system, and if the modulus of the error vector component of the error vector corresponding to the map lane line in the transverse axis direction of the vehicle body coordinate system corresponding to the pose information exceeds first data, determining that the map lane line has position deviation in the transverse axis direction of the vehicle body coordinate system;

Judging whether the modulus of the error vector component of the error vector corresponding to the map lane line in the longitudinal axis direction of the vehicle body coordinate system corresponding to the pose information exceeds a second numerical value, if the modulus of the error vector component of the error vector corresponding to the map lane line in the longitudinal axis direction of the vehicle body coordinate system corresponding to the pose information does not exceed second data, determining that the map lane line has no position deviation in the longitudinal axis direction of the vehicle body coordinate system, and if the modulus of the error vector component of the error vector corresponding to the map lane line in the longitudinal axis direction of the vehicle body coordinate system corresponding to the pose information exceeds first data, determining that the map lane line has position deviation in the longitudinal axis direction of the vehicle body coordinate system.

5. The method of any of claims 1-4, wherein the sensory data comprises a sensory traffic sign and the map semantic data comprises a map traffic sign; the quality detection result comprises a detection result of the turning condition of the map traffic sign board;

6. The method of claim 5, wherein the step of determining whether the map traffic sign has a rollover condition based on the mapped position information of the map traffic sign in the vehicle body coordinate system corresponding to the pose information and the mapped position information of the perceived traffic sign corresponding to the map traffic sign in the vehicle body coordinate system corresponding to the pose information comprises:

7. The method according to claim 6, wherein after the step of determining the quality detection result of the electronic navigation map based on the map position information of the map semantic data corresponding to the pose information in the electronic navigation map and/or the observed position information of the perception data corresponding to the pose information in the corresponding road image for each pose information, the method further comprises:

8. The method for detecting the quality of the electronic navigation map is characterized by comprising the following steps of:

obtaining an electronic navigation map to be detected;

the perception data comprises perception traffic signboards, and the map semantic data comprises map traffic signboards; the quality detection result comprises a detection result of the turning condition of the map traffic sign board;

9. The method of claim 8, wherein the quality detection result includes a detection result of a position deviation condition of each map semantic data;

10. The method of claim 8, wherein the perceived data includes perceived lane lines and the map semantic data includes map lane lines; the quality detection result comprises a detection result of position deviation of the map lane line in the elevation direction;

11. The method of claim 10, wherein the map lane line comprises a plurality of discrete points, and the map lane line mapping position information in the vehicle body coordinate system corresponding to the pose information comprises: mapping position information of a plurality of discrete points corresponding to the map lane lines;

12. The method of claim 8, wherein the step of determining whether the map traffic sign has a rollover condition based on the mapped position information of the map traffic sign in the vehicle body coordinate system corresponding to the pose information and the mapped position information of the perceived traffic sign corresponding to the map traffic sign in the vehicle body coordinate system corresponding to the pose information comprises:

13. The method according to any one of claims 8-12, wherein after the step of determining the quality detection result of the electronic navigation map for each pose information based on map position information of map semantic data corresponding to the pose information in the electronic navigation map and/or observed position information of perception data corresponding to the pose information in the corresponding road image, the method further comprises:

14. An electronic navigation map quality detection apparatus, characterized in that the apparatus comprises:

the second determining module is configured to determine a quality detection result of the electronic navigation map according to the map position information of the map semantic data corresponding to the pose information in the electronic navigation map and/or the observation position information of the perception data corresponding to the pose information in the corresponding road image aiming at each pose information;

15. The apparatus of claim 14, wherein the quality detection result includes a detection result of a position deviation condition of each map semantic data;

16. The apparatus of claim 14, wherein the awareness data comprises awareness lane lines and the map semantic data comprises map lane lines; the quality detection result comprises a detection result of position deviation of the map lane line in the elevation direction;

17. The apparatus of claim 16, wherein the map lane line comprises a plurality of discrete points, and the map lane line mapping position information in the vehicle body coordinate system corresponding to the pose information comprises: mapping position information of a plurality of discrete points corresponding to the map lane lines;

the second determining module is specifically configured to calculate, for each discrete point included in each map lane line corresponding to each pose information, an error sub-vector between the discrete point and a perceived lane line corresponding to the map lane line based on mapping position information of the discrete point and mapping position information of the perceived lane line corresponding to the map lane line in a vehicle body coordinate system corresponding to the pose information;

18. The apparatus of any of claims 14-17, wherein the sensory data comprises a sensory traffic sign and the map semantic data comprises a map traffic sign; the quality detection result comprises a detection result of the turning condition of the map traffic sign board;

19. The apparatus of claim 18, wherein the second determining module is specifically configured to obtain, based on the mapping position information of the map traffic sign in the vehicle body coordinate system corresponding to the pose information and a preset plane fitting algorithm, a first fitting surface corresponding to the map traffic sign;

20. The apparatus of claim 19, wherein the apparatus further comprises:

21. An electronic navigation map quality detection apparatus, characterized in that the apparatus comprises:

22. The apparatus of claim 21, wherein the quality detection result includes a detection result of a positional deviation condition of each map semantic data;

23. The apparatus of claim 21, wherein the awareness data comprises awareness lane lines and the map semantic data comprises map lane lines; the quality detection result comprises a detection result of position deviation of the map lane line in the elevation direction;

24. The apparatus of claim 23, wherein the map lane line comprises a plurality of discrete points, and the map lane line mapping position information in the vehicle body coordinate system corresponding to the pose information comprises: mapping position information of a plurality of discrete points corresponding to the map lane lines;

25. The apparatus of claim 21, wherein the second determining module is specifically configured to obtain, based on the mapping position information of the map traffic sign in the vehicle body coordinate system corresponding to the pose information and a preset plane fitting algorithm, a first fitting surface corresponding to the map traffic sign;

26. The apparatus of any one of claims 21-25, wherein the apparatus further comprises: