CN111750882B - Method and device for correcting vehicle pose during initialization of navigation map - Google Patents
Method and device for correcting vehicle pose during initialization of navigation map Download PDFInfo
- Publication number
- CN111750882B CN111750882B CN201910253289.0A CN201910253289A CN111750882B CN 111750882 B CN111750882 B CN 111750882B CN 201910253289 A CN201910253289 A CN 201910253289A CN 111750882 B CN111750882 B CN 111750882B
- Authority
- CN
- China
- Prior art keywords
- indicator
- vehicle
- navigation map
- mark
- pose
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 76
- 238000012937 correction Methods 0.000 claims abstract description 155
- 230000008447 perception Effects 0.000 claims abstract description 105
- 238000012545 processing Methods 0.000 claims abstract description 89
- 238000005457 optimization Methods 0.000 claims description 13
- 238000012986 modification Methods 0.000 claims description 5
- 230000004048 modification Effects 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 13
- 238000012549 training Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000013135 deep learning Methods 0.000 description 2
- 241000283070 Equus zebra Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Navigation (AREA)
Abstract
The embodiment of the invention discloses a method and a device for correcting the vehicle pose of a navigation map during initialization, wherein the method is applied to a normal road section with a relatively comprehensive indication mark, and comprises the following steps: correcting the elevation of the vehicle provided by a preset positioning device based on lane line information corresponding to the current position of the vehicle in the navigation map; selecting a target indicator matched with the perception image from the navigation map; performing first correction processing on the current pose of the vehicle based on the position of the target indicator mark; determining second indicating marks of other types except the first indicating mark in the navigation map and the image according to the pose and the elevation of the vehicle after the first correction processing; and performing second correction processing on the vehicle pose after the first correction based on the positions of the target indicator mark and the matched second indicator mark.
Description
Technical Field
The invention relates to the technical field of automatic driving, in particular to a method and a device for correcting the vehicle pose of a navigation map during initialization.
Background
In the field of automatic driving, navigation and positioning are of great importance. In recent years, the development of the image semantic segmentation and image recognition field is greatly promoted by the achievement of technologies such as deep learning, and the like, so that a solid foundation is provided for navigation maps and navigation positioning.
In the positioning scheme based on the high-precision map, when the unmanned vehicle runs on a normal road section with comprehensive information such as traffic signs, traffic marking lines and the like, if the vehicle enters the high-precision map for the first time, the global and accurate position information needs to be obtained for initialization, then the high-precision map can be used for accurate positioning, and the absolute position accuracy can reach the centimeter level. However, in a Positioning scheme of a consumer-grade device, such as a single-point GPS (Global Positioning System) and an inexpensive IMU (Inertial measurement unit), because an error of Positioning accuracy information provided by the single-point GPS is large, when performing a re-projection matching between traffic sign information in a high-accuracy map and traffic sign information in an image, such as a traffic sign, sensed by a deep learning sensing model, and using a position provided by the single-point GPS, a problem of a left-right matching error of a lane line, a front-back matching error of a street lamp pole, and the like is easily caused. If the vehicle body position is corrected by using wrong matching information, the position accuracy of the vehicle body cannot reach a centimeter level by using a high-precision map, and the position of the vehicle body may deviate from the real position more.
Disclosure of Invention
The embodiment of the invention discloses a method and a device for correcting the position and posture of a vehicle during initialization of a navigation map, which solve the problem that the positioning precision of an unmanned vehicle is not high by using a consumption-level preset positioning device in the scene of a normal road section with comprehensive traffic signs and traffic marking information, and achieve the technical effect that the consumption-level preset positioning device can also be used for high-precision positioning.
In a first aspect, an embodiment of the invention discloses a method for correcting a vehicle pose of a navigation map during initialization, which comprises the following steps:
acquiring the current position of a vehicle provided by a preset positioning device, and correcting the elevation of the vehicle provided by the preset positioning device based on lane line information corresponding to the current position in a navigation map;
selecting a target indicator which is matched with each first indicator in the perception image from the first indicators of the navigation map, wherein the first indicators comprise traffic signs;
performing first correction processing on the pose of the vehicle in the navigation map based on the position of the target indicator mark;
determining other types of second indicating signs matched with the navigation map and the perception image except the first indicating signs according to the pose and the elevation of the vehicle after the first correction processing, wherein the second indicating signs comprise lane lines and/or street lamp poles;
and performing second correction processing on the vehicle pose after the first correction processing based on the positions of the target indicator mark and the matched second indicator mark, so that the positions of the first indicator mark and the second indicator mark in the navigation map are respectively matched with the positions of the first indicator mark and the second indicator mark in the perception image according to the vehicle pose after the second correction processing.
Optionally, based on the position of the target indicator, performing a first correction process on the pose of the vehicle in the navigation map, including:
and performing first correction processing on position three degrees of freedom in six degrees of freedom of the vehicle through a nonlinear optimization algorithm based on the position of the target indicator, so that the projection error of each first indicator in the navigation map and the perception image on a preset standardized plane based on the position of the vehicle after the first correction processing is smaller than a first preset distance.
Optionally, determining a similarity value between the traffic sign in the projected navigation map and the traffic sign in the projected perceptual image includes:
and calculating the ratio of the projection length of the traffic sign in the projected navigation map to the projection length of the traffic sign in the projected perception image, and taking the ratio as a similarity value.
Optionally, performing second correction processing on the vehicle pose after the first correction processing based on the positions of the target indicator and the matched second indicator, so that the positions of the first indicator and the second indicator in the navigation map are respectively matched with the positions of the first indicator and the second indicator in the perception image according to the vehicle pose after the second correction processing, including:
performing second correction processing on the vehicle pose subjected to the first correction processing through a nonlinear optimization algorithm based on the positions of the target indicator and the matched second indicator;
respectively projecting each first indicator mark and each second indicator mark in the navigation map and the perception image to a preset standardized plane based on the pose of the vehicle after second correction processing;
on the preset standardized plane, respectively judging whether the projection distances between the first indicator mark and the second indicator mark projected in the navigation map and the corresponding first indicator mark and second indicator mark in the perception image are both smaller than a corresponding second preset distance;
if the first indication mark and the second indication mark in the navigation map are smaller than the second preset distance, determining that the positions of the first indication mark and the second indication mark in the navigation map are matched with the positions of the first indication mark and the second indication mark in the perception image according to the vehicle pose after the second correction processing;
and the second preset distances corresponding to the first indication mark and the second indication mark are smaller than the first preset distances corresponding to the first indication mark and the second indication mark respectively.
Optionally, selecting a target indicator matching each first indicator in the perceptual image from the first indicators of the navigation map includes:
and reconstructing each first indicator mark in the perception image, comparing the similarity of the reconstructed first indicator mark with the similarity of the first indicator marks in the navigation map, and taking the first indicator mark with the similarity value reaching a first set threshold value as a matched target indicator mark.
Optionally, selecting a target indicator matching each first indicator in the perception image from the first indicators of the navigation map includes:
and projecting the first indicator mark in the navigation map to a plane where a perception image is located, comparing the similarity of the first indicator mark in the perception image with the similarity of the first indicator mark in the perception image, and taking the first indicator mark with the similarity value reaching a second set threshold value as a matched target indicator mark.
Optionally, the correcting the elevation of the vehicle provided by the preset positioning device based on the lane line information corresponding to the current position in the navigation map includes:
determining an average value of the elevations of the lane lines corresponding to the current position in the navigation map;
and taking the average value of the elevations of the lane lines as the elevation of the vehicle at the current position so as to correct the elevation of the vehicle provided by a preset positioning device.
Optionally, after performing the second correction processing on the vehicle pose in the navigation map, the method further includes:
updating display content in the navigation map based on the pose of the vehicle after the second correction processing;
and returning to execute the operation of acquiring the current position of the vehicle provided by the preset positioning device to correct the pose of the vehicle again if the indicator is not acquired in the perception image with the continuously set frame number and/or the indicator in the navigation map during the running process of the vehicle.
Optionally, the method further includes:
and if the position of the vehicle provided by the preset positioning device is detected to have no corresponding coverage area in the navigation map, stopping the initialization operation of the navigation map, and switching the current automatic driving mode into the manual driving mode.
In a second aspect, an embodiment of the present invention further provides an apparatus for correcting a vehicle pose of a navigation map during initialization, where the apparatus includes:
the elevation correction module is configured to acquire the current position of the vehicle provided by a preset positioning device and correct the elevation of the vehicle provided by the preset positioning device based on lane line information corresponding to the current position in a navigation map;
a target indicator determination module configured to select a target indicator from the first indicators of the navigation map that matches the first indicators in the perceived image, the first indicator comprising a traffic sign;
a first correction module configured to perform a first correction process on the pose of the vehicle in the navigation map based on the position of the target indicator;
a second indication mark determining module configured to determine, according to the pose and the elevation of the vehicle after the first correction processing, second indication marks of other types, which are matched with the navigation map and the perception image except the first indication marks, wherein the second indication marks comprise lane lines and/or street lamp poles;
and the second correction module is configured to perform second correction processing on the vehicle pose after the first correction processing based on the positions of the target indicator and the matched second indicator, so that the positions of the first indicator and the second indicator in the navigation map are respectively matched with the positions of the first indicator and the second indicator in the perception image according to the vehicle pose after the second correction processing.
Optionally, the first modification module is specifically configured to:
and based on the position of the target indicator, performing first correction processing on position three degrees of freedom in six degrees of freedom of the vehicle through a nonlinear optimization algorithm, so that the projection error of each first indicator in the navigation map and the perception image on a preset standardized plane based on the position of the vehicle after the first correction processing is smaller than a first preset distance.
Optionally, the second modification module is specifically configured to:
performing second correction processing on the vehicle pose subjected to the first correction processing through a nonlinear optimization algorithm based on the positions of the target indicator and the matched second indicator;
respectively projecting each first indicator mark and each second indicator mark in the navigation map and the perception image to a preset standardized plane based on the pose of the vehicle after second correction processing;
on the preset standardized plane, respectively judging whether the projection distances between the first indicator mark and the second indicator mark projected in the navigation map and the corresponding first indicator mark and second indicator mark in the perception image are both smaller than a corresponding second preset distance;
if the first indication mark and the second indication mark in the navigation map are smaller than the second preset distance, determining that the positions of the first indication mark and the second indication mark in the navigation map are matched with the positions of the first indication mark and the second indication mark in the perception image according to the vehicle pose after the second correction processing;
and the second preset distances corresponding to the first indication mark and the second indication mark are smaller than the first preset distances corresponding to the first indication mark and the second indication mark respectively.
Optionally, the target indicator determination module is specifically configured to:
and reconstructing each first indicator mark in the perception image, comparing the similarity of the reconstructed first indicator mark with the similarity of the first indicator marks in the navigation map, and taking the first indicator mark with the similarity value reaching a first set threshold value as a matched target indicator mark.
Optionally, the target indicator determination module is specifically configured to:
selecting a target indicator matching each first indicator in the perceptual image from the first indicators of the navigation map, comprising:
and projecting the first indicator mark in the navigation map to a plane where a perception image is located, comparing the similarity of the first indicator mark in the perception image with the similarity of the first indicator mark in the perception image, and taking the first indicator mark with the similarity value reaching a second set threshold value as a matched target indicator mark.
Optionally, the elevation correction module is specifically configured to:
determining an average value of the elevations of the lane lines corresponding to the current position in the navigation map;
and taking the average value of the elevations of the lane lines as the elevation of the vehicle at the current position so as to correct the elevation of the vehicle provided by a preset positioning device.
Optionally, the apparatus further comprises:
after second correction processing is carried out on the pose of the vehicle in the navigation map, updating display content in the navigation map based on the pose of the vehicle after the second correction processing;
and returning to execute the operation of acquiring the current position of the vehicle provided by the preset positioning device to correct the pose of the vehicle again if the indicator is not acquired in the perception image with the continuously set frame number and/or the indicator in the navigation map during the running process of the vehicle.
Optionally, the apparatus further comprises:
and if the position of the vehicle provided by the preset positioning device is detected to have no corresponding coverage area in the navigation map, stopping the initialization operation of the navigation map, and switching the current automatic driving mode into the manual driving mode.
In a third aspect, an embodiment of the present invention further provides a vehicle-mounted terminal, including:
a memory storing executable program code;
a processor coupled with the memory;
the processor calls the executable program codes stored in the memory to execute part or all of the steps of the method for correcting the vehicle pose of the navigation map during initialization, which is provided by any embodiment of the invention.
In a fourth aspect, the embodiment of the present invention further provides a computer-readable storage medium storing a computer program including instructions for executing part or all of the steps of the method for correcting the vehicle pose at the time of initialization of the navigation map provided in any embodiment of the present invention.
In a fifth aspect, the embodiment of the present invention further provides a computer program product, which when run on a computer, causes the computer to execute part or all of the steps of the method for correcting the vehicle pose at initialization of the navigation map provided in any embodiment of the present invention.
According to the technical scheme provided by the embodiment of the invention, in the normal road section with comprehensive traffic indication information such as traffic signs, traffic marking lines and the like, the first correction processing, namely rough correction, of the vehicle pose is completed by utilizing the position of the target traffic indication sign (generally referring to a traffic sign) matched with the sensing image in the navigation map. Because the traffic indication information in the normal road section is relatively comprehensive, after the rough correction of the vehicle is finished, the position and posture of the vehicle can be subjected to second correction processing, namely accurate correction, by using the indication marks such as a lane line or a light pole, so that more accurate vehicle positioning precision is obtained, and the problem of low positioning precision due to the use of a consumption-level preset positioning device is solved. Under the application scene of comprehensive information such as traffic signs, the consumption-level preset positioning device has the function of providing centimeter-level position accuracy.
The invention comprises the following steps:
1. under the application scene of comprehensive information such as traffic signs, the traffic signs such as traffic signposts in the perception images and the navigation map can be identified, and the traffic signposts can be used for correcting the pose of the vehicle, so that the initialization operation of the navigation map is completed, and the consumer-grade positioning equipment has a high-precision positioning function.
2. When the first indication marks such as traffic signs are screened, the first indication marks in the perception images are subjected to three-dimensional reconstruction, or the first indication marks in the navigation map are projected to the plane where the perception images are located, and the similarity between the first indication marks and the traffic marks in the navigation map is used as one of the weights for judging the superiority and inferiority of the indication marks, so that the target first indication marks matched with the positions in the navigation map in the perception images are screened out, and the method is one of the invention points of the invention.
3. When the position of the vehicle is corrected, a more accurate position precision can be obtained by adopting an iterative correction mode, and the method is one of the invention points of the invention.
4. The method is characterized in that the elevation of the lane line within a range of several meters around the current position of the vehicle in the navigation map is determined, and the determined elevation of the lane line can be used as the elevation of the current position of the vehicle to finish the correction of the elevation of the vehicle, so that the probability of correct matching of the subsequent navigation map and the perception image is increased.
5. In the driving process of the vehicle, if the indication marks such as a lane line, a traffic sign or a light pole and the like are not acquired in the perception image with the set frame number and/or the indication marks in the navigation map are not acquired, the initial state of the navigation map needs to be switched to ensure the normal operation of the vehicle, and the method is one of the invention points.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for correcting a vehicle pose when a navigation map is initialized according to an embodiment of the present invention;
fig. 2a is a schematic flow chart of a method for correcting a vehicle pose when a navigation map is initialized according to an embodiment of the present invention;
FIG. 2b is a schematic diagram of a projection of a vehicle before elevation correction according to an embodiment of the present invention;
FIG. 2c is a schematic view of a vehicle elevation corrected projection according to an embodiment of the present invention;
fig. 2d is a schematic projection diagram of a vehicle before rough pose correction according to an embodiment of the present invention;
fig. 2e is a schematic projection diagram of a vehicle after rough pose correction according to an embodiment of the present invention;
fig. 2f is a schematic projection diagram of a vehicle after accurate pose correction according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a device for correcting a vehicle pose when a navigation map is initialized according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a vehicle-mounted terminal 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 drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It is to be noted that the terms "comprises" and "comprising" and any variations thereof in the embodiments and drawings of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
Example one
Referring to fig. 1, fig. 1 is a schematic flow chart illustrating a method for correcting a vehicle pose when a navigation map is initialized according to an embodiment of the present invention. The method is typically applied to a scene that an unmanned vehicle enters an outdoor high-precision map at a normal road section with relatively comprehensive information such as a traffic sign and the like for the first time, and can be executed by a vehicle pose correction device during initialization of a navigation map, the device can be realized in a software and/or hardware mode, and can be generally integrated in a vehicle-mounted terminal such as a vehicle-mounted Computer, a vehicle-mounted Industrial control Computer (IPC) and the like. As shown in fig. 1, the method provided in this embodiment specifically includes:
110. and acquiring the current position of the vehicle provided by a preset positioning device, and correcting the elevation of the vehicle provided by the positioning device based on the lane line information corresponding to the current position in the navigation map.
The preset positioning device is a single-point GPS or low-precision consumer-grade positioning device. The navigation map is a high-precision map with centimeter-level error level applied to automatic driving.
In this embodiment, the elevation of the vehicle refers to the altitude of the vehicle provided by the consumer-grade location device. When the consumer-grade positioning equipment is used for positioning the vehicle, the positioning accuracy is low, and sometimes errors of several meters or even tens of meters exist, but the height of the lane line does not change greatly within the error range. Therefore, according to the current position of the vehicle provided by the consumer-level positioning equipment, the lane line information which is several meters near the current position can be searched in the navigation map, so that the elevation of the vehicle can be corrected by using the lane line information, and the vehicle can be pulled to the height of the lane line.
Specifically, the lane line within a range of several meters around the current position of the vehicle may be searched in the navigation map, and the average height of the lane line, that is, the elevation of the lane line, may be calculated. And taking the calculated elevation of the lane line as the elevation of the current position of the vehicle to finish the correction of the elevation of the vehicle. This arrangement may result in an increased probability that the subsequent navigation map matches the perceived image correctly.
It should be noted that, in the embodiment of the present invention, there is no difference in the order of correcting the elevation and the pose of the vehicle, the elevation of the vehicle may be corrected first, and then the pose of the vehicle may be corrected, or the elevation of the vehicle may be corrected first, and then the pose of the vehicle may be corrected.
120. And selecting a target indicator which is matched with each first indicator in the perception image from the first indicators of the navigation map.
The sensing image is obtained by identifying an image which is acquired by a camera and contains a traffic indication sign by using a preset sensing model. The preset perception model can be used for training the perception model by adopting a large number of road sample images marked with image semantic features in advance. The image semantic features can comprise traffic signs such as traffic signs, lane lines, lane line dotted line endpoints, prismatic lines, zebra news and the like. The road image containing the traffic indication sign is input into a trained preset perception model, and the image semantic features in the road image can be obtained based on the recognition result of the preset perception model. The preset perception model can be obtained through the following modes:
constructing a training sample set, wherein the training sample set comprises a plurality of groups of training sample data, and each group of training sample data comprises a road sample image and a corresponding road perception sample image marked with image semantic features; training the built initial neural network based on the training sample set to obtain a preset perception model, wherein the preset perception model enables the road sample images in each set of training sample data to be associated with the corresponding road perception sample images marked with image semantic features. The output of the model is called a perception image.
In the embodiment, the traffic sign is preferably used as a first indication sign to roughly correct the vehicle pose on a normal road section with a relatively comprehensive traffic indication sign, and a second indication sign with a type different from that of the first indication sign, such as a lane line and/or a street lamp pole, is selected to accurately correct the vehicle pose. Compared with a special road section lacking in traffic signs, when a vehicle runs to the special road section, the indication signs such as the light pole or the lane line can only be used as the indication signs for correcting the rough pose of the vehicle due to the lack of the positioning signs such as the traffic sign boards.
Illustratively, selecting the target indicator matching each first indicator in the perception image from the first indicators in the navigation map can be realized by:
and reconstructing each first indicator mark in the perception image by adopting a triangulation algorithm, comparing the similarity of the reconstructed first indicator mark with the first indicator mark in the navigation map, and taking the first indicator mark with the similarity value reaching a first set threshold value as a matched target indicator mark.
Illustratively, selecting the target indicator which is matched with each first indicator in the perception image from the first indicators of the navigation map can be realized by the following steps:
and projecting the first indicator mark in the navigation map to a plane where the perception image is located, comparing the similarity of the first indicator mark in the navigation map with the similarity of the first indicator mark in the perception image, and taking the first indicator mark with the similarity value reaching a second set threshold value as a matched target indicator mark.
Furthermore, the determination of the target indication marks shows that the target indication marks in the perception image and the corresponding target indication marks in the navigation map establish a one-to-one matching relationship, so that the pose of the vehicle in the navigation map can be continuously corrected based on the positions of the target indication marks. When the vehicle pose is corrected, the target indication marks comprise a plurality of groups of indication marks with similarity values meeting requirements, so that the target indication marks can be sequenced from high to low according to the similarity values, and the next step of correcting the vehicle pose is sequentially performed according to the sequence from high to low of the similarity values.
130. And performing first correction processing on the pose of the vehicle in the navigation map based on the position of the target indicator mark.
The pose of the vehicle is corrected to minimize the deviation between the current position of the vehicle and the actual correct position of the vehicle, and the current position of the vehicle can be continuously approximated to the actual position of the vehicle by adopting an iterative correction mode.
In this embodiment, in a normal road section with a comprehensive traffic indicator, a matched target indicator, such as a traffic sign, may be identified from the navigation map and the perception image as a criterion for correcting the vehicle pose. The first correction processing is to roughly correct the vehicle pose using the position of the target traffic sign, so that the distance error between the vehicle pose and the true pose is reduced.
140. And determining other types of second indicators matched with the navigation map and the perception image except the first indicators according to the pose and the elevation of the vehicle after the first correction processing.
After the coarse pose correction is performed on the vehicle in step 130, the pose of the vehicle is changed. Therefore, based on the corrected vehicle position, the display content in the navigation map is changed accordingly. After the display content in the navigation map is updated, the indication mark matched with the navigation map in the perception map is also updated accordingly. Since the embodiment is mainly applied to normal road sections with comprehensive traffic signs, the vehicle pose can be further corrected by combining with other types of signs besides the traffic signs, for example, the lane lines can provide the constraint on the position of the vehicle body in the up-down and left-right directions, and the light poles can provide the constraint on the vehicle body in the front-back and left-right directions, so that the lane lines, the light poles or the combination of the two can be used as second signs different from the first signs, and the vehicle pose can be further corrected.
150. And performing second correction processing on the vehicle pose after the first correction processing based on the positions of the target indicator mark and the matched second indicator mark, so that the positions of the first indicator mark and the second indicator mark in the navigation map are respectively matched with the positions of the first indicator mark and the second indicator mark in the perception image according to the vehicle pose after the second correction processing.
For example, the second pose correction processing for the vehicle may still be implemented by using a non-linear correction algorithm. The second correction processing of the vehicle pose is to perform further accurate correction on the vehicle pose in combination with various types of indicators recognizable in a road section with comprehensive traffic indicator information, such as light poles, lane lines and the like, on the basis of performing rough pose correction on the vehicle. The second correction processing result may be checked by projecting various types of indicators in the navigation map onto a plane where the sensing image is located, determining a projection distance between the sensing image and the corresponding type of indicators in the sensing image, and if the projection distance satisfies an error convergence condition, it may be said that the positions of the various types of indicators in the navigation map are matched with the positions of the corresponding types of indicators in the sensing image according to the vehicle pose after the second correction processing, that is, the result of the vehicle accurate correction reaches a preset requirement, that is, the accurate correction of the vehicle pose at the traffic sign-deficient road section is completed. At this time, the display information in the navigation map may be updated to complete initialization of the navigation map, and the matching relationship between the navigation map and the perception image may be saved.
It should be noted that, because the traffic sign has the most abundant and comprehensive information compared with other indicators, the traffic sign is preferably used as the first indicator to perform the first correction process on the vehicle, and the light pole and the lane line are preferably used as the second indicator to perform the second correction process on the vehicle. However, since the embodiment is applied to a normal road section with comprehensive information such as a traffic sign, various types of signs in a perception image and a navigation map can be generally recognized, the first sign is not limited to a traffic sign, and a first correction process can be performed on a vehicle by using signs such as a light pole or a lane line as the first sign, and a second correction process can be performed on the vehicle by using the traffic sign as a second sign.
According to the technical scheme provided by the embodiment of the invention, in the normal road section with comprehensive traffic indication information such as traffic signs, traffic marking lines and the like, the first correction processing, namely rough correction, of the vehicle pose is completed by utilizing the position of the target traffic indication sign (generally referring to a traffic sign) matched with the sensing image in the navigation map. Because the traffic indication information in the normal road section is relatively comprehensive, after the rough correction of the vehicle is finished, the position and posture of the vehicle can be subjected to second correction processing, namely accurate correction, by using the indication marks such as a lane line or a light pole, so that more accurate vehicle positioning precision is obtained, and the problem of low positioning precision due to the use of a consumption-level preset positioning device is solved. Under the application scene of comprehensive information such as traffic signs, the consumption-level preset positioning device has the function of providing centimeter-level position accuracy.
Further, after the initialization of the navigation map is completed, if the indicator (including the first indicator and/or the second indicator) in the perception image with the continuously set frame number is not acquired and/or the indicator in the navigation map is not acquired during the driving process of the unmanned vehicle, returning to execute the operation of acquiring the current position of the vehicle provided by the preset positioning device, so as to update the display content in the navigation map again, that is, to perform the initialization process again. However, if the position of the vehicle provided by the preset positioning device is detected that the corresponding coverage area does not exist in the navigation map, the initialization operation of the navigation map is stopped, and the current automatic driving mode is switched to the manual driving mode, namely, the initialization state is exited, so that the stability of a vehicle system is ensured.
Example two
Referring to fig. 2a, fig. 2a is a schematic flow chart illustrating a method for correcting a vehicle pose when a navigation map is initialized according to an embodiment of the present invention. The embodiment optimizes the vehicle pose correction process on the basis of the embodiment. As shown in fig. 2a, the method comprises:
210. and acquiring the current position of the vehicle provided by the preset positioning device, and correcting the elevation of the vehicle provided by the preset positioning device based on the lane line information corresponding to the current position in the navigation map.
FIG. 2b is a schematic diagram of a projection of a vehicle before elevation correction according to an embodiment of the present invention. FIG. 2c is a schematic diagram of a projection of a vehicle after elevation correction according to an embodiment of the present invention. Wherein, 1 represents a light pole in the perception image; 2, a light pole in the navigation map; 3 represents the true position of the vehicle; and 4, the current position of the vehicle in the navigation map. By correcting the elevation of the vehicle, the vehicle may be pulled to lane line height, as shown in fig. 2b and 2 c.
220. And selecting a target indicator which is matched with each first indicator in the perception image from the first indicators of the navigation map, wherein the first indicators comprise traffic signs.
230. And based on the position of the target indicator, performing first correction processing on position three degrees of freedom in six degrees of freedom of the vehicle through a nonlinear optimization algorithm, so that the projection error of each first indicator in the navigation map and the perception image on a preset standardized plane based on the position of the vehicle after the first correction processing is smaller than a first preset distance.
In this embodiment, step 230 is a process of performing rough pose correction on the vehicle. This process primarily uses the target indicators identified in 220, such as traffic signs, to correct the position of the vehicle so that the distance between the position of the vehicle and its true position is reduced. After the rough pose correction is performed on the vehicle, that is, after the first optimization processing is completed, the optimized position can be checked, specifically, the error between the projection position of the corrected vehicle pose on the preset standardized plane and the projection position of the corresponding traffic sign in the perception image on the preset standardized plane can be judged through the traffic sign in the navigation map, and if the projection error is reduced, for example, if the error value is smaller than a 20-30 pixel value, the next accurate pose correction process of the vehicle can be performed. The preset standardized plane is preferably a plane where the perception image is located, and may also be a normalized plane of the camera, the normalized plane may be established in a camera coordinate system, and the distance from the origin of the camera coordinate system is 1 meter.
Specifically, fig. 2d is a schematic projection diagram before the vehicle is subjected to the rough pose correction according to the embodiment of the present invention, and fig. 2e is a schematic projection diagram after the vehicle is subjected to the rough pose correction according to the embodiment of the present invention. Wherein, 1 represents a traffic sign in the perception image; 2, a traffic indicator board projected in the navigation map; 3 represents the true position of the vehicle; and 4, the current position of the vehicle in the navigation map. After the coarse pose correction of the vehicle, the projected positions of the matching traffic signs in the navigation map and the perception image on the normalized plane are reduced relative to fig. 2 e. In the road section with more comprehensive traffic indication signs, the positions of the vehicles can be corrected by using the navigation map and the positions of the traffic indication boards matched with the sensing image, so that the positions of the vehicles in the figure 2e are closer to the real positions of the vehicles.
240. And determining other types of second indicators matched with the navigation map except the first indicator in the perception image according to the pose and the elevation of the vehicle after the first correction processing, wherein the second indicators comprise lane lines and/or light poles.
250. And performing second correction processing on the vehicle pose subjected to the first correction processing through a nonlinear optimization algorithm based on the positions of the target indicator and the matched second indicator.
In this embodiment, step 250 is a process of performing accurate pose correction on the vehicle. After the coarse pose correction is performed on the vehicle in step 230, the pose of the vehicle in the navigation map is changed. Therefore, based on the corrected vehicle position, the display content in the navigation map is changed accordingly. After the display content in the navigation map is updated, the traffic signs matched with the navigation map in the perception map are also updated accordingly. In the process of accurately correcting the vehicle pose on a normal road section with comprehensive traffic sign information, the vehicle pose can be further optimized by using other matched signs, such as lane lines or street lamp poles, or combining the positions of the lane lines and the street lamp poles, except for a traffic sign in a navigation map and a perception image, namely, second correction processing is carried out, and after the second correction processing, the position of the vehicle is closer to the real position.
260. And respectively projecting each first indicator mark and each second indicator mark in the navigation map and the perception image to a preset standardized plane based on the pose of the vehicle after the second correction processing.
270. On a preset standardized plane, respectively judging whether the projection distances between the first indicator mark and the second indicator mark projected in the navigation map and the corresponding first indicator mark and second indicator mark in the perception image are both smaller than a corresponding second preset distance; and if the first indication mark and the second indication mark are both smaller than the second preset distance, determining that the positions of the first indication mark and the second indication mark in the navigation map are matched with the positions of the first indication mark and the second indication mark in the perception image according to the vehicle pose after the second correction processing.
And the second preset distances corresponding to the first indication mark and the second indication mark are smaller than the first preset distances corresponding to the first indication mark and the second indication mark respectively.
In this embodiment, the second correction processing result is checked in the same manner as the first correction processing result, that is, projection errors between the projection positions of the traffic signs, such as the traffic signs, the light poles, and the lane lines, in the navigation map and the projection positions of the corresponding traffic signs, such as the traffic signs, the light poles, and the lane lines, in the perception image are respectively determined on the normalized plane or the plane where the perception image is located, and if the errors are smaller than a second preset distance, for example, smaller than 10-15 pixels, it is determined that the correction result of the vehicle pose meets the condition of error convergence. For example, in the checking process, if the projection error is still greater than the second preset distance, the nonlinear optimization algorithm may be continuously used to iteratively correct the vehicle pose until the projection error is less than the second preset distance.
Specifically, fig. 2f is a schematic projection diagram after the vehicle is subjected to accurate pose correction according to the embodiment of the present invention. Wherein, 1 represents a traffic sign in the perception image; 2, a traffic indicator in the projected navigation map; 3 represents the true position of the vehicle; 4 represents the current position of the vehicle in the navigation map; 5 denotes a light pole in the perceived image; 6, a light pole in the projected navigation map; 7 denotes a lane line in the perception image; and 8, a lane line in the projected navigation map. As shown in fig. 2f, in a normal road section where the traffic indication signs are relatively comprehensive, after the accurate pose correction is performed on the vehicle pose by using the light pole and the lane line, the projections of various types of traffic indication signs in the navigation map and the corresponding various types of traffic indication signs in the perception image on the normalization plane are close to coincidence. At this time, the updating operation of the display content of the navigation map can be performed, and the initialization process of the navigation map is completed.
According to the technical scheme provided by the embodiment, in the normal road section with comprehensive indication marks, the rough correction of the vehicle pose can be realized by utilizing the first indication marks such as the traffic sign in the navigation map and the perception image. After the rough correction is finished, the position of the street lamp pole and the lane line are combined, the pose of the vehicle can be further corrected, so that the pose of the vehicle after correction approaches to the real pose, the problem that the positioning precision is not high when the consumption-level preset positioning device is used is solved, and the consumption-level positioning device also has a high-precision positioning function.
EXAMPLE III
Referring to fig. 3, fig. 3 is a schematic structural diagram of a device for correcting a vehicle pose when a navigation map is initialized according to an embodiment of the present invention. As shown in FIG. 3, the apparatus includes an elevation correction module 310, a target index determination module 320, a first correction module 330, a second index determination module 340, and a second correction module 330; wherein the content of the first and second substances,
the elevation correction module 310 is configured to acquire a current position of a vehicle provided by a preset positioning device, and correct an elevation of the vehicle provided by the preset positioning device based on lane line information corresponding to the current position in a navigation map;
a target indicator determination module 320 configured to select a target indicator from the first indicators of the navigation map that matches the first indicators in the perceived image, the first indicator comprising a traffic sign;
a first correction module 330 configured to perform a first correction process on the pose of the vehicle in the navigation map based on the position of the target indicator;
a second indicator determination module 340 configured to determine, according to the pose and the elevation of the vehicle after the first correction processing, second indicators of other types in the navigation map and the perception image, which are matched with the first indicators, wherein the second indicators include lane lines and/or street lamp poles;
a second correction module 350, configured to perform a second correction process on the vehicle pose after the first correction process based on the positions of the target indicator and the matched second indicator, so that the positions of the first indicator and the second indicator in the navigation map respectively match the positions of the first indicator and the second indicator in the perception image according to the vehicle pose after the second correction process.
According to the technical scheme provided by the embodiment of the invention, in the normal road section with comprehensive traffic indication information such as traffic signs, traffic marking lines and the like, the first correction processing, namely rough correction, of the vehicle pose is completed by utilizing the position of the target traffic indication sign (generally referring to a traffic sign) matched with the sensing image in the navigation map. Because the traffic indication information in the normal road section is relatively comprehensive, after the rough correction of the vehicle is finished, the position and posture of the vehicle can be subjected to second correction processing, namely accurate correction, by using the indication marks such as a lane line or a light pole, so that more accurate vehicle positioning precision is obtained, and the problem of low positioning precision due to the use of a consumption-level preset positioning device is solved. Under the application scene of comprehensive information such as traffic signs, the consumption-level preset positioning device has the function of providing centimeter-level position accuracy.
Optionally, the first modification module is specifically configured to:
and performing first correction processing on position three degrees of freedom in six degrees of freedom of the vehicle through a nonlinear optimization algorithm based on the position of the target indicator, so that the projection error of each first indicator in the navigation map and the perception image on a preset standardized plane based on the position of the vehicle after the first correction processing is smaller than a first preset distance.
Optionally, the second modification module is specifically configured to:
performing second correction processing on the vehicle pose subjected to the first correction processing through a nonlinear optimization algorithm based on the positions of the target indicator and the matched second indicator;
respectively projecting each first indicator mark and each second indicator mark in the navigation map and the perception image to a preset standardized plane based on the pose of the vehicle after second correction processing;
on the preset standardized plane, respectively judging whether the projection distances between the first indicator mark and the second indicator mark projected in the navigation map and the corresponding first indicator mark and second indicator mark in the perception image are both smaller than a corresponding second preset distance;
if the first indication mark and the second indication mark in the navigation map are smaller than a second preset distance, determining that the positions of the first indication mark and the second indication mark in the navigation map are matched with the positions of the first indication mark and the second indication mark in the perception image according to the vehicle pose after the second correction processing;
and the second preset distances corresponding to the first indication mark and the second indication mark are smaller than the first preset distances corresponding to the first indication mark and the second indication mark respectively.
Optionally, the target indicator determination module is specifically configured to:
and reconstructing each first indicator mark in the perception image, comparing the similarity of the reconstructed first indicator mark with the similarity of the first indicator marks in the navigation map, and taking the first indicator mark with the similarity value reaching a first set threshold value as a matched target indicator mark.
Optionally, the target indicator determination module is specifically configured to:
selecting a target indicator matching each first indicator in the perceptual image from the first indicators of the navigation map, comprising:
and projecting the first indicator mark in the navigation map to a plane where a perception image is located, comparing the similarity of the first indicator mark in the perception image with the similarity of the first indicator mark in the perception image, and taking the first indicator mark with the similarity value reaching a second set threshold value as a matched target indicator mark.
Optionally, the elevation correction module is specifically configured to:
determining an average value of the elevations of the lane lines corresponding to the current position in the navigation map;
and taking the average value of the elevations of the lane lines as the elevation of the vehicle at the current position so as to correct the elevation of the vehicle provided by a preset positioning device.
Optionally, the apparatus further comprises:
after second correction processing is carried out on the pose of the vehicle in the navigation map, updating display content in the navigation map based on the pose of the vehicle after the second correction processing;
and returning to execute the operation of acquiring the current position of the vehicle provided by the preset positioning device to correct the pose of the vehicle again if the indicator is not acquired in the perception image with the continuously set frame number and/or the indicator in the navigation map during the running process of the vehicle.
Optionally, the apparatus further comprises:
and if the position of the vehicle provided by the preset positioning device is detected to have no corresponding coverage area in the navigation map, stopping the initialization operation of the navigation map, and switching the current automatic driving mode into the manual driving mode.
The device for correcting the vehicle pose of the navigation map during initialization provided by the embodiment of the invention can execute the method for correcting the vehicle pose of the navigation map during initialization provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method. Technical details that are not described in detail in the above embodiments may be referred to a method for correcting a vehicle pose at initialization of a navigation map provided in any embodiment of the present invention.
Example four
Referring to fig. 4, fig. 4 is a schematic structural diagram of a vehicle-mounted terminal according to an embodiment of the present invention. As shown in fig. 4, the in-vehicle terminal may include:
a memory 701 in which executable program code is stored;
a processor 702 coupled to the memory 701;
the processor 702 calls the executable program code stored in the memory 701 to execute the method for correcting the vehicle pose at the time of initialization of the navigation map provided by any embodiment of the present invention.
The embodiment of the invention discloses a computer-readable storage medium which stores a computer program, wherein the computer program enables a computer to execute the method for correcting the vehicle pose of a navigation map provided by any embodiment of the invention during initialization.
The embodiment of the invention discloses a computer program product, wherein when the computer program product runs on a computer, the computer is enabled to execute part or all of the steps of the method for correcting the vehicle pose of the navigation map provided by any embodiment of the invention during initialization.
In various embodiments of the present invention, it should be understood that the sequence numbers of the above-mentioned processes do not imply an inevitable order of execution, and the execution order of the processes should be determined by their functions and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
In the embodiments provided herein, it should be understood that "B corresponding to A" means that B is associated with A from which B can be determined. It should also be understood, however, that determining B from a does not mean determining B from a alone, but may also be determined from a and/or other information.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated units, if implemented as software functional units and sold or used as a stand-alone product, may be stored in a computer accessible memory. Based on such understanding, the technical solution of the present invention, which is a part of or contributes to the prior art in essence, or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a memory and includes several requests for causing a computer device (which may be a personal computer, a server, a network device, or the like, and may specifically be a processor in the computer device) to execute part or all of the steps of the above-described method of each embodiment of the present invention.
It will be understood by those skilled in the art that all or part of the steps in the methods of the above embodiments may be implemented by program instructions associated with hardware, and the program may be stored in a computer-readable storage medium, wherein the storage medium includes Read-Only Memory (ROM), Random Access Memory (RAM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), One-time Programmable Read-Only Memory (OTPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Compact Disc Read-Only Memory (CD-ROM), or other Memory, disk Memory, or other storage device, A tape memory, or any other medium readable by a computer that can be used to carry or store data.
The method and the device for correcting the vehicle pose during initialization of the navigation map disclosed by the embodiment of the invention are described in detail, a specific example is applied in the text to explain the principle and the implementation mode of the invention, and the description of the embodiment is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. A method for correcting the vehicle pose of a navigation map during initialization is applied to automatic driving, and is characterized by comprising the following steps:
acquiring the current position of a vehicle provided by a preset positioning device, and correcting the elevation of the vehicle provided by the preset positioning device based on lane line information corresponding to the current position in a navigation map;
selecting target indicators matched with the first indicators in the perception image from the first indicators of the navigation map, wherein the first indicators comprise traffic signs, and the target indicators are as follows: the similarity between each first indicator mark of the navigation map and each first indicator mark in the perception image meets the requirement;
performing first correction processing on the pose of the vehicle in the navigation map based on the position of the target indicator mark;
determining other types of second indicating signs matched with the navigation map and the perception image except the first indicating signs according to the pose and the elevation of the vehicle after the first correction processing, wherein the second indicating signs comprise lane lines and/or street lamp poles;
and performing second correction processing on the vehicle pose after the first correction processing based on the positions of the target indicator and the matched second indicator, so that the positions of the first indicator and the second indicator in the navigation map are respectively matched with the positions of the first indicator and the second indicator in the perception image according to the vehicle pose after the second correction processing.
2. The method according to claim 1, wherein performing a first correction process on the pose of the vehicle in the navigation map based on the position of the target indicator includes:
and performing first correction processing on position three degrees of freedom in six degrees of freedom of the vehicle through a nonlinear optimization algorithm based on the position of the target indicator, so that the projection error of each first indicator in the navigation map and the perception image on a preset standardized plane based on the position of the vehicle after the first correction processing is smaller than a first preset distance.
3. The method according to claim 1 or 2, wherein performing second correction processing on the first correction-processed vehicle pose based on the positions of the target indicator and the matched second indicator so that the positions of the first indicator and the second indicator in the navigation map respectively match the positions of the first indicator and the second indicator in the perception image according to the second correction-processed vehicle pose comprises:
performing second correction processing on the vehicle pose subjected to the first correction processing through a nonlinear optimization algorithm based on the positions of the target indicator and the matched second indicator;
respectively projecting each first indicator mark and each second indicator mark in the navigation map and the perception image to a preset standardized plane based on the pose of the vehicle after second correction processing;
on the preset standardized plane, respectively judging whether the projection distances of the first indicator mark and the second indicator mark projected in the navigation map and the corresponding first indicator mark and second indicator mark in the perception image are smaller than the corresponding second preset distance;
if the first indication mark and the second indication mark in the navigation map are smaller than the second preset distance, determining that the positions of the first indication mark and the second indication mark in the navigation map are matched with the positions of the first indication mark and the second indication mark in the perception image according to the vehicle pose after the second correction processing;
and the second preset distances corresponding to the first indication mark and the second indication mark are smaller than the first preset distances corresponding to the first indication mark and the second indication mark respectively.
4. The method of claim 1, wherein selecting a target indicator from the first indicators of the navigation map that matches the first indicators in the perceptual image comprises:
and reconstructing each first indicator mark in the perception image, comparing the similarity of the reconstructed first indicator mark with the similarity of the first indicator marks in the navigation map, and taking the first indicator mark with the similarity value reaching a first set threshold value as a matched target indicator mark.
5. The method of claim 1, wherein selecting a target indicator from the first indicators of the navigation map that matches the first indicators in the perceptual image comprises:
and projecting the first indicator mark in the navigation map to a plane where a perception image is located, comparing the similarity of the first indicator mark in the perception image with the similarity of the first indicator mark in the perception image, and taking the first indicator mark with the similarity value reaching a second set threshold value as a matched target indicator mark.
6. The method according to claim 1, wherein the correcting the elevation of the vehicle provided by the preset positioning device based on the lane line information corresponding to the current position in the navigation map comprises:
determining an average value of the elevations of the lane lines corresponding to the current position in the navigation map;
and taking the average value of the elevations of the lane lines as the elevation of the vehicle at the current position so as to correct the elevation of the vehicle provided by a preset positioning device.
7. The method according to claim 1, characterized in that after the second correction processing of the vehicle pose in the navigation map, the method further comprises:
updating display content in the navigation map based on the pose of the vehicle after the second correction processing;
and returning to execute the operation of acquiring the current position of the vehicle provided by the preset positioning device to correct the pose of the vehicle again if the indicator is not acquired in the perception image with the continuously set frame number and/or the indicator in the navigation map during the running process of the vehicle.
8. The method of claim 1, further comprising:
and if the position of the vehicle provided by the preset positioning device is detected to have no corresponding coverage area in the navigation map, stopping the initialization operation of the navigation map, and switching the current automatic driving mode into the manual driving mode.
9. A device for correcting the vehicle pose of a navigation map during initialization is applied to automatic driving, and is characterized by comprising the following steps:
the elevation correction module is configured to acquire the current position of the vehicle provided by a preset positioning device and correct the elevation of the vehicle provided by the preset positioning device based on lane line information corresponding to the current position in a navigation map;
a target indicator determination module configured to select a target indicator from the first indicators of the navigation map that matches the first indicators in the perceived image, the first indicator comprising a traffic sign, the target indicator being: the similarity between each first indicator mark of the navigation map and each first indicator mark in the perception image meets the requirement;
a first correction module configured to perform a first correction process on the pose of the vehicle in the navigation map based on the position of the target indicator;
a second indication mark determining module configured to determine, according to the pose and the elevation of the vehicle after the first correction processing, second indication marks of other types, which are matched with the navigation map and the perception image except the first indication marks, wherein the second indication marks comprise lane lines and/or street lamp poles;
and the second correction module is configured to perform second correction processing on the vehicle pose after the first correction processing based on the positions of the target indicator and the matched second indicator, so that the positions of the first indicator and the second indicator in the navigation map are respectively matched with the positions of the first indicator and the second indicator in the perception image according to the vehicle pose after the second correction processing.
10. The apparatus of claim 9, wherein the first modification module is specifically configured to:
and performing first correction processing on position three degrees of freedom in six degrees of freedom of the vehicle through a nonlinear optimization algorithm based on the position of the target indicator, so that the projection error of each first indicator in the navigation map and the perception image on a preset standardized plane based on the position of the vehicle after the first correction processing is smaller than a first preset distance.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910253289.0A CN111750882B (en) | 2019-03-29 | 2019-03-29 | Method and device for correcting vehicle pose during initialization of navigation map |
| PCT/CN2019/113480 WO2020199564A1 (en) | 2019-03-29 | 2019-10-26 | Method and apparatus for correcting vehicle position and posture during initialization of navigation map |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910253289.0A CN111750882B (en) | 2019-03-29 | 2019-03-29 | Method and device for correcting vehicle pose during initialization of navigation map |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111750882A CN111750882A (en) | 2020-10-09 |
| CN111750882B true CN111750882B (en) | 2022-05-27 |
Family
ID=72664885
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910253289.0A Active CN111750882B (en) | 2019-03-29 | 2019-03-29 | Method and device for correcting vehicle pose during initialization of navigation map |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111750882B (en) |
| WO (1) | WO2020199564A1 (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112802097A (en) * | 2020-12-30 | 2021-05-14 | 深圳市慧鲤科技有限公司 | Positioning method, positioning device, electronic equipment and storage medium |
| CN113280822B (en) * | 2021-04-30 | 2023-08-22 | 北京觉非科技有限公司 | Vehicle positioning method and positioning device |
| CN113566817B (en) * | 2021-07-23 | 2024-03-08 | 北京经纬恒润科技股份有限公司 | Vehicle positioning method and device |
| CN114111817B (en) * | 2021-11-22 | 2023-10-13 | 武汉中海庭数据技术有限公司 | Vehicle positioning method and system based on SLAM map and high-precision map matching |
| CN114419590B (en) * | 2022-01-17 | 2024-03-19 | 北京百度网讯科技有限公司 | Verification method, device, equipment and storage medium of high-precision map |
Family Cites Families (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09152348A (en) * | 1995-12-01 | 1997-06-10 | Pioneer Electron Corp | Car navigation device |
| JP2001264087A (en) * | 2000-03-17 | 2001-09-26 | Datatron:Kk | On-vehicle position management information display device |
| JP4377284B2 (en) * | 2004-06-02 | 2009-12-02 | 株式会社ザナヴィ・インフォマティクス | Car navigation system |
| CN103303313A (en) * | 2012-03-06 | 2013-09-18 | 北京四维图新科技股份有限公司 | Vehicle control method and vehicle control system |
| JP6165422B2 (en) * | 2012-06-28 | 2017-07-19 | 株式会社ナビタイムジャパン | Information processing system, information processing device, server, terminal device, information processing method, and program |
| US9342888B2 (en) * | 2014-02-08 | 2016-05-17 | Honda Motor Co., Ltd. | System and method for mapping, localization and pose correction of a vehicle based on images |
| KR101843773B1 (en) * | 2015-06-30 | 2018-05-14 | 엘지전자 주식회사 | Advanced Driver Assistance System, Display apparatus for vehicle and Vehicle |
| CN105021201B (en) * | 2015-08-17 | 2017-12-01 | 武汉光庭信息技术有限公司 | Utilize the anti-system and method for pushing away automobile self-position of the coordinate of traffic marking board |
| CN105718860B (en) * | 2016-01-15 | 2019-09-10 | 武汉光庭科技有限公司 | Localization method and system based on driving safety map and binocular Traffic Sign Recognition |
| CN105783936B (en) * | 2016-03-08 | 2019-09-24 | 武汉中海庭数据技术有限公司 | For the road markings drawing and vehicle positioning method and system in automatic Pilot |
| CN107643086B (en) * | 2016-07-22 | 2021-04-13 | 北京四维图新科技股份有限公司 | Vehicle positioning method, device and system |
| CN106405601A (en) * | 2016-10-21 | 2017-02-15 | 北京汽车集团有限公司 | Vehicle positioning method and apparatus, and vehicle |
| CN106651953B (en) * | 2016-12-30 | 2019-10-18 | 山东大学 | A kind of vehicle position and orientation estimation method based on traffic sign |
| CN106842269A (en) * | 2017-01-25 | 2017-06-13 | 北京经纬恒润科技有限公司 | Localization method and system |
| CN108303103B (en) * | 2017-02-07 | 2020-02-07 | 腾讯科技（深圳）有限公司 | Method and device for determining target lane |
| CN107144285B (en) * | 2017-05-08 | 2020-06-26 | 深圳地平线机器人科技有限公司 | Pose information determination method and device and movable equipment |
| CN107389088B (en) * | 2017-05-27 | 2020-11-17 | 纵目科技（上海）股份有限公司 | Error correction method, device, medium and equipment for vehicle-mounted inertial navigation |
| US10551509B2 (en) * | 2017-06-30 | 2020-02-04 | GM Global Technology Operations LLC | Methods and systems for vehicle localization |
| CN107328410B (en) * | 2017-06-30 | 2020-07-28 | 百度在线网络技术（北京）有限公司 | Method for locating an autonomous vehicle and vehicle computer |
| CN107957266B (en) * | 2017-11-16 | 2020-09-01 | 北京小米移动软件有限公司 | Positioning method, positioning device and storage medium |
| CN108090456B (en) * | 2017-12-27 | 2020-06-19 | 北京初速度科技有限公司 | Training method for recognizing lane line model, and lane line recognition method and device |
| CN109141444B (en) * | 2018-08-28 | 2019-12-06 | 北京三快在线科技有限公司 | positioning method, positioning device, storage medium and mobile equipment |
| CN109405824A (en) * | 2018-09-05 | 2019-03-01 | 武汉契友科技股份有限公司 | A kind of multi-source perceptual positioning system suitable for intelligent network connection automobile |
-
2019
- 2019-03-29 CN CN201910253289.0A patent/CN111750882B/en active Active
- 2019-10-26 WO PCT/CN2019/113480 patent/WO2020199564A1/en active Application Filing
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020199564A1 (en) | 2020-10-08 |
| CN111750882A (en) | 2020-10-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110954112B (en) | Method and device for updating matching relation between navigation map and perception image | |
| CN111750882B (en) | Method and device for correcting vehicle pose during initialization of navigation map | |
| CN111750881B (en) | Vehicle pose correction method and device based on light pole | |
| CN110954113B (en) | Vehicle pose correction method and device | |
| CN111750878B (en) | Vehicle pose correction method and device | |
| CN110146097B (en) | Method and system for generating automatic driving navigation map, vehicle-mounted terminal and server | |
| CN109141444B (en) | positioning method, positioning device, storage medium and mobile equipment | |
| CN110146096B (en) | Vehicle positioning method and device based on image perception | |
| CN111854727B (en) | Vehicle pose correction method and device | |
| CN111912416B (en) | Method, device and equipment for positioning equipment | |
| CN110906954A (en) | High-precision map test evaluation method and device based on automatic driving platform | |
| CN111065042B (en) | Method for improving positioning of road side unit, road side unit and system for providing position information | |
| CN108693548B (en) | Navigation method and system based on scene target recognition | |
| CN110597252B (en) | Fusion positioning control method, device and equipment for automatic driving automobile and storage medium | |
| CN110608746B (en) | Method and device for determining the position of a motor vehicle | |
| CN114459471B (en) | Positioning information determining method and device, electronic equipment and storage medium | |
| CN110018503B (en) | Vehicle positioning method and positioning system | |
| US11327155B2 (en) | Radar sensor misalignment detection for a vehicle | |
| CN114677663A (en) | Vehicle positioning method and device, electronic equipment and computer-readable storage medium | |
| CN113048988B (en) | Method and device for detecting change elements of scene corresponding to navigation map | |
| CN115112125A (en) | Positioning method and device for automatic driving vehicle, electronic equipment and storage medium | |
| CN109945890A (en) | More positioning systems switch and merge bearing calibration and its device | |
| CN110398243A (en) | A kind of vehicle positioning method and device | |
| CN113566824A (en) | Vehicle positioning method and device, electronic equipment and storage medium | |
| CN113503883A (en) | Method for collecting data for constructing map, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220228 Address after: 100083 unit 501, block AB, Dongsheng building, No. 8, Zhongguancun East Road, Haidian District, Beijing Applicant after: BEIJING MOMENTA TECHNOLOGY Co.,Ltd. Address before: Room 28, 4 / F, block a, Dongsheng building, No. 8, Zhongguancun East Road, Haidian District, Beijing 100089 Applicant before: BEIJING CHUSUDU TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |