WO2020199566A1 - 一种导航地图与感知图像匹配关系的更新方法和装置 - Google Patents

一种导航地图与感知图像匹配关系的更新方法和装置 Download PDF

Info

Publication number
WO2020199566A1
WO2020199566A1 PCT/CN2019/113485 CN2019113485W WO2020199566A1 WO 2020199566 A1 WO2020199566 A1 WO 2020199566A1 CN 2019113485 W CN2019113485 W CN 2019113485W WO 2020199566 A1 WO2020199566 A1 WO 2020199566A1
Authority
WO
WIPO (PCT)
Prior art keywords
traffic sign
navigation map
vehicle
distance
preset
Prior art date
Application number
PCT/CN2019/113485
Other languages
English (en)
French (fr)
Inventor
李江龙
侯政华
Original Assignee
魔门塔(苏州)科技有限公司
北京初速度科技有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 魔门塔(苏州)科技有限公司, 北京初速度科技有限公司 filed Critical 魔门塔(苏州)科技有限公司
Publication of WO2020199566A1 publication Critical patent/WO2020199566A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/28Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
    • G01C21/30Map- or contour-matching
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/09Arrangements for giving variable traffic instructions
    • G08G1/0962Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/0968Systems involving transmission of navigation instructions to the vehicle
    • G08G1/0969Systems involving transmission of navigation instructions to the vehicle having a display in the form of a map

Definitions

  • the invention relates to the technical field of automatic driving, in particular to a method and device for updating the matching relationship between a navigation map and a perceived image.
  • the embodiment of the invention discloses a method and device for updating the matching relationship between a navigation map and a perceived image, which solves the problem of low positioning accuracy using a consumer-level preset positioning device, and realizes that the consumer-level preset positioning device can also perform high-precision positioning Technical effect.
  • an embodiment of the present invention discloses a method for updating the matching relationship between a navigation map and a perceived image, and the method includes:
  • the traffic sign group includes at least any two first traffic signs;
  • the pose of the vehicle in the navigation map is corrected, and the matching relationship between the navigation map and the perception image is updated based on the height and pose of the corrected vehicle.
  • arranging and combining traffic sign groups in the navigation map and the perceived image collected by the camera to determine a target traffic sign with a matching position from the navigation map and the perceived image including:
  • the second traffic sign group Combine the first traffic signs in the navigation map that meets the set distance requirement with the current location in pairs to form a first traffic sign group, and combine the first traffic signs in the perceived image collected by the camera to form the first traffic sign group.
  • the second traffic sign group ;
  • the first traffic sign group in the navigation map after sorting and the second traffic sign group in the corresponding perception map are taken as the target traffic Sign.
  • the updating the matching relationship between the navigation map and the perceived image based on the height and pose of the corrected vehicle includes:
  • the re-projection error is less than the set threshold corresponding to that type of traffic sign, the matching relationship between the navigation map and the perceived image is updated according to the re-projection error.
  • the reprojection error between the traffic sign in the navigation map after the judgment content is updated and the traffic sign in the perceived image includes:
  • the second traffic sign is a traffic sign of a different type from the first traffic sign.
  • the method further includes:
  • correcting the elevation of the vehicle provided by the preset positioning device includes:
  • the elevation of the lane line is taken as the elevation of the vehicle at the current position to correct the elevation of the vehicle provided by the preset positioning device.
  • the first traffic sign is a street light pole
  • the second traffic sign includes a lane line or a traffic sign.
  • an embodiment of the present invention also provides a device for updating the matching relationship between a navigation map and a perceived image, the device including:
  • the elevation correction module is configured to obtain the current position of the vehicle provided by the preset positioning device, and based on the lane line information corresponding to the current position in the navigation map, correct the elevation of the vehicle provided by the preset positioning device;
  • the target traffic sign determination module is configured to arrange and combine traffic sign groups whose current location meets the set distance requirement in the navigation map and the perceived image collected by the camera, respectively, to obtain information from the navigation map and the perceived image Determine the target traffic sign with matching position in the image, and the traffic sign group includes at least any two first traffic signs;
  • the matching relationship update module is configured to correct the pose of the vehicle in the navigation map according to the location of the target traffic sign, and update the navigation map and the perception image based on the height and pose of the corrected vehicle The matching relationship between.
  • the target traffic sign determination module includes:
  • the permutation and combination unit is configured to combine the first traffic signs in the navigation map that meets the set distance requirement from the current position in pairs to form a first traffic sign group, and combine the first traffic sign group in the perception image collected by the camera.
  • the traffic signs are combined in pairs to form the second traffic sign group;
  • the sorting unit is configured to sort the first traffic sign group according to the distance from the current position from short to far, and to sort the second traffic sign group according to the distance between the two end points from the longest to the shortest. Way to sort;
  • the vehicle position estimation unit is configured to calculate the geometric relationship between the upper end points of any group of traffic sign groups in the navigation map after sorting and the upper end points of any group of traffic sign groups in the perceptual image after sorting To determine the estimated position of the vehicle;
  • the target traffic sign determining unit is configured to, if the distance between the estimated position and the current position is less than a first preset distance, the first traffic sign group in the navigation map after sorting and the corresponding perception map The second traffic sign group is used as the target traffic sign.
  • the matching relationship update module includes:
  • the pose correction unit is configured to correct the pose of the vehicle in the navigation map according to the position of the target traffic sign;
  • the display content update unit is configured to update the display content in the navigation map according to the height and pose of the vehicle after correction;
  • the actual distance judging unit is configured to judge whether the distance between the position of the vehicle after the position correction in the navigation map after the display content is updated and the current position is less than a second preset distance, wherein the second preset The distance is less than the first preset distance;
  • the projection unit is configured to, if the distance between the position of the corrected vehicle in the navigation map after the display content is updated and the current position is less than the second preset distance, the navigation map after the content update is based on the corrected navigation map.
  • the vehicle pose is projected onto a preset standardized plane, and the display content in the perception image is also projected onto the preset standardized plane;
  • the re-projection error determining unit is configured to determine, on the standardized plane, the re-projection error of each traffic sign in the updated navigation map and the corresponding traffic sign in the perceived image;
  • the matching relationship update unit is configured to, for any type of traffic sign, if the re-projection error is less than the set threshold corresponding to the type of traffic sign, update the navigation map and the perception according to the re-projection error The matching relationship between the images.
  • the reprojection error judgment unit is specifically configured as:
  • the second traffic sign is a traffic sign of a different type from the first traffic sign.
  • the apparatus further includes:
  • the uncertainty receiving module is configured to receive the uncertainty of the vehicle pose
  • the state switching module is configured to, if the uncertainty is greater than the set threshold, return to execute the vehicle elevation correction operation to renew the matching relationship.
  • the elevation correction module is specifically configured as:
  • the elevation of the lane line is taken as the elevation of the vehicle at the current position to correct the elevation of the vehicle provided by the preset positioning device.
  • the first traffic sign is a street light pole
  • the second traffic sign includes a lane line or a traffic sign.
  • an embodiment of the present invention also provides a vehicle-mounted terminal, including:
  • a memory storing executable program codes
  • a processor coupled with the memory
  • the processor calls the executable program code stored in the memory to execute part or all of the steps of the method for updating the matching relationship between the navigation map and the perceived image provided by any embodiment of the present invention.
  • an embodiment of the present invention also provides a computer-readable storage medium that stores a computer program, and the computer program includes a method for executing the matching relationship between a navigation map and a perception image provided by any embodiment of the present invention. Instructions for some or all of the steps.
  • the embodiments of the present invention also provide a computer program product, which when the computer program product runs on a computer, causes the computer to execute the matching relationship between the navigation map and the perceived image provided by any embodiment of the present invention. Part or all of the steps in the update method.
  • the technical solution provided by this embodiment after completing the vehicle elevation correction, arranges and combines the navigation map and the perception image collected by the camera with the traffic sign group whose current position meets the set distance requirement to obtain the navigation map and perception Identify the target traffic sign that matches the location in the image.
  • the pose of the vehicle in the navigation map can be corrected, so that the position of the vehicle body can be aligned with the position of the navigation map, so that a correct matching relationship between the perceived image and the navigation map can be obtained.
  • the invention points of the present invention include:
  • traffic signs such as street light poles exist, they can be accurately identified, and the traffic signs can be used to correct the pose of the vehicle, thereby completing the initialization operation of the navigation map, making the consumer-grade positioning equipment have high-precision positioning functions , Is one of the invention points of the present invention.
  • the estimated position of the vehicle is determined based on the geometric relationship between the endpoints of the traffic sign group in the perception image and the navigation map, and the estimated position of the vehicle is compared with the prior
  • the traffic sign group corresponding to the distance between the positions less than the set threshold is used as the target traffic sign, which is one of the invention points of the present invention.
  • the determined vehicle line elevation can be used as the elevation of the current position of the vehicle to complete the correction of the vehicle elevation, thereby adding subsequent navigation maps and perception images
  • the probability of correct matching is one of the invention points of the present invention.
  • Fig. 1a is a schematic flowchart of a method for updating the matching relationship between a navigation map and a perceived image according to an embodiment of the present invention
  • FIG. 1b is a schematic diagram of the geometric relationship between a street light pole in a perception image and a street light pole in a navigation map according to an embodiment of the present invention
  • 2a is a schematic flowchart of a method for updating the matching relationship between a navigation map and a perceived image according to an embodiment of the present invention
  • Figure 2b is a schematic diagram of a vehicle elevation correction provided by an embodiment of the present invention.
  • Figure 2c is a schematic diagram of a rough pose correction of a vehicle provided by an embodiment of the present invention.
  • 2d is a schematic diagram of updating the position of a vehicle displayed in a navigation map according to an embodiment of the present invention
  • FIG. 3 is a schematic structural diagram of a device for updating the matching relationship between a navigation map and a perceived image provided by an embodiment of the present invention
  • Fig. 4 is a schematic structural diagram of a vehicle-mounted terminal provided by an embodiment of the present invention.
  • FIG. 1a is a schematic flowchart of a method for updating the matching relationship between a navigation map and a perceived image according to an embodiment of the present invention.
  • This method is typically applied to a scene where an unmanned vehicle enters an outdoor high-precision map for the first time, and can be executed by a device for updating the matching relationship between the navigation map and the perceived image, and the device can be implemented by software and/or hardware.
  • the device can be implemented by software and/or hardware.
  • it can be integrated in an in-vehicle terminal such as an in-vehicle computer and an in-vehicle industrial control computer (IPC), which is not limited in the embodiment of the present invention.
  • IPC industrial control computer
  • the method provided in this embodiment specifically includes:
  • the preset positioning device is a single-point GPS or a low-precision consumer-grade positioning device.
  • the navigation map refers to a high-precision map with a centimeter-level error level applied to automatic driving.
  • the elevation of the vehicle refers to the altitude of the vehicle provided by the consumer-grade positioning device.
  • the positioning accuracy is low, sometimes with an error of a few meters or even a dozen meters, but the lane line height does not change much within the error range. Therefore, according to the current position of the vehicle provided by the consumer-grade positioning device, the navigation map can search for lane line information a few meters near the current position, so as to use the lane line information to correct the height of the vehicle to pull the vehicle to the height of the lane line.
  • the vehicle elevation and pose correction sequence there is no prioritization of the vehicle elevation and pose correction sequence.
  • the vehicle elevation can be corrected first, and then the vehicle pose can be corrected, or the vehicle can also be corrected first.
  • the posture is corrected, and then the elevation of the vehicle is corrected, which is not specifically limited in this embodiment.
  • traffic signs include street light poles, lane lines and traffic signs.
  • the street light pole has more information. Therefore, in this embodiment, the street light pole is preferably used as the first traffic sign, and the street light pole is used to provide front-to-back and left-right constraints on the vehicle body position. The pose of the vehicle is roughly corrected.
  • any two street light poles (referred to as map poles) in the navigation map and any two street light poles in the perception image (referred to as perception image poles) may have a matching relationship. Therefore, in order to It is determined that there are map poles and perceptual image poles that have a corresponding matching relationship.
  • a traffic sign group such as a street light pole group, is established, and each group of street light poles includes any two street light poles.
  • the navigation map and the traffic sign group in the perceived image collected by the camera are arranged and combined to determine the target traffic sign with a matching position from the navigation map and the perceived image, which can be implemented in the following manner:
  • this embodiment uses the perception image and the upper end of the street light pole in the navigation map to calculate a rough vehicle body position.
  • all the street light pole groups in the perceived image can be projected onto the image plane or on the normalized plane of the camera and sorted according to the distance between the upper and lower end points from long to short.
  • the normalized plane can be established in the camera coordinate system, and the distance from the origin of the camera coordinate system is 1 meter.
  • the traffic sign group Since the navigation map and the perception image both contain multiple sets of traffic signs, if the estimated position of the vehicle determined by the current traffic sign set and the current position of the vehicle body (that is, the prior position) are too large, for example, greater than the first For a preset distance, the matching relationship between the navigation map and the perception image can be deleted, and other traffic sign groups can be selected in turn for matching.
  • FIG. 1b is a schematic diagram of the geometric relationship between a street light pole in a perception image and a street light pole in a navigation map according to an embodiment of the present invention.
  • a pair of street light poles in the perception image The connection between the upper end point of the transformation plane or the projection on the image plane and the upper end point of a pair of street lamp poles in the navigation map can locate the estimated position of the vehicle.
  • a rough screen is performed according to the distance between the estimated position of the vehicle body and the prior position, and the street light pole group whose estimated position and the prior position are greater than the first preset distance can be deleted, thereby further reducing the algorithm time complexity.
  • each street light pole in the street light pole group whose distance between the estimated position and the prior position is less than the first preset distance can be used as a target traffic sign.
  • the matching rate can be improved and the time complexity of the algorithm calculation can be reduced.
  • the purpose of correcting the pose of the vehicle is to minimize the deviation between the current position of the vehicle and the actual correct position of the vehicle.
  • the iterative correction method can be used to continuously approach the current position of the vehicle to the true position of the vehicle.
  • the determination of the target traffic sign indicates that the target traffic sign in the perception image has established a one-to-one correspondence with the corresponding target traffic sign in the navigation map.
  • the non-linear optimization algorithm can be used to correct the front and rear and left and right directions of the vehicle body (vehicle elevation has been corrected through step 110).
  • a second traffic sign that matches a different type of the first traffic sign can be introduced, such as lane lines and/or traffic signs, etc., to correct the pose of the vehicle, that is, use the updated matching Relations and lane lines non-linearly optimize the front and rear position, left and right position and elevation of the vehicle body, and update the matching relationship between the navigation map and the perception image based on the updated vehicle pose.
  • the matching relationship can be checked before the matching relationship is output.
  • the specific checking method can be: judging whether the optimized vehicle position and the prior position If the distance meets the set distance requirement, and the reprojection residuals of the lamp poles and lane lines in the updated matching relationship under the latest vehicle pose are all less than the corresponding set threshold, the navigation map
  • the matching relationship with the perceived image has reached the standard, and the updated matching relationship can be output at this time to complete the initialization of the navigation map.
  • the car body can obtain centimeter-level positioning accuracy, and the car body can be aligned with the navigation map.
  • the technical solution provided by this embodiment after completing the vehicle elevation correction, arranges and combines the navigation map and the perception image collected by the camera with the traffic sign group whose current position meets the set distance requirement to obtain the navigation map and perception Identify the target traffic sign that matches the location in the image.
  • the pose of the vehicle in the navigation map can be corrected, so that the position of the vehicle body can be aligned with the position of the navigation map, so that a correct matching relationship between the perceived image and the navigation map can be obtained.
  • the matching relationship between the navigation map and the perceived image is updated, if it is determined that the received vehicle pose uncertainty, that is, the covariance information, is greater than the set threshold, then return to execute the vehicle elevation correction operation, To re-update the matching relationship, that is, switch to the initialization state again, to ensure the correctness of the matching relationship and the accuracy of the vehicle body position.
  • FIG. 2a is a schematic flowchart of a method for updating the matching relationship between a navigation map and a perceived image according to an embodiment of the present invention.
  • this embodiment optimizes the process of updating the matching relationship between the navigation map and the perceived image based on the height and pose of the corrected vehicle, and adds verification of the matching relationship when outputting the matching relationship. Whether the operation is reasonable.
  • the method includes:
  • Figure 2b is a schematic diagram of a vehicle elevation correction provided by an embodiment of the present invention. As shown in Figure 2b, the vehicle can be pulled to the height of the lane line by correcting the height of the vehicle.
  • step 230 is the process of roughly correcting the vehicle's pose. This process mainly uses the target traffic signs identified in 220, such as street light poles, to correct the position of the vehicle, so that the distance between the position of the vehicle and its real position is reduced.
  • target traffic signs identified in 220 such as street light poles
  • FIG. 2c is a schematic diagram of a rough pose correction of a vehicle provided by an embodiment of the present invention.
  • 1-6 respectively represent the street light poles in the navigation map; 7-10 respectively represent the street light poles in the perception image; street light poles 1 and 6 in the navigation map can form a map street light pole group, and the perception image
  • the street light poles 7 and 10 can form an image street light pole group.
  • the display content in the navigation map will change accordingly. After updating the display content in the navigation map, correspondingly, the traffic signs matching the navigation map in the perception map should be updated accordingly.
  • traffic signs such as lane lines and traffic signs, that match the perception map are identified in the navigation map after the display content is updated
  • these traffic signs can be used to determine the position of the vehicle. Further nonlinear optimization. After further optimization, the updated car body position in the navigation map is closer to the real position.
  • FIG. 2d is a schematic diagram of updating the position of a vehicle displayed in a navigation map according to an embodiment of the present invention. As shown in Figure 2d, after further optimizing the vehicle's rough calibration position, the updated vehicle body position is close to the actual vehicle body position, which achieves the effect of aligning the vehicle pose with the navigation map.
  • step 250 Determine whether the distance between the position of the vehicle after the position correction and the current position in the navigation map after the display content is updated is less than the second preset distance, if yes, perform step 260; otherwise, return to step 220.
  • the second preset distance is smaller than the first preset distance.
  • step 270 Project the updated navigation map to the preset standardized plane according to the corrected vehicle pose, and project the display content in the perception image to the preset standardized plane, and continue to perform step 270.
  • step 280 determines whether the reprojection error between the various types of traffic signs in the updated navigation map and the corresponding traffic signs in the perceived image is less than the corresponding traffic signs of this type If yes, go to step 280; otherwise, go to step 220.
  • the residual thresholds are set for different types of traffic signs.
  • step 270 may include: determining whether the re-projection residual between the first traffic sign in the updated navigation map and the corresponding first traffic sign in the perception image is less than a first preset residual threshold;
  • the reprojection residual between the second traffic sign in the updated navigation map and the corresponding second traffic sign in the perception image is less than the second preset residual threshold ;
  • the second traffic sign is a different type of traffic sign from the first traffic sign.
  • the first traffic sign is preferably a street light pole, and the second traffic sign includes a lane line or a traffic sign.
  • step 250 the distance between the corrected position of the vehicle and the prior position meets the preset distance requirement
  • step 270 it is determined that at least two types of traffic signs are in the latest vehicle pose Only when the reprojection residuals of each meet the corresponding projection threshold requirements, the matching relationship between the navigation map and the perceived image can be output, and the initialization operation can be completed.
  • the position of the vehicle body has been well registered with the high-precision map.
  • the updated pose of the vehicle can be closer to the real pose.
  • it can be determined whether the distance between the corrected position of the vehicle and the prior position meets the preset requirements, and at least two types of traffic in the navigation map and the perceived image Mark whether the re-projection residual convergence conditions are met under the latest vehicle pose. If the above two conditions are met, it indicates the matching relationship between the navigation map and the perceived image or the perception image determined based on the corrected vehicle pose When the requirements are met, the matching relationship can be updated and output at this time to complete the initialization process.
  • FIG. 3 is a schematic structural diagram of a device for updating the matching relationship between a navigation map and a perceived image according to an embodiment of the present invention.
  • the device includes: an elevation correction module 310, a target traffic sign determination module 320, and a matching relationship update module 330.
  • the elevation correction module 310 is configured to obtain the current position of the vehicle provided by the preset positioning device, and based on the lane line information corresponding to the current position in the navigation map, perform the elevation of the vehicle provided by the preset positioning device.
  • the target traffic sign determination module 320 is configured to arrange and combine the traffic sign groups whose current position meets the set distance requirement in the navigation map and the perceived image collected by the camera, respectively, to obtain information from the navigation map and the Identifying target traffic signs with matching positions in the perception image, and the traffic sign group includes at least any two first traffic signs;
  • the matching relationship update module 330 is configured to correct the pose of the vehicle in the navigation map according to the location of the target traffic sign, and update the navigation map and the perception based on the height and pose of the corrected vehicle The matching relationship between the images.
  • the technical solution provided by this embodiment after completing the vehicle elevation correction, arranges and combines the navigation map and the perception image collected by the camera with the traffic sign group whose current position meets the set distance requirement to obtain the navigation map and perception Identify the target traffic sign that matches the location in the image.
  • the pose of the vehicle in the navigation map can be corrected, so that the position of the vehicle body can be aligned with the position of the navigation map, so that a correct matching relationship between the perceived image and the navigation map can be obtained.
  • the target traffic sign determination module includes:
  • the permutation and combination unit is configured to combine the first traffic signs in the navigation map that meets the set distance requirement from the current position in pairs to form a first traffic sign group, and combine the first traffic sign group in the perception image collected by the camera.
  • the traffic signs are combined in pairs to form the second traffic sign group;
  • the sorting unit is configured to sort the first traffic sign group according to the distance from the current position from short to far, and to sort the second traffic sign group according to the distance between the two end points from the longest to the shortest. Way to sort;
  • the vehicle position estimation unit is configured to calculate the geometric relationship between the upper end points of any group of traffic sign groups in the navigation map after sorting and the upper end points of any group of traffic sign groups in the perceptual image after sorting To determine the estimated position of the vehicle;
  • the target traffic sign determining unit is configured to, if the distance between the estimated position and the current position is less than a first preset distance, the first traffic sign group in the navigation map after sorting and the corresponding perception map The second traffic sign group is used as the target traffic sign.
  • the matching relationship update module includes:
  • the pose correction unit is configured to correct the pose of the vehicle in the navigation map according to the position of the target traffic sign;
  • the display content update unit is configured to update the display content in the navigation map according to the height and pose of the vehicle after correction;
  • the actual distance judging unit is configured to judge whether the distance between the position of the vehicle after the position correction in the navigation map after the display content is updated and the current position is less than a second preset distance, wherein the second preset The distance is less than the first preset distance;
  • the projection unit is configured to, if the distance between the position of the corrected vehicle in the navigation map after the display content is updated and the current position is less than the second preset distance, the navigation map after the content update is based on the corrected navigation map.
  • the vehicle pose is projected onto a preset standardized plane, and the display content in the perception image is also projected onto the preset standardized plane;
  • the re-projection error determining unit is configured to determine, on the standardized plane, the re-projection error of each traffic sign in the updated navigation map and the corresponding traffic sign in the perceived image;
  • the matching relationship update unit is configured to, for any type of traffic sign, if the re-projection error is less than the set threshold corresponding to the type of traffic sign, update the navigation map and the perception according to the re-projection error The matching relationship between the images.
  • the reprojection error judgment unit is specifically configured as:
  • the second traffic sign is a traffic sign of a different type from the first traffic sign.
  • the apparatus further includes:
  • the uncertainty receiving module is configured to receive the uncertainty of the vehicle pose
  • the state switching module is configured to, if the uncertainty is greater than the set threshold, return to execute the vehicle elevation correction operation to renew the matching relationship.
  • the elevation correction module is specifically configured as:
  • the elevation of the lane line is taken as the elevation of the vehicle at the current position to correct the elevation of the vehicle provided by the preset positioning device.
  • the first traffic sign is a street light pole
  • the second traffic sign includes a lane line or a traffic sign.
  • the device for updating the matching relationship between the navigation map and the perceived image provided by the embodiment of the present invention can execute the method for updating the matching relationship between the navigation map and the perceived image provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for the execution method.
  • the method for updating the matching relationship between the navigation map and the perceived image provided by any embodiment of the present invention refer to the method for updating the matching relationship between the navigation map and the perceived image provided by any 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.
  • the vehicle-mounted terminal may include:
  • a memory 701 storing executable program codes
  • a processor 702 coupled with the memory 701;
  • the processor 702 calls the executable program code stored in the memory 701 to execute the method for updating the matching relationship between the navigation map and the perceived image provided by any embodiment of the present invention.
  • the embodiment of the present invention discloses a computer-readable storage medium that stores a computer program, where the computer program enables a computer to execute the method for updating the matching relationship between a navigation map and a perception image provided by any embodiment of the present invention.
  • the embodiment of the present invention discloses a computer program product, wherein when the computer program product runs on a computer, the computer is caused to execute part or all of the steps of the method for updating the matching relationship between the navigation map and the perceived image provided by any embodiment of the present invention.
  • B corresponding to A means that B is associated with A, and B can be determined according to A.
  • determining B according to A does not mean that B is determined only according to A, and B can also be determined according to A and/or other information.
  • the 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 may be integrated into one unit.
  • the above-mentioned integrated unit can be implemented in the form of hardware or software functional unit.
  • the aforementioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-accessible memory.
  • the essence of the technical solution of the present invention or the part that contributes to the existing technology or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory.
  • a computer device which may be a personal computer, a server, or a network device, etc., specifically a processor in a computer device
  • the program can be stored in a computer-readable storage medium.
  • the storage medium includes read-only Memory (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), Electronically-Erasable Programmable Read-Only Memory (EEPROM), CD-ROM (Compact Disc) Read-Only Memory, CD-ROM) or other optical disk storage, magnetic disk storage, tape storage, or any other computer-readable medium that can be used to carry or store data.
  • Read-Only Memory ROM
  • RAM Random Access Memory
  • PROM Programmable Read-only Memory
  • EPROM Erasable Programmable Read Only Memory
  • OTPROM One-time Programmable Read-Only Memory
  • EEPROM Electronically-Erasable Programmable Read-Only Memory
  • CD-ROM Compact Disc

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Navigation (AREA)

Abstract

一种导航地图与感知图像匹配关系的更新方法和装置,该方法包括:获取预设定位装置提供的车辆的当前位置,并基于导航地图中当前位置对应的车道线信息,对预设定位装置提供的车辆的高程进行修正(110);分别将导航地图和摄像头所采集感知图像中与当前位置满足设定距离要求的交通标志组进行排列组合,以从导航地图和感知图像中确定位置相匹配的目标交通标志(120);根据目标交通标志的位置对导航地图中车辆的位姿进行修正,并基于修正后车辆的高程和位姿更新导航地图与感知图像之间的匹配关系(130)。通过采用上述技术方案,解决了使用消费级预设定位装置定位精度不高的问题,使得消费级预设定位装置也能进行高精度定位的效果。

Description

一种导航地图与感知图像匹配关系的更新方法和装置 技术领域
本发明涉及自动驾驶技术领域,具体涉及一种导航地图与感知图像匹配关系的更新方法和装置。
背景技术
在自动驾驶领域,高精度定位至关重要。近年来,深度学习等技术的成果,极大促进了图像语义分割、图像识别领域的发展,这为高精度地图及高精度定位提供了坚实的基础。
在基于高精度地图的定位方案中,当无人驾驶车辆第一次进入高精度地图时,需要获得一个全局而精准的位置信息进行初始化,继而可以使用高精度地图进行精准定位,即绝对位置精度可达到厘米级。但在消费级设备,例如单点GPS(Global Positioning System,全球定位系统)与廉价IMU(Inertial measurement unit,惯性测量单元)的定位方案中,由于单点GPS所提供的定位精度信息的误差较大,利用单点GPS所提供的位置,将高精度地图中的交通标志信息与利用深度学习感知模型感知出图像中的交通标志信息,例如车道线、路灯杆等,进行重投影匹配时,容易造成车道线左右匹配错误,路灯杆前后向匹配错误等问题。如果利用错误的匹配信息对车体位置进行修正,不仅不能利用高精地图使车体的位置精度达到厘米级,反而可能会使车体的位置与真实位置偏离更大。
发明内容
本发明实施例公开一种导航地图与感知图像匹配关系的更新方法和装置,解决了使用消费级预设定位装置定位精度不高的问题,实现了消费级预设定位装置也能进行高精度定位的技术效果。
第一方面,本发明实施例公开了一种导航地图与感知图像匹配关系的更新方法,该方法包括:
获取预设定位装置提供的车辆的当前位置,并基于导航地图中所述当前位置对应的车道线信息,对所述预设定位装置提供的车辆的高程进行修正;
分别将所述导航地图和摄像头所采集感知图像中与所述当前位置满足设定距离要求的交通标志组进行排列组合,以从所述导航地图和所述感知图像中确定位置相匹配的目标交通标志,所述交通标志组中包括至少任意两个第一交通标志;
根据所述目标交通标志的位置,对所述导航地图中车辆的位姿进行修正,并基于修正后车辆的高程和位姿更新所述导航地图与所述感知图像之间的匹配关系。
可选的,分别将所述导航地图和摄像头所采集感知图像中的交通标志组进行排列组合,以从所述导航地图和所述感知图像中确定位置相匹配的目标交通标志,包括:
将所述导航地图中与所述当前位置符合设定距离要求的第一交通标志进行两两组合形成第一交通标志组,并将摄像头所采集感知图像中的第一交通标志进行两两组合形成第二交通标志组;
将所述第一交通标志组按照与所述当前位置的距离由近到远的方式进行排序,并将所述第二交通标志组按照两端端点距离由长到短的方式进行排序;
根据排序后导航地图中的任意一组交通标志组的上端点,与排序后感知图像中的任意一组交通标志组的上端点之间的几何关系,确定车辆的估计位置;
如果所述估计位置与所述当前位置之间的距离小于第一预设距离,则将排序后所述导航地图中的第一交通标志组和对应感知地图中的第二交通标志组作为目标交通标志。
可选的,所述基于修正后车辆的高程和位姿更新所述导航地图与所述感知图像之间的匹配关系,包括:
将所述导航地图中的显示内容根据修正后车辆的高程和位姿进行更新;
判断位置修正后的车辆在显示内容更新后的导航地图中的位置与所述当前位置之间的距离是否小于第二预设距离,其中,所述第二预设距离小于第一预设距离;
如果小于所述第二预设距离,则将内容更新后的导航地图根据修正后的车辆位姿投影到预设标准化平面,并将所述感知图像中的显示内容投影到所述预设标准化平面;
在所述标准化平面上,判断内容更新后的导航地图中的各交通标志与所述感知图像中的对应交通标志 的重投影误差;
对于任意一种类型的交通标志,如果所述重新投误差小于该类型交通标志对应的设定阈值,则根据所述重投影误差更新所述导航地图与所述感知图像之间的匹配关系。
可选的,所述判断内容更新后的导航地图中的交通标志与所述感知图像中的交通标志的重投影误差,包括:
判断内容更新后的导航地图中的第一交通标志与所述感知图像中对应的第一交通标志之间的重投影残差是否小于第一预设残差阈值;
如果小于第一预设残差阈值,则判断内容更新后的导航地图中的第二交通标志与所述感知图像中对应的第二交通标志之间的重投影残差是否小于第二预设残差阈值;
其中,所述第二交通标志位为与所述第一交通标志不同类型的交通标志。
可选的,在所述匹配关系更新后,所述方法还包括:
接收车辆位姿的不确定度;
如果所述不确定度大于设定阈值,则返回执行车辆高程的修正操作,以重新更新所述匹配关系。
可选的,基于导航地图中所述当前位置对应的车道线信息,对所述预设定位装置提供的车辆的高程进行修正,包括:
确定导航地图中所述当前位置对应的车道线的高程;
将所述车道线的高程作为当前位置处车辆的高程,以对预设定位装置提供的车辆的高程进行修正。
可选的,所述第一交通标志为路灯杆;
所述第二交通标志位包括车道线或交通牌。
第二方面,本发明实施例还提供了一种导航地图与感知图像匹配关系的更新装置,该装置包括:
高程修正模块,被配置为获取预设定位装置提供的车辆的当前位置,并基于导航地图中所述当前位置对应的车道线信息,对所述预设定位装置提供的车辆的高程进行修正;
目标交通标志确定模块,被配置为分别将所述导航地图和摄像头所采集感知图像中与所述当前位置满足设定距离要求的交通标志组进行排列组合,以从所述导航地图和所述感知图像中确定位置相匹配的目标交通标志,所述交通标志组中包括至少任意两个第一交通标志;
匹配关系更新模块,被配置为根据所述目标交通标志的位置,对所述导航地图中车辆的位姿进行修正,并基于修正后车辆的高程和位姿更新所述导航地图与所述感知图像之间的匹配关系。
可选的,所述目标交通标志确定模块,包括:
排列组合单元,被配置为将所述导航地图中与所述当前位置符合设定距离要求的第一交通标志进行两两组合形成第一交通标志组,并将摄像头所采集感知图像中的第一交通标志进行两两组合形成第二交通标志组;
排序单元,被配置为将所述第一交通标志组按照与所述当前位置的距离由近到远的方式进行排序,并将所述第二交通标志组按照两端端点距离由长到短的方式进行排序;
车辆位置估计单元,被配置为根据排序后所述导航地图中的任意一组交通标志组的上端点,与排序后所述感知图像中的任意一组交通标志组的上端点之间的几何关系,确定车辆的估计位置;
目标交通标志确定单元,被配置为如果所述估计位置与所述当前位置之间的距离小于第一预设距离,则将排序后所述导航地图中的第一交通标志组和对应感知地图中的第二交通标志组作为目标交通标志。
可选的,所述匹配关系更新模块,包括:
位姿修正单元,被配置为根据所述目标交通标志的位置,对所述导航地图中车辆的位姿进行修正;
显示内容更新单元,被配置为将所述导航地图中的显示内容根据修正后车辆的高程和位姿进行更新;
实际距离判断单元,被配置为判断位置修正后的车辆在显示内容更新后的导航地图中的位置与所述当前位置之间的距离是否小于第二预设距离,其中,所述第二预设距离小于第一预设距离;
投影单元,被配置为如果修正后的车辆在显示内容更新后的导航地图中的位置与所述当前位置之间的距离小于第二预设距离,则将内容更新后的导航地图根据修正后的车辆位姿投影到预设标准化平面,并将所述感知图像中的显示内容也投影到所述预设标准化平面;
重投影误差判断单元,被配置为在所述标准化平面上,判断内容更新后的导航地图中的各交通标志与所述感知图像中的对应交通标志的重投影误差;
匹配关系更新单元,被配置为对于任意一种类型的交通标志,如果所述重新投误差小于该类型交通标志对应的设定阈值,则根据所述重投影误差更新所述导航地图与所述感知图像之间的匹配关系。
可选的,所述重投影误差判断单元,具体被配置为:
判断内容更新后的导航地图中的第一交通标志与所述感知图像中对应的第一交通标志之间的重投影残差是否小于第一预设残差阈值;
如果小于第一预设残差阈值,则判断内容更新后的导航地图中的第二交通标志与所述感知图像中对应的第二交通标志之间的重投影残差是否小于第二预设残差阈值;
其中,所述第二交通标志位为与所述第一交通标志不同类型的交通标志。
可选的,在所述匹配关系更新后,所述装置还包括:
不确定度接收模块,被配置为接收车辆位姿的不确定度;
状态切换模块,被配置为如果所述不确定度大于设定阈值,则返回执行车辆高程的修正操作,以重新更新所述匹配关系。
可选的,所述高程修正模块,具体被配置为:
确定导航地图中所述当前位置对应的车道线的高程;
将所述车道线的高程作为当前位置处车辆的高程,以对预设定位装置提供的车辆的高程进行修正。
可选的,所述第一交通标志为路灯杆;
所述第二交通标志位包括车道线或交通牌。
第三方面,本发明实施例还提供了一种车载终端,包括:
存储有可执行程序代码的存储器;
与所述存储器耦合的处理器;
所述处理器调用所述存储器中存储的所述可执行程序代码,执行本发明任意实施例所提供的导航地图与感知图像匹配关系的更新方法的部分或全部步骤。
第四面,本发明实施例还提供了一种计算机可读存储介质,其存储计算机程序,所述计算机程序包括用于执行本发明任意实施例所提供的导航地图与感知图像匹配关系的更新方法的部分或全部步骤的指令。
第五方面,本发明实施例还提供了一种计算机程序产品,当所述计算机程序产品在计算机上运行时,使得所述计算机执行本发明任意实施例所提供的导航地图与感知图像匹配关系的更新方法的部分或全部步骤。
本实施例提供的技术方案,在完成车辆高程的修正后,通过将导航地图和摄像头所采集感知图像中与车辆当前位置满足设定距离要求的交通标志组进行排列组合,以从导航地图和感知图像中确定位置相匹配的目标交通标志。利用目标交通标志的位置,可对导航地图中车辆的位姿进行修正,使得车体位置能够与导航地图位置对齐,从而可以获得正确的感知图像和导航地图之间的匹配关系。
本发明的发明点包括:
1、在如路灯杆等交通标志存在时,可以对其进行准确识别,并利用交通标志对车辆位姿进行修正,从而完成导航地图的初始化操作,使得消费级的定位设备具有高精度的定位功能,是本发明的发明点之一。
2、在从多个交通标志组中筛选目标交通标志时,通过基于感知图像和导航地图中交通标志组上端点之间的几何关系所确定出车辆的估算位置,将车辆的估算位置与先验位置之间的距离小于设定阈值所对应的交通标志组作为目标交通标志,是本发明的发明点之一。
3、通过确定导航地图中车辆当前位置周围几米范围内的车道线高程,可将确定出的车辆线高程作为车辆当前位置的高程,以完成对车辆高程的修正,从而增加后续导航地图与感知图像匹配正确的概率,是本发明的发明点之一。
4、将车辆的不确定度作为初始化状态切换的条件,只要检测到车辆的不确定度大于设定阈值,则切换到导航地图的初始化状态,以保证车辆的正常运行,是本发明的发明点之一。
附图说明
为了更清楚地说明本发明实施例中的技术方案,下面将对实施例中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。
图1a是本发明实施例提供的一种导航地图与感知图像匹配关系的更新方法的流程示意图;
图1b为本发明实施例提供的一种感知图像中的路灯杆与导航地图中的路灯杆的几何关系示意图;
图2a是本发明实施例提供的一种导航地图与感知图像匹配关系的更新方法的流程示意图;
图2b为本发明实施例提供的一种对车辆进行高程修正的示意图;
图2c为本发明实施例提供的一种对车辆进行粗略位姿修正的示意图;
图2d为本发明实施例提供的一种对导航地图中显示的车辆进行位置更新的示意图;
图3是本发明实施例提供的一种导航地图与感知图像匹配关系的更新装置的结构示意图;
图4是本发明实施例提供的一种车载终端的结构示意图。
具体实施方式
下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅是本发明一部分实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都属于本发明保护的范围。
需要说明的是,本发明实施例及附图中的术语“包括”和“具有”以及它们任何变形,意图在于覆盖不排他的包含。例如包含了一系列步骤或单元的过程、方法、系统、产品或设备没有限定于已列出的步骤或单元,而是可选地还包括没有列出的步骤或单元,或可选地还包括对于这些过程、方法、产品或设备固有的其它步骤或单元。
实施例一
请参阅图1a,图1a是本发明实施例提供的一种导航地图与感知图像匹配关系的更新方法的流程示意图。该方法典型的是应用于无人驾驶车辆第一次进入室外高精度地图的场景下,可由导航地图与感知图像匹配关系的更新装置来执行,该装置可通过软件和/或硬件的方式实现,一般可集成在车载电脑、车载工业控制计算机(Industrial personal Computer,IPC)等车载终端中,本发明实施例不做限定。如图1a所示,本实施例提供的方法具体包括:
110、获取预设定位装置提供的车辆的当前位置,并基于导航地图中当前位置对应的车道线信息,对预设定位装置提供的车辆的高程进行修正。
其中,预设定位装置为单点GPS或低精度的消费级定位设备。导航地图是指应用于自动驾驶的误差级别为厘米级的高精度地图。
本实施例中,车辆的高程是指消费级定位设备提供的车辆的海拔高度。在利用消费级定位设备对车辆进行定位时,定位精度较低,有时会有几米甚至十几米的误差,但在该误差范围内车道线高度变化不大。因此,可根据消费级定位设备提供的车辆当前位置,在导航地图中搜索当前位置附近几米的车道线信息,从而利用该车道线信息对车辆的高程进行修正,以将车辆拉到车道线高度。
具体的,可在导航地图中搜索车辆当前位置周围几米范围内车道线,并计算车道线的平均高度,即车道线的高程。将计算出的车道线的高程作为车辆当前位置的高程,以完成对车辆高程的修正。这样设置可使得后续导航地图与感知图像匹配正确的概率增加。
需要说明的是,本发明实施例对车辆高程和位姿的修正顺序不存在先后之分,可先对车辆的高程进行修正,然后再修正车辆的位姿,或者也可以先完成对车辆的位姿进行修正,然后再修正车辆的高程,本实施例对此不做具体限定。
120、分别将导航地图和摄像头所采集感知图像中与当前位置满足设定距离要求的交通标志组进行排列组合,以从导航地图和感知图像中确定位置相匹配的目标交通标志。
其中,交通标志包括路灯杆、车道线和交通牌等。由于路灯杆相对于其他交通标志信息更为丰富,因此本实施例中优选将路灯杆作为第一交通标志,利用路灯杆为车体位置提供前后向和左右向的约束,即可 利用路灯杆对车辆的位姿进行粗略修正。
示例性的,在对车辆的位姿进行修正时,可通过导航地图和感知图像中至少两组相匹配的路灯杆来实现。但在车体准确位置未知的情况下,导航地图中的任意两根路灯杆(简称地图杆)和感知图像中的任意两根路灯杆(简称感知图像杆)都可能存在匹配关系,因此,为了确定存在对应匹配关系的地图杆和感知图像杆,本实施例建立了交通标志组,例如路灯杆组,每组路灯杆中包括任意两根路灯杆。通过分别将导航地图和感知图像中与当前位置满足设定距离要求的交通标志组进行排列组合,并依次进行遍历匹配,可确定出导航地图与感知图像中相匹配的目标交通标志。
示例性的,分别将导航地图和摄像头所采集感知图像中的交通标志组进行排列组合,以从导航地图和感知图像中确定位置相匹配的目标交通标志,可通过如下方式来实现:
将导航地图中与车辆当前位置符合设定距离要求的第一交通标志进行两两组合形成第一交通标志组,并将摄像头所采集感知图像中的第一交通标志进行两两组合形成第二交通标志组;将第一交通标志组按照与当前位置的距离由近到远的方式进行排序,并将第二交通标志组按照两端端点距离由长到短的方式进行排序;根据排序后导航地图中的任意一组交通标志组的上端点,与排序后感知图像中的任意一组交通标志组的上端点之间的几何关系,确定车辆的估计位置;如果估计位置与当前位置之间的距离小于第一预设距离,则将排序后导航地图中的第一交通标志组和对应感知地图中的第二交通标志组作为目标交通标志。
需要说明的是,由于感知图像中的路灯杆组投影归一化平面上是直线信息,而由于车辆、花丛遮挡等原因,路灯杆投影到归一化平面上后,下端点往往位置不准确,但是路灯杆上端点的图像投影位置比下端点误差小很多,因此本实施例利用感知图像和导航地图中路灯杆的上端点计算出一个粗略的车体位置。
本实施例中,可以将感知图像中的路灯杆组均投影到图像平面或者在摄像头的归一化平面上并按照上下端点距离由长到短的方式进行排序。其中,该归一化平面可建立在摄像头坐标系下,且距离摄像头坐标系原点的距离为1米。具体的,在对交通标志组进行依次遍历匹配的过程中。由于导航地图中和感知图像中均包含多组交通标志,因此,如果利用当前交通标志组确定的车辆的估算位置与车体当前位置(即先验位置)之间的距离过大,例如大于第一预设距离,则可删除导航地图中和感知图像中二者之间的匹配关系,并依次选择其他交通标志组进行匹配。
具体的,图1b为本发明实施例提供的一种感知图像中的路灯杆与导航地图中的路灯杆的几何关系示意图,如图1b所示,利用感知图像中的一对路灯杆在归一化平面或在图像平面上的投影的上端点,与导航地图中的一对路灯杆的上端点之间的连线,可定位出车辆的估计位置。根据车体的估算位置与先验位置的距离进行一次粗筛,可删除估算位置与先验位置距离大于第一预设距离的路灯杆组,从而进一步减小算法时间复杂度。对于估算位置与先验位置距离小于第一预设距离路灯杆组中的各路灯杆,可将其作为目标交通标志。本实施例中,通过将导航地图中的路灯杆组和感知图像中的路灯杆组进行排序可以提高匹配率,减小算法计算的时间复杂度。
130、根据目标交通标志的位置,对导航地图中车辆的位姿进行修正,并基于修正后车辆的高程和位姿更新导航地图与感知图像之间的匹配关系。
其中,对车辆的位姿进行修正是为了使车辆的当前位置与车辆实际的正确位置之间的偏差降到最低,即可采用迭代修正的方式将车辆的当前位置不断逼近于车辆的真实位置。
本实施中,目标交通标志的确定说明感知图像中的目标交通标志已经与导航地图中对应的目标交通标志建立了一一对应的关系。基于目标交通标志中各组交通标志组之间的匹配关系,可利用非线性优化算法修正车体的前后向和左右向(车辆高程通过步骤110已得到修正)。
进一步的,在车辆的位姿和高程得到粗略修正后,车体的位置与高精度地图已经进行了较好的配准。为了得到更加精准的匹配关系,可引入与第一交通标志不同类型的相匹配的第二交通标志,例如车道线和/或交通牌等,对车辆的位姿进行修正,即利用更新后的匹配关系和车道线对车体的前后向位置、左右向位置及高程进行非线性优化,并基于更新后车辆的位姿来更新导航地图和感知图像之间的匹配关系。
进一步的,为了保证感知图像与导航地图之间匹配关系的准确性,可在该匹配关系输出之前对其进行校核,具体的校核方式可以为:判断优化后车辆的位置与先验位置之间的距离,如果该距离满足设定距离要求,并且更新后的匹配关系中的路灯杆和车道线等在最新的车辆位姿下的重投影残差均小于对应设定阈 值,则说明导航地图与感知图像之间的匹配关系已达到标准,此时可输出更新后的该匹配关系,以完成导航地图的初始化。此时,车体可获得厘米级的定位精度,车体可与导航地图保持对齐。
本实施例提供的技术方案,在完成车辆高程的修正后,通过将导航地图和摄像头所采集感知图像中与车辆当前位置满足设定距离要求的交通标志组进行排列组合,以从导航地图和感知图像中确定位置相匹配的目标交通标志。利用目标交通标志的位置,可对导航地图中车辆的位姿进行修正,使得车体位置能够与导航地图位置对齐,从而可以获得正确的感知图像和导航地图之间的匹配关系。
进一步的,在导航地图与感知图像之间的匹配关系更新后,如果判断出接收到的车辆位姿的不确定度,即协方差信息,大于设定阈值,则返回执行车辆高程的修正操作,以重新更新该匹配关系,即重新切换到初始化状态,以保证匹配关系的正确性和车体位置的精度。
实施例二
请参阅图2a,图2a是本发明实施例提供的一种导航地图与感知图像匹配关系的更新方法的流程示意图。本实施例在上述实施例的基础上,对基于修正后车辆的高程和位姿更新导航地图与感知图像之间的匹配关系的过程进行了优化,在输出该匹配关系时增加了验证该匹配关系是否合理的操作。如图2a所示,该方法包括:
210、获取预设定位装置提供的车辆的当前位置,并基于导航地图中当前位置对应的车道线信息,对预设定位装置提供的车辆的高程进行修正。
图2b为本发明实施例提供的一种对车辆进行高程修正的示意图。如图2b所示,通过对车辆的高程进行修正,可以将车辆拉到车道线高度。
220、分别将导航地图和摄像头所采集感知图像中与当前位置满足设定距离要求的交通标志组进行排列组合,以从导航地图和感知图像中确定位置相匹配的目标交通标志。
230、根据目标交通标志的位置,利用非线性优化算法对导航地图中车辆的位姿进行修正。
本实施例中,步骤230即为对车辆进行粗略位姿修正的过程。此过程主要是利用220中识别出的目标交通标志,例如路灯杆对车辆的位置进行修正,使得车辆的位置与其真实位置之间的距离有所减小。
具体的,图2c为本发明实施例提供的一种对车辆进行粗略位姿修正的示意图。如图2c所示,1-6分别表示导航地图中的路灯杆;7-10分别表示感知图像中的路灯杆;导航地图中的路灯杆1和6可形成地图路灯杆组,感知图像中的路灯杆7和10可形成图像路灯杆组,通过地图路灯杆组和图像路灯杆组之间的匹配关系,可将车辆进行位姿粗校准,使得校准后的位置接近于其实际车体位置。
240、将导航地图中的显示内容根据修正后车辆的高程和位姿进行更新。
基于修正后的车辆位置,导航地图中的显示内容会相应的发生改变。在更新导航地图中的显示内容后,相应的,感知地图中与导航地图相匹配的交通标志也应随之得到更新。
进一步的,如果在显示内容更新后的导航地图中识别出除路灯杆之外与感知地图相匹配的其他交通标志,例如车道线和交通牌等,则可利用这些交通标志对车辆的位姿进行进一步非线性优化。在进一步的优化处理后,导航地图中更新后的车体位置与真实位置更加接近。
具体的,图2d为本发明实施例提供的一种对导航地图中显示的车辆进行位置更新的示意图。如图2d所示,对车辆的从粗校准位置进行进一步优化处理后,得到更新后的车体位置与实际车体位置接近于重合,达到了将车辆位姿与导航地图进行对齐的效果。
250、判断位置修正后的车辆在显示内容更新后的导航地图中的位置与当前位置之间的距离是否小于第二预设距离,若是,则执行步骤260;否则,返回执行步骤220。
其中,第二预设距离小于第一预设距离。
260、将内容更新后的导航地图根据修正后的车辆位姿投影到预设标准化平面,并将感知图像中的显示内容投影到预设标准化平面,继续执行步骤270。
270、在标准化平面上,对于任意一种类型的交通标志,判断内容更新后的导航地图中的各种类型的交通标志与感知图像中的对应交通标志的重投影误差是否小于该类型交通标志对应的设定阈值,若是,则执行步骤280;否则,执行步骤220。
示例性的,如果步骤270中的交通标志中包含有不同种类型的交通标志,例如路灯杆、交通牌和车道线等,则不同该类型的交通标志都对应设置残差阈值。
具体的,步骤270可以包括:判断内容更新后的导航地图中的第一交通标志与感知图像中对应的第一交通标志之间的重投影残差是否小于第一预设残差阈值;
如果小于第一预设残差阈值,则判断内容更新后的导航地图中的第二交通标志与感知图像中对应的第二交通标志之间的重投影残差是否小于第二预设残差阈值;
其中,第二交通标志位为与第一交通标志不同类型的交通标志。第一交通标志优选为路灯杆,第二交通标志位包括车道线或交通牌等。
280、更新导航地图与感知图像之间的匹配关系。
示例性的,如果不同类型交通标志的重投影误差不满足预设误差要求,则说明导航地图与感知图像之间未建立良好的匹配关系,此时仍需返回执行步骤220,以重新执行初始化操作。
示例性的,如果更新后的匹配关系中一种类型的交通标志,例如只有路灯杆,而没有其他类型的交通标志时,则认为对车体位置的约束不足,仍需返回执行步骤220,以重新执行初始化操作。
290、输出更新后的匹配关系和更新后的车辆位姿。
需要说明的是,只有在步骤250(车辆修正后的位置与先验位置之间的距离符合预设距离要求),且在步骤270中判断出至少两种类型的交通标志在最新车辆位姿下的重投影残差分别都满足各自对应的投影阈值要求时,才可将导航地图与感知图像之间匹配关系输出,完成初始化操作。
本实施例提供的技术方案,在对车辆的位姿进行修正后,车体的位置与高精度地图已经进行了较好的配准。利用导航地图和感知图像中除路灯杆之外其他相匹配的交通标志对车辆的位姿进行进一步优化处理后,可使得更新后车辆的位姿与真实位姿更为接近。此外,为了保证导航地图与感知图像匹配关系的准确性,可判断车辆修正后的位置与先验位置之间的距离是否满足预设要求,且导航地图与感知图像中的至少两种类型的交通标志在最新的车辆位姿下是否均满足重投影残差收敛的条件,如果上述两个条件都满足,则说明基于修正后的车辆位姿所确定的导航地图和感知图像或者之间的匹配关系达到了要求,此时可更新并输出该匹配关系,完成初始化过程。
实施例三
请参阅图3,图3是本发明实施例提供的一种导航地图与感知图像匹配关系的更新装置的结构示意图。如图3所示,该装置包括:高程修正模块310、目标交通标志确定模块320和匹配关系更新模块330。
其中,高程修正模块310,被配置为获取预设定位装置提供的车辆的当前位置,并基于导航地图中所述当前位置对应的车道线信息,对所述预设定位装置提供的车辆的高程进行修正;
目标交通标志确定模块320,被配置为分别将所述导航地图和摄像头所采集感知图像中与所述当前位置满足设定距离要求的交通标志组进行排列组合,以从所述导航地图和所述感知图像中确定位置相匹配的目标交通标志,所述交通标志组中包括至少任意两个第一交通标志;
匹配关系更新模块330,被配置为根据所述目标交通标志的位置,对所述导航地图中车辆的位姿进行修正,并基于修正后车辆的高程和位姿更新所述导航地图与所述感知图像之间的匹配关系。
本实施例提供的技术方案,在完成车辆高程的修正后,通过将导航地图和摄像头所采集感知图像中与车辆当前位置满足设定距离要求的交通标志组进行排列组合,以从导航地图和感知图像中确定位置相匹配的目标交通标志。利用目标交通标志的位置,可对导航地图中车辆的位姿进行修正,使得车体位置能够与导航地图位置对齐,从而可以获得正确的感知图像和导航地图之间的匹配关系。
可选的,所述目标交通标志确定模块,包括:
排列组合单元,被配置为将所述导航地图中与所述当前位置符合设定距离要求的第一交通标志进行两两组合形成第一交通标志组,并将摄像头所采集感知图像中的第一交通标志进行两两组合形成第二交通标志组;
排序单元,被配置为将所述第一交通标志组按照与所述当前位置的距离由近到远的方式进行排序,并将所述第二交通标志组按照两端端点距离由长到短的方式进行排序;
车辆位置估计单元,被配置为根据排序后所述导航地图中的任意一组交通标志组的上端点,与排序后所述感知图像中的任意一组交通标志组的上端点之间的几何关系,确定车辆的估计位置;
目标交通标志确定单元,被配置为如果所述估计位置与所述当前位置之间的距离小于第一预设距离,则将排序后所述导航地图中的第一交通标志组和对应感知地图中的第二交通标志组作为目标交通标志。
可选的,所述匹配关系更新模块,包括:
位姿修正单元,被配置为根据所述目标交通标志的位置,对所述导航地图中车辆的位姿进行修正;
显示内容更新单元,被配置为将所述导航地图中的显示内容根据修正后车辆的高程和位姿进行更新;
实际距离判断单元,被配置为判断位置修正后的车辆在显示内容更新后的导航地图中的位置与所述当前位置之间的距离是否小于第二预设距离,其中,所述第二预设距离小于第一预设距离;
投影单元,被配置为如果修正后的车辆在显示内容更新后的导航地图中的位置与所述当前位置之间的距离小于第二预设距离,则将内容更新后的导航地图根据修正后的车辆位姿投影到预设标准化平面,并将所述感知图像中的显示内容也投影到所述预设标准化平面;
重投影误差判断单元,被配置为在所述标准化平面上,判断内容更新后的导航地图中的各交通标志与所述感知图像中的对应交通标志的重投影误差;
匹配关系更新单元,被配置为对于任意一种类型的交通标志,如果所述重新投误差小于该类型交通标志对应的设定阈值,则根据所述重投影误差更新所述导航地图与所述感知图像之间的匹配关系。
可选的,所述重投影误差判断单元,具体被配置为:
判断内容更新后的导航地图中的第一交通标志与所述感知图像中对应的第一交通标志之间的重投影残差是否小于第一预设残差阈值;
如果小于第一预设残差阈值,则判断内容更新后的导航地图中的第二交通标志与所述感知图像中对应的第二交通标志之间的重投影残差是否小于第二预设残差阈值;
其中,所述第二交通标志位为与所述第一交通标志不同类型的交通标志。
可选的,在所述匹配关系更新后,所述装置还包括:
不确定度接收模块,被配置为接收车辆位姿的不确定度;
状态切换模块,被配置为如果所述不确定度大于设定阈值,则返回执行车辆高程的修正操作,以重新更新所述匹配关系。
可选的,所述高程修正模块,具体被配置为:
确定导航地图中所述当前位置对应的车道线的高程;
将所述车道线的高程作为当前位置处车辆的高程,以对预设定位装置提供的车辆的高程进行修正。
可选的,所述第一交通标志为路灯杆;
所述第二交通标志位包括车道线或交通牌。
本发明实施例所提供的导航地图与感知图像匹配关系的更新装置可执行本发明任意实施例所提供的导航地图与感知图像匹配关系的更新方法,具备执行方法相应的功能模块和有益效果。未在上述实施例中详尽描述的技术细节,可参见本发明任意实施例所提供的导航地图与感知图像匹配关系的更新方法。
实施例四
请参阅图4,图4是本发明实施例提供的一种车载终端的结构示意图。如图4所示,该车载终端可以包括:
存储有可执行程序代码的存储器701;
与存储器701耦合的处理器702;
其中,处理器702调用存储器701中存储的可执行程序代码,执行本发明任意实施例所提供的导航地图与感知图像匹配关系的更新方法。
本发明实施例公开一种计算机可读存储介质,其存储计算机程序,其中,该计算机程序使得计算机执行本发明任意实施例所提供的导航地图与感知图像匹配关系的更新方法。
本发明实施例公开一种计算机程序产品,其中,当计算机程序产品在计算机上运行时,使得计算机执 行本发明任意实施例所提供的导航地图与感知图像匹配关系的更新方法的部分或全部步骤。
在本发明的各种实施例中,应理解,上述各过程的序号的大小并不意味着执行顺序的必然先后,各过程的执行顺序应以其功能和内在逻辑确定,而不应对本发明实施例的实施过程构成任何限定。
在本发明所提供的实施例中,应理解,“与A相应的B”表示B与A相关联,根据A可以确定B。但还应理解,根据A确定B并不意味着仅仅根据A确定B,还可以根据A和/或其他信息确定B。
另外,在本发明各实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用软件功能单元的形式实现。
上述集成的单元若以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可获取的存储器中。基于这样的理解,本发明的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或者部分,可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储器中,包括若干请求用以使得一台计算机设备(可以为个人计算机、服务器或者网络设备等,具体可以是计算机设备中的处理器)执行本发明的各个实施例上述方法的部分或全部步骤。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成,该程序可以存储于一计算机可读存储介质中,存储介质包括只读存储器(Read-Only Memory,ROM)、随机存储器(Random Access Memory,RAM)、可编程只读存储器(Programmable Read-only Memory,PROM)、可擦除可编程只读存储器(Erasable Programmable Read Only Memory,EPROM)、一次可编程只读存储器(One-time Programmable Read-Only Memory,OTPROM)、电子抹除式可复写只读存储器(Electrically-Erasable Programmable Read-Only Memory,EEPROM)、只读光盘(Compact Disc Read-Only Memory,CD-ROM)或其他光盘存储器、磁盘存储器、磁带存储器、或者能够用于携带或存储数据的计算机可读的任何其他介质。
以上对本发明实施例公开的一种导航地图与感知图像匹配关系的更新方法和装置进行了详细介绍,本文中应用了具体个例对本发明的原理及实施方式进行了阐述,以上实施例的说明只是用于帮助理解本发明的方法及其核心思想;同时,对于本领域的一般技术人员,依据本发明的思想,在具体实施方式及应用范围上均会有改变之处,综上所述,本说明书内容不应理解为对本发明的限制。

Claims (10)

  1. 一种导航地图与感知图像匹配关系的更新方法,应用于自动驾驶,其特征在于,包括:
    获取预设定位装置提供的车辆的当前位置,并基于导航地图中所述当前位置对应的车道线信息,对所述预设定位装置提供的车辆的高程进行修正;
    分别将所述导航地图和摄像头所采集感知图像中与所述当前位置满足设定距离要求的交通标志组进行排列组合,以从所述导航地图和所述感知图像中确定位置相匹配的目标交通标志,所述交通标志组中包括至少任意两个第一交通标志;
    根据所述目标交通标志的位置,对所述导航地图中车辆的位姿进行修正,并基于修正后车辆的高程和位姿更新所述导航地图与所述感知图像之间的匹配关系。
  2. 根据权利要求1所述的方法,其特征在于,分别将所述导航地图和摄像头所采集感知图像中的交通标志组进行排列组合,以从所述导航地图和所述感知图像中确定位置相匹配的目标交通标志,包括:
    将所述导航地图中与所述当前位置符合设定距离要求的第一交通标志进行两两组合形成第一交通标志组,并将摄像头所采集感知图像中的第一交通标志进行两两组合形成第二交通标志组;
    将所述第一交通标志组按照与所述当前位置的距离由近到远的方式进行排序,并将所述第二交通标志组按照两端端点距离由长到短的方式进行排序;
    根据排序后导航地图中的任意一组交通标志组的上端点,与排序后感知图像中的任意一组交通标志组的上端点之间的几何关系,确定车辆的估计位置;
    如果所述估计位置与所述当前位置之间的距离小于第一预设距离,则将排序后所述导航地图中的第一交通标志组和对应感知地图中的第二交通标志组作为目标交通标志。
  3. 根据权利要求1所述的方法,其特征在于,所述基于修正后车辆的高程和位姿更新所述导航地图与所述感知图像之间的匹配关系,包括:
    将所述导航地图中的显示内容根据修正后车辆的高程和位姿进行更新;
    判断位置修正后的车辆在显示内容更新后的导航地图中的位置与所述当前位置之间的距离是否小于第二预设距离,其中,所述第二预设距离小于第一预设距离;
    如果小于所述第二预设距离,则将内容更新后的导航地图根据修正后的车辆位姿投影到预设标准化平面,并将所述感知图像中的显示内容投影到所述预设标准化平面;
    在所述标准化平面上,判断内容更新后的导航地图中的各交通标志与所述感知图像中的对应交通标志的重投影误差;
    对于任意一种类型的交通标志,如果所述重新投误差小于该类型交通标志对应的设定阈值,则根据所述重投影误差更新所述导航地图与所述感知图像之间的匹配关系。
  4. 根据权利要求3所述的方法,其特征在于,所述判断内容更新后的导航地图中的交通标志与所述感知图像中的交通标志的重投影误差,包括:
    判断内容更新后的导航地图中的第一交通标志与所述感知图像中对应的第一交通标志之间的重投影残差是否小于第一预设残差阈值;
    如果小于第一预设残差阈值,则判断内容更新后的导航地图中的第二交通标志与所述感知图像中对应的第二交通标志之间的重投影残差是否小于第二预设残差阈值;
    其中,所述第二交通标志位为与所述第一交通标志不同类型的交通标志。
  5. 根据权利要求1-4任一所述的方法,其特征在于,在所述匹配关系更新后,所述方法还包括:
    接收车辆位姿的不确定度;
    如果所述不确定度大于设定阈值,则返回执行车辆高程的修正操作,以重新更新所述匹配关系。
  6. 根据权利要求1-5任一所述的方法,其特征在于,基于导航地图中所述当前位置对应的车道线信息,对所述预设定位装置提供的车辆的高程进行修正,包括:
    确定导航地图中所述当前位置对应的车道线的高程;
    将所述车道线的高程作为当前位置处车辆的高程,以对预设定位装置提供的车辆的高程进行修正。
  7. 根据权利要求4所述的方法,其特征在于:
    所述第一交通标志为路灯杆;
    所述第二交通标志位包括车道线或交通牌。
  8. 一种导航地图与感知图像匹配关系的更新装置,应用于自动驾驶,其特征在于,包括:
    高程修正模块,被配置为获取预设定位装置提供的车辆的当前位置,并基于导航地图中所述当前位置对应的车道线信息,对所述预设定位装置提供的车辆的高程进行修正;
    目标交通标志确定模块,被配置为分别将所述导航地图和摄像头所采集感知图像中与所述当前位置满足设定距离要求的交通标志组进行排列组合,以从所述导航地图和所述感知图像中确定位置相匹配的目标交通标志,所述交通标志组中包括至少任意两个第一交通标志;
    匹配关系更新模块,被配置为根据所述目标交通标志的位置,对所述导航地图中车辆的位姿进行修正,并基于修正后车辆的高程和位姿更新所述导航地图与所述感知图像之间的匹配关系。
  9. 根据权利要求8所述的装置,其特征在于,所述目标交通标志确定模块,包括:
    排列组合单元,被配置为将所述导航地图中与所述当前位置符合设定距离要求的第一交通标志进行两两组合形成第一交通标志组,并将摄像头所采集感知图像中的第一交通标志进行两两组合形成第二交通标志组;
    排序单元,被配置为将所述第一交通标志组按照与所述当前位置的距离由近到远的方式进行排序,并将所述第二交通标志组按照两端端点距离由长到短的方式进行排序;
    车辆位置估计单元,被配置为根据排序后所述导航地图中的任意一组交通标志组的上端点,与排序后所述感知图像中的任意一组交通标志组的上端点之间的几何关系,确定车辆的估计位置;
    目标交通标志确定单元,被配置为如果所述估计位置与所述当前位置之间的距离小于第一预设距离,则将排序后所述导航地图中的第一交通标志组和对应感知地图中的第二交通标志组作为目标交通标志。
  10. 根据权利要求8所述的装置,其特征在于,所述匹配关系更新模块,包括:
    位姿修正单元,被配置为根据所述目标交通标志的位置,对所述导航地图中车辆的位姿进行修正;
    显示内容更新单元,被配置为将所述导航地图中的显示内容根据修正后车辆的高程和位姿进行更新;
    实际距离判断单元,被配置为判断位置修正后的车辆在显示内容更新后的导航地图中的位置与所述当前位置之间的距离是否小于第二预设距离,其中,所述第二预设距离小于第一预设距离;
    投影单元,被配置为如果修正后的车辆在显示内容更新后的导航地图中的位置与所述当前位置之间的距离小于第二预设距离,则将内容更新后的导航地图根据修正后的车辆位姿投影到预设标准化平面,并将所述感知图像中的显示内容也投影到所述预设标准化平面;
    重投影误差判断单元,被配置为在所述标准化平面上,判断内容更新后的导航地图中的各交通标志与所述感知图像中的对应交通标志的重投影误差;
    匹配关系更新单元,被配置为对于任意一种类型的交通标志,如果所述重新投误差小于该类型交通标志对应的设定阈值,则根据所述重投影误差更新所述导航地图与所述感知图像之间的匹配关系。
PCT/CN2019/113485 2019-03-29 2019-10-26 一种导航地图与感知图像匹配关系的更新方法和装置 WO2020199566A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910253282.9 2019-03-29
CN201910253282.9A CN110954112B (zh) 2019-03-29 2019-03-29 一种导航地图与感知图像匹配关系的更新方法和装置

Publications (1)

Publication Number Publication Date
WO2020199566A1 true WO2020199566A1 (zh) 2020-10-08

Family

ID=69975421

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/113485 WO2020199566A1 (zh) 2019-03-29 2019-10-26 一种导航地图与感知图像匹配关系的更新方法和装置

Country Status (2)

Country Link
CN (1) CN110954112B (zh)
WO (1) WO2020199566A1 (zh)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113749562A (zh) * 2021-08-13 2021-12-07 珠海格力电器股份有限公司 扫地机器人及其控制方法、装置、设备和存储介质
CN115223118A (zh) * 2022-06-09 2022-10-21 广东省智能网联汽车创新中心有限公司 一种高精地图置信度判断方法、系统及车辆
CN115962787A (zh) * 2023-03-16 2023-04-14 安徽蔚来智驾科技有限公司 地图更新、自动驾驶控制方法、设备、介质及车辆
CN117330097A (zh) * 2023-12-01 2024-01-02 深圳元戎启行科技有限公司 车辆定位优化方法、装置、设备及存储介质
CN117930297A (zh) * 2024-03-21 2024-04-26 北京理工大学 一种基于车载摄像头和地图的车辆定位方法及系统

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111833717B (zh) * 2020-07-20 2022-04-15 阿波罗智联(北京)科技有限公司 用于定位交通工具的方法、装置、设备和存储介质
CN112149624B (zh) * 2020-10-16 2022-06-10 腾讯科技(深圳)有限公司 一种交通标识图像处理方法和装置
CN112444246B (zh) * 2020-11-06 2024-01-26 北京易达恩能科技有限公司 高精度的数字孪生场景中的激光融合定位方法
CN112734918B (zh) * 2020-12-31 2023-05-23 潍柴动力股份有限公司 平台端三维电子地图的动态更新方法、装置、设备及介质
CN113776533A (zh) * 2021-07-29 2021-12-10 北京旷视科技有限公司 可移动设备的重定位方法及装置
CN114323033B (zh) * 2021-12-29 2023-08-29 北京百度网讯科技有限公司 基于车道线和特征点的定位方法、设备及自动驾驶车辆
CN114608591B (zh) * 2022-03-23 2023-01-10 小米汽车科技有限公司 车辆定位方法、装置、存储介质、电子设备、车辆及芯片
CN115265553A (zh) * 2022-07-11 2022-11-01 重庆长安汽车股份有限公司 地图数据的处理方法、装置、车辆及存储介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20160037486A (ko) * 2014-09-29 2016-04-06 현대모비스 주식회사 내비게이션 시스템의 지도 매칭 장치 및 방법
CN105718860A (zh) * 2016-01-15 2016-06-29 武汉光庭科技有限公司 基于驾驶安全地图及双目交通标志识别的定位方法及系统
CN105783936A (zh) * 2016-03-08 2016-07-20 武汉光庭信息技术股份有限公司 用于自动驾驶中的道路标识制图及车辆定位方法及系统
CN108303103A (zh) * 2017-02-07 2018-07-20 腾讯科技(深圳)有限公司 目标车道的确定方法和装置
US20180283892A1 (en) * 2017-04-03 2018-10-04 Robert Bosch Gmbh Automated image labeling for vehicles based on maps
CN109186616A (zh) * 2018-09-20 2019-01-11 禾多科技(北京)有限公司 基于高精度地图和场景检索的车道线辅助定位方法
CN109186615A (zh) * 2018-09-03 2019-01-11 武汉中海庭数据技术有限公司 基于高精度地图的车道边线距离检测方法、装置及存储介质

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108318043B (zh) * 2017-12-29 2020-07-31 百度在线网络技术(北京)有限公司 用于更新电子地图的方法、装置和计算机可读存储介质
CN108802785B (zh) * 2018-08-24 2021-02-02 清华大学 基于高精度矢量地图和单目视觉传感器的车辆自定位方法

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20160037486A (ko) * 2014-09-29 2016-04-06 현대모비스 주식회사 내비게이션 시스템의 지도 매칭 장치 및 방법
CN105718860A (zh) * 2016-01-15 2016-06-29 武汉光庭科技有限公司 基于驾驶安全地图及双目交通标志识别的定位方法及系统
CN105783936A (zh) * 2016-03-08 2016-07-20 武汉光庭信息技术股份有限公司 用于自动驾驶中的道路标识制图及车辆定位方法及系统
CN108303103A (zh) * 2017-02-07 2018-07-20 腾讯科技(深圳)有限公司 目标车道的确定方法和装置
US20180283892A1 (en) * 2017-04-03 2018-10-04 Robert Bosch Gmbh Automated image labeling for vehicles based on maps
CN109186615A (zh) * 2018-09-03 2019-01-11 武汉中海庭数据技术有限公司 基于高精度地图的车道边线距离检测方法、装置及存储介质
CN109186616A (zh) * 2018-09-20 2019-01-11 禾多科技(北京)有限公司 基于高精度地图和场景检索的车道线辅助定位方法

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113749562A (zh) * 2021-08-13 2021-12-07 珠海格力电器股份有限公司 扫地机器人及其控制方法、装置、设备和存储介质
CN113749562B (zh) * 2021-08-13 2022-08-16 珠海格力电器股份有限公司 扫地机器人及其控制方法、装置、设备和存储介质
CN115223118A (zh) * 2022-06-09 2022-10-21 广东省智能网联汽车创新中心有限公司 一种高精地图置信度判断方法、系统及车辆
CN115223118B (zh) * 2022-06-09 2024-03-01 广东省智能网联汽车创新中心有限公司 一种高精地图置信度判断方法、系统及车辆
CN115962787A (zh) * 2023-03-16 2023-04-14 安徽蔚来智驾科技有限公司 地图更新、自动驾驶控制方法、设备、介质及车辆
CN117330097A (zh) * 2023-12-01 2024-01-02 深圳元戎启行科技有限公司 车辆定位优化方法、装置、设备及存储介质
CN117330097B (zh) * 2023-12-01 2024-05-10 深圳元戎启行科技有限公司 车辆定位优化方法、装置、设备及存储介质
CN117930297A (zh) * 2024-03-21 2024-04-26 北京理工大学 一种基于车载摄像头和地图的车辆定位方法及系统
CN117930297B (zh) * 2024-03-21 2024-06-11 北京理工大学 一种基于车载摄像头和地图的车辆定位方法及系统

Also Published As

Publication number Publication date
CN110954112B (zh) 2021-09-21
CN110954112A (zh) 2020-04-03

Similar Documents

Publication Publication Date Title
WO2020199566A1 (zh) 一种导航地图与感知图像匹配关系的更新方法和装置
WO2020199565A1 (zh) 一种基于路灯杆的车辆位姿的修正方法和装置
WO2020192105A1 (zh) 一种车辆位姿的修正方法和装置
WO2020199564A1 (zh) 一种导航地图在初始化时车辆位姿的修正方法和装置
WO2020237996A1 (zh) 一种车辆位姿的修正方法和装置
KR102221286B1 (ko) 위치 업데이트 방법, 위치 및 내비게이션 노선의 표시 방법, 차량과 시스템
EP4365552A1 (en) Vehicle trajectory deviation correction method and apparatus, and electronic device
WO2020224305A1 (zh) 用于设备定位的方法、装置及设备
CN105225510A (zh) 用于验证地图的路网的方法和系统
US11193790B2 (en) Method and system for detecting changes in road-layout information
US11281228B2 (en) Method and device for determining a position of a transportation vehicle
CN111854727B (zh) 一种车辆位姿的修正方法和装置
US20200370915A1 (en) Travel assist system, travel assist method, and computer readable medium
CN108693548A (zh) 一种基于场景目标识别的导航方法及系统
CN110109165B (zh) 行驶轨迹中异常点的检测方法及装置
CN114445575A (zh) 一种基于路口拓扑信息的不同地图之间的匹配方法及系统
WO2021051361A1 (zh) 高精度地图定位方法、系统、平台及计算机可读存储介质
US20230154203A1 (en) Path planning method and system using the same
CN113048988B (zh) 一种导航地图对应场景的变化元素检测方法及装置
CN111462243A (zh) 车载流媒体后视镜标定方法、系统及装置
CN114910085A (zh) 一种基于路政设施识别的车辆融合定位方法及装置
CN114739416A (zh) 自动驾驶车辆定位方法、装置及电子设备、存储介质
CN114111817A (zh) 基于slam地图与高精度地图匹配的车辆定位方法及系统
KR20220092262A (ko) 운전자 지원 정밀 지도 제공 및 업데이트 시스템
KR20200036990A (ko) 정밀지도 업데이트 장치 및 그 방법

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19922970

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19922970

Country of ref document: EP

Kind code of ref document: A1