WO2023019509A1 - 基于环境匹配的车辆定位方法、装置、车辆及存储介质 - Google Patents

基于环境匹配的车辆定位方法、装置、车辆及存储介质 Download PDF

Info

Publication number
WO2023019509A1
WO2023019509A1 PCT/CN2021/113515 CN2021113515W WO2023019509A1 WO 2023019509 A1 WO2023019509 A1 WO 2023019509A1 CN 2021113515 W CN2021113515 W CN 2021113515W WO 2023019509 A1 WO2023019509 A1 WO 2023019509A1
Authority
WO
WIPO (PCT)
Prior art keywords
road image
environment
vehicle
matching
road
Prior art date
Application number
PCT/CN2021/113515
Other languages
English (en)
French (fr)
Inventor
金晨
卢红喜
周俊杰
衡阳
杜濠杰
Original Assignee
浙江吉利控股集团有限公司
宁波吉利汽车研究开发有限公司
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 浙江吉利控股集团有限公司, 宁波吉利汽车研究开发有限公司 filed Critical 浙江吉利控股集团有限公司
Priority to KR1020247003644A priority Critical patent/KR20240064620A/ko
Priority to CN202180097566.9A priority patent/CN117256009A/zh
Priority to PCT/CN2021/113515 priority patent/WO2023019509A1/zh
Priority to EP21953755.2A priority patent/EP4375856A1/en
Publication of WO2023019509A1 publication Critical patent/WO2023019509A1/zh
Priority to US18/429,828 priority patent/US20240169743A1/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • 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
    • G01C21/28—Navigation; 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
    • G01C21/30—Map- or contour-matching
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/51—Indexing; Data structures therefor; Storage structures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30248—Vehicle exterior or interior
    • G06T2207/30252—Vehicle exterior; Vicinity of vehicle
    • G06T2207/30256—Lane; Road marking

Definitions

  • the present invention relates to the technical field of automatic driving, in particular to a vehicle positioning method, device, vehicle and storage medium based on environment matching.
  • inertial navigation is used for position estimation, so that high-precision positioning can be achieved in different directions; another way is to use laser, vision and other single sensors or multi-sensor fusion (vision, laser, mmWave, etc.) for map collection, and use the mapping tool chain for simultaneous positioning and mapping (Simultaneous Localization And Mapping, SLAM), when the automatic driving system is running on the road, it uses sensors to perform feature matching to achieve high-precision positioning.
  • SLAM Simultaneous Localization And Mapping
  • the high-precision map (Map for Highly Automated Driving, HAD Map) requires map collection.
  • the map collection team is full-time to collect or update map information.
  • the main purpose of the present invention is to provide a vehicle positioning method, device, vehicle and storage medium based on environment matching, aiming at solving the technical problem of how to improve the vehicle positioning accuracy under different environmental conditions.
  • the present invention provides a vehicle positioning method based on environment matching, the method includes the following steps:
  • the current position information of the vehicle to be positioned is determined according to the target environment affecting road image.
  • the step of finding the environment-affected road image set matching the current environment data it may further include:
  • the basic road images are respectively injected according to the environmental impact feature information corresponding to different environmental impacts, so as to generate environmental impact road image sets under different environmental impacts.
  • the step of acquiring a road image set in a preset environment mode, and performing environmental impact removal processing on the road image set to obtain a basic road image set includes:
  • the step of injecting the basic road image according to the environmental impact feature information corresponding to different environmental impacts to generate the environmental impact road image sets under different environmental impacts includes:
  • the environmental composite factors are respectively injected into the basic road images to generate environmental impact road image sets under different environmental influences.
  • the step of respectively injecting the environmental composite factors into the basic road image to generate an environmental impact road image set under different environmental influences includes:
  • the road component elements in the basic road image set are respectively rendered according to the environmental composite factors, so as to generate environmental impact road image sets under different environmental influences.
  • the step of searching for an environment-impacted road image set matching the current environment data includes:
  • the step of determining the current location information of the vehicle to be positioned according to the target environment affecting the road image includes:
  • the current location information of the vehicle to be positioned is determined according to the historical GPS positioning information and the location information corresponding to the target environment-affected road image.
  • the present invention also proposes a vehicle positioning device based on environment matching, and the vehicle positioning device based on environment matching includes:
  • the data acquisition module is used to acquire the current environmental data of the location of the vehicle to be positioned and the current road image;
  • An image set search module configured to search for an image set of environmental impact roads matching the current environmental data
  • An image matching module configured to match the current road image with the environmental impact road images in the environmental impact road image set to obtain a target environmental impact road image matched with the current road image
  • a vehicle positioning module configured to determine the current position information of the vehicle to be positioned according to the target environment affecting road image.
  • the present invention also proposes a vehicle, the vehicle includes: a memory, a processor, and a vehicle positioning program based on environment matching that is stored in the memory and can run on the processor.
  • the vehicle positioning program based on environment matching is configured to realize the steps of the above-mentioned vehicle positioning method based on environment matching.
  • the present invention also proposes a storage medium, on which a vehicle positioning program based on environment matching is stored, and when the vehicle positioning program based on environment matching is executed by a processor, the above-mentioned The steps of the vehicle localization method based on environment matching.
  • the current environment data and the current road image of the location of the vehicle to be positioned are obtained, the environment-influenced road image set matching the current environment data is searched, and the current road image and the environment-influenced road image set are combined
  • the environment-affected road images are respectively matched to obtain a target environment-affected road image matched with the current road image, and the current position information of the vehicle to be positioned is determined according to the target environment-affected road image.
  • the vehicle positioning is carried out by using high-precision maps made under sunny daytime conditions, ignoring the positioning errors caused by weather and time periods.
  • the environmental impact road image set, and the current road image where the vehicle to be positioned is located is matched with the environmental impact road image in the environmental impact road image set, and the target environmental impact road image matched with the current road image is obtained , and then determine the current location information of the vehicle to be positioned according to the target environmental impact road image to fully consider the mapping effects caused by different environmental factors, reduce the positioning error caused by environmental interference, and improve the positioning accuracy of the vehicle under different environmental conditions .
  • Fig. 1 is a schematic structural diagram of a vehicle in a hardware operating environment involved in the solution of an embodiment of the present invention
  • FIG. 2 is a schematic flowchart of the first embodiment of the vehicle positioning method based on environment matching in the present invention
  • FIG. 3 is a schematic flowchart of a second embodiment of the vehicle positioning method based on environment matching in the present invention
  • FIG. 4 is a schematic diagram of dual positioning involved in the second embodiment of the vehicle positioning method based on environment matching in the present invention
  • FIG. 5 is a schematic flowchart of a third embodiment of the vehicle positioning method based on environment matching in the present invention.
  • Fig. 6 is a structural block diagram of the first embodiment of the vehicle positioning device based on environment matching according to the present invention.
  • FIG. 1 is a schematic diagram of the vehicle structure of the hardware operating environment involved in the solution of the embodiment of the present invention.
  • the vehicle may include: a processor 1001, such as a central processing unit (Central Processing Unit, CPU), communication bus 1002, user interface 1003, network interface 1004, memory 1005.
  • a processor 1001 such as a central processing unit (Central Processing Unit, CPU)
  • communication bus 1002 is used to realize connection and communication between these components.
  • the user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface.
  • the network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface).
  • WIreless-FIdelity WI-FI
  • Memory 1005 can be a high-speed random access memory (Random Access Memory, RAM), can also be a stable non-volatile memory (Non-Volatile Memory, NVM), such as disk storage.
  • RAM Random Access Memory
  • NVM Non-Volatile Memory
  • the memory 1005 may also be a storage device independent of the aforementioned processor 1001 .
  • FIG. 1 does not constitute a limitation to the vehicle, and may include more or less components than those shown in the illustration, or combine some components, or arrange different components.
  • the memory 1005 as a storage medium may include an operating system, a data storage module, a network communication module, a user interface module, and a vehicle positioning program based on environment matching.
  • the network interface 1004 is mainly used for data communication with the network server;
  • the user interface 1003 is mainly used for data interaction with the user;
  • the processor 1001 and the memory 1005 in the vehicle of the present invention can be arranged in the vehicle , the vehicle uses the processor 1001 to invoke the environment matching-based vehicle positioning program stored in the memory 1005, and executes the environment matching-based vehicle positioning method provided by the embodiment of the present invention.
  • FIG. 2 is a schematic flowchart of a first embodiment of the vehicle positioning method based on environment matching in the present invention.
  • the vehicle positioning method based on environment matching includes the following steps:
  • Step S10 Obtain the current environment data and the current road image of the location of the vehicle to be positioned;
  • the execution subject of this embodiment may be the processor 1001 mentioned above. etc.) to collect the current road image where the vehicle to be positioned is located, wherein the current road image can be understood as the image corresponding to the road where the vehicle to be positioned is currently located. is the image corresponding to the area where the vehicle to be positioned is currently located, where the size of the area can be set according to actual needs, which is not limited in this embodiment.
  • the current environmental data of the location of the vehicle to be positioned can also be obtained, the current environmental data includes current weather data and current time period data, which can be obtained through
  • the current weather data reflects the current weather conditions of the location of the vehicle to be positioned, such as sunny, cloudy, rainy, snowy, foggy, etc.
  • the current time period data reflects the current time period of the location of the vehicle to be positioned , such as early morning, noon, evening, late night, etc.
  • Step S20 Finding an image set of environment-impacted roads matching the current environment data
  • the environmental impact road image set matching the current environmental data can be searched in the preset road image library, wherein the environmental impact road image set can be understood as including
  • the environmental impact road image set can be understood as including
  • the preset road image library can be It is understood as a database that stores image sets corresponding to different roads (or different areas) under different environmental influences and is updated in real time.
  • Step S30 matching the current road image with the environmental impact road images in the environmental impact road image set to obtain a target environmental impact road image matching the current road image;
  • Step S40 Determine the current location information of the vehicle to be positioned according to the target environment affecting road image.
  • the current road image of the vehicle to be positioned can be combined with the environmental impact of the environmental impact road image set
  • the road images are respectively matched to obtain the target environment-affected road image matched with the current road image, and the current position information of the vehicle to be positioned is determined according to the target environment-affected road image.
  • the environmental impact road image set draws a corresponding high-precision map through synchronous positioning and mapping technology, and then performs vehicle positioning based on the obtained high-precision map.
  • the target environmental impact road image can be corresponding to the high-precision map
  • the location information of the vehicle to be positioned is used as the current location information of the vehicle to be positioned. For example, if the location coordinates corresponding to the target environmental impact road image are (a, b, c), then (a, b, c) is used as the location to be positioned The current location information of the vehicle.
  • the current environment data and the current road image of the location of the vehicle to be positioned are acquired, an environment-influenced road image set matching the current environment data is searched, and the current road image and the environment-influenced road image are collected together.
  • the environment-affected road images are respectively matched to obtain a target environment-affected road image matched with the current road image, and the current position information of the vehicle to be positioned is determined according to the target environment-affected road image.
  • the vehicle positioning is performed through high-precision maps made in sunny daytime conditions, ignoring the positioning errors caused by weather and time periods.
  • the current environmental data of the location of the vehicle to be positioned is searched.
  • the corresponding environmental impact road image set, and the current road image where the vehicle to be positioned is located is matched with the environmental impact road image in the environmental impact road image set, and the target environmental impact road matched with the current road image is obtained image, and then determine the current location information of the vehicle to be positioned according to the target environment impact road image to fully consider the mapping effects caused by different environmental factors, reduce the positioning error caused by environmental interference, and improve the vehicle positioning under different environmental conditions precision.
  • FIG. 3 is a schematic flowchart of a second embodiment of the vehicle positioning method based on environment matching in the present invention.
  • the method before the step S20, the method further includes:
  • Step S01 Obtain a road image set in a preset environment mode, and perform environmental impact removal processing on the road image set to obtain a basic road image set;
  • the image recognition result of the road component elements of a certain road is a street lamp on a dimly lit road, Then the corresponding road feature marks are: evening/late night, street lights, and for example, the image recognition result of the road component elements of a certain road is a warning sign covered by snow, then the corresponding road feature marks are: snow, warning sign;
  • the road composition elements can be understood as different elements that make up the road, such as road traffic sign elements (such as warning signs, prohibition signs, guide signs, etc.), road traffic marking elements (such as indicator lines, prohibition signs, etc.), Marking lines, warning marking lines, etc.), elements of traffic facilities (such as traffic lights, street lights, anti-collision barriers, etc.), elements of building facilities (such as residences, schools, hospitals, etc.), etc.
  • the label correction information input by the user can also be received, and the image feature label can be added/deleted/modified according to the label correction information; or, the road feature label input by the user can be directly received.
  • the road image set can be subjected to an environmental impact removal process according to the road feature label to obtain a basic road image set, wherein the environmental impact process can be understood as Carry out corresponding post-effect processing on the road image sets affected by environmental factors according to the different environmental impacts, and obtain the basic road image sets without environmental impacts.
  • the corresponding effect processing plug-ins can be selected according to the different environmental impacts , and then perform corresponding post-effect processing on the road image set through different effect processing plug-ins to obtain the basic road image set.
  • the mark for identifying the weather in the road feature mark is: snow
  • the corresponding effect processing plug-in can also be called in combination with the mark of the identification element category in the feature mark to perform environmental impact removal processing.
  • the road feature mark is: evening/late night, street light, then call and evening/late night and street light
  • the corresponding effect processing plug-in, or the effect plug-in corresponding to the element category of evening/late night and street lights ie, traffic facility elements
  • the road feature is marked as: snow, warning sign, then the call is related to snow and
  • the effect processing plug-in corresponding to the warning sign, or the effect plug-in corresponding to the element category to which the snow and warning signs belong ie, road traffic sign elements).
  • the corresponding basic high-precision map can also be drawn through synchronous positioning and mapping technology according to the basic road image set, and then the vehicle can be initially positioned based on the obtained basic high-precision map.
  • the environmental impact road image set draws corresponding high-precision maps through simultaneous positioning and mapping technology, and then performs dual positioning based on the obtained basic high-precision maps and high-precision maps to further improve vehicle positioning accuracy and user safety.
  • Step S02 Perform injection processing on the basic road images according to the environmental impact feature information corresponding to different environmental impacts, so as to generate environmental impact road image sets under different environmental impacts.
  • the weather impact factors and time period impact factors in the environmental feature information corresponding to different environmental impacts can be obtained, wherein the weather impact factors It can be understood as the corresponding image influencing factors under different weather conditions, such as rain, wind, snow, fog, sand, etc., and the time period influencing factors can be understood as corresponding image influencing factors under different periods, such as temperature and humidity, light brightness, etc. , and then, combine the weather influencing factors and time period influencing factors according to the preset combination rules to obtain different environmental composite factors, the preset combination rules can be set according to actual needs, for example, each weather The impact factor is combined with the impact factor of each period, which is not limited in this embodiment.
  • the corresponding effect processing plug-ins can be matched according to the environmental compounding factors, and the The effect processing plug-in injects the environmental compounding factors into the basic road image respectively to generate environmental impact road image sets under different environmental influences.
  • the environmental compounding factor is a combination of snow and light brightness
  • the matching effect processing The plug-in may process the plug-in for effects corresponding to snow and evening/late night.
  • the road component elements in the basic road image set can also be obtained, and the basic roads can be calculated according to the environmental composite factors
  • the road component elements in the image set are rendered to generate an environmental impact road image set under different environmental impacts.
  • the corresponding effect processing plug-in can be matched according to the environmental composite factor, and the road component elements in the basic road image set are respectively rendered through the effect processing plug-in to generate different environmental effects.
  • Environmental impact road image set in order to improve the accuracy of the obtained environment-influenced road image sets under different environmental influences, the corresponding effect processing plug-ins can also be matched in combination with road component elements.
  • the environmental composite factor is a combination of snow and low light brightness
  • the road component elements For anti-collision barriers call the effect processing plug-ins corresponding to snow, evening/late night and anti-collision barriers, and render the anti-collision barriers through the effect processing plug-ins; or call snow, evening/ An effect plug-in corresponding to the element category to which the anti-collision guardrail belongs (that is, the traffic facility element), and renders the anti-collision guardrail through the effect processing plug-in.
  • road component elements in the basic road image set are traversed to obtain environmental impact road image sets under different environmental influences.
  • a corresponding high-precision map can be drawn through synchronous positioning and mapping technology based on the environmental impact road image set, and then vehicle positioning can be performed based on the obtained high-precision map.
  • FIG. 4 is a schematic diagram of dual positioning involved in the second embodiment of the vehicle positioning method based on environment matching in the present invention.
  • the environmental impact stripping that is, the above-mentioned environmental impact removal process
  • the basic road image set draws the corresponding basic high-precision map through synchronous positioning and mapping technology, and then performs environmental impact injection on the basic high-precision map (that is, the above-mentioned environmental impact feature information corresponding to different environmental impacts is respectively applied to all Based on the above basic road image for injection processing), to generate the environmental impact road image set under different environmental influences, and based on the environmental impact road image set, the corresponding high-precision map is drawn through synchronous positioning and mapping technology, and then combined with the matched current environment
  • the high-precision map under the influence and the basic high-precision map perform real-time dual positioning to further improve the vehicle positioning accuracy and the user's riding safety.
  • the road image set in the preset environment mode is obtained, and the environmental impact removal process is performed on the road image set to obtain the basic road image set, and the environmental impact characteristic information corresponding to different environmental impacts is respectively processed.
  • the base road image is injected to generate a set of environment-affected road images under different environmental influences.
  • the basic road image set is obtained by performing environmental impact removal processing on the road image set in the preset environmental mode, and then injecting the basic road image according to the environmental impact feature information corresponding to different environmental impacts to generate different environmental impacts.
  • the environmental impact road image set under different environmental impacts in order to improve the accuracy of the obtained environmental impact road image sets under different environmental impacts and the accuracy of the subsequent high-precision maps drawn based on the environmental impact road image sets under different environmental impacts, further, also improve The accuracy of vehicle positioning based on the obtained high-precision map is improved.
  • FIG. 5 is a schematic flowchart of a third embodiment of the vehicle positioning method based on environment matching in the present invention.
  • the step S20 includes:
  • Step S201 Obtain the historical GPS positioning information of the vehicle to be positioned, and determine the corresponding image set of the region according to the historical GPS positioning information;
  • Step S202 Searching for an image set of environment-affected roads matching the current environment data in the image set of the region to which it belongs.
  • the historical GPS positioning information of the vehicle to be positioned can be obtained first, and the corresponding regional image set is determined according to the historical GPS positioning information.
  • the environment-influenced road image set matched with the current environment data. It is easy to understand that during the driving process of the vehicle, there will be situations where it is difficult to locate the vehicle due to weak GPS signals.
  • the historical GPS positioning information can be obtained, and the corresponding image set of the corresponding area can be determined according to the historical GPS positioning information.
  • the region image set can be understood as different image sets stored in the preset road image library according to different divisions of the region, and the preset road image library can be understood as a real-time updated store with different roads (or different regions) in different areas.
  • the area size can be set according to actual requirements, which is not limited in this embodiment.
  • what is acquired in this embodiment is not limited to the historical GPS positioning information of the vehicle to be positioned, and may also be inertial navigation positioning information, etc., which is not limited in this embodiment.
  • step S40 includes:
  • Step S401 Determine the current location information of the vehicle to be positioned according to the historical GPS positioning information and the location information corresponding to the target environment-affected road image.
  • the GPS positioning information at the current moment can also be predicted according to the historical GPS positioning information, and then the location information corresponding to the road image can be affected according to the predicted GPS positioning information at the current moment and the target environment Determine the current location information of the vehicle to be positioned.
  • the preset error rate is less than or equal to the preset error rate, and when it is less than or equal to the preset error, set the weight corresponding to the GPS positioning information at the current moment of the prediction and the position information corresponding to the target environment affecting the road image in different scenarios , and then determine the current location information of the vehicle to be positioned according to the two and their corresponding weights, wherein the preset error rate can be set according to actual needs, which is not limited in this embodiment.
  • a corresponding high-precision map can be drawn through synchronous positioning and mapping technology according to the set of environmental impact road images, and then the corresponding position information of the target environmental impact road image in the high-precision map can be obtained, and Determine the current position information of the vehicle to be positioned according to the corresponding position information of the target environment-affected road image in the high-precision map and the predicted GPS positioning information at the current moment, for example, the target environment-affected road image corresponds to
  • the position coordinates are (a, b, c)
  • the corresponding weight is 0.7
  • the predicted GPS positioning information at the current moment is (d, e, f)
  • the corresponding weight is 0.3
  • the current position information of the vehicle to be positioned can be is (0.7a+0.3d, 0.7b+0.3e, 0.7c+0.3f).
  • the historical GPS positioning information of the vehicle to be positioned is obtained, and the corresponding image set of the area to which it belongs is determined according to the historical GPS positioning information, and the environmental impact road matching the current environmental data is searched in the image set of the belonging area image set.
  • the current location information of the vehicle to be positioned is determined according to the historical GPS positioning information and the location information corresponding to the target environmental impact road image.
  • the current location information of the vehicle to be positioned is determined by combining the historical GPS positioning information of the vehicle to be positioned and the location information corresponding to the target environment impact road image, so as to reduce the vehicle positioning error as much as possible and improve the positioning accuracy of the vehicle at the same time , providing double protection for vehicle positioning and improving the safety of users.
  • the embodiment of the present invention also proposes a storage medium, on which a vehicle positioning program based on environment matching is stored.
  • a vehicle positioning program based on environment matching is executed by a processor, the above-mentioned environment-based Steps of a matching vehicle location method.
  • FIG. 6 is a structural block diagram of the first embodiment of the vehicle positioning device based on environment matching according to the present invention.
  • the vehicle positioning device based on environment matching proposed by the embodiment of the present invention includes:
  • the data acquisition module 10 is used to acquire the current environment data and the current road image of the position of the vehicle to be positioned;
  • An image set search module 20 configured to search for an environment-affected road image set matching the current environment data
  • An image matching module 30, configured to match the current road image with the environment-affected road images in the environment-affected road image set to obtain a target environment-affected road image matched with the current road image;
  • the vehicle positioning module 40 is configured to determine the current position information of the vehicle to be positioned according to the target environment affecting road image.
  • the current environment data and the current road image of the location of the vehicle to be positioned are acquired, an environment-influenced road image set matching the current environment data is searched, and the current road image and the environment-influenced road image are collected together.
  • the environment-affected road images are respectively matched to obtain a target environment-affected road image matched with the current road image, and the current position information of the vehicle to be positioned is determined according to the target environment-affected road image.
  • the vehicle positioning is performed through high-precision maps made in sunny daytime conditions, ignoring the positioning errors caused by weather and time periods.
  • the current environmental data of the location of the vehicle to be positioned is searched.
  • the corresponding environmental impact road image set, and the current road image where the vehicle to be positioned is located is matched with the environmental impact road image in the environmental impact road image set, and the target environmental impact road matched with the current road image is obtained image, and then determine the current location information of the vehicle to be positioned according to the target environment impact road image to fully consider the mapping effects caused by different environmental factors, reduce the positioning error caused by environmental interference, and improve the vehicle positioning under different environmental conditions precision.
  • a second embodiment of the vehicle positioning device based on environment matching in the present invention is proposed.
  • the data acquisition module 10 is further configured to acquire a road image set in a preset environment mode, and perform environmental impact removal processing on the road image set to obtain a basic road image set;
  • the data acquisition module 10 is further configured to perform injection processing on the basic road images according to the environmental impact characteristic information corresponding to different environmental impacts, so as to generate environmental impact road image sets under different environmental impacts.
  • the data acquisition module 10 is also used to respectively acquire road image sets under different weather and different time periods, and perform image recognition and feature marks on the road image sets to obtain road feature marks;
  • the data acquisition module 10 is further configured to perform environmental impact removal processing on the road image set according to the road feature mark, so as to obtain a basic road image set.
  • the data acquisition module 10 is also used to acquire weather impact factors and period impact factors in the environmental feature information corresponding to different environmental impacts;
  • the data acquisition module 10 is also used to combine the weather influencing factors and time period influencing factors according to preset combination rules to obtain different environmental composite factors;
  • the data acquisition module 10 is further configured to respectively inject the environmental composite factors into the basic road images to generate environmental impact road image sets under different environmental influences.
  • the data acquisition module 10 is also used to acquire road component elements in the basic road image set;
  • the data acquisition module 10 is further configured to respectively render the road component elements in the basic road image set according to the environmental composite factors, so as to generate environmental impact road image sets under different environmental influences.
  • the image set search module 20 is also used to obtain the historical GPS positioning information of the vehicle to be positioned, and determine the corresponding image set of the region according to the historical GPS positioning information;
  • the image set search module 20 is further configured to search for an image set of environment-affected roads matching the current environment data in the image set of the region to which it belongs.
  • the vehicle positioning module 40 is further configured to determine the current position information of the vehicle to be positioned according to the historical GPS positioning information and the position information corresponding to the target environmental impact road image.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Software Systems (AREA)
  • Automation & Control Theory (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Medical Informatics (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Molecular Biology (AREA)
  • Mathematical Physics (AREA)
  • Navigation (AREA)

Abstract

一种基于环境匹配的车辆定位方法、装置、车辆及存储介质，涉及自动驾驶技术领域，所述方法包括：步骤S10：获取待定位车辆所处位置的当前环境数据以及当前道路图像；步骤S20：查找与当前环境数据匹配的环境影响道路图像集；步骤S30：将当前道路图像与环境影响道路图像集中的环境影响道路图像分别进行匹配，获得与当前道路图像匹配的目标环境影响道路图像；步骤S40：根据目标环境影响道路图像确定待定位车辆的当前位置信息。相较于现有技术多通过在晴天的白天状况下制作的高精度地图进行车辆定位，忽略了因天气、时段带来的定位误差，通过上述步骤以充分考虑不同环境因素造成的制图影响，降低因环境干扰带来的定位误差，提高不同环境状况下的车辆定位精度。

Description

基于环境匹配的车辆定位方法、装置、车辆及存储介质 技术领域
本发明涉及自动驾驶技术领域，尤其涉及一种基于环境匹配的车辆定位方法、装置、车辆及存储介质。
 背景技术
随着自动驾驶技术的发展及迭代，实现自动驾驶车辆量产的日子也越来越近。在自动驾驶系统的自动运行过程中，为了更好地了解自身姿态，进行精确的行为规划和车身控制，就不得不提及高精度定位功能。当前行业公认的高精度定位功能有两种方式实现，一种是基于卫星定位及惯性导航系统组合成的高精度定位系统，这种定位系统依靠固定频率的多卫星通讯实现定位，在隧道高架等部分地区无法进行卫星通讯时，利用惯性导航进行位置估值，从而实现不同方位都可以实现高精度定位的效果；另外一种方式是通过激光、视觉等单一传感器或者多传感器融合（视觉、激光、毫米波等）进行地图采集，同时利用制图工具链进行同步定位与建图(Simultaneous Localization And Mapping，SLAM)，自动驾驶系统在道路运行时，利用传感器进行特征匹配，实现高精度定位。
在具体实现中，高精度地图（Map for Highly Automated Driving，HAD Map）的制作是需要进行地图采集的。当前国内外进行地图数据采集多采用以下两种方式：1、地图采集车队专职进行地图信息采集或者更新。2、以数据众包的形式进行地图采集或者更新。无论是基于哪种方式，当前的制图方式都是先建立高精度地图，然后在自动驾驶需要进行高精度地图定位时则使用即时的环境感知与高精度地图进行匹配定位。但在这种形式下存在一个信息差，因高精度地图是基于采集到的地图信息建立，但是进行实时定位时感知到的环境差异较大，例如晴天、阴天、白天、夜晚、雨天、雪天、雾天等不同天气、不同时段造成的影响。因此，如何提高不同环境状况下的车辆定位精度，成为一个亟待解决的问题。
上述内容仅用于辅助理解本发明的技术方案，并不代表承认上述内容是现有技术。
 技术问题
本发明的主要目的在于提供了一种基于环境匹配的车辆定位方法、装置、车辆及存储介质，旨在解决如何提高不同环境状况下的车辆定位精度的技术问题。
 技术解决方案
为实现上述目的，本发明提供了一种基于环境匹配的车辆定位方法，所述方法包括以下步骤：
获取待定位车辆所处位置的当前环境数据以及当前道路图像；
查找与所述当前环境数据匹配的环境影响道路图像集；
将所述当前道路图像与所述环境影响道路图像集中的环境影响道路图像分别进行匹配，获得与所述当前道路图像匹配的目标环境影响道路图像；
根据所述目标环境影响道路图像确定所述待定位车辆的当前位置信息。
可选地，所述查找与所述当前环境数据匹配的环境影响道路图像集的步骤之前，还包括：
获取预设环境模式下的道路图像集，并对所述道路图像集进行环境影响去除处理，以获得基础道路图像集；
根据不同环境影响对应的环境影响特征信息分别对所述基础道路图像进行注入处理，以生成不同环境影响下的环境影响道路图像集。
可选地，所述获取预设环境模式下的道路图像集，并对所述道路图像集进行环境影响去除处理，以获得基础道路图像集的步骤，包括：
分别获取不同天气和不同时段下的道路图像集，并对所述道路图像集进行图像识别以及特征标记，获得道路特征标记；
根据所述道路特征标记对所述道路图像集进行环境影响去除处理，以获得基础道路图像集。
可选地，所述根据不同环境影响对应的环境影响特征信息分别对所述基础道路图像进行注入处理，以生成不同环境影响下的环境影响道路图像集的步骤，包括：
获取不同环境影响对应的环境特征信息中的天气影响因子和时段影响因子；
将所述天气影响因子和时段影响因子按照预设组合规则进行组合，以获得不同的环境复合因子；
将所述环境复合因子分别注入至所述基础道路图像，以生成不同环境影响下的环境影响道路图像集。
可选地，所述将所述环境复合因子分别注入至所述基础道路图像，以生成不同环境影响下的环境影响道路图像集的步骤，包括：
获取所述基础道路图像集中的道路组成元素；
根据所述环境复合因子分别对所述基础道路图像集中的所述道路组成元素进行渲染，以生成不同环境影响下的环境影响道路图像集。
可选地，所述查找与所述当前环境数据匹配的环境影响道路图像集的步骤，包括：
获取待定位车辆的历史GPS定位信息，并根据所述历史GPS定位信息确定对应的所属区域图像集；
在所述所属区域图像集中查找与所述当前环境数据匹配的环境影响道路图像集。
可选地，所述根据所述目标环境影响道路图像确定所述待定位车辆的当前位置信息的步骤，包括：
根据所述历史GPS定位信息和所述目标环境影响道路图像对应的位置信息确定所述待定位车辆的当前位置信息。
此外，为实现上述目的，本发明还提出一种基于环境匹配的车辆定位装置，所述基于环境匹配的车辆定位装置包括：
数据获取模块，用于获取待定位车辆所处位置的当前环境数据以及当前道路图像；
图像集查找模块，用于查找与所述当前环境数据匹配的环境影响道路图像集；
图像匹配模块，用于将所述当前道路图像与所述环境影响道路图像集中的环境影响道路图像分别进行匹配，获得与所述当前道路图像匹配的目标环境影响道路图像；
车辆定位模块，用于根据所述目标环境影响道路图像确定所述待定位车辆的当前位置信息。
此外，为实现上述目的，本发明还提出一种车辆，所述车辆包括：存储器、处理器及存储在所述存储器上并可在所述处理器上运行的基于环境匹配的车辆定位程序，所述基于环境匹配的车辆定位程序配置为实现如上文所述的基于环境匹配的车辆定位方法的步骤。
此外，为实现上述目的，本发明还提出一种存储介质，所述存储介质上存储有基于环境匹配的车辆定位程序，所述基于环境匹配的车辆定位程序被处理器执行时实现如上文所述的基于环境匹配的车辆定位方法的步骤。
 有益效果
本发明中，获取待定位车辆所处位置的当前环境数据以及当前道路图像，查找与所述当前环境数据匹配的环境影响道路图像集，将所述当前道路图像与所述环境影响道路图像集中的环境影响道路图像分别进行匹配，获得与所述当前道路图像匹配的目标环境影响道路图像，根据所述目标环境影响道路图像确定所述待定位车辆的当前位置信息。相较于现有技术多通过在晴天的白天状况下制作的高精度地图进行车辆定位，忽略了因天气、时段带来的定位误差，本发明通过查找待定位车辆所处位置的当前环境数据对应的环境影响道路图像集，并将待定位车辆所处位置的当前道路图像与所述环境影响道路图像集中的环境影响道路图像分别进行匹配，获得与所述当前道路图像匹配的目标环境影响道路图像，再根据所述目标环境影响道路图像确定所述待定位车辆的当前位置信息以充分考虑不同环境因素造成的制图影响，降低因环境干扰带来的定位误差，提高不同环境状况下的车辆定位精度。
 附图说明
图1是本发明实施例方案涉及的硬件运行环境的车辆的结构示意图；
图2为本发明基于环境匹配的车辆定位方法第一实施例的流程示意图；
图3为本发明基于环境匹配的车辆定位方法第二实施例的流程示意图；
图4为本发明基于环境匹配的车辆定位方法第二实施例涉及的双重定位示意图；
图5为本发明基于环境匹配的车辆定位方法第三实施例的流程示意图；
图6为本发明基于环境匹配的车辆定位装置第一实施例的结构框图。
本发明目的的实现、功能特点及优点将结合实施例，参照附图做进一步说明。
 本发明的实施方式
应当理解，此处所描述的具体实施例仅用以解释本发明，并不用于限定本发明。
参照图1，图1为本发明实施例方案涉及的硬件运行环境的车辆结构示意图。
如图1所示，该车辆可以包括：处理器1001，例如中央处理器（Central Processing Unit，CPU），通信总线1002、用户接口1003，网络接口1004，存储器1005。其中，通信总线1002用于实现这些组件之间的连接通信。用户接口1003可以包括显示屏（Display）、输入单元比如键盘（Keyboard），可选用户接口1003还可以包括标准的有线接口、无线接口。网络接口1004可选的可以包括标准的有线接口、无线接口（如无线保真（WIreless-FIdelity，WI-FI）接口）。存储器1005可以是高速的随机存取存储器（Random Access Memory，RAM），也可以是稳定的非易失性存储器（Non-Volatile Memory，NVM），例如磁盘存储器。存储器1005可选的还可以是独立于前述处理器1001的存储装置。
本领域技术人员可以理解，图1中示出的结构并不构成对车辆的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。
如图1所示，作为一种存储介质的存储器1005中可以包括操作系统、数据存储模块、网络通信模块、用户接口模块以及基于环境匹配的车辆定位程序。
在图1所示的车辆中，网络接口1004主要用于与网络服务器进行数据通信；用户接口1003主要用于与用户进行数据交互；本发明车辆中的处理器1001、存储器1005可以设置在车辆中，所述车辆通过处理器1001调用存储器1005中存储的基于环境匹配的车辆定位程序，并执行本发明实施例提供的基于环境匹配的车辆定位方法。
本发明实施例提供了一种基于环境匹配的车辆定位方法，参照图2，图2为本发明基于环境匹配的车辆定位方法第一实施例的流程示意图。
本实施例中，所述基于环境匹配的车辆定位方法包括以下步骤：
步骤S10：获取待定位车辆所处位置的当前环境数据以及当前道路图像；
易于理解的是，本实施例的执行主体可为上述处理器1001，在具体实现中，可通过与所述处理器1001相连的激光、视觉等单一传感器或者多传感器融合（视觉、激光、毫米波等）采集待定位车辆所处位置的当前道路图像，其中，所述当前道路图像可理解为待定位车辆当前所处道路对应的图像，在具体实现中，因也存在未规划道路，故也可为待定位车辆当前所处区域对应的图像，其中，区域大小可根据实际需求进行设置，本实施例对此不加以限制。
在具体实现中，为了提高数据采集精度，以进一步提高车辆定位精度，还可获取待定位车辆所处位置的当前环境数据，所述当前环境数据包括当前天气数据和当前时段数据，其中，可通过所述当前天气数据反映待定位车辆所处位置的当前天气状况，如，晴天、阴天、雨天、雪天、雾天等；通过所述当前时段数据反映待定位车辆所处位置的当前所属时段，如，清晨、中午、傍晚、深夜等。
步骤S20：查找与所述当前环境数据匹配的环境影响道路图像集；
需要说明的是，在获得所述当前环境数据后，可在预设道路图像库中查找与所述当前环境数据匹配的环境影响道路图像集，其中，所述环境影响道路图像集可理解为包含有不同环境影响下对应的道路图像的数据集，如，雨天的深夜对应的道路图像、雾天的清晨对应的道路图像、阴天的傍晚对应的道路图像等，所述预设道路图像库可理解为实时更新的存储有不同道路（或不同区域）在不同环境影响下对应的图像集的数据库。
步骤S30：将所述当前道路图像与所述环境影响道路图像集中的环境影响道路图像分别进行匹配，获得与所述当前道路图像匹配的目标环境影响道路图像；
步骤S40：根据所述目标环境影响道路图像确定所述待定位车辆的当前位置信息。
易于理解的是，在获得与待定位车辆所处位置的当前环境数据匹配的环境影响道路图像集时，可将待定位车辆所处位置的当前道路图像与所述环境影响道路图像集中的环境影响道路图像分别进行匹配，获得与所述当前道路图像匹配的目标环境影响道路图像，并根据所述目标环境影响道路图像确定所述待定位车辆的当前位置信息，在具体实现中，可根据所述环境影响道路图像集通过同步定位与建图技术绘制对应的高精度地图，再基于获得的高精度地图进行车辆定位，进一步地，可将所述目标环境影响道路图像在所述高精度地图中对应的位置信息作为所述待定位车辆的当前位置信息，如，所述目标环境影响道路图像对应的位置坐标为（a，b，c），则将（a，b，c）作为所述待定位车辆的当前位置信息。
本实施例中，获取待定位车辆所处位置的当前环境数据以及当前道路图像，查找与所述当前环境数据匹配的环境影响道路图像集，将所述当前道路图像与所述环境影响道路图像集中的环境影响道路图像分别进行匹配，获得与所述当前道路图像匹配的目标环境影响道路图像，根据所述目标环境影响道路图像确定所述待定位车辆的当前位置信息。相较于现有技术多通过在晴天的白天状况下制作的高精度地图进行车辆定位，忽略了因天气、时段带来的定位误差，本实施例通过查找待定位车辆所处位置的当前环境数据对应的环境影响道路图像集，并将待定位车辆所处位置的当前道路图像与所述环境影响道路图像集中的环境影响道路图像分别进行匹配，获得与所述当前道路图像匹配的目标环境影响道路图像，再根据所述目标环境影响道路图像确定所述待定位车辆的当前位置信息以充分考虑不同环境因素造成的制图影响，降低因环境干扰带来的定位误差，提高不同环境状况下的车辆定位精度。
参考图3，图3为本发明基于环境匹配的车辆定位方法第二实施例的流程示意图。
基于上述第一实施例，在本实施例中，所述步骤S20之前，所述方法还包括：
步骤S01：获取预设环境模式下的道路图像集，并对所述道路图像集进行环境影响去除处理，以获得基础道路图像集；
需要说明的是，为了获得不同环境影响下的环境影响道路图像集，可先分别获取不同天气（如，晴天、阴天、雨天、雪天、雾天等）和不同时段（如，清晨、中午、傍晚、深夜等）下的道路图像集，并对所述道路图像集进行图像识别，获得图像识别结果，再对所述图像识别结果进行特征标记，获得道路特征标记，其中，特征标记可理解为标记图像识别结果中的特征信息，可用于标识天气、时段、道路组成元素、道路组成元素所属类别等，如，某一道路的道路组成元素的图像识别结果为光线昏暗的道路上的路灯，则对应的道路特征标记为：傍晚/深夜，路灯，又如，某一道路的道路组成元素的图像识别结果为被雪覆盖的警告标志，则对应的道路特征标记为：雪天，警告标志；其中，所述道路组成元素可理解为组成道路的不同元素，如，道路交通标志类元素（如警告标志、禁令标志、指路标志等）、道路交通标线类元素（如指示标线、禁止标线、警告标线等）、交通设施类元素（如红绿灯、路灯、防撞护栏等）、建筑设施类元素（如住宅、学校、医院等）等。在具体实现中，为了提高特征标记精度，也可接收用户输入的标记修正信息，并根据所述标记修正信息增加/删除/修改所述图像特征标记；或，直接接收用户输入的道路特征标记。
易于理解的是，在获得所述道路特征标记时，可根据所述道路特征标记对所述道路图像集进行环境影响去除处理，以获得基础道路图像集，其中，所述环境影响处理可理解为分别对有环境因素影响的道路图像集根据环境影响的不同进行对应的后期效果处理，获得无环境影响下的基础道路图像集，在具体实现中，可根据环境影响的不同选择对应的效果处理插件，再通过不同的效果处理插件对所述道路图像集进行对应的后期效果处理，以获得基础道路图像集。如，道路特征标记中标识天气的标记为：雪天，则调取与雪天对应的效果处理插件，又如，道路特征标记中标识时段的标记为：傍晚/深夜，则调取与傍晚/深夜对应的效果处理插件。进一步地，还可结合特征标记中的标识元素类别的标记调取对应的效果处理插件进行环境影响去除处理，如，道路特征标记为：傍晚/深夜，路灯，则调取与傍晚/深夜以及路灯对应的效果处理插件，或，与傍晚/深夜以及路灯所属元素类别（即交通设施类元素）对应的效果插件；又如，道路特征标记为：雪天，警告标志，则调取与雪天以及警告标志对应的效果处理插件，或，与雪天以及警告标志所属元素类别（即道路交通标志类元素）对应的效果插件。
在具体实现中，还可根据所述基础道路图像集通过同步定位与建图技术绘制对应的基础高精度地图，再基于获得的基础高精度地图进行车辆初步定位，进一步地，还可结合后续基于环境影响道路图像集通过同步定位与建图技术绘制对应的高精度地图，再基于获得的基础高精度地图和高精度地图进行双重定位，以进一步提高车辆定位精度和用户的乘车安全性。
步骤S02：根据不同环境影响对应的环境影响特征信息分别对所述基础道路图像进行注入处理，以生成不同环境影响下的环境影响道路图像集。
需要说明的是，为了提高获得的不同环境影响下的环境影响道路图像集的图像精度，可获取不同环境影响对应的环境特征信息中的天气影响因子和时段影响因子，其中，所述天气影响因子可理解为不同天气下对应的图像影响因素，如，雨、风、雪、雾、沙尘等，所述时段影响因子可理解为不同时段下对应的图像影响因素，如温湿度、光照亮度等，然后，将所述天气影响因子和时段影响因子按照预设组合规则进行组合，以获得不同的环境复合因子，所述预设组合规则可根据实际需求进行设置，如，将分别将每个天气影响因子与每个时段影响因子进行组合，本实施例对此不加以限制。再将所述环境复合因子分别注入至所述基础道路图像，以生成不同环境影响下的环境影响道路图像集，在具体实现中，可根据环境复合因子匹配对应的效果处理插件，并通过所述效果处理插件将所述环境复合因子分别注入至所述基础道路图像，以生成不同环境影响下的环境影响道路图像集，如，环境复合因子为雪和光照亮度低的组合，则匹配的效果处理插件可为雪天以及傍晚/深夜所对应的效果处理插件。
易于理解的是，为了提高获得的不同环境影响下的环境影响道路图像集的图像精度，还可获取所述基础道路图像集中的道路组成元素，并根据所述环境复合因子分别对所述基础道路图像集中的所述道路组成元素进行渲染，以生成不同环境影响下的环境影响道路图像集。在具体实现中，可根据所述环境复合因子匹配对应的效果处理插件，并分别对所述基础道路图像集中的所述道路组成元素通过所述效果处理插件进行渲染，以生成不同环境影响下的环境影响道路图像集。进一步地，为了提高获得的不同环境影响下的环境影响道路图像集的精度，还可结合道路组成元素匹配对应的效果处理插件，如，环境复合因子为雪和光照亮度低的组合，道路组成元素为防撞护栏，则调取与雪天、傍晚/深夜以及防撞护栏对应的效果处理插件，并对所述防撞护栏通过该效果处理插件进行渲染；或，调取与雪天、傍晚/深夜以及防撞护栏所属元素类别（即交通设施类元素）对应的效果插件，并对所述防撞护栏通过该效果处理插件进行渲染。以此，遍历所述基础道路图像集中的道路组成元素，获得不同环境影响下的环境影响道路图像集。进一步地，可根据所述环境影响道路图像集通过同步定位与建图技术绘制对应的高精度地图，再基于获得的高精度地图进行车辆定位。
参考图4，图4为本发明基于环境匹配的车辆定位方法第二实施例涉及的双重定位示意图。
图4中，在采集到地图数据（即上述预设环境模式下的道路图像集）后，可对地图数据进行环境影响剥离（即上述环境影响去除处理），以获得基础道路图像集，再根据所述基础道路图像集通过同步定位与建图技术绘制对应的基础高精度地图，然后，对所述基础高精度地图进行环境影响注入（即上述根据不同环境影响对应的环境影响特征信息分别对所述基础道路图像进行注入处理），以生成不同环境影响下的环境影响道路图像集，并基于环境影响道路图像集通过同步定位与建图技术绘制对应的高精度地图，再结合匹配到的当前环境影响下的高精度地图和所述基础高精度地图进行实时双重定位，以进一步提高车辆定位精度和用户的乘车安全性。
本实施例中，获取预设环境模式下的道路图像集，并对所述道路图像集进行环境影响去除处理，以获得基础道路图像集，根据不同环境影响对应的环境影响特征信息分别对所述基础道路图像进行注入处理，以生成不同环境影响下的环境影响道路图像集。通过对预设环境模式下的道路图像集进行环境影响去除处理，以获得基础道路图像集，再根据不同环境影响对应的环境影响特征信息分别对所述基础道路图像进行注入处理，生成不同环境影响下的环境影响道路图像集，以提高获得的不同环境影响下的环境影响道路图像集的精度和后续基于不同环境影响下的环境影响道路图像集绘制的高精度地图的精度，进一步地，也提高了基于获得的高精度地图进行车辆定位的精准度。
参考图5，图5为本发明基于环境匹配的车辆定位方法第三实施例的流程示意图。
基于上述各实施例，在本实施例中，所述步骤S20包括：
步骤S201：获取待定位车辆的历史GPS定位信息，并根据所述历史GPS定位信息确定对应的所属区域图像集；
步骤S202：在所述所属区域图像集中查找与所述当前环境数据匹配的环境影响道路图像集。
易于理解的是，为了提高图像集查找效率，可先获取待定位车辆的历史GPS定位信息，并根据所述历史GPS定位信息确定对应的所属区域图像集，再在所述所属区域图像集中查找与所述当前环境数据匹配的环境影响道路图像集。易于理解的是，在车辆行驶过程中，会存在因GPS信号弱等难以进行车辆定位的情形，此时可获取历史GPS定位信息，并根据历史GPS定位信息确定对应的所属区域图像集，其中，所述区域图像集可理解为预设道路图像库中存储的依据区域的不同划分的不同图像集，所述预设道路图像库可理解为实时更新的存储有不同道路（或不同区域）在不同环境影响下对应的图像集的数据库，在具体实现中，区域大小可根据实际需求进行设置，本实施例对此不加以限制。此外，需要说明的是，本实施例所获取的并不仅限于待定位车辆的历史GPS定位信息，还可为惯性导航定位信息等，本实施例对此不加以限制。
相应地，所述步骤S40包括：
步骤S401：根据所述历史GPS定位信息和所述目标环境影响道路图像对应的位置信息确定所述待定位车辆的当前位置信息。
本实施例中，为了提高车辆定位精度，还可根据所述历史GPS定位信息预测当前时刻的GPS定位信息，再根据预测的当前时刻的GPS定位信息和所述目标环境影响道路图像对应的位置信息确定所述待定位车辆的当前位置信息，在具体实现中，还可判断不同场景下所述预测的当前时刻的GPS定位信息和所述目标环境影响道路图像对应的位置信息这二者之间的误差率是否小于等于预设误差率，在小于等于预设误差时，设置不同场景下所述预测的当前时刻的GPS定位信息和所述目标环境影响道路图像对应的位置信息这二者对应的权重，再根据二者及其对应的权重确定所述待定位车辆的当前位置信息，其中，所述预设误差率可根据实际需求进行设置，本实施例对此不加以限制。在具体实现中，可根据所述环境影响道路图像集通过同步定位与建图技术绘制对应的高精度地图，再获取所述目标环境影响道路图像在所述高精度地图中对应的位置信息，并根据所述目标环境影响道路图像在所述高精度地图中对应的位置信息和预测的当前时刻的GPS定位信息确定所述待定位车辆的当前位置信息，如，所述目标环境影响道路图像对应的位置坐标为（a，b，c），对应权重为0.7，预测的当前时刻的GPS定位信息为（d，e，f），对应的权重为0.3，则所述待定位车辆的当前位置信息可为（0.7a+0.3d，0.7b+0.3e，0.7c+0.3f）。
本实施例中，获取待定位车辆的历史GPS定位信息，并根据所述历史GPS定位信息确定对应的所属区域图像集，在所述所属区域图像集中查找与所述当前环境数据匹配的环境影响道路图像集。通过根据待定位车辆的历史GPS定位信息确定对应的所属区域图像集，并在所述所属区域图像集中查找与所述当前环境数据匹配的环境影响道路图像集来提高图像集搜索效率，以进一步提高后续基于图像集进行车辆定位的定位效率。此外，本实施例中，根据所述历史GPS定位信息和所述目标环境影响道路图像对应的位置信息确定所述待定位车辆的当前位置信息。通过结合待定位车辆的历史GPS定位信息和所述目标环境影响道路图像对应的位置信息来确定所述待定位车辆的当前位置信息，以实现尽可能减小车辆定位误差，提高车辆定位精度的同时，为车辆定位提供双重保障，提高用户的乘车安全性。
此外，本发明实施例还提出一种存储介质，所述存储介质上存储有基于环境匹配的车辆定位程序，所述基于环境匹配的车辆定位程序被处理器执行时实现如上文所述的基于环境匹配的车辆定位方法的步骤。
参照图6，图6为本发明基于环境匹配的车辆定位装置第一实施例的结构框图。
如图6所示，本发明实施例提出的基于环境匹配的车辆定位装置包括：
数据获取模块10，用于获取待定位车辆所处位置的当前环境数据以及当前道路图像；
图像集查找模块20，用于查找与所述当前环境数据匹配的环境影响道路图像集；
图像匹配模块30，用于将所述当前道路图像与所述环境影响道路图像集中的环境影响道路图像分别进行匹配，获得与所述当前道路图像匹配的目标环境影响道路图像；
车辆定位模块40，用于根据所述目标环境影响道路图像确定所述待定位车辆的当前位置信息。
本实施例中，获取待定位车辆所处位置的当前环境数据以及当前道路图像，查找与所述当前环境数据匹配的环境影响道路图像集，将所述当前道路图像与所述环境影响道路图像集中的环境影响道路图像分别进行匹配，获得与所述当前道路图像匹配的目标环境影响道路图像，根据所述目标环境影响道路图像确定所述待定位车辆的当前位置信息。相较于现有技术多通过在晴天的白天状况下制作的高精度地图进行车辆定位，忽略了因天气、时段带来的定位误差，本实施例通过查找待定位车辆所处位置的当前环境数据对应的环境影响道路图像集，并将待定位车辆所处位置的当前道路图像与所述环境影响道路图像集中的环境影响道路图像分别进行匹配，获得与所述当前道路图像匹配的目标环境影响道路图像，再根据所述目标环境影响道路图像确定所述待定位车辆的当前位置信息以充分考虑不同环境因素造成的制图影响，降低因环境干扰带来的定位误差，提高不同环境状况下的车辆定位精度。
基于本发明上述基于环境匹配的车辆定位装置第一实施例，提出本发明基于环境匹配的车辆定位装置的第二实施例。
在本实施例中，所述数据获取模块10，还用于获取预设环境模式下的道路图像集，并对所述道路图像集进行环境影响去除处理，以获得基础道路图像集；
所述数据获取模块10，还用于根据不同环境影响对应的环境影响特征信息分别对所述基础道路图像进行注入处理，以生成不同环境影响下的环境影响道路图像集。
所述数据获取模块10，还用于分别获取不同天气和不同时段下的道路图像集，并对所述道路图像集进行图像识别以及特征标记，获得道路特征标记；
所述数据获取模块10，还用于根据所述道路特征标记对所述道路图像集进行环境影响去除处理，以获得基础道路图像集。
所述数据获取模块10，还用于获取不同环境影响对应的环境特征信息中的天气影响因子和时段影响因子；
所述数据获取模块10，还用于将所述天气影响因子和时段影响因子按照预设组合规则进行组合，以获得不同的环境复合因子；
所述数据获取模块10，还用于将所述环境复合因子分别注入至所述基础道路图像，以生成不同环境影响下的环境影响道路图像集。
所述数据获取模块10，还用于获取所述基础道路图像集中的道路组成元素；
所述数据获取模块10，还用于根据所述环境复合因子分别对所述基础道路图像集中的所述道路组成元素进行渲染，以生成不同环境影响下的环境影响道路图像集。
所述图像集查找模块20，还用于获取待定位车辆的历史GPS定位信息，并根据所述历史GPS定位信息确定对应的所属区域图像集；
所述图像集查找模块20，还用于在所述所属区域图像集中查找与所述当前环境数据匹配的环境影响道路图像集。
所述车辆定位模块40，还用于根据所述历史GPS定位信息和所述目标环境影响道路图像对应的位置信息确定所述待定位车辆的当前位置信息。
本发明基于环境匹配的车辆定位装置的其他实施例或具体实现方式可参照上述各方法实施例，此处不再赘述。
需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者系统不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者系统所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者系统中还存在另外的相同要素。
上述本发明实施例序号仅仅为了描述，不代表实施例的优劣。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。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介质（如只读存储器/随机存取存储器、磁碟、光盘）中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，空调器，或者网络设备等)执行本发明各个实施例所述的方法。
以上仅为本发明的优选实施例，并非因此限制本发明的专利范围，凡是利用本发明说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本发明的专利保护范围内。

Claims (10)

  1. 一种基于环境匹配的车辆定位方法，其特征在于，所述基于环境匹配的车辆定位方法包括以下步骤：
    获取待定位车辆所处位置的当前环境数据以及当前道路图像；
    查找与所述当前环境数据匹配的环境影响道路图像集；
    将所述当前道路图像与所述环境影响道路图像集中的环境影响道路图像分别进行匹配，获得与所述当前道路图像匹配的目标环境影响道路图像；
    根据所述目标环境影响道路图像确定所述待定位车辆的当前位置信息。
  2. 如权利要求1所述的基于环境匹配的车辆定位方法，其特征在于，所述查找与所述当前环境数据匹配的环境影响道路图像集的步骤之前，还包括：
    获取预设环境模式下的道路图像集，并对所述道路图像集进行环境影响去除处理，以获得基础道路图像集；
    根据不同环境影响对应的环境影响特征信息分别对所述基础道路图像进行注入处理，以生成不同环境影响下的环境影响道路图像集。
  3. 如权利要求2所述的基于环境匹配的车辆定位方法，其特征在于，所述获取预设环境模式下的道路图像集，并对所述道路图像集进行环境影响去除处理，以获得基础道路图像集的步骤，包括：
    分别获取不同天气和不同时段下的道路图像集，并对所述道路图像集进行图像识别以及特征标记，获得道路特征标记；
    根据所述道路特征标记对所述道路图像集进行环境影响去除处理，以获得基础道路图像集。
  4. 如权利要求2所述的基于环境匹配的车辆定位方法，其特征在于，所述根据不同环境影响对应的环境影响特征信息分别对所述基础道路图像进行注入处理，以生成不同环境影响下的环境影响道路图像集的步骤，包括：
    获取不同环境影响对应的环境特征信息中的天气影响因子和时段影响因子；
    将所述天气影响因子和时段影响因子按照预设组合规则进行组合，以获得不同的环境复合因子；
    将所述环境复合因子分别注入至所述基础道路图像，以生成不同环境影响下的环境影响道路图像集。
  5. 如权利要求4所述的基于环境匹配的车辆定位方法，其特征在于，所述将所述环境复合因子分别注入至所述基础道路图像，以生成不同环境影响下的环境影响道路图像集的步骤，包括：
    获取所述基础道路图像集中的道路组成元素；
    根据所述环境复合因子分别对所述基础道路图像集中的所述道路组成元素进行渲染，以生成不同环境影响下的环境影响道路图像集。
  6. 如权利要求1~5中任一项所述的基于环境匹配的车辆定位方法，其特征在于，所述查找与所述当前环境数据匹配的环境影响道路图像集的步骤，包括：
    获取待定位车辆的历史GPS定位信息，并根据所述历史GPS定位信息确定对应的所属区域图像集；
    在所述所属区域图像集中查找与所述当前环境数据匹配的环境影响道路图像集。
  7. 如权利要求6所述的基于环境匹配的车辆定位方法，其特征在于，所述根据所述目标环境影响道路图像确定所述待定位车辆的当前位置信息的步骤，包括：
    根据所述历史GPS定位信息和所述目标环境影响道路图像对应的位置信息确定所述待定位车辆的当前位置信息。
  8. 一种基于环境匹配的车辆定位装置，其特征在于，所述基于环境匹配的车辆定位装置包括：
    数据获取模块，用于获取待定位车辆所处位置的当前环境数据以及当前道路图像；
    图像集查找模块，用于查找与所述当前环境数据匹配的环境影响道路图像集；
    图像匹配模块，用于将所述当前道路图像与所述环境影响道路图像集中的环境影响道路图像分别进行匹配，获得与所述当前道路图像匹配的目标环境影响道路图像；
    车辆定位模块，用于根据所述目标环境影响道路图像确定所述待定位车辆的当前位置信息。
  9. 一种车辆，其特征在于，所述车辆包括：存储器、处理器及存储在所述存储器上并可在所述处理器上运行的基于环境匹配的车辆定位程序，所述基于环境匹配的车辆定位程序配置为实现如权利要求1至7中任一项所述的基于环境匹配的车辆定位方法的步骤。
  10. 一种存储介质，其特征在于，所述存储介质上存储有基于环境匹配的车辆定位程序，所述基于环境匹配的车辆定位程序被处理器执行时实现如权利要求1至7中任一项所述的基于环境匹配的车辆定位方法的步骤。
PCT/CN2021/113515 2021-08-19 2021-08-19 基于环境匹配的车辆定位方法、装置、车辆及存储介质 WO2023019509A1 (zh)

Priority Applications (5)

Application Number Priority Date Filing Date Title
KR1020247003644A KR20240064620A (ko) 2021-08-19 2021-08-19 환경 매칭 기반의 차량 위치 측정 방법, 장치, 차량 및 저장 매체
CN202180097566.9A CN117256009A (zh) 2021-08-19 2021-08-19 基于环境匹配的车辆定位方法、装置、车辆及存储介质
PCT/CN2021/113515 WO2023019509A1 (zh) 2021-08-19 2021-08-19 基于环境匹配的车辆定位方法、装置、车辆及存储介质
EP21953755.2A EP4375856A1 (en) 2021-08-19 2021-08-19 Environment matching-based vehicle localization method and apparatus, vehicle, and storage medium
US18/429,828 US20240169743A1 (en) 2021-08-19 2024-02-01 Vehicle positioning method and device based on environment matching, vehicle and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2021/113515 WO2023019509A1 (zh) 2021-08-19 2021-08-19 基于环境匹配的车辆定位方法、装置、车辆及存储介质

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/429,828 Continuation US20240169743A1 (en) 2021-08-19 2024-02-01 Vehicle positioning method and device based on environment matching, vehicle and storage medium

Publications (1)

Publication Number Publication Date
WO2023019509A1 true WO2023019509A1 (zh) 2023-02-23

Family

ID=85239451

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/113515 WO2023019509A1 (zh) 2021-08-19 2021-08-19 基于环境匹配的车辆定位方法、装置、车辆及存储介质

Country Status (5)

Country Link
US (1) US20240169743A1 (zh)
EP (1) EP4375856A1 (zh)
KR (1) KR20240064620A (zh)
CN (1) CN117256009A (zh)
WO (1) WO2023019509A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116958084A (zh) * 2023-07-20 2023-10-27 上海韦地科技集团有限公司 基于核工业大数据的图像智能感知系统及方法

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2574958A1 (en) * 2011-09-28 2013-04-03 Honda Research Institute Europe GmbH Road-terrain detection method and system for driver assistance systems
US20150142248A1 (en) * 2013-11-20 2015-05-21 Electronics And Telecommunications Research Institute Apparatus and method for providing location and heading information of autonomous driving vehicle on road within housing complex
WO2016177372A1 (de) * 2015-05-06 2016-11-10 Continental Teves Ag & Co. Ohg Verfahren und vorrichtung zur erkennung und bewertung von umwelteinflüssen und fahrbahnzustandsinformationen im fahrzeugumfeld
CN107024216A (zh) * 2017-03-14 2017-08-08 重庆邮电大学 引入全景地图的智能车辆融合定位系统及方法
CN109446973A (zh) * 2018-10-24 2019-03-08 中车株洲电力机车研究所有限公司 一种基于深度神经网络图像识别的车辆定位方法
CN110657812A (zh) * 2018-06-29 2020-01-07 比亚迪股份有限公司 车辆定位方法、装置及车辆
CN111351493A (zh) * 2018-12-24 2020-06-30 上海欧菲智能车联科技有限公司 一种定位方法和系统
CN111508258A (zh) * 2020-04-17 2020-08-07 北京三快在线科技有限公司 一种定位方法及装置

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2574958A1 (en) * 2011-09-28 2013-04-03 Honda Research Institute Europe GmbH Road-terrain detection method and system for driver assistance systems
US20150142248A1 (en) * 2013-11-20 2015-05-21 Electronics And Telecommunications Research Institute Apparatus and method for providing location and heading information of autonomous driving vehicle on road within housing complex
WO2016177372A1 (de) * 2015-05-06 2016-11-10 Continental Teves Ag & Co. Ohg Verfahren und vorrichtung zur erkennung und bewertung von umwelteinflüssen und fahrbahnzustandsinformationen im fahrzeugumfeld
CN107024216A (zh) * 2017-03-14 2017-08-08 重庆邮电大学 引入全景地图的智能车辆融合定位系统及方法
CN110657812A (zh) * 2018-06-29 2020-01-07 比亚迪股份有限公司 车辆定位方法、装置及车辆
CN109446973A (zh) * 2018-10-24 2019-03-08 中车株洲电力机车研究所有限公司 一种基于深度神经网络图像识别的车辆定位方法
CN111351493A (zh) * 2018-12-24 2020-06-30 上海欧菲智能车联科技有限公司 一种定位方法和系统
CN111508258A (zh) * 2020-04-17 2020-08-07 北京三快在线科技有限公司 一种定位方法及装置

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116958084A (zh) * 2023-07-20 2023-10-27 上海韦地科技集团有限公司 基于核工业大数据的图像智能感知系统及方法

Also Published As

Publication number Publication date
EP4375856A1 (en) 2024-05-29
US20240169743A1 (en) 2024-05-23
KR20240064620A (ko) 2024-05-13
CN117256009A (zh) 2023-12-19

Similar Documents

Publication Publication Date Title
EP3505869B1 (en) Method, apparatus, and computer readable storage medium for updating electronic map
CN112069856B (zh) 地图生成方法、驾驶控制方法、装置、电子设备及系统
CN113642633B (zh) 用于对驾驶场景数据进行分类的方法、装置、设备和介质
CN101676689B (zh) 驾驶评价系统以及驾驶评价方法
CN109141444B (zh) 定位方法、装置、存储介质及移动设备
CN113034566B (zh) 高精度地图构建方法、装置、电子设备及存储介质
CN104819726A (zh) 导航数据处理方法、装置及导航终端
US20240169743A1 (en) Vehicle positioning method and device based on environment matching, vehicle and storage medium
CN109387208B (zh) 一种地图数据的处理方法、装置、设备和介质
CN114509065B (zh) 地图构建方法、系统、车辆终端、服务器端及存储介质
CN115164918B (zh) 语义点云地图构建方法、装置及电子设备
WO2022083487A1 (zh) 生成高精度地图的方法、装置和计算机可读存储介质
WO2023040712A1 (zh) 地图数据处理方法和装置
CN112146682A (zh) 智能汽车的传感器标定方法、装置、电子设备及介质
CN116222539A (zh) 高精度地图数据差异化更新方法及系统
CN116935656B (zh) 道路交通数据处理方法、装置、电子设备及存储介质
KR101394425B1 (ko) 지도 데이터 유지보수 장치 및 방법
CN114356951B (zh) 引导点的关联信息的更新方法和装置
CN114722931A (zh) 车载数据处理方法、装置、数据采集设备和存储介质
US20230273047A1 (en) Method and Apparatus for Providing a High-Resolution Digital Map
CN113535868A (zh) 一种基于公开导航地图的自主泊车高精地图生成方法
CN113345251A (zh) 一种车辆逆行检测方法及相关装置
CN112698372A (zh) 时空数据处理方法、装置、电子设备及存储介质
CN106649813B (zh) 一种基于环境感知与用户反馈的垂直领域知识库构建方法
CN117739950B (zh) 一种地图的生成方法、装置及设备

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 202180097566.9

Country of ref document: CN

ENP Entry into the national phase

Ref document number: 2024506274

Country of ref document: JP

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 2021953755

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 2021953755

Country of ref document: EP

Effective date: 20240220

NENP Non-entry into the national phase

Ref country code: DE