CN114494435A - Rapid optimization method, system and medium for matching and positioning of vision and high-precision map - Google Patents
Rapid optimization method, system and medium for matching and positioning of vision and high-precision map Download PDFInfo
- Publication number
- CN114494435A CN114494435A CN202210085360.0A CN202210085360A CN114494435A CN 114494435 A CN114494435 A CN 114494435A CN 202210085360 A CN202210085360 A CN 202210085360A CN 114494435 A CN114494435 A CN 114494435A
- Authority
- CN
- China
- Prior art keywords
- map
- matching
- positioning
- calculation
- result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000005457 optimization Methods 0.000 title claims abstract description 32
- 238000004364 calculation method Methods 0.000 claims abstract description 50
- 230000000007 visual effect Effects 0.000 claims abstract description 16
- 230000008447 perception Effects 0.000 claims abstract description 15
- 238000012545 processing Methods 0.000 claims abstract description 9
- 230000006870 function Effects 0.000 claims description 42
- 239000011159 matrix material Substances 0.000 claims description 19
- 238000003860 storage Methods 0.000 claims description 11
- 238000005070 sampling Methods 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 238000000354 decomposition reaction Methods 0.000 claims description 5
- 230000004807 localization Effects 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 12
- 238000004590 computer program Methods 0.000 description 11
- 238000004891 communication Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
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
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- 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
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
- G01S19/45—Determining position by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement
-
- 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
- G06N3/045—Combinations of networks
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
- G06T2207/10012—Stereo images
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
- G06T2207/30244—Camera pose
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Automation & Control Theory (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Navigation (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to a method, a system and a medium for quickly optimizing visual and high-precision map matching positioning, wherein the method comprises the following steps: acquiring monocular image information and GNSS signals in real time; after the monocular image information is subjected to perception processing, a map element result of image perception is obtained; obtaining map positioning elements around the vehicle in the map according to the GNSS signal; and performing map matching calculation on the map element result and map positioning elements around the vehicle to obtain a global six-degree-of-freedom pose as an optimization result of map matching positioning. The invention can reduce the complexity of positioning calculation and is suitable for a calculation platform with lower calculation power for the application scene of the intelligent networked automobile.
Description
Technical Field
The invention relates to the field of intelligent networking automobile environment perception, in particular to a method, a system and a medium for quickly optimizing vision and high-precision map matching positioning.
Background
The intelligent networked automobile needs to accurately sense the surrounding environment and the state of the intelligent networked automobile so as to support subsequent decision and control. And accurate estimation of the self pose is the basis for the functions of track planning, control and the like of the intelligent network connection vehicle. The estimation and estimation of the passive pose based on the GPS are limited by satellite signals, and all running conditions of high-level automatic driving are difficult to support. One low cost solution is to use the camera image and a high precision map for matching, thereby performing the positioning. However, the matching calculation of the visual and high-precision map is usually more computationally intensive, and has higher requirements on the computational power of the computing device. Therefore, the invention provides a quick solving method for visual and high-precision map matching positioning, so that the complexity of calculation is reduced, and the method is suitable for an embedded calculation platform with lower calculation force.
Disclosure of Invention
In view of the above problems, an object of the present invention is to provide a method, a system, and a medium for fast optimization of visual and high-precision map matching positioning, which can reduce the complexity of positioning calculation and a computing platform with lower adaptive computing power for an application scenario of an intelligent networked automobile.
In order to achieve the purpose, the invention adopts the following technical scheme: a method for fast optimization of visual and high-precision map matching positioning comprises the following steps: acquiring monocular image information and GNSS signals in real time; sensing the monocular image information to obtain a map element result of image sensing; obtaining map positioning elements around the vehicle in the map according to the GNSS signal; and performing map matching calculation on the map element result and map positioning elements around the vehicle to obtain a global six-degree-of-freedom pose as an optimization result of map matching positioning.
Further, the performing perception processing on the monocular image information includes: and after the monocular image information is scaled to a preset size, the monocular image information is input into a neural network to be subjected to forward calculation, and a map element result of image perception is obtained.
Further, the obtaining map positioning elements around the vehicle in the map according to the GNSS signals includes:
taking the GNSS signal as a center, and taking a preset radius as a search range;
and in the map, judging whether the elements are in the search range or not for the lane line and the lamp post elements, and if so, outputting the elements as positioning elements.
Furthermore, after the positioning elements are determined, three-dimensional points are adopted to describe the positioning elements, and linear interpolation is carried out on a series of three-dimensional points, so that all the positioning elements are uniformly described by sampling points.
Further, the map matching calculation includes:
calculating a matching cost function of the map element result and the map positioning element;
compressing the matching cost function, and simplifying matching calculation through an approximate matching cost function to reduce the calculation complexity;
and obtaining a global positioning result through simplified matching calculation.
Further, the calculating of the matching cost function includes:
performing distance transformation on the map element result, and obtaining a matching cost function of the map element three-dimensional points according to the camera internal reference matrix and the initial pose of the camera;
and summing the matching cost functions of all the map sampling points to obtain a map matching cost result.
Further, the compressing the matching cost function includes:
calculating a partial derivative of the integral cost function with respect to the initial pose of the camera;
calculating an observation Hessian matrix H and an observation residual vector b according to the partial derivative;
cholesky decomposition is carried out on the observation Hessian matrix H, and a cost function is converted into an observation Jacobian matrix J*For partial derivatives, observe the residual vector r*A matching cost function for the residual;
optimization by LM optimization method, with J*And r*And optimizing to obtain a map matching positioning result for the partial derivative and the residual error.
A system for rapid optimization of visual and high-precision map-matching positioning, comprising: the data acquisition module acquires monocular image information and GNSS signals in real time; the perception module is used for perceiving the monocular image information to obtain a map element result perceived by the image; the map positioning element acquisition module is used for acquiring map positioning elements around the vehicle in a map according to the GNSS signals; and the map matching calculation module is used for performing map matching calculation on the map element result and map positioning elements around the vehicle to obtain a global six-degree-of-freedom pose as an optimization result of map matching positioning.
A computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a computing device, cause the computing device to perform any of the above methods.
A computing device, comprising: one or more processors, memory, and one or more programs stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for performing any of the above-described methods.
Due to the adoption of the technical scheme, the invention has the following advantages:
1. the method can effectively accelerate the calculation of matching of the vision and the map and simultaneously ensure the calculation precision.
2. The method and the device can be suitable for scenes with low computational power, and the equipment cost is reduced.
Drawings
FIG. 1 is a schematic flow chart of an algorithm acceleration system for visual and map matching positioning according to an embodiment of the present invention;
FIG. 2 is a flow diagram of a map matching calculation module in one embodiment of the invention;
FIG. 3 is a schematic diagram of a computing device in an embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the drawings of the embodiments of the present invention. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the described embodiments of the invention, are within the scope of the invention.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The invention provides a method, a system and a medium for quickly optimizing visual and high-precision map matching positioning, wherein the method comprises the following steps: acquiring monocular image information and GNSS signals in real time; sensing monocular image information to obtain a map element result of image sensing; obtaining map positioning elements around the vehicle in the map according to the GNSS signals; and carrying out map matching calculation on the map element result and map positioning elements around the vehicle to obtain a global six-degree-of-freedom pose as an optimization result of map matching positioning. The invention can reduce the complexity of positioning calculation and is suitable for a calculation platform with lower calculation power for the application scene of the intelligent networked automobile.
In an embodiment of the present invention, a method for fast optimizing visual and high-precision map matching positioning is provided, and this embodiment is exemplified by applying the method to a terminal, and it is to be understood that the method may also be applied to a server, and may also be applied to a system including a terminal and a server, and is implemented by interaction between the terminal and the server. As shown in fig. 1, in this embodiment, the method includes the following steps:
1) acquiring monocular image information and GNSS signals in real time;
2) sensing monocular image information to obtain a map element result of image sensing;
3) obtaining map positioning elements around the vehicle in the map according to the GNSS signals;
4) and carrying out map matching calculation on the map element result and map positioning elements around the vehicle to obtain a global six-degree-of-freedom pose as an optimization result of map matching positioning.
In the step 2), the sensing processing of the monocular image information is specifically: and after the monocular image information is scaled to a preset size, the monocular image information is input into a neural network to be subjected to forward calculation, and a map element result of image perception is obtained.
In the embodiment, an image segmentation model based on a convolutional neural network is included, and input is monocular image information and output is a classification result of each pixel in an image. The monocular image is scaled to 768 × 480, then the monocular image is sent to a neural network, and forward calculation of the neural network is carried out through a GPU/FPGA/AI chip calculation unit, so that a final classification result of each pixel of the image is obtained. The classification type is determined by the type of map-locating elements, in this embodiment lane-lines and light poles.
In the step 3), obtaining map positioning elements around the vehicle in the map according to the GNSS signal includes the following steps:
3.1) taking the GNSS signal as a center and taking a preset radius as a search range;
in this embodiment, it is preferable to use a radius of 40 meters as the search range.
And 3.2) judging whether the elements are in the searching range or not for the lane line and the lamp post elements in the map, and if so, outputting the elements as positioning elements.
In the step 3.2), after the positioning elements are determined, three-dimensional points are adopted to describe the positioning elements, and linear interpolation is performed on a series of three-dimensional points, so that all the positioning elements are uniformly described by using sampling points.
In this embodiment, the lane lines are depicted as a series of three-dimensional points and the light poles are depicted as two three-dimensional points at the top and bottom. After the output positioning elements are determined, linear interpolation is carried out on the series of three-dimensional points, so that all elements are uniformly described by sampling points with the interval of 0.2 m.
In the step 4), as shown in fig. 2, the map matching calculation includes the following steps:
4.1) calculating a matching cost function of the map element result and the map positioning element;
4.2) compressing the matching cost function, and simplifying the matching calculation through the approximate matching cost function to reduce the calculation complexity;
4.3) obtaining a global positioning result through simplified matching calculation.
In the step 4.1), the calculation of the matching cost function includes the following steps:
4.1.1) carrying out distance transformation on the map element result, and obtaining a matching cost function of the map element three-dimensional points according to the camera internal reference matrix and the initial pose of the camera;
in the present embodiment, an image perception result (i.e., a map element result) S is inputtAnd high precision map location element M ═ { M ═ MiEach Mi={mi,jIn which m isi,jThree-dimensional sampling points of each map element are shown, i represents the ith element, and j represents the jth point in the element.
Perception of the result S of the imagetPerforming distance transformation, i.e. based on the image perception result StGenerating a distance map DtWherein D istIs a floating point number, representing the perceived result S in the imagetThe euclidean distance of the nearest non-zero pixel to the pixel.
Assume that the camera internal reference matrix is K and the initial pose of the camera is { R }t,ttIn which R istRepresenting the rotation matrix of the camera, ttRepresenting a translation matrix of the camera. The three-dimensional point m of the map elementi,jIs matched withThe cost function is:
wherein the content of the first and second substances,points representing the map projected onto the pixels of the image, rMRepresenting a map matching cost function.
4.1.2) summing the matching cost functions of all map sampling points to obtain a map matching cost result;
in this embodiment, the matching cost functions for all map sample points are summed:
wherein N isiThe total number of sample points representing the ith object, and N each represent the total number of map elements.
In the step 4.2), the matched cost function is compressed, the input is the calculation result of the cost function, and the output is the simplified cost function, so that the calculation is accelerated; which comprises the following steps:
4.2.1) calculating a partial derivative of the integral cost function relative to the initial pose of the camera;
defining a cost function:
calculate each term rM(St,mi,j,Rt,tt) About { Rt,ttPartial derivatives of }:
calculating the overall cost function rM(St,M,Rt,tt) About { Rt,ttThe partial derivatives of are:
4.2.2) calculating an observation Hessian matrix H and an observation residual vector b according to the partial derivative;
4.2.3) Cholesky decomposition of the matrix H, transforming the cost function into an equivalent observation Jacobian matrix J*As partial derivative, equivalent observation residual vector r*A matching cost function for the residual;
wherein, Cholesky decomposition is carried out on the matrix H to obtain:
wherein L represents an upper triangular matrix for Cholesky decomposition of H, and LTIs the transpose of L, R6×6Real number matrix, R, representing 6x66×1Representing a 6x1 real vector.
4.2.4) optimization by LM optimization method to equivalently observe Jacobian matrix J*And equivalent observation residual r*And optimizing to obtain a map matching positioning result for the partial derivative and the residual error. Experiments show that the calculation method can greatly accelerate the optimization speed of map matching, thereby effectively reducing the calculation amount.
In one embodiment of the present invention, a system for fast optimization of visual and high-precision map matching localization is provided, comprising:
the data acquisition module acquires monocular image information and GNSS signals in real time;
the perception module is used for perceiving the monocular image information to obtain a map element result perceived by the image;
the map positioning element acquisition module is used for acquiring map positioning elements around the vehicle in the map according to the GNSS signal;
and the map matching calculation module is used for performing map matching calculation on the map element result and map positioning elements around the vehicle to obtain a global six-degree-of-freedom pose as an optimization result of map matching positioning.
The system provided in this embodiment is used for executing the above method embodiments, and for details of the process and the details, reference is made to the above embodiments, which are not described herein again.
As shown in fig. 3, which is a schematic structural diagram of a computing device provided in an embodiment of the present invention, the computing device may be a terminal, and may include: a processor (processor), a communication Interface (communication Interface), a memory (memory), a display screen and an input device. The processor, the communication interface and the memory are communicated with each other through a communication bus. The processor is used to provide computing and control capabilities. The memory includes a non-volatile storage medium, an internal memory, the non-volatile storage medium storing an operating system and a computer program that when executed by the processor implements an optimization method; the internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The communication interface is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, a manager network, NFC (near field communication) or other technologies. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on a shell of the computing equipment, an external keyboard, a touch pad or a mouse and the like. The processor may call logic instructions in memory to perform the following method: acquiring monocular image information and GNSS signals in real time; sensing monocular image information to obtain a map element result of image sensing; obtaining map positioning elements around the vehicle in the map according to the GNSS signals; and carrying out map matching calculation on the map element result and map positioning elements around the vehicle to obtain a global six-degree-of-freedom pose as an optimization result of map matching positioning.
In addition, the logic instructions in the memory may be implemented in the form of software functional units and may be stored in a computer readable storage medium when sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Those skilled in the art will appreciate that the architecture shown in fig. 3 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects may be applied, and that a particular computing device may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment of the invention, a computer program product is provided, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions that, when executed by a computer, enable the computer to perform the methods provided by the above-described method embodiments, for example, comprising: acquiring monocular image information and GNSS signals in real time; sensing monocular image information to obtain a map element result of image sensing; obtaining map positioning elements around the vehicle in the map according to the GNSS signals; and carrying out map matching calculation on the map element result and map positioning elements around the vehicle to obtain a global six-degree-of-freedom pose as an optimization result of map matching positioning.
In one embodiment of the invention, a non-transitory computer-readable storage medium is provided, which stores server instructions that cause a computer to perform the methods provided by the above embodiments, for example, including: acquiring monocular image information and GNSS signals in real time; sensing monocular image information to obtain a map element result of image sensing; obtaining map positioning elements around the vehicle in the map according to the GNSS signals; and carrying out map matching calculation on the map element result and map positioning elements around the vehicle to obtain a global six-degree-of-freedom pose as an optimization result of map matching positioning.
The implementation principle and technical effect of the computer-readable storage medium provided by the above embodiments are similar to those of the above method embodiments, and are not described herein again.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A quick optimization method for matching and positioning vision and high-precision maps is characterized by comprising the following steps:
acquiring monocular image information and GNSS signals in real time;
after the monocular image information is subjected to perception processing, a map element result of image perception is obtained;
obtaining map positioning elements around the vehicle in the map according to the GNSS signal;
and performing map matching calculation on the map element result and map positioning elements around the vehicle to obtain a global six-degree-of-freedom pose as an optimization result of map matching positioning.
2. The method for fast optimization of visual and high-precision map matching localization according to claim 1, wherein the perceptually processing the monocular image information comprises: and after the monocular image information is scaled to a preset size, the monocular image information is input into a neural network to be subjected to forward calculation, and a map element result of image perception is obtained.
3. The method for fast optimization of visual and high-precision map-matching positioning according to claim 1, wherein the obtaining map-positioning elements around the vehicle in the map according to the GNSS signals comprises:
taking the GNSS signal as a center, and taking a preset radius as a search range;
and in the map, judging whether the elements are in the search range or not for the lane line and the lamp post elements, and if so, outputting the elements as positioning elements.
4. The method as claimed in claim 3, wherein after the positioning elements are determined, the positioning elements are described by using three-dimensional points, and linear interpolation is performed on a series of three-dimensional points, so that all the positioning elements are uniformly described by using sampling points.
5. The method for fast optimization of visual and high-precision map-matching localization according to claim 1, wherein the map-matching computation comprises:
calculating a matching cost function of the map element result and the map positioning element;
compressing the matching cost function, and simplifying matching calculation through an approximate matching cost function to reduce the calculation complexity;
and obtaining a global positioning result through simplified matching calculation.
6. The method for fast optimization of visual and high-precision map matching localization according to claim 5, wherein the calculation of the matching cost function comprises:
performing distance transformation on the map element result, and obtaining a matching cost function of the map element three-dimensional points according to the camera internal reference matrix and the initial pose of the camera;
and summing the matching cost functions of all the map sampling points to obtain a map matching cost result.
7. The method for fast optimization of visual and high-precision map matching localization according to claim 5, wherein said compressing said matching cost function comprises:
calculating a partial derivative of the integral cost function with respect to the initial pose of the camera;
calculating an observation Hessian matrix H and an observation residual vector b according to the partial derivative;
cholesky decomposition is carried out on the observation Hessian matrix H, and a cost function is converted into an observation Jacobian matrix J*For partial derivatives, observe the residual vector r*A matching cost function for the residual;
optimization by LM optimization method, with J*And r*And optimizing to obtain a map matching positioning result for the partial derivative and the residual error.
8. A system for fast optimization of visual and high-precision map matching positioning, comprising:
the data acquisition module acquires monocular image information and GNSS signals in real time;
the perception module is used for perceiving the monocular image information to obtain a map element result perceived by the image;
the map positioning element acquisition module is used for acquiring map positioning elements around the vehicle in the map according to the GNSS signal;
and the map matching calculation module is used for performing map matching calculation on the map element result and map positioning elements around the vehicle to obtain a global six-degree-of-freedom pose as an optimization result of map matching positioning.
9. A computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a computing device, cause the computing device to perform any of the methods of claims 1-7.
10. A computing device, comprising: one or more processors, memory, and one or more programs stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for performing any of the methods of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210085360.0A CN114494435A (en) | 2022-01-25 | 2022-01-25 | Rapid optimization method, system and medium for matching and positioning of vision and high-precision map |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210085360.0A CN114494435A (en) | 2022-01-25 | 2022-01-25 | Rapid optimization method, system and medium for matching and positioning of vision and high-precision map |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114494435A true CN114494435A (en) | 2022-05-13 |
Family
ID=81473801
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210085360.0A Pending CN114494435A (en) | 2022-01-25 | 2022-01-25 | Rapid optimization method, system and medium for matching and positioning of vision and high-precision map |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114494435A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115235493A (en) * | 2022-07-19 | 2022-10-25 | 合众新能源汽车有限公司 | Method and device for automatic driving positioning based on vector map |
CN116189145A (en) * | 2023-02-15 | 2023-05-30 | 清华大学 | Extraction method, system and readable medium of linear map elements |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107229063A (en) * | 2017-06-26 | 2017-10-03 | 奇瑞汽车股份有限公司 | A kind of pilotless automobile navigation and positioning accuracy antidote merged based on GNSS and visual odometry |
US20180188032A1 (en) * | 2017-01-04 | 2018-07-05 | Qualcomm Incorporated | Systems and methods for using a global positioning system velocity in visual-inertial odometry |
CN108802785A (en) * | 2018-08-24 | 2018-11-13 | 清华大学 | Vehicle method for self-locating based on High-precision Vector map and monocular vision sensor |
CN113436261A (en) * | 2021-06-24 | 2021-09-24 | 湖南大学 | Monocular vision inertial positioning method for automatic driving of closed park |
-
2022
- 2022-01-25 CN CN202210085360.0A patent/CN114494435A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180188032A1 (en) * | 2017-01-04 | 2018-07-05 | Qualcomm Incorporated | Systems and methods for using a global positioning system velocity in visual-inertial odometry |
CN107229063A (en) * | 2017-06-26 | 2017-10-03 | 奇瑞汽车股份有限公司 | A kind of pilotless automobile navigation and positioning accuracy antidote merged based on GNSS and visual odometry |
CN108802785A (en) * | 2018-08-24 | 2018-11-13 | 清华大学 | Vehicle method for self-locating based on High-precision Vector map and monocular vision sensor |
CN113436261A (en) * | 2021-06-24 | 2021-09-24 | 湖南大学 | Monocular vision inertial positioning method for automatic driving of closed park |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115235493A (en) * | 2022-07-19 | 2022-10-25 | 合众新能源汽车有限公司 | Method and device for automatic driving positioning based on vector map |
CN116189145A (en) * | 2023-02-15 | 2023-05-30 | 清华大学 | Extraction method, system and readable medium of linear map elements |
CN116189145B (en) * | 2023-02-15 | 2024-06-11 | 清华大学 | Extraction method, system and readable medium of linear map elements |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6862409B2 (en) | Map generation and moving subject positioning methods and devices | |
CN109683699B (en) | Method and device for realizing augmented reality based on deep learning and mobile terminal | |
CN108764187A (en) | Extract method, apparatus, equipment, storage medium and the acquisition entity of lane line | |
CN113168510A (en) | Segmenting objects a priori by refining shape | |
US20210073997A1 (en) | Future semantic segmentation prediction using 3d structure | |
CN111739005B (en) | Image detection method, device, electronic equipment and storage medium | |
CN114494435A (en) | Rapid optimization method, system and medium for matching and positioning of vision and high-precision map | |
EP3847619B1 (en) | Unsupervised depth prediction neural networks | |
CN113989450A (en) | Image processing method, image processing apparatus, electronic device, and medium | |
CN112927234A (en) | Point cloud semantic segmentation method and device, electronic equipment and readable storage medium | |
KR20200046437A (en) | Localization method based on images and map data and apparatus thereof | |
CN114842035A (en) | License plate desensitization method, device and equipment based on deep learning and storage medium | |
CN112396657A (en) | Neural network-based depth pose estimation method and device and terminal equipment | |
CN110645996B (en) | Method and system for extracting perception data | |
CN112836698A (en) | Positioning method, positioning device, storage medium and electronic equipment | |
CN114170290A (en) | Image processing method and related equipment | |
CN117197388A (en) | Live-action three-dimensional virtual reality scene construction method and system based on generation of antagonistic neural network and oblique photography | |
CN113313824B (en) | Three-dimensional semantic map construction method | |
CN117876608A (en) | Three-dimensional image reconstruction method, three-dimensional image reconstruction device, computer equipment and storage medium | |
CN116543143A (en) | Training method of target detection model, target detection method and device | |
CN116012483A (en) | Image rendering method and device, storage medium and electronic equipment | |
CN115902977A (en) | Transformer substation robot double-positioning method and system based on vision and GPS | |
CN116883770A (en) | Training method and device of depth estimation model, electronic equipment and storage medium | |
CN115526987A (en) | Label element reconstruction method, system, device and medium based on monocular camera | |
JP2024521816A (en) | Unrestricted image stabilization |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |