CN111025364B - Machine vision positioning system and method based on satellite assistance - Google Patents
Machine vision positioning system and method based on satellite assistance Download PDFInfo
- Publication number
- CN111025364B CN111025364B CN201911300312.3A CN201911300312A CN111025364B CN 111025364 B CN111025364 B CN 111025364B CN 201911300312 A CN201911300312 A CN 201911300312A CN 111025364 B CN111025364 B CN 111025364B
- Authority
- CN
- China
- Prior art keywords
- satellite
- visual
- data
- coordinate system
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- 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
- G01S19/48—Determining position by combining or switching between position solutions derived from the satellite radio beacon positioning system and position solutions derived from a further system
-
- 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
- G01C21/005—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 with correlation of navigation data from several sources, e.g. map or contour matching
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Automation & Control Theory (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
- Navigation (AREA)
Abstract
The invention discloses a satellite-assisted machine vision positioning system, which comprises a data preprocessing module, a vision SLAM module, a parameter resolving module, a data management module and a position resolving module, wherein the data preprocessing module is used for preprocessing data; the invention also discloses a machine vision positioning method based on satellite assistance, which solves the problem that the existing monocular vision navigation method cannot provide geographic position service under the condition of satellite signal intermittent rejection. When satellite navigation fails, the method designed in the invention can be utilized to calculate the scale factors lacking in monocular vision and the transformation relation between the vision coordinate system and the geographic coordinate system by utilizing the satellite navigation information; further, the geographic location service information is continuously output in combination with the monocular vision SLAM technology.
Description
Technical Field
The invention relates to the technical field of positioning navigation, in particular to a satellite-assisted machine vision positioning system and method.
Background
A global navigation satellite system (Global Navigation Satellite System, abbreviated as GNSS) is an all-weather radio navigation system covering the world, which is built by using navigation satellites, and can provide all-weather three-dimensional coordinates and speed and time information for a user at any place on the surface of the earth or near-earth space. At present, satellite navigation is a relatively mature navigation mode from the theoretical research and the application level, and is one of the common navigation methods. The global navigation satellite system greatly promotes the development of the innovation and related industries of navigation positioning theory and application.
Location-based services (Location Based Services, LBS for short) refer to services deployed around geographic location data that are used by mobile terminals to acquire geographic location coordinate information of a user based on a spatial database and integrate with other information to provide the user with the desired location-related value-added services using a wireless communication network (or satellite positioning system). However, with the continuous complexity of application environments and the continuous increase of user demands, the development of systems faces new problems and challenges.
Technological innovation of visual sensing equipment and rapid development of computer visual technology promote a technological breakthrough in the research fields of robots, automatic driving intelligent vehicles (Automated Guided Vehicle, AGVs for short) and the like. Visual navigation has been developed as a key technology for machine-aware world environments and for autonomous positioning navigation. For a motion carrier carrying a plurality of sensors, the synchronous positioning and map construction technology (Simultaneous Localization and Mapping, SLAM for short) establishes an incremental map of the surrounding environment through acquisition and sensing of environment information, thereby achieving the purpose of simultaneous positioning and map construction and creating a good environment for the development of autonomous navigation positioning technology of the carrier.
In general, although the satellite navigation system positioning mode can provide a positioning result with higher precision, the satellite navigation system positioning mode is easy to be interfered by external environment, and the machine vision-based navigation mode also has the following defects
1) The working principle of monocular vision causes the scale difference between a visual coordinate system and a real geographic coordinate system;
2) The binocular vision navigation has the problems of large registration and calculation amount, and has the problem of high manufacturing cost like the depth camera navigation scheme;
3) Visual navigation schemes of a single information source are not able to provide location services.
Disclosure of Invention
The invention aims to solve the technical problem of providing a machine vision positioning system and a machine vision positioning method based on satellite assistance, which are used for overcoming the defects of the prior art, when satellite navigation fails, the method designed in the invention can be used for calculating the scale factor of monocular vision and the transformation relation between a vision coordinate system and a geographic coordinate system by utilizing the position information before the satellite navigation fails; further, the geographic location service information is continuously output in combination with the monocular vision SLAM technology.
The invention adopts the following technical scheme for solving the technical problems:
the invention provides a satellite-assisted machine vision positioning system, which comprises a data preprocessing module, a vision SLAM module, a parameter resolving module, a data management module and a position resolving module, wherein the data preprocessing module is used for preprocessing data; wherein, the liquid crystal display device comprises a liquid crystal display device,
the data preprocessing module is used for carrying out interpolation processing on the vision sensor data acquired by different working frequencies and satellite receiver data so as to acquire satellite data corresponding to each frame of image, and further used for generating a satellite data set subsequently;
the visual SLAM module is used for taking images and satellite data as input, adding the constraint of relative satellite positioning information between the images on the basis of monocular visual SLAM, constructing a global map, generating a visual map data set, and outputting the current position information of the carrier under a visual coordinate system in real time;
the parameter resolving module is used for screening and solving the transformation relation between the key frame visual coordinate system and the geographic coordinate system to generate a coordinate transformation parameter set;
the data management module is used for managing the visual map data set generated by the visual SLAM module, the satellite data set corresponding to the visual map key frame, the coordinate conversion parameter set solved by the parameter resolving module and the mapping table among the three;
and the position resolving module is used for calculating and outputting a positioning result by combining the coordinate conversion parameters extracted from the data management module by utilizing the current position of the carrier under the visual coordinate system output by the visual SLAM module.
A machine vision positioning method based on satellite assistance comprises a positioning method under the condition that satellite signals are available, and specifically comprises the following steps:
step 1, running a monocular vision SLAM program under the condition that a satellite navigation system is available, and acquiring satellite positioning information corresponding to a key frame;
step 2, adding constraint conditions of satellite positioning information in the construction of a global map;
step 3, estimating a transformation relation between the visual coordinate system and the geographic coordinate system by utilizing least squares, calculating a positioning result and outputting the positioning result;
and step 4, updating the coordinate conversion parameter set after global map optimization is performed when the moving track loops.
As a further optimization scheme of the satellite-aided machine vision positioning method, the step 1 comprises the following steps:
step 11: synchronously acquiring satellite positioning data of each frame of image, and operating a mapping mode of SLAM;
step 12: and eliminating satellite navigation data of images outside the key frames.
As a further optimization scheme of the satellite-aided machine vision positioning method of the present invention, the step 2 includes:
step 21: extracting satellite positioning data of key frames;
step 22: calculating relative satellite positioning information between key frames;
step 23: and adding the relative satellite positioning information into constraint conditions for global map construction, and constructing a global map.
As a further optimization scheme of the satellite-aided machine vision positioning method of the present invention, the step 3 includes:
step 31: establishing a similarity transformation model between a visual coordinate system and a geographic coordinate system;
step 32: establishing an objective function to be solved for the current key frame, and solving the least square solution of the objective function;
step 33: storing the obtained transformation relation of the visual coordinate system/geographic coordinate system of the current key frame into a data management model;
step 34: establishing a mapping table of a visual map data set, a satellite data set and a coordinate conversion parameter set;
step 35: and converting and outputting the result of visual positioning.
As a further optimization scheme of the machine vision positioning method based on satellite assistance, in the step 11, satellite positioning data of each frame of image is acquired, and a scheme of interpolation processing is adopted for the real-time acquired image and the satellite data.
As a further optimization scheme of the satellite-aided machine vision positioning method, in the step 32, an objective function to be solved is established for the current key frame, a criterion that every N continuous key frames are adopted and a coordinate transformation relation is solved in M meters nearby is not solved, N is an integer between 29 and 51, and M is a natural number between 2 and 6;
solving least square solution of the objective function in the step 32, wherein the solution is participated by adopting adjacent N key frames instead of adopting the whole visual map data;
in the step 32, an objective function to be solved is established for the current key frame, and a least square solution of the objective function is solved; the method comprises the following steps: establishing an objective function as (1) by adopting a similar transformation model between a visual coordinate system and a geographic coordinate system, and solving a least square solution to obtain a rotation matrix R, a translation vector t and a scale factor s;
wherein e 2 (R, t, s) is the coordinate transformation error, N is the number of key frames involved in the coordinate transformation,
for the position of the kth keyframe under the geographical coordinate system,/for the position of the kth keyframe under the geographical coordinate system>
For the position of the kth keyframe in the visual coordinate system, the set of coordinate points in the visual coordinate system is marked +.>
The corresponding set of coordinate points in the geographic coordinate system is marked +.>
In the step 34, a mapping table of the visual map data set, the satellite data set and the coordinate conversion parameter set is established, that is, a mapping relation of the visual map key frame, the satellite navigation data and the coordinate conversion parameter set is established, the key frame corresponds to the satellite navigation data one by one, and the key frame corresponds to the coordinate conversion parameter set in a many-to-one relation, that is, a plurality of key frames correspond to one coordinate conversion parameter;
in the step 35, the result of visual positioning is converted and output, and the position of the carrier under the current visual coordinate system is converted into a geographic coordinate system according to the formula (2) by utilizing the coordinate transformation parameters obtained in the step 32;
X g ＝sRX v +t (2)。
as a further optimization scheme of the satellite-aided machine vision positioning method, the data management model comprises four parts of contents: a visual map data set, a satellite data set, a coordinate conversion parameter set, and a key frame/satellite/conversion parameter mapping table; the visual map data set is a visual map generated by the visual SLAM module, the satellite data set is a set of satellite data corresponding to a key frame of the visual map, the coordinate conversion parameter set is a set of conversion parameters of a visual coordinate system/geographic coordinate system corresponding to the key frame, and the mapping relation among the three data sets is recorded in the mapping table.
A machine vision positioning method based on satellite assistance comprises a positioning method under the condition that satellite signals are unavailable, and specifically comprises the following steps:
step (1), after satellite signals are refused, continuing to run a monocular vision SLAM program, and calculating the position information of the current carrier under a vision coordinate system in real time;
step (2), retrieving a data management model to obtain the latest key frame information of the current position of the carrier;
step (3), extracting coordinate conversion parameters of the key frames obtained in the step (2), calculating a positioning result and outputting the positioning result;
and (4) if the satellite signals are recovered in the period, performing global map optimization by using the current satellite data.
As a further optimization scheme of the satellite-aided machine vision positioning method, in the step (1), the position information of the current carrier under a vision coordinate system is calculated in real time, namely, the carrier position is calculated by adopting a monocular vision SLAM technology only;
the step (4) comprises:
step 41: acquiring satellite positioning data of a current key frame;
step 42: retrieving a data management model, and acquiring information of W key frames adjacent to the current position of the carrier, wherein W is an integer from 9 to 21;
step 43: calculating relative satellite positioning information between the current key frame and the key frame obtained in the step 42;
step 44: and adding the relative satellite positioning information into constraint conditions of global map construction, optimizing the global map, and updating a coordinate conversion parameter set.
Compared with the prior art, the technical scheme provided by the invention has the following technical effects:
(1) The problem that a satellite navigation system is easily interfered by external environment is solved, namely, under the condition that satellite navigation fails, the position information under a geographic coordinate system is output by utilizing visual navigation;
(2) The satellite data under the available condition of the satellite navigation system is utilized to restore the visual scale, so that the problem of variable scale in monocular visual navigation is solved;
(3) In the practical use process, a binocular camera or a depth camera is not needed, and the system is low in implementation cost.
Drawings
Fig. 1 is a schematic diagram of the positioning principle of the present invention in the case of satellite availability.
Fig. 2 is a schematic diagram of the positioning principle of the present invention in the case of satellite rejection.
Fig. 3 is a schematic diagram of a data management module structure.
Detailed Description
The technical scheme of the invention is further described in detail below with reference to the accompanying drawings:
the embodiments of the present invention described by referring to the drawings are exemplary only and are not to be construed as limiting the invention.
The invention provides a machine vision positioning method based on satellite assistance, which can solve the problem that a navigation system cannot position under the condition that satellite signals are blocked or stopped.
1. The machine vision positioning method based on satellite assistance is further described with reference to the schematic diagram of the principle of the invention.
Fig. 1 is a schematic diagram of a positioning principle of a satellite based machine vision positioning method with satellite assistance in a satellite available condition.
The positioning system comprises 5 functional modules, namely a data preprocessing module 101, a visual SLAM module 102, a parameter data management module 103, a parameter resolving module 104 and a position resolving module 105.
The data preprocessing module 101 is configured to interpolate the vision sensor and satellite receiver data acquired at different working frequencies to acquire satellite data corresponding to each frame of image;
the visual SLAM module 102 takes images and satellite data as input, adds constraint of relative satellite positioning information between the images on the basis of monocular visual SLAM, builds a global map, and outputs position information under a visual coordinate system in real time;
the data management module 103 is configured to manage the visual map data set generated by the visual SLAM module, the corresponding satellite data set, the coordinate conversion parameter set solved by the parameter calculation module, and the mapping table among the three.
The parameter resolving module 104 is used for screening and resolving a transformation relation between the key frame visual coordinate system and the geographic coordinate system;
the position resolving module 105 is configured to calculate and output a positioning result by using the current position of the carrier under the visual coordinate system output by the visual SLAM module and combining the coordinate conversion parameters extracted from the data management module.
The positioning flow of the machine vision positioning method based on satellite assistance under the condition that satellites are available is as follows:
1. and aligning the acquired image information with the satellite information through the data preprocessing module 101 to obtain satellite data corresponding to each image.
2. The processed image data and the corresponding satellite data are transmitted to the vision SLAM module 102, the relative satellite positioning information between key frames is calculated, and the relative satellite positioning information is added into the constraint condition of map construction to carry out global map construction.
3. A similar transformation model between the visual coordinate system and the geographic coordinate system is established, and a transformation relationship between the visual coordinate system and the geographic coordinate system of the current key frame is estimated in the parameter resolving module 104 by using least squares.
4. A data management model is built in the data management module 103, including a visual map data set, a satellite data set, a coordinate conversion parameter set, and a key frame/satellite/conversion parameter mapping table.
5. In the position calculating module 105, the visual SLAM module 102 calculates the position of the current carrier under the visual coordinate system, and combines the visual coordinate system/geographic coordinate system transformation relationship obtained by the mapping relationship of the data management module 103 to calculate the positioning result under the geographic coordinate system.
Establishing an objective function to be solved for the current key frame, and adopting a criterion that every 30 continuous key frames are solved when the coordinate transformation relation is not solved in 3 meters nearby so as to reduce the waste of computing resources; and solving the least square solution of the objective function, wherein the adjacent 30 key frames are adopted instead of the whole visual map data to participate in the solution, so that the precision of the coordinate transfer parameters of the adjacent positions of the current key frames is improved, and the solving difficulty is reduced.
As shown in fig. 2, the positioning flow of the machine vision positioning method based on satellite assistance under the condition of satellite rejection according to the invention is as follows:
1. the image information is transmitted into the visual SLAM module 102, and the position of the current carrier under a visual coordinate system is calculated;
2. retrieving a data management model in the data management module 103 to obtain the latest key frame information of the current position of the carrier;
3. extracting coordinate conversion parameters of the key frames according to the mapping relation in the data management module 103;
4. the position of the current carrier in the geographical coordinate system is resolved in a position resolving module 105.
2. The data management model is further described below in connection with a data management module architecture diagram.
As shown in fig. 3, the data management model includes four parts of content: a visual map data set 301, a satellite data set 302, a coordinate conversion parameter set 303, and a key frame/satellite/conversion parameter mapping table 304.
The visual map data set 301 is a visual map generated by the visual SLAM module 102, the satellite data set 302 is a set of satellite data corresponding to a key frame, the coordinate conversion parameter set 303 is a set of visual coordinate system/geographic coordinate system conversion parameters corresponding to the key frame, and the mapping table 304 records mapping relations among the three data sets, namely, mapping relations among the key frame of the visual map, satellite navigation data and the coordinate conversion parameter set. The key frames are in one-to-one correspondence with the satellite data, and the key frames are in a many-to-one relationship with the coordinate conversion parameter sets, namely, the plurality of key frames correspond to one coordinate conversion parameter.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any changes or substitutions easily contemplated by those skilled in the art within the scope of the present invention should be included in the scope of the present invention.
Claims (10)
1. The machine vision positioning system based on satellite assistance is characterized by comprising a data preprocessing module, a vision SLAM module, a parameter resolving module, a data management module and a position resolving module; wherein, the liquid crystal display device comprises a liquid crystal display device,
the data preprocessing module is used for carrying out interpolation processing on the vision sensor data acquired by different working frequencies and satellite receiver data so as to acquire satellite data corresponding to each frame of image, and further used for generating a satellite data set subsequently;
the visual SLAM module is used for taking images and satellite data as input, adding the constraint of relative satellite positioning information between the images on the basis of monocular visual SLAM, constructing a global map, generating a visual map data set, and outputting the current position information of the carrier under a visual coordinate system in real time;
the parameter resolving module is used for screening and solving the transformation relation between the key frame visual coordinate system and the geographic coordinate system to generate a coordinate transformation parameter set;
the data management module is used for managing the visual map data set generated by the visual SLAM module, the satellite data set corresponding to the visual map key frame, the coordinate conversion parameter set solved by the parameter resolving module and the mapping table among the three;
and the position resolving module is used for obtaining coordinate conversion parameters from the mapping table by utilizing the current position of the carrier under the visual coordinate system output by the visual SLAM module, and calculating and outputting a positioning result by combining the coordinate conversion parameters.
2. The machine vision positioning method based on satellite assistance is applied to the machine vision positioning system based on satellite assistance as claimed in claim 1, and is characterized by comprising the following specific steps:
step 1, running a monocular vision SLAM program under the condition that a satellite navigation system is available, and acquiring satellite positioning information corresponding to a key frame;
step 2, adding constraint conditions of satellite positioning information in the construction of a global map;
step 3, estimating a transformation relation between the visual coordinate system and the geographic coordinate system by utilizing least squares, calculating a result of converting the visual positioning into the geographic coordinate system and outputting the result;
and step 4, updating the coordinate conversion parameter set after global map optimization is performed when the moving track loops.
3. The satellite-based machine vision positioning method of claim 2, wherein step 1 comprises:
step 11: synchronously acquiring satellite positioning data of each frame of image, and operating a mapping mode of SLAM;
step 12: and eliminating satellite navigation data of images outside the key frames.
4. The satellite-based machine vision positioning method of claim 2, wherein step 2 comprises:
step 21: extracting satellite positioning data of key frames;
step 22: calculating relative satellite positioning information between key frames;
step 23: and adding the relative satellite positioning information into constraint conditions for global map construction, and constructing a global map.
5. The satellite-based machine vision positioning method of claim 2, wherein step 3 comprises:
step 31: establishing a similarity transformation model between a visual coordinate system and a geographic coordinate system;
step 32: establishing an objective function to be solved for the current key frame, and solving the least square solution of the objective function;
step 33: storing the obtained transformation relation between the visual coordinate system of the current key frame and the geographic coordinate system into a data management model;
step 34: establishing a mapping table of a visual map data set, a satellite data set and a coordinate conversion parameter set; the visual map data set is a visual map generated by the visual SLAM module, the satellite data set is a set of satellite data corresponding to key frames of the visual map, and the coordinate conversion parameter set is a set of transformation parameters of a visual coordinate system and a geographic coordinate system corresponding to the key frames;
step 35: and converting and outputting the result of visual positioning.
6. A satellite-assisted machine vision positioning method according to claim 3, wherein in step 11, satellite positioning data of each frame of image is obtained, and a scheme of interpolating the real-time acquired image and the satellite data is adopted.
7. The satellite-aided machine vision positioning method of claim 5, wherein in the step 32, an objective function to be solved is established for the current keyframe, a criterion that every N consecutive keyframes are solved if the coordinate transformation relation is not solved in M meters nearby is adopted, N is an integer between 29 and 51, and M is a natural number between 2 and 6;
solving least square solution of the objective function in the step 32, wherein the solution is participated by adopting adjacent N key frames instead of adopting the whole visual map data;
in the step 32, an objective function to be solved is established for the current key frame, and a least square solution of the objective function is solved; the method comprises the following steps: establishing an objective function as (1) by adopting a similar transformation model between a visual coordinate system and a geographic coordinate system, and solving a least square solution of the objective function to obtain a rotation matrix R, a translation vector t and a scale factor s;
wherein e 2 (R, t, s) is the coordinate transformation error, N is the number of key frames involved in the coordinate transformation,
for the position of the kth keyframe under the geographical coordinate system,/for the position of the kth keyframe under the geographical coordinate system>
For the position of the kth keyframe in the visual coordinate system, the set of coordinate points in the visual coordinate system is marked +.>
The corresponding set of coordinate points in the geographic coordinate system is marked +.>
In the step 34, a mapping table of the visual map data set, the satellite data set and the coordinate conversion parameter set is established, that is, a mapping relation of the visual map key frame, the satellite navigation data and the coordinate conversion parameter set is established, the key frame corresponds to the satellite navigation data one by one, and the key frame corresponds to the coordinate conversion parameter set in a many-to-one relation, that is, a plurality of key frames correspond to one coordinate conversion parameter;
in the step 35, the result of visual positioning is converted and output, and the position of the carrier under the current visual coordinate system is converted into a geographic coordinate system according to the formula (2) by utilizing the coordinate transformation parameters obtained in the step 32;
X g ＝sRX v +t(2)。
8. the satellite-aided based machine vision positioning method of claim 5, wherein the data management model comprises four parts: a visual map data set, a satellite data set, a coordinate conversion parameter set, and a key frame-satellite-conversion parameter mapping table; the visual map data set is a visual map generated by the visual SLAM module, the satellite data set is a set of satellite data corresponding to key frames of the visual map, the coordinate conversion parameter set is a set of conversion parameters of a visual coordinate system and a geographic coordinate system corresponding to the key frames, and the mapping relation among the three data sets is recorded in the mapping table; the key frame-satellite-conversion parameter mapping table is used for establishing a mapping relation among the key frame of the visual map, satellite navigation data and a coordinate conversion parameter set, wherein the key frame corresponds to the satellite navigation data one by one, and the key frame corresponds to the coordinate conversion parameter set one by one, namely a plurality of key frames correspond to one coordinate conversion parameter.
9. The machine vision positioning method based on satellite assistance is characterized by comprising the following specific steps of:
step (1), after satellite signals are refused, continuing to run a monocular vision SLAM program, and calculating the position information of the current carrier under a vision coordinate system in real time;
step (2), retrieving a data management model to obtain the latest key frame information of the current position of the carrier;
step (3), extracting coordinate conversion parameters of the key frames obtained in the step (2), calculating a result of converting visual positioning into a geographic coordinate system, and outputting the result;
and (4) if the satellite signals are recovered in the period, performing global map optimization by using the current satellite data.
10. The satellite-aided machine vision positioning method of claim 9, wherein in the step (1), the position information of the current carrier under the vision coordinate system is calculated in real time, namely, the carrier position is calculated only by adopting a monocular vision SLAM technology;
the step (4) comprises:
step 41: acquiring satellite positioning data of a current key frame;
step 42: retrieving a data management model, and acquiring information of W key frames adjacent to the current position of the carrier, wherein W is an integer from 9 to 21;
step 43: calculating relative satellite positioning information between the current key frame and the key frame obtained in the step 42;
step 44: and adding the relative satellite positioning information into constraint conditions of global map construction, optimizing the global map, and updating a coordinate conversion parameter set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911300312.3A CN111025364B (en) | 2019-12-17 | 2019-12-17 | Machine vision positioning system and method based on satellite assistance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911300312.3A CN111025364B (en) | 2019-12-17 | 2019-12-17 | Machine vision positioning system and method based on satellite assistance |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111025364A CN111025364A (en) | 2020-04-17 |
| CN111025364B true CN111025364B (en) | 2023-05-16 |
Family
ID=70209920
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911300312.3A Active CN111025364B (en) | 2019-12-17 | 2019-12-17 | Machine vision positioning system and method based on satellite assistance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111025364B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113758415A (en) * | 2021-06-30 | 2021-12-07 | 广东食品药品职业学院 | Machine vision positioning support, system and positioning method based on deep learning |
| CN116929407A (en) * | 2022-04-02 | 2023-10-24 | 北京三快在线科技有限公司 | Self-adaptive data calibration method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102435188A (en) * | 2011-09-15 | 2012-05-02 | 南京航空航天大学 | Monocular vision/inertia autonomous navigation method for indoor environment |
| CN109405824A (en) * | 2018-09-05 | 2019-03-01 | 武汉契友科技股份有限公司 | A kind of multi-source perceptual positioning system suitable for intelligent network connection automobile |
| CN109901207A (en) * | 2019-03-15 | 2019-06-18 | 武汉大学 | A kind of high-precision outdoor positioning method of Beidou satellite system and feature combinations |
| WO2019219077A1 (en) * | 2018-05-18 | 2019-11-21 | 京东方科技集团股份有限公司 | Positioning method, positioning apparatus, positioning system, storage medium, and method for constructing offline map database |
| CN110542916A (en) * | 2019-09-18 | 2019-12-06 | 上海交通大学 | satellite and vision tight coupling positioning method, system and medium |
-
2019
- 2019-12-17 CN CN201911300312.3A patent/CN111025364B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102435188A (en) * | 2011-09-15 | 2012-05-02 | 南京航空航天大学 | Monocular vision/inertia autonomous navigation method for indoor environment |
| WO2019219077A1 (en) * | 2018-05-18 | 2019-11-21 | 京东方科技集团股份有限公司 | Positioning method, positioning apparatus, positioning system, storage medium, and method for constructing offline map database |
| CN109405824A (en) * | 2018-09-05 | 2019-03-01 | 武汉契友科技股份有限公司 | A kind of multi-source perceptual positioning system suitable for intelligent network connection automobile |
| CN109901207A (en) * | 2019-03-15 | 2019-06-18 | 武汉大学 | A kind of high-precision outdoor positioning method of Beidou satellite system and feature combinations |
| CN110542916A (en) * | 2019-09-18 | 2019-12-06 | 上海交通大学 | satellite and vision tight coupling positioning method, system and medium |
Non-Patent Citations (4)
| Title |
|---|
| 孟旭炯.基于单目视觉的同时定位与地图重建算法研究.《中国博士学位论文全文数据库信息科技辑》.2011,(第8期),正文第63-97页. * |
| 张凯威.基于视觉 SLAM 的移动机器人导航算法研究.《中国优秀硕士学位论文全文数据库信息科技辑》.2019,(第7期),正文第8-54页. * |
| 杨承忠.基于改进关键帧的单目视觉SLAM研究.《电子技术》.2019,(第3期),第76页. * |
| 薛杨 等.基准地图测绘下的视觉导航算法.《兵工自动化》.2019,第38卷(第10期),第22-27页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111025364A (en) | 2020-04-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112129281B (en) | High-precision image navigation positioning method based on local neighborhood map | |
| CN110446159A (en) | A kind of system and method for interior unmanned plane accurate positioning and independent navigation | |
| CA3054243C (en) | Co-localisation | |
| CN101241011B (en) | High precision positioning and posture-fixing device on laser radar platform and method | |
| US10520605B2 (en) | Satellite signal reception characteristic estimation apparatus, method thereof, and program thereof | |
| CN111880207B (en) | Visual inertial satellite tight coupling positioning method based on wavelet neural network | |
| CN109100730A (en) | A kind of fast run-up drawing method of more vehicle collaborations | |
| CN111025364B (en) | Machine vision positioning system and method based on satellite assistance | |
| CN113269878B (en) | Multi-sensor-based mapping method and system | |
| CN107270894A (en) | GNSS/SINS deep integrated navigation systems based on Dimensionality Reduction | |
| CN110751123B (en) | Monocular vision inertial odometer system and method | |
| CN107316280A (en) | Li Island satellite image RPC models high accuracy geometry location method | |
| CN112762945A (en) | Information synchronization method, system and device of high-precision map full-element acquisition equipment | |
| CN114942013A (en) | A remote sensing unmanned aerial vehicle for topographic information gathers | |
| CN116153140A (en) | River basin emergency unmanned aerial vehicle management method and platform | |
| CN115469308A (en) | Multi-track InSAR inter-seismic deformation rate field splicing method, device, equipment and medium | |
| US11965752B2 (en) | Methods and systems using digital map data | |
| CN113959437A (en) | Measuring method and system for mobile measuring equipment | |
| CN109975848B (en) | Precision optimization method of mobile measurement system based on RTK technology | |
| CN111679297A (en) | Noise point drift removal method for GPS positioning track | |
| Bardaro et al. | Accessible urban routes reconstruction by fusing mobile sensors data | |
| Liu et al. | Tightly coupled stereo vision aided inertial navigation using continuously tracked features for land vehicles | |
| CN117132728B (en) | Method and device for constructing map, electronic equipment and storage medium | |
| CN115638788B (en) | Semantic vector map construction method, computer equipment and storage medium | |
| WO2023006213A1 (en) | Device and method for navigation |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |