CN108180917A - A kind of top mark map constructing method based on the optimization of pose figure - Google Patents
A kind of top mark map constructing method based on the optimization of pose figure Download PDFInfo
- Publication number
- CN108180917A CN108180917A CN201711495070.9A CN201711495070A CN108180917A CN 108180917 A CN108180917 A CN 108180917A CN 201711495070 A CN201711495070 A CN 201711495070A CN 108180917 A CN108180917 A CN 108180917A
- Authority
- CN
- China
- Prior art keywords
- road sign
- pose
- coordinate system
- image
- coordinate
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—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
- G01C21/32—Structuring or formatting of map data
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The present invention is suitable for robot localization technical field, provides a kind of top mark map constructing method optimized based on pose figure, this method comprises the following steps：S1, the pose figure based on shooting picture construction road sign coordinate system；S2, the optimization based on pose figure calculate pose of each road sign coordinate system in map coordinates system；S3, coordinate of each road sign point in map coordinates system is calculated based on pose of each road sign coordinate system in map coordinates system.Top mark map constructing method provided in an embodiment of the present invention based on the optimization of pose figure, by rectangular coordinate system present in different top marks as the pose transformation for being same rectangular coordinate system, optimize the coordinate to calculate road sign point using pose figure, for the pose figure built based on camera posture, the mobile robot indoor map structure precision based on top mark can be greatly improved, and calculate simply, it is as a result more stable.
Description
Technical field
The invention belongs to robot localization technical fields, provide a kind of calibration map structuring side optimized based on pose figure
Method.
Background technology
With the development of society and the progress of technology, the deeper and deeper daily life for getting involved in the mankind of mobile robot
In, such as the clean robot in family, the transfer robot in factory and meal delivery robot in restaurant etc..Mobile machine
People want to realize it is above-mentioned it is functional just have to accurately know the position where itself, and what robot can position in real time
Prerequisite is to establish map, this is the key that robot navigation and other intelligent behaviors.Mobile robot builds figure and positioning is normal
Sensor has video camera and laser radar etc..Wherein laser radar hardware cost is higher, is unfavorable for the big of mobile robot
Range popularizes.And carry out that location hardware is at low cost, positioning accuracy is high using video camera, and in positioning indoors, view-based access control model
Localization method be widely used.The indoor positioning of view-based access control model first has to structure accurately indoor map, for absolutely sitting
The lower calculating of video camera posture of mark system and the planning of robot mobile route.Accurate geometry can be built by artificial landmark
Map can also build map using environment terrestrial reference.Although wherein based on environment calibration method universality is preferable, do not need to
Additional mark is manually laid, but calculates complexity, practicability is poor.Artificial landmark is often in visual signatures such as color, shapes
It is upper that there is apparent uniqueness, easily artificial landmark can be identified by computer vision methods.Wherein have one
The method that kind lays artificial landmark on roof, roof environment is single to be easy to extract, and the visual field of video camera is not readily susceptible to interfere,
It is widely used in positioning indoors.
But existing top mark map constructing method is to calculate position of the unknown road sign in map successively according to known road sign
It puts, the error in calculating process can accumulate back-propagation, and when top mark number is more, map structuring result is inaccurate, causes to position
Failure.
Invention content
The embodiment of the present invention provides a kind of calibration map constructing method based on the optimization of pose figure, it is intended to solve existing top mark
Map constructing method when calculating position of the unknown road sign in map successively based on known road sign, the error meeting in calculating process
The problem of accumulating back-propagation, map structuring result being caused inaccurate when top mark number is more.
The invention is realized in this way a kind of calibration map constructing method based on the optimization of pose figure, this method are included such as
Lower step：
S1, the pose figure based on shooting picture construction road sign coordinate system；
S2, the optimization based on pose figure calculate pose of each road sign coordinate system in map coordinates system；
S3, seat of each road sign point in map coordinates system is calculated based on pose of each road sign coordinate system in map coordinates system
Mark.
Further, the step S1 includes the following steps：
All road signs in S11, extraction shooting image；
S12, judge whether current key frame set is empty set, if judging result is no, perform step S13, if judging
As a result it is yes, then identifies with the presence or absence of initial road sign in the road sign set in present image, if in the presence of initial road sign is set
It for initial frame, and preserves into key frame set, enters step S13, if being not present, perform step S11,
S13, the known road sign in identification image and unknown road sign traverse all known road signs in image, judge current
Known road sign is associated with whether the other known road sign in image has built up, if judging result is no, is established currently known
Connection relation in road sign and image between other known road sign traverses all unknown road signs in image, establishes current unknown road
The connection relation of mark and known road signs all in image, and current unknown road sign is saved as into a key frame；The known road
Mark refers to the road sign being included into pose figure；Unknown road sign refers to not bring the road sign in pose figure into；
The pose figure of road sign movement is established in all paths in S14, traversal map.
Further, the method for building up of connection relation includes the following steps between road sign point：
Image coordinate based on road sign n Roads punctuate and the world coordinates in current road sign coordinate system calculate camera and exist
Posture R under the road sign coordinate system of road sign nn、tn；
Image coordinate based on road sign m Roads punctuate and the world coordinates in current road sign coordinate system calculate camera and exist
Posture R under the road sign coordinate system of road sign mm、tm；
Spin matrix from road sign coordinate system n to road sign coordinate system m isTranslation vector isPose from road sign coordinate system n to road sign coordinate system m is transformed to (tnm(0),tnm(1),atan2(Rnm
(1,0),Rnm(0,0))。
Further, the computational methods of camera posture under road sign s coordinate systems are as follows：
Utilize affine transformation equationCalculate spin matrixAnd translation vectorPhotography depth is removed again
The factor obtains spin matrix R, translation vector t, wherein,xiImage coordinate x for road sign point known in road sign si,
XwFor the world coordinates of road sign point known in road sign s, McamThe internal reference matrix of camera.
Further, based on formula Xw=R*X 'w+ t calculates coordinate of each road sign point in map coordinates system, wherein, R
For the spin matrix of current road sign coordinate system, translation vectors of the t for current road sign coordinate system, X 'wIt is road sign point in road sign coordinate
Coordinate in system.
Top mark map constructing method provided in an embodiment of the present invention based on the optimization of pose figure, present in different top marks
Rectangular coordinate system regard be same rectangular coordinate system pose transformation, optimize to calculate the coordinate of road sign point using pose figure,
For the pose figure built based on camera posture, the mobile robot indoor map structure based on top mark can be greatly improved
Precision is built, and is calculated simply, it is as a result more stable.
Description of the drawings
Fig. 1 is the flow chart of the calibration map constructing method provided in an embodiment of the present invention based on the optimization of pose figure.
Specific embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, with reference to the accompanying drawings and embodiments, it is right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
Flow charts of the Fig. 1 for the calibration map constructing method provided in an embodiment of the present invention based on the optimization of pose figure, the party
Method includes the following steps：
S1, the pose figure based on shooting picture construction road sign coordinate system；
In embodiments of the present invention, road sign is set on the roof in robot motion region, and video camera is parallel to roof setting, uses
Road sign in shooting roof；
Specifically comprise the following steps in step S1 of the present invention：
S11, all road signs in shooting image are extracted using image zooming-out algorithm；
S12, judge whether current key frame set is empty set, if judging result is no, perform step S13, if judging
As a result it is yes, then identifies with the presence or absence of initial road sign in the road sign set in present image, if in the presence of initial road sign is set
It for initial frame, and preserves into key frame set, enters step S13, if being not present, perform step S11,
S13, the known road sign in identification image and unknown road sign traverse all known road signs in image, judge current
Known road sign is associated with whether the other known road sign in image has built up, if judging result is no, is established currently known
Connection relation in road sign and image between other known road sign traverses all unknown road signs in image, establishes current unknown road
The connection relation of mark and known road signs all in image, and current unknown road sign is saved as into a key frame, it is known that road sign is
Refer to the road sign being included into pose figure, unknown road sign refers to not bring the road sign in pose figure into.
In embodiments of the present invention, the method for building up of connection relation is specific as follows between road sign point：
Based on the image coordinate and world coordinates of road sign n Roads punctuate, camera is calculated under the road sign coordinate system of road sign n
Posture Rn、tn；
Based on the image coordinate and world coordinates of road sign m Roads punctuate, camera is calculated under the road sign coordinate system of road sign m
Posture Rm、tm；
Spin matrix from road sign coordinate system n to road sign coordinate system m isTranslation vector isPose from road sign coordinate system n to road sign coordinate system m is transformed to (tnm(0),tnm(1),atan2(Rnm
(1,0),Rnm(0,0))。
In embodiments of the present invention, the computational methods of camera posture under road sign s coordinate systems are as follows：
Utilize affine transformation equationCalculate spin matrixAnd translation vectorPhotography depth is removed again
The factor obtains spin matrix R, translation vector t, wherein,xiImage coordinate x for road sign point known in road sign si,
XwFor the world coordinates of road sign point known in road sign s, McamThe internal reference matrix of camera.
The pose figure of road sign movement is established in all paths in S14, traversal map.
In embodiments of the present invention, map is included in all road signs for map coordinates system, in map coordinates system,
Some road sign coordinate system is generally selected as map coordinates system.
S2, the optimization based on pose figure calculate pose of each road sign coordinate system in map coordinates system；
In embodiments of the present invention, pose illustraton of model is described with equation, equation represents as follows：
Wherein, xkFor k-th of node location information, k node is the origin of k-th of road sign coordinate system；zkIt is k-th
The location information that node is observed；ekFor xkWith zkBetween error；Ω is information matrix, is the inverse of covariance matrix；
Error term F (x) represents as follows：
To the e on kth sidek(xk) carry out first order Taylor expansion：
Above-mentioned JkFor ekAbout xkDerivative, matrix form is lower Jacobi battle array, to the object function on kth side into one
Step expansion has：
Fk(xk+ Δ x)=ek(xk+Δx)TΩkek(xk+Δx)
≈(ek+JkΔx)TΩk(ek+JkΔx)
≈Ck+2bkΔx+ΔxTHkΔx
Wherein CkFor constant term, 2bkFor Monomial coefficient, HkF for secondary term coefficient, then object functionkThe value of change is
ΔFk=2bkΔx+ΔxTHkΔx
It enables
Then the problem is transformed into the solution of a linear equation：HkΔ x=-bk；
Solve the x of global optimum*=x+ Δ x, and initial value substitution F (x) is iterated calculating the most, is finally calculated
The pose of each key frame, i.e., pose of each road sign coordinate system in map coordinates system.
S3, seat of each road sign point in map coordinates system is calculated based on pose of each road sign coordinate system in map coordinates system
Mark.
In embodiments of the present invention, based on formula Xw=R*X 'w+ t calculates seat of each road sign point in map coordinates system
Mark, wherein, spin matrixs of the R for current road sign coordinate system, translation vectors of the t for current road sign coordinate system, X 'wExist for road sign point
Coordinate in road sign coordinate system.
Top mark map constructing method provided in an embodiment of the present invention based on the optimization of pose figure, present in different top marks
Rectangular coordinate system regard be same rectangular coordinate system pose transformation, optimize to calculate the coordinate of road sign point using pose figure,
For the pose figure built based on camera posture, the mobile robot indoor map structure based on top mark can be greatly improved
Precision is built, and is calculated simply, it is as a result more stable.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
All any modification, equivalent and improvement made within refreshing and principle etc., should all be included in the protection scope of the present invention.
Claims (5)
1. a kind of top mark map constructing method based on the optimization of pose figure, which is characterized in that described method includes following steps：
S1, the pose figure based on shooting picture construction road sign coordinate system；
S2, the optimization based on pose figure calculate pose of each road sign coordinate system in map coordinates system；
S3, coordinate of each road sign point in map coordinates system is calculated based on pose of each road sign coordinate system in map coordinates system.
2. the top mark map constructing method as described in claim 1 based on the optimization of pose figure, which is characterized in that the step S1
Include the following steps：
All road signs in S11, extraction shooting image；
S12, judge whether current key frame set is empty set, if judging result is no, step S13 is performed, if judging result
It is yes, then identifies with the presence or absence of initial road sign in the road sign set in present image, if in the presence of initial road sign is set as just
Beginning frame, and preserve into key frame set, S13 is entered step, if being not present, performs step S11,
S13, the known road sign in identification image and unknown road sign traverse all known road signs in image, judge currently known
Road sign is associated with whether the other known road sign in image has built up, if judging result is no, establishes currently known road sign
With the connection relation between road sign other known in image, traverse all unknown road signs in image, establish current unknown road sign with
The connection relation of all known road signs in image, and current unknown road sign is saved as into a key frame；The known road sign is
Refer to the road sign being included into pose figure；Unknown road sign refers to not bring the road sign in pose figure into；
The pose figure of road sign movement is established in all paths in S14, traversal map.
3. the top mark map constructing method as claimed in claim 2 based on the optimization of pose figure, which is characterized in that connect between road sign point
The method for building up for connecing relationship includes the following steps：
Image coordinate based on road sign n Roads punctuate and the world coordinates in current road sign coordinate system calculate camera in road sign n
Road sign coordinate system under posture Rn、tn；
Image coordinate based on road sign m Roads punctuate and the world coordinates in current road sign coordinate system calculate camera in road sign m
Road sign coordinate system under posture Rm、tm；
Spin matrix from road sign coordinate system n to road sign coordinate system m isTranslation vector isPose from road sign coordinate system n to road sign coordinate system m is transformed to (tnm(0),tnm(1),atan2(Rnm
(1,0),Rnm(0,0))。
4. the top mark map constructing method as claimed in claim 3 based on the optimization of pose figure, which is characterized in that camera is in road sign
The computational methods of posture are as follows under s coordinate systems：
Utilize affine transformation equationCalculate spin matrixAnd translation vectorPhotography depth factor is removed again
Spin matrix R, translation vector t are obtained, wherein,xiImage coordinate x for road sign point known in road sign si, XwFor
The world coordinates of known road sign point, M in road sign scamThe internal reference matrix of camera.
5. the top mark map constructing method as described in claim 1 based on the optimization of pose figure, which is characterized in that based on formula Xw
=R*X 'w+ t calculates coordinate of each road sign point in map coordinates system, wherein, R is the spin matrix of current road sign coordinate system,
Translation vectors of the t for current road sign coordinate system, X 'wFor coordinate of the road sign point in road sign coordinate system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711495070.9A CN108180917B (en) | 2017-12-31 | 2017-12-31 | Top map construction method based on pose graph optimization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711495070.9A CN108180917B (en) | 2017-12-31 | 2017-12-31 | Top map construction method based on pose graph optimization |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108180917A true CN108180917A (en) | 2018-06-19 |
| CN108180917B CN108180917B (en) | 2021-05-14 |
Family
ID=62549470
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711495070.9A Active CN108180917B (en) | 2017-12-31 | 2017-12-31 | Top map construction method based on pose graph optimization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108180917B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109612468A (en) * | 2018-12-28 | 2019-04-12 | 芜湖哈特机器人产业技术研究院有限公司 | A kind of top mark map structuring and robot localization method |
| CN109613547A (en) * | 2018-12-28 | 2019-04-12 | 芜湖哈特机器人产业技术研究院有限公司 | It is a kind of that grating map construction method is occupied based on reflector |
| CN109613549A (en) * | 2018-12-28 | 2019-04-12 | 芜湖哈特机器人产业技术研究院有限公司 | A kind of laser radar positioning method based on Kalman filter |
| CN109613550A (en) * | 2018-12-28 | 2019-04-12 | 芜湖哈特机器人产业技术研究院有限公司 | A kind of laser radar map structuring and localization method based on reflector |
| CN110954114A (en) * | 2019-11-26 | 2020-04-03 | 苏州智加科技有限公司 | Method and device for generating electronic map, terminal and storage medium |
| CN111256676A (en) * | 2018-11-30 | 2020-06-09 | 杭州海康机器人技术有限公司 | Mobile robot positioning method, device and computer readable storage medium |
| CN111553342A (en) * | 2020-04-01 | 2020-08-18 | 深圳一清创新科技有限公司 | Visual positioning method and device, computer equipment and storage medium |
| CN112070068A (en) * | 2020-10-13 | 2020-12-11 | 上海美迪索科电子科技有限公司 | Map construction method, device, medium and equipment |
| WO2021109167A1 (en) * | 2019-12-06 | 2021-06-10 | 苏州艾吉威机器人有限公司 | Three-dimensional laser mapping method and system |
| CN113688678A (en) * | 2021-07-20 | 2021-11-23 | 深圳市普渡科技有限公司 | Road sign multi-ambiguity processing method, robot and storage medium |
| WO2023098415A1 (en) * | 2021-11-30 | 2023-06-08 | 珠海一微半导体股份有限公司 | Positioning method for ceiling vision robot |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103292804B (en) * | 2013-05-27 | 2015-07-15 | 浙江大学 | Monocular natural vision landmark assisted mobile robot positioning method |
| CN103528568B (en) * | 2013-10-08 | 2016-08-17 | 北京理工大学 | A kind of object pose image measuring method based on wireless channel |
| CN103886107B (en) * | 2014-04-14 | 2017-10-03 | 张文强 | Robot localization and map structuring system based on ceiling image information |
| CN106651990B (en) * | 2016-12-23 | 2020-08-11 | 芜湖哈特机器人产业技术研究院有限公司 | Indoor map construction method and indoor positioning method based on indoor map |
| CN107063258A (en) * | 2017-03-07 | 2017-08-18 | 重庆邮电大学 | A kind of mobile robot indoor navigation method based on semantic information |
-
2017
- 2017-12-31 CN CN201711495070.9A patent/CN108180917B/en active Active
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111256676B (en) * | 2018-11-30 | 2022-02-11 | 杭州海康机器人技术有限公司 | Mobile robot positioning method, device and computer readable storage medium |
| CN111256676A (en) * | 2018-11-30 | 2020-06-09 | 杭州海康机器人技术有限公司 | Mobile robot positioning method, device and computer readable storage medium |
| CN109613547A (en) * | 2018-12-28 | 2019-04-12 | 芜湖哈特机器人产业技术研究院有限公司 | It is a kind of that grating map construction method is occupied based on reflector |
| CN109613549A (en) * | 2018-12-28 | 2019-04-12 | 芜湖哈特机器人产业技术研究院有限公司 | A kind of laser radar positioning method based on Kalman filter |
| CN109613550A (en) * | 2018-12-28 | 2019-04-12 | 芜湖哈特机器人产业技术研究院有限公司 | A kind of laser radar map structuring and localization method based on reflector |
| CN109612468A (en) * | 2018-12-28 | 2019-04-12 | 芜湖哈特机器人产业技术研究院有限公司 | A kind of top mark map structuring and robot localization method |
| CN109613549B (en) * | 2018-12-28 | 2023-04-07 | 芜湖哈特机器人产业技术研究院有限公司 | Laser radar positioning method based on Kalman filtering |
| CN109613550B (en) * | 2018-12-28 | 2023-04-07 | 芜湖哈特机器人产业技术研究院有限公司 | Laser radar map construction and positioning method based on reflector |
| CN109613547B (en) * | 2018-12-28 | 2022-05-27 | 芜湖哈特机器人产业技术研究院有限公司 | Method for constructing occupied grid map based on reflector |
| CN110954114A (en) * | 2019-11-26 | 2020-04-03 | 苏州智加科技有限公司 | Method and device for generating electronic map, terminal and storage medium |
| CN110954114B (en) * | 2019-11-26 | 2021-11-23 | 苏州智加科技有限公司 | Method and device for generating electronic map, terminal and storage medium |
| WO2021109167A1 (en) * | 2019-12-06 | 2021-06-10 | 苏州艾吉威机器人有限公司 | Three-dimensional laser mapping method and system |
| CN111553342A (en) * | 2020-04-01 | 2020-08-18 | 深圳一清创新科技有限公司 | Visual positioning method and device, computer equipment and storage medium |
| CN111553342B (en) * | 2020-04-01 | 2023-08-08 | 深圳一清创新科技有限公司 | Visual positioning method, visual positioning device, computer equipment and storage medium |
| CN112070068A (en) * | 2020-10-13 | 2020-12-11 | 上海美迪索科电子科技有限公司 | Map construction method, device, medium and equipment |
| CN113688678A (en) * | 2021-07-20 | 2021-11-23 | 深圳市普渡科技有限公司 | Road sign multi-ambiguity processing method, robot and storage medium |
| CN113688678B (en) * | 2021-07-20 | 2024-04-12 | 深圳市普渡科技有限公司 | Road sign multi-ambiguity processing method, robot and storage medium |
| WO2023098415A1 (en) * | 2021-11-30 | 2023-06-08 | 珠海一微半导体股份有限公司 | Positioning method for ceiling vision robot |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108180917B (en) | 2021-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108180917A (en) | A kind of top mark map constructing method based on the optimization of pose figure | |
| CN108303099B (en) | Autonomous navigation method in unmanned plane room based on 3D vision SLAM | |
| CN108225327B (en) | Construction and positioning method of top mark map | |
| CN109506658B (en) | Robot autonomous positioning method and system | |
| Cheng et al. | Improving monocular visual SLAM in dynamic environments: an optical-flow-based approach | |
| Sim et al. | Integrated position estimation using aerial image sequences | |
| CN106407315B (en) | A kind of vehicle autonomic positioning method based on street view image database | |
| Lategahn et al. | Vision-only localization | |
| CN105241445B (en) | A kind of indoor navigation data capture method and system based on intelligent mobile terminal | |
| CN110095116A (en) | A kind of localization method of vision positioning and inertial navigation combination based on LIFT | |
| US9420275B2 (en) | Visual positioning system that utilizes images of a working environment to determine position | |
| CN108917759A (en) | Mobile robot pose correct algorithm based on multi-level map match | |
| CN103175524B (en) | A kind of position of aircraft without view-based access control model under marking environment and attitude determination method | |
| Chen et al. | Vision-based autonomous vehicle guidance for indoor security patrolling by a SIFT-based vehicle-localization technique | |
| CN109583409A (en) | A kind of intelligent vehicle localization method and system towards cognitive map | |
| US20130158865A1 (en) | Method and apparatus for estimating position of moving object | |
| CN108051836A (en) | A kind of localization method, device, server and system | |
| CN109579825A (en) | Robot positioning system and method based on binocular vision and convolutional neural networks | |
| CN111912416A (en) | Method, device and equipment for positioning equipment | |
| CN109612468A (en) | A kind of top mark map structuring and robot localization method | |
| CN110749308B (en) | SLAM-oriented outdoor positioning method using consumer-grade GPS and 2.5D building models | |
| Lin et al. | A sparse visual odometry technique based on pose adjustment with keyframe matching | |
| Antigny et al. | Pedestrian track estimation with handheld monocular camera and inertial-magnetic sensor for urban augmented reality | |
| CN109443354A (en) | Vision-inertia close coupling Combinated navigation method based on firefly group's optimization PF | |
| Tao et al. | Automated processing of mobile mapping image sequences |
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 |