CN110006420A - Build drawing method, image acquisition and processing system and localization method - Google Patents
Build drawing method, image acquisition and processing system and localization method Download PDFInfo
- Publication number
- CN110006420A CN110006420A CN201811475564.5A CN201811475564A CN110006420A CN 110006420 A CN110006420 A CN 110006420A CN 201811475564 A CN201811475564 A CN 201811475564A CN 110006420 A CN110006420 A CN 110006420A
- Authority
- CN
- China
- Prior art keywords
- picture
- parameter
- location parameter
- attitude parameter
- attitude
- 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
- 238000000034 method Methods 0.000 title claims abstract description 76
- 238000012545 processing Methods 0.000 title claims description 43
- 230000004807 localization Effects 0.000 title claims description 13
- 238000005259 measurement Methods 0.000 claims description 42
- NJPPVKZQTLUDBO-UHFFFAOYSA-N novaluron Chemical compound C1=C(Cl)C(OC(F)(F)C(OC(F)(F)F)F)=CC=C1NC(=O)NC(=O)C1=C(F)C=CC=C1F NJPPVKZQTLUDBO-UHFFFAOYSA-N 0.000 claims description 23
- 238000011478 gradient descent method Methods 0.000 claims description 21
- 241000208340 Araliaceae Species 0.000 claims description 9
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 9
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 9
- 235000008434 ginseng Nutrition 0.000 claims description 9
- 230000008878 coupling Effects 0.000 claims description 3
- 238000010168 coupling process Methods 0.000 claims description 3
- 238000005859 coupling reaction Methods 0.000 claims description 3
- 230000000875 corresponding effect Effects 0.000 description 23
- 238000010586 diagram Methods 0.000 description 14
- 238000006073 displacement reaction Methods 0.000 description 13
- 230000006870 function Effects 0.000 description 9
- 238000006243 chemical reaction Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 230000007423 decrease Effects 0.000 description 5
- 241000209094 Oryza Species 0.000 description 4
- 235000007164 Oryza sativa Nutrition 0.000 description 4
- 235000009566 rice Nutrition 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000009434 installation Methods 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 238000009795 derivation Methods 0.000 description 2
- 230000004907 flux Effects 0.000 description 2
- 210000004209 hair Anatomy 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000011664 signaling Effects 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 230000003321 amplification Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000013011 mating Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 239000002344 surface layer Substances 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
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
- G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
- G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
- G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
- G01C21/165—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation combined with non-inertial navigation instruments
-
- 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
- G01C21/20—Instruments for performing navigational calculations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/001—Texturing; Colouring; Generation of texture or colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
Abstract
The present invention provides a kind of pair of place and carries out the method for building figure, comprising: establishes or obtain the coordinate system in the place;The place is scanned, the picture of calibration point, the picture of position to be positioned and location parameter corresponding with the picture and attitude parameter are obtained;Picture, the location parameter and the attitude parameter of picture, the position to be positioned based on the calibration point correct the location parameter and attitude parameter of the picture of the position to be positioned.
Description
Technical field
The present invention relate generally to intelligent storage field more particularly to it is a kind of can be used for intelligent storage build drawing method, Image Acquisition
Processing system and localization method.
Background technique
In existing intelligent repository, it is often necessary to positioning place is measured, establishes physical coordinates system, physical coordinates system with
Common parasang as linear module, such as rice, decimetre, centimetre, permission is described with integer, decimal, fractional form, than
Such as 1 meter, 1 decimeter, 1 centimetre, 0.55 meter, 0.2 decimeter, 1.4 centimetres, half rice etc., the generally same building in coordinate system direction
Enclosure wall is parallel, or parallel with all directions direction.
The automatic guide vehicle AGV of cargo is transported in intelligent repository, it is often necessary to accurately be positioned to its position.But it is existing
Localization method, precision is typically not capable of the requirement of work, especially when the location parameter and appearance for being necessary to precisely determine AGV
When state parameter, even more in this way.This is unfavorable for the operation and control of operator very much.
Therefore, there is an urgent need to the method and apparatus that one kind more accurately can carry out building figure and positioning in the prior art.
The content of background technology part is only the technology that inventor is known, not natural representative's state of the art.
Summary of the invention
For the prior art there are one or more of problem, the present invention provides a kind of pair of place and carries out the method for building figure, packet
Include: establishing or obtain the coordinate system in the place;Scan the place, obtain the picture of calibration point, the picture of position to be positioned,
And location parameter corresponding with the picture and attitude parameter;Picture, the position to be positioned based on the calibration point
Picture, the location parameter and the attitude parameter correct the location parameter and posture of the picture of the position to be positioned
Parameter.
According to an aspect of the present invention, the location parameter includes abscissa and ordinate, it preferably includes vertical coordinate, institute
Stating attitude parameter includes course angle, it preferably includes pitch angle and roll angle.
According to an aspect of the present invention, the step of amendment includes: to construct the set of tie point, each tie point packet
It includes a width picture, the location parameter corresponding with the width picture and the attitude parameter and whether the picture is right
Answer calibration point;Based on the set of the tie point, the location parameter and posture ginseng of the picture of the position to be positioned are corrected
Number.
According to an aspect of the present invention, wherein the modified step includes: to obtain distance from the set of the tie point
Two tie points no more than predetermined value are connected as one, establish the set of connection;To each of the set of the connection
Two included tie points of connection, calculate the connection confidence level between described two tie points, and filter out connection confidence level
It is connected higher than those of predetermined threshold, as building figure articulation set;Figure articulation set is built based on described, corrects the position to be positioned
The location parameter and attitude parameter for the picture set.
According to an aspect of the present invention, the amendment step further include: execute gradient decline in described build on figure articulation set
Method, wherein when executing the initialization step of gradient descent method, by the location parameter of the picture of the tie point of non-calibration point
Primary iteration parameter with attitude parameter as the gradient descent method.
According to an aspect of the present invention, wherein the amendment step further include: the gradient descent method is executed, until iteration becomes
Rate is lower than predetermined threshold.
According to an aspect of the present invention, wherein to some or all in calibration point, multiple picture collection is carried out, and obtain
Location parameter corresponding with each picture collection and attitude parameter.
According to an aspect of the present invention, this method further include: by the coordinate system, the picture, described undetermined of the calibration point
The picture of position position, the location parameter of the picture of the calibration point and attitude parameter and the revised position to be positioned
Picture location parameter and attitude parameter store into database or in file, establish map office.
According to an aspect of the present invention, the coordinate system is physical coordinates system.
According to an aspect of the present invention, the predetermined value is the half of the length or width of the picture.
The present invention also provides a kind of automatic guide vehicles for Image Acquisition, comprising: pedestal;Camera, the camera installation
On the pedestal and it is configured to that the picture in the region below the pedestal can be acquired;Measure component, the measurement component installation
On the pedestal, and be configured to can measure or calculate the location parameter of corresponding with the picture automatic guide vehicle and
Attitude parameter.
According to an aspect of the present invention, automatic guide vehicle further includes light emitting device, and the light emitting device is mounted on the pedestal
It goes up and is configured to that the region below the pedestal can be illuminated, acquire picture for the camera.
According to an aspect of the present invention, which further includes the control device being mounted on the pedestal, described to take the photograph
As head and the measurement component are all coupled to the control device, the control device, which is configured to control the trolley, marches to mark
Note point and position to be positioned are to acquire the picture of the mark point and the picture of the position to be positioned.
According to an aspect of the present invention, automatic guide vehicle further includes processing unit, the processing unit and the camera and
The measurement component coupling, and based on the picture and the location parameter and attitude parameter, correct the position to be positioned
The location parameter and attitude parameter for the picture set.
According to an aspect of the present invention, the processing unit corrects the picture of the position to be positioned by the following method
Location parameter and attitude parameter: constructing the set of tie point, and each tie point includes a width picture and the width picture
Whether the corresponding location parameter and the attitude parameter and the picture correspond to calibration point;From the collection of the tie point
In conjunction, two tie points of the distance no more than predetermined value are obtained as a connection, establish the set of connection;To the collection of the connection
Two included tie points of each of conjunction connection, calculate the connection confidence level between described two tie points, and filter
Connection confidence level is higher than the connection of those of predetermined threshold out, as building figure articulation set;It is executed in described build on figure articulation set
Gradient descent method is paid in advance until iteration change rate is lower than, wherein when executing the initialization step of gradient descent method, it will be non-
Primary iteration parameter of the location parameter and attitude parameter of the picture of the tie point of calibration point as the gradient descent method.
According to an aspect of the present invention, automatic guide vehicle further includes hood, and the hood is mounted on the pedestal, is used
The light that the light emitting device described in softening issues, the light emitting device are preferably installed around the hood.
According to an aspect of the present invention, wherein the measurement component is inertial navigation measurement component.
According to an aspect of the present invention, wherein the location parameter includes abscissa and ordinate, it preferably includes vertical to sit
Mark, the attitude parameter includes course angle, it preferably includes pitch angle and roll angle.
According to an aspect of the present invention, wherein the measurement component includes that laser SLAM measuring device and/or vision SLAM are surveyed
Measure device.
According to an aspect of the present invention, wherein the processing unit be configured to by the coordinate system, the calibration point picture,
The picture of the position to be positioned, the location parameter of the picture of the calibration point and attitude parameter and it is revised it is described to
The location parameter and attitude parameter of the picture of position location are stored into database or in file, establish map office.
The present invention also provides a kind of image acquisition and processing systems, comprising: automatic guide vehicle as described above;And processing unit,
The processing unit is coupled with the camera and the measurement component, and based on the picture and the location parameter with
And attitude parameter, correct the location parameter and attitude parameter of the picture.
According to an aspect of the present invention, wherein the processing unit is configured to build drawing method described in executable go up.
Figure and positioning system are built for automatic guide vehicle the present invention also provides a kind of, comprising: camera, the camera setting
At the image that can be acquired below the automatic guide vehicle;Light emitting device, the light emitting device is configured to can to illuminate described to be drawn automatically
The lower section of guide-car;Inertial navigation measures component, and the inertial navigation measurement component Configuration is that can measure the automatic guide vehicle
Location parameter and attitude parameter;Processing unit, the camera and inertial navigation measurement component are all coupled to the place
Device is managed, the control device is configured to correct the picture based on described image, the location parameter and attitude parameter
Location parameter and attitude parameter.
According to an aspect of the present invention, wherein the processing unit is configured to executable any one of such as claim 1-10
Described builds drawing method.
The present invention also provides the equipment that a kind of pair of place carries out building figure, comprising: is configured to establish or obtain the coordinate in the place
The device of system;Be configured to scan the place, obtain the picture of calibration point and the picture of multiple positions to be positioned and with institute
State the device of picture corresponding location parameter and attitude parameter;It is configured to based on the picture, the location parameter and the appearance
State parameter corrects the location parameter of the picture of the position to be positioned and the device of attitude parameter.
The present invention also provides a kind of localization methods, comprising: load obtains the ground obtained by method described in any of the above embodiments
Figure;Acquire or obtain the picture and location parameter corresponding with the picture and attitude parameter of position to be positioned;According to describedly
The picture of figure, retrieval and the position to be positioned is apart from nearest picture.
According to an aspect of the present invention, localization method further include: calculate the position to be positioned using phase correlation method
Confidence level, location parameter offset and attitude parameter between picture and the nearest picture of the distance deviate.
According to an aspect of the present invention, when the confidence level being calculated using phase correlation method is lower than preset value, abandoning should
Apart from nearest picture, the picture that and confidence level nearest with the picture of the position to be positioned distance is higher than preset value is retrieved again.
Detailed description of the invention
Attached drawing is used to provide further understanding of the present invention, and constitutes part of specification, with the embodiment of the present invention
It is used to explain the present invention, is not construed as limiting the invention together.In the accompanying drawings:
Fig. 1 is the flow chart according to an embodiment of the invention for building drawing method;
Fig. 2 is the schematic diagram of physical coordinates according to an embodiment of the invention;
Fig. 3 is the schematic diagram of logical coordinates according to an embodiment of the invention;
Fig. 4 is the schematic diagram of tie point according to an embodiment of the invention;
Fig. 5 is the schematic diagram of calibration point according to an embodiment of the invention;
Fig. 6 is the location parameter of amendment position picture to be positioned according to an embodiment of the invention and the method stream of attitude parameter
Cheng Tu;
Fig. 7 is the example being overlapped according to an embodiment of the present invention by the picture that phase correlation method calculates;
Fig. 8 is the schematic diagram of connection according to an embodiment of the invention;
Fig. 9 shows the map screenshot after completing physical coordinates system and logical coordinates system of pulse train mapping;
Figure 10 is the schematic diagram of the automatic guide vehicle according to an embodiment of the invention for Image Acquisition;
Figure 11 is the flow chart of localization method according to an embodiment of the invention;With
Figure 12 is the block diagram of computer program product according to an embodiment of the invention.
Specific embodiment
Hereinafter, certain exemplary embodiments are simply just described.As one skilled in the art will recognize that as,
Without departing from the spirit or scope of the present invention, described embodiment can be modified by various different modes.Therefore,
Attached drawing and description are considered essentially illustrative rather than restrictive.
In the description of the present invention, it is to be understood that, term " center ", " longitudinal direction ", " transverse direction ", " length ", " width ", " thickness
Under degree ", " go up ", " ", " preceding ", " afterwards ", " left side ", " right side ", " heavily fortified point directly interior ", " outside ", " up time in ", " level ", " top ", " bottom ", "
Needle ", " " orientation or positional relationship of equal instructions is to be based on the orientation or positional relationship shown in the drawings, and is merely for convenience of counterclockwise
The description present invention and simplified description, rather than the device or element of indication or suggestion meaning must have a particular orientation, with spy
Fixed orientation construction and operation, therefore be not considered as limiting the invention.In addition, term " first ", " second " are only used for
Purpose is described, relative importance is not understood to indicate or imply or implicitly indicates the quantity of indicated technical characteristic.
" first " is defined as a result, the feature of " second " can explicitly or implicitly include one or more feature.?
In description of the invention, " multiple " are meant that two or more, unless otherwise specifically defined.
In the description of the present invention, it should be noted that unless otherwise clearly defined and limited, term " installation ", " phase
Even ", " connection " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or be integrally connected: can
To be mechanical connection, it is also possible to be electrically connected or can mutually communicate;It can be directly connected, it can also be by between intermediary
It connects connected, can be the connection inside two elements or the interaction relationship of two elements.For the ordinary skill of this field
For personnel, the specific meanings of the above terms in the present invention can be understood according to specific conditions.
In the present invention unless specifically defined or limited otherwise, fisrt feature second feature its " upper " or it " under " can be with
Directly contacted including the first and second features, also may include the first and second features be not direct contact but by them it
Between other characterisation contact.Moreover, fisrt feature second feature " on ", " top " and " above " exist including fisrt feature
Right above second feature and oblique upper, or first feature horizontal height is merely representative of higher than second feature.Fisrt feature is second
Feature " under ", " lower section " and it is " following " including fisrt feature right above second feature and oblique upper, or be merely representative of first
Characteristic level height is less than second feature.
Following disclosure provides many different embodiments or example is used to realize different structure of the invention.For simplification
Disclosure of the invention is hereinafter described the component of specific examples and setting.Certainly, they are merely examples, and mesh
Do not lie in limitation the present invention.In addition, the present invention can in different examples repeat reference numerals and/or reference letter, it is this
Repetition is for purposes of simplicity and clarity, itself not indicate the relationship between discussed various embodiments and/or setting.
In addition, the present invention provides various specific techniques and material example, but those of ordinary skill in the art will be appreciated that
To the application of other techniques and/or the use of other materials.
Hereinafter, preferred embodiments of the present invention will be described with reference to the accompanying drawings, it should be understood that preferred embodiment described herein
Only for the purpose of illustrating and explaining the present invention and is not intended to limit the present invention.
Referring initially to Fig. 1 description it is according to a first embodiment of the present invention build drawing method 100, such as can be used for building place
Figure.
In step S101, the coordinate system in the place is established or obtained.The coordinate system can be physical coordinates system, be also possible to
Logical coordinates system of pulse train, this is within.The definition of coordinate system generally includes the position of origin, the side of XY reference axis
To etc..
Such as the place that can be positioned to needs measures, and establishes physical coordinates system, physical coordinates system is with common parasang
As linear module, for example, rice, decimetre, centimetre, permission is described with integer, decimal, fractional form, for example, 1 meter, 1 decimeter,
1 centimetre, 0.55 meter, 0.2 decimeter, 1.4 centimetres, half rice etc., coordinate system direction is generally parallel with building enclosure wall, or
It is parallel with all directions direction, it then follows the coordinate that the above principle is established is known as physical coordinates system in the present system, such as Fig. 2 institute
Show.
According to the coordinate system that business actual conditions are set, referred to as logical coordinates system of pulse train in the present system.Illustratively and not restrictive
, the difference of logical coordinates system of pulse train and physical coordinates system can for example be, logical coordinates system of pulse train is usually using integer as retouching
State, such as (1,2), (5,10), and coordinate system direction is not necessarily overlapped with physical coordinates system, and logical coordinates system of pulse train away from
From the not necessarily common physical unit of unit, but it is defined with actual job needs, such as A point, B point, C point in Fig. 3,
B point logical coordinates is (3,7), and A point logical coordinates is (3,8), and C point logical coordinates is (4,7), using lower left corner point as origin,
If each logical place spacing is 1.35 meters of calculating, the physical coordinates of A point are then (4.05,9.45).Therefore logical place and
Physical location can be completely the same, can also both there are certain conversion relations.Why there is the reason of logical place to be for
Facilitate planning service logic or conveniently build figure calculating, for example by taking shelf presence as an example, the position of shelf is sat with logic
Mark system position is saved, such as (3,7) position, if using physical location, just will appear above-mentioned (4.05,9.45)
Description, be unfavorable for very much the understanding and operation of operator, when if necessary to physical location, can be changed by conversion relation
It calculates, is to be called logical place spacing, and in the x-direction and the z-direction may not be used multiplied by a coefficient when generally conversion
Together.For example the shelf in warehouse are 1.3 meters * 1.3 meters, shelf spacing is 0.05 meter, so that it may which defining logical place spacing is
1.35 meters, if shelf are 1.2 meters * 1.0 meters, can define logical place spacing in the X-axis direction is 1.25 meters, Y-axis
It is 1.05 meters on direction, so that the equipment for carrying out physical positioning is needed to find corresponding physical location shelf.Above changes
Calculating is only conventional conversion mode, and there are also increasingly complex conversion methods, such as coordinate system rotation conversion, nonlinear conversion etc. to change
Calculation method, is not developed in details as space is limited herein.Description above with respect to logical coordinates system of pulse train is merely exemplary and not restrictive
's.Logical coordinates system of pulse train refers to the coordinate system set according to business actual conditions.Under idea of the invention, under logical coordinates system of pulse train
Location parameter is not limited to integer, can also have decimal.These are all within the scope of the present invention.If had built up in advance
Having got well the physical coordinates system in place, perhaps logical coordinates system of pulse train can be obtained from corresponding file or database.Hereafter
It is illustrated by taking physical coordinates system as an example.
In step S102, scan the place, obtain calibration point picture (about the definition of calibration point, seeing below), to
The picture (pictures of preferably multiple positions to be positioned) of position location and with the calibration point picture and position to be positioned
Set the corresponding location parameter of picture and attitude parameter.
The automatically guiding trolley for carrying equipment (will be described below) of the invention can be used for example, the place is swept
It retouches, obtains picture, calibration point picture and the corresponding location parameter of both above picture and attitude parameter of position to be positioned.
Here so-called position to be positioned can determine that e.g. automatic guide vehicle needs the position that reaches according to actual condition.
With reference to being described for Fig. 2, the location parameter is, for example, in some calibration point or the position for needing to position
(i.e. horizontal position, such as the coordinate or picture of center picture are a certain for abscissa and ordinate of the picture under physical coordinates system
The coordinate at a angle), naturally it is also possible to it is the horizontal distance and fore-and-aft distance relative to some basic point;The attitude parameter is for example
The angle of the picture of acquisition, such as the angle (i.e. course angle) relative to horizontal axis or the longitudinal axis.One according to the present invention preferred real
Example is applied, can also obtaining the parameters such as the corresponding pitch angle of the picture, roll angle, vertical height, (i.e. automatically guiding trolley obtains
Pitch angle, roll angle, vertical height when photo etc.).According to a preferred embodiment of the present invention, it can use of the invention
The inertial navigation measuring device that carries on automatically guiding trolley provides above-mentioned data.Inertial navigation measuring device is for example including wheel
Sub-encoders, accelerometer (1~3 axis), gyroscope (1~3 axis), magnetic flux transducer (1~3 axis), baroceptor and
Can feed back course angle, pitch angle, roll angle, horizontal position, upright position measuring device.Using wheel sub-encoders, accelerate
Spending the data that meter, gyroscope, magnetic flux transducer, baroceptor obtain can be obtained course angle (i.e. picture by calculating
Angle relative to trunnion axis or the longitudinal axis), pitch angle, roll angle, horizontal position, upright position, obtained above data is folded
Picture is added to, (picture, course angle (i.e. picture angle), pitch angle, roll angle, horizontal position (i.e. x-axis abscissa and y-axis are formed
Ordinate), upright position, if be calibration point) seven tuple datas combination, as shown in figure 4, in the present system be known as connect
Point continues figure input as after.Certainly, it will be appreciated by those skilled in the art that the tie point does not need the number for having whole
According to four metadata compositions for example including (whether picture course angle, horizontal position, is calibration point) can realize the present invention
Purpose.It should be noted that according to a preferred embodiment of the present invention, picture and corresponding position ginseng for calibration point
Several and attitude parameter, as much as possible can acquire, help more accurately to establish positioning map and more accurate positioning, adopt
When collection, it can repeatedly pass through the same area, multi collect, it is also possible that positioning map is more accurate.Certainly guarantor of the invention
Shield range is not limited to the coordinate under physical coordinates system, the coordinate being also possible under logical coordinates system of pulse train.
About calibration point, represents those coordinates and have already passed through exactly determined point.The point of the A as marked in Fig. 3, B point, C
Point, the coordinate of these points have already passed through confirmation, be it is artificially defined, priori.
An example of calibration point is shown in Fig. 5, wherein showing that calibration point A, its logical coordinates are (5,8), physical coordinates
For (3.75,4.10).Certainly in the present invention, calibration point is not limited to must simultaneously have logical coordinates and physical coordinates.It can be with
Multiple means are taken to identify and confirm calibration point.Such as one is there is cross hairs on image, marked thereon position, image are adopted
Calibration point and its position coordinates can be identified after collection;Also one is have encoded information, such as bar code or two dimension above
Program decoding can be used in code after image acquisition, decodes the position coordinates that the content come is exactly the calibration point.According to this
Invention one embodiment, since the coordinate of calibration point is prior by confirmation, so in step S102, calibration point picture
Location parameter of the location parameter using the calibration point, rather than the measured calibration point diagram come out of inertial navigation measuring device
The location parameter of piece.
In step S103, picture, the location parameter and the appearance of picture, the position to be positioned based on the calibration point
State parameter corrects the location parameter and attitude parameter of the picture of the position to be positioned.
For the picture of position to be positioned, location parameter and attitude parameter are such as to pass through inertia by being measured from
Navigation measuring device is measured and is obtained, and there are measurement error in operating condition at the scene, needs further to correct to improve its precision.
And the picture of calibration point can be used as good benchmark, for correct position to be positioned picture location parameter and posture ginseng
Number.
One embodiment of step S103 is described below with reference to Fig. 6.
In step S1031: constructing the set of tie point.As described above, each tie point, including (picture, course angle (i.e. picture
Angle), pitch angle, roll angle, horizontal position, upright position, if be calibration point) seven tuple datas combination, or including
Four metadata compositions of (whether picture course angle, horizontal position, is calibration point).Tie point is constructed using these tie points
Set.About the parameter of " whether being calibration point ", if occurring calibration point in the picture and normally obtaining the calibration point
Priori position parameter, the parameter be " being calibration point ";Otherwise the parameter is " non-calibration point ".Can also with logical zero or 1 come
It indicates.
In step S1032, articulation set is established and exported based on the Pointcut.Incoming junction set, according to even
The horizontal position for including in contact i.e. xy axial coordinate, is grouped operation, group to the principle of operation for example are as follows: the mark of two pictures
It infuses positional distance and is no more than predetermined value, such as no more than 50%, 30% or the 20% of picture length or width.For example,
The horizontal position tie point A is (0,0), and the horizontal position tie point B is (5,0), then the distance of A to B is 5, if picture size
It can partner for 10*10 then A, B just meet the standard no more than 50% picture size, in the present system such group
Conjunction is called connection, and each connection includes two tie points, exports the whole connections that can make up, is known as connection collection in the present system
It closes.
In step S1033: inputting articulation set generated, each of articulation set is connected, extract connection the inside
Two tie points A, B, for the convenience of description, tie point A is known as datum mark, tie point B is known as abutment points, is original with datum mark
Point is offset with abutment points, using datum mark picture and abutment points picture as input, such as executes phase correlation method, is connected
Connect confidence level (conf) (characterizing similarity degree between the two), the direction x relative displacement (delta_x), the relative displacement of the direction y
(delta_y), relative angle (theta) is rotated, by 4 yuan of (conf, delta_x, delta_y, theta) composition in this system
Group is known as cross correlation results, is put into corresponding connection and saves, and confidence level is greater than certain threshold value (such as 10, it will be appreciated that mutual for this
The probability that correlated results occurs at random be less than 10 Sigma position of normal distribution represented by probability value) connection retain, output
Filtered confidence level is greater than the threshold value, new articulation set containing cross correlation results, is known as building figure connection in the present system
Set.Connection confidence level above is the output of phase correlation method, is the sharp journey by calculating phase correlation method value peak value
Degree, the distribution near spike calculates in other words, it is assumed that distribution is normal state, then being aware of peak value and mean value, so that it may calculate
Confidence level out.Cross correlation results are what the relatedness computation according to phase correlation method above, by calculating two pictures came out.
During executing phase correlation method, it is related to crosspower spectrum calculating, using crosspower spectrum function, can obtains in different positions
Cross-correlation under the conditions of shifting is horizontal, it is assumed that the horizontal Normal Distribution of cross-correlation can calculate normal state by statistical method
The relevant parameter of distribution is divided by using the parameter and maximum cross-correlation numerical value, can calculate connection confidence level.
According to one embodiment, figure articulation set of founding a capital is without there are two the connections that point is calibration point.
As shown in fig. 7, surface layer is picture A in figure, bottom is picture B, illustrates the overlapping region of two pictures, which is logical
Cross what phase relevant calculation came out.Such as the cross correlation results that two pictures A and B are calculated in Fig. 7 are as follows: confidence level 131.542, x
Direction relative displacement 33.4, the direction y phase-shifted 10.7 rotate 0.3 degree of angle.
Fig. 8 shows the schematic diagram of connection, including datum mark and abutment points.
In step S1034: executing gradient descent method on building figure articulation set, correct the position of the picture of the position to be positioned
Parameter and attitude parameter.Wherein according to one embodiment, the transverse and longitudinal coordinate and angle of calibration point picture are constant, gradient adjustment be with
For non-calibration point image parameters as variable, demarcating picture may be considered constant.Or it builds figure articulation set and can be defined as not
Containing there are two the connection that point is all calibration point, because adjusting so nonsensical, calibration point should not be natively adjusted, and be solved
It will not be solved when gradient.Majorized function is for example as shown in formula 1:
Formula 1:
Formula 2:
Formula 3:
Formula 4:
Formula 5:
Formula 6:
Formula 7:
Wherein N expression, which is built figure articulation set and had altogether, contains N number of connection, and i indicates i-th built in figure articulation set connection, AiTable
Show the datum mark of i-th of connection, BiIndicate the abutment points of i-th of connection, RiIndicate the cross correlation results of i-th of connection,Table
Show the course angle of datum mark,Indicate the course angle of abutment points,Indicate the rotation relative angle in cross correlation results, gθ
(Ai,Bi) it can be understood as the angle difference of datum mark and abutment points under inertial navigation measurement component, gθ(Ai,Bi)-uθ(Ri)
The angle difference that can be understood as under inertial navigation measurement component is (mutual with the difference of the rotation relative angle in cross correlation results
Closing the rotation angle in result is exactly the theta calculated by phase correlation method, this value characterizes abutment points picture and needs
Rotating how many angles could be parallel with datum mark picture), wherein fθFor course angle weighting function, for indicating that course angle is fitted
In the process, weighted of the different tie point attribute (such as: calibration point and non-calibration point) in map iteration is (as one
Example, the weight being generally designated a little is bigger, such as 1000, and the weight of non-calibration point is smaller, such as 1);vθFor cross-correlation knot
The weighting function of angle difference in fruit, for indicate different connection attribute (such as: connection, mark between two non-calibration points
Connection between fixed point and non-calibration point) weight of cross correlation results angle (if the connection of two non-calibration points, is changed
Degree should be it is reciprocity, be called in other words it is impartial because the status of two codes is equal, but calibration point and non-calibration
Point variation degree is not reciprocity, the variation degree of non-calibration point, noticeably greater than calibration point, therefore to be controlled by weight.It can
To give weight according to the actual situation).According to a preferred embodiment, the connection of calibration point non-for two, weight are desirable
1, according to same horizontal adjustment;For demarcating the connection with non-calibration point, weight can also take 1, because calibration point is constant,
It cannot participate in gradient calculating, it is believed that gradient is constant.If it is considered that if being finely adjusted to calibration point, calibration point with it is non-
The weight ratio of the connection of calibration point can be up to 99 to 1.
Remainder formula description is similar with above description, and the X axis direction difference calculated separately under inertial navigation measurement component is same
Y direction difference under difference and inertial navigation the measurement component of X-direction relative displacement in cross correlation results is the same as mutual
The difference of the Y direction relative displacement in result is closed, above-mentioned weighting function can be according to service conditions, algorithm mating situation tune
It is whole.Indicate the x-axis coordinate of datum mark,Indicate the x-axis coordinate of abutment points,Indicate the direction the x phase in cross correlation results
To displacement, gx(Ai,Bi) it can be understood as the direction the x coordinate difference of datum mark and abutment points under inertial navigation measurement component,
gx(Ai,Bi)-ux(Ri) can be understood as inertial navigation measurement component under the direction x coordinate difference similarities and differences cross correlation results in the side x
To the difference of relative displacement, (direction the x relative displacement in cross correlation results is exactly to be calculated by phase correlation method
Delta_x, this value characterize abutment points picture and need to translate how much distance could be aligned with datum mark picture in the x-direction),
Middle fxFor x-axis weighting function, for indicating in x-axis coordinate fit procedure, different tie point attributes (such as: calibration point and non-
Calibration point) (as an example, the weight being generally designated a little is bigger, such as 1000, non-for weighted in map iteration
The weight of calibration point is smaller, such as 1);vxAdjustment weight for cross correlation results relative to x-axis relative displacement, such as can be with
Value 1.
Indicate the y-axis coordinate of datum mark,Indicate the y-axis coordinate of abutment points,Indicate the direction the y phase in cross correlation results
To displacement, gy(Ai,Bi) it can be understood as the direction the y coordinate difference of datum mark and abutment points under inertial navigation measurement component, gy
(Ai,Bi)-uy(Ri) can be understood as inertial navigation measurement component under the direction y coordinate difference similarities and differences cross correlation results in the direction y
(direction the y relative displacement in cross correlation results is exactly the delta_ calculated by phase correlation method to the difference of relative displacement
Y, this value characterize abutment points picture and need to translate how many distances in the y-direction and could be aligned with datum mark picture), wherein fyFor
X axis weighting function, for indicating in y-axis coordinate fit procedure, different tie point attributes (such as: calibration point and non-calibration
Point) (as an example, the weight being generally designated a little is bigger, such as 1000, non-calibration for weighted in map iteration
The weight of point is smaller, such as 1);vyAdjustment weight for cross correlation results relative to y-axis relative displacement, such as can be with value
1。
λ1、λ2、λ3Weight of theta, x, y variable quantity in final fitting result is respectively indicated, some scenes are for theta's
Variation is more sensitive, and λ can be turned up1.According to a preferred embodiment, λ1、λ2、λ3It is 1.
Independent variable in formula 1 isBy each independent variable to formula 1 into
Row derivation has obtained the direction of each independent variable gradient decline, or perhaps one group of gradient set, for carrying out gradient decline
The initialization step for executing gradient descent method, using the location parameter of inertial navigation mark and attitude parameter as the first of picture
Beginning position.Input one of gradient descent method is last iteration set, and one is gradient, and one is step-length, and wherein gradient is logical
It crosses and 1 derivation of formula is obtained, iteration initial sets are assigned for example, by the location parameter and attitude parameter of inertial navigation mark
Value, step-length is fixed or variable.
After gradient and iteration initial sets have been determined, step length decline is carried out to gradient direction, Lai Liyong formula 1 carries out excellent
Change.Customized step length algorithm, this system fixed step size preferably can be used to carry out gradient decline as needed.It repeats, until
Iteration change rate is less than given threshold, and this system such as given threshold is 0.1%.Change rate is, for example, the value that last computation obtains
The difference for the value being calculated with current iteration is exactly change rate divided by the value of last time.Finally obtain each picture basic point
The physical coordinates and attitude parameter of (such as central point), location parameter and posture as revised position to be positioned are joined
Number.
Note that during executing gradient descent method on building figure articulation set, location parameter and the posture ginseng of calibration point picture
Number is without variation.
The x-axis coordinate, y-axis coordinate and course angle of picture have been used in execution gradient descent method described above.According to this hair
A bright preferred embodiment, also may include the corresponding vertical coordinate of picture, pitch angle and roll angle, especially in place height
In the case where low injustice, this is very helpful.These are all within the scope of the present invention.
According to a preferred embodiment of the present invention, to some or all in calibration point, multiple picture collection is carried out, and obtain
Take location parameter corresponding with each picture collection and attitude parameter.By the picture multi collect to calibration point, may make repeatedly
It is more accurate for result, increase the number of connection.
According to a preferred embodiment of the present invention, further includes: by the coordinate system, the picture, described undetermined of the calibration point
The picture of position position, the location parameter of the picture of the calibration point and attitude parameter and the revised position to be positioned
Picture location parameter and attitude parameter store into database or in file, establish map.According to a preferred embodiment,
The set of the connection and/or the figure articulation set of building are stored into the database or file simultaneously, as map
A part.Fig. 9 shows the diagram for the map established according to the present invention.
Preferably, desk checking and fine tuning in addition are carried out for the map after iteration, just completes physical coordinates system and logic is sat
The stable mapping of system is marked, subsequent positioning is used for.
Below with reference to the accompanying drawings 10 the automatic guide vehicle 10 in accordance with another embodiment of the present invention for Image Acquisition is described.Such as figure
Shown in 10, the internal part of automatic guide vehicle 10 is shown, and the components such as its shell are omitted for clarity.Automatically
Guide car 10 includes: pedestal 6;Light emitting device 5-2, the light emitting device are mounted on the pedestal and are configured to illuminate described
Region below pedestal;Camera 5-3, the camera are mounted on the pedestal and are configured to that pedestal lower zone can be acquired
Picture, such as the picture in region illuminated by the light emitting device;Component 3 is measured, the measurement component is mounted on the base
On seat, and it is configured to can measure or calculate the location parameter of the automatic guide vehicle corresponding with the picture and posture ginseng
Number.
Driving wheel 1 is mounted on base 6, including motor, retarder, encoder, and wherein motor provides driving force, retarder amplification
Driving force, encoder is for obtaining motor rotational angle, it is hereby achieved that the horizontal position of automatic guide vehicle or driving wheel.
Driving wheel 2 cooperates with driving wheel 1 completes motion control.The measurement component 3 is, for example, inertial navigation measuring device, can be provided
Instantaneous velocity, instantaneous angular, instantaneous position one or several, such as abscissa, ordinate, vertical coordinate, course angle, bow
The elevation angle and roll angle.According to one embodiment of present invention, the encoder of the driving wheel is also possible to the measurement component 3
A part.Control device 4 is mounted on the pedestal 6, with measurement component 3 and camera 5-3 coupling.The control device 4 is matched
It is set to the control trolley and marches to mark point and position to be positioned to acquire the picture of the mark point and the position to be positioned
The picture set, and the camera 5-3 and the measurement component 3 can be synchronized, so that while camera acquires picture,
The measurement component 3 can measure the location parameter and attitude parameter of the trolley, that is, obtain corresponding with the picture
Location parameter and attitude parameter.
The camera 5-3 is, for example, lower view camera, is formed together image-taking device together with light emitting device 5-2 and hood 5-1
5, wherein camera 5-3 is installed on the base, under illuminating for obtaining automatic guide vehicle lower images, light emitting device 5-2
Depending on camera shooting area.Hood 5-1 is mounted on the pedestal, for the light of light emitting device to be become more soft,
Prevent the generation of reflective phenomenon.The light emitting device is preferably installed around the hood.
According to a preferred embodiment of the present invention, automatic guide vehicle 10 further includes processing unit (not shown), the processing dress
It sets and is coupled with the camera 5-3 and the measurement component 3, to receive picture and the measurement component measurement of the camera acquisition
Location parameter and attitude parameter correct described undetermined and based on the picture and the location parameter and attitude parameter
The location parameter and attitude parameter of the picture of position position.It will be appreciated by those skilled in the art that processing unit can integrate in institute
State in automatic guide vehicle 10, can also physically be separated with the automatic guide vehicle, by it is wired or wirelessly with
Other component is communicated.These are within.
According to a preferred embodiment of the present invention, the processing unit corrects the position to be positioned by the following method
The location parameter and attitude parameter of picture:
The set of tie point is constructed, each tie point includes a width picture, the position corresponding with the width picture
Whether parameter and the attitude parameter and the picture correspond to calibration point;
From the set of the tie point, two tie points of the distance no more than predetermined value are obtained as a connection, establish connection
Set;
Two included tie points of each of set to connection connection, calculate between described two tie points
Confidence level is connected, and filters out connection confidence level and is higher than the connection of those of predetermined threshold, as building figure articulation set;
Gradient descent method is executed in described build on figure articulation set, is paid in advance until iteration change rate is lower than, wherein executing
When the initialization step of gradient descent method, using the location parameter of the picture of the tie point of non-calibration point and attitude parameter as
The primary iteration parameter of the gradient descent method.Specific calculating process is as shown in formula 1-7.
According to a preferred embodiment of the present invention, the measurement component is inertial navigation measurement component, the location parameter packet
Include abscissa and ordinate, it preferably includes vertical coordinate, the attitude parameter include course angle, it preferably includes pitch angle and
Roll angle.
According to a preferred embodiment of the present invention, the measurement component includes laser SLAM measuring device and/or vision SLAM
Measuring device.
According to a preferred embodiment of the present invention, the processing unit is configured to the figure of the coordinate system, the calibration point
Piece, the picture of the position to be positioned, the calibration point picture location parameter and attitude parameter and revised described
The location parameter and attitude parameter of the picture of position to be positioned are stored into database or in file, establish map.
The present invention also provides a kind of image acquisition and processing systems, comprising: automatic guide vehicle as described above;And processing unit,
The processing unit communicates with the camera and the measurement component, and is configured to based on the picture and institute's rheme
Parameter and attitude parameter are set, the location parameter and attitude parameter of the picture are corrected.Wherein the processing unit is not for example
It is arranged on the automatic guide vehicle.
Wherein the processing unit is for example configured to can be performed builds drawing method 100 as described above.
Figure and positioning system are built for automatic guide vehicle the present invention also provides a kind of, comprising: camera, the camera setting
At the image that can be acquired below the automatic guide vehicle;Light emitting device, the light emitting device is configured to can to illuminate described to be drawn automatically
The lower section of guide-car;Inertial navigation measures component, and the inertial navigation measurement component Configuration is that can measure the automatic guide vehicle
Location parameter and attitude parameter;Processing unit, the camera and inertial navigation measurement component are all coupled to the processing
Device is based on described image, the location parameter and attitude parameter, corrects the location parameter and attitude parameter of the picture.
Wherein the processing unit is for example configured to can be performed builds drawing method 100 as described above.
The present invention also provides the equipment that a kind of pair of place carries out building figure, comprising: is configured to establish or obtain the coordinate in the place
The device of system;Be configured to scan the place, obtain the picture of calibration point and the picture of multiple positions to be positioned and with institute
State the device of picture corresponding location parameter and attitude parameter;It is configured to based on the picture, the location parameter and the appearance
State parameter corrects the location parameter of the picture of the position to be positioned and the device of attitude parameter.
Based on the map established by method 100, the present invention also provides a kind of localization methods 200.It is described below with reference to Figure 11
Localization method 200 according to the present invention.
As shown in figure 11, in step S201, load or the map for obtaining 100 acquisitions by means of the present invention, such as can lead to
It crosses load or reads map file or database to carry out.
In step S202, acquire or obtain position to be positioned picture and location parameter corresponding with the picture and posture ginseng
Number.Such as in AGV operational process, while acquiring picture, location parameter corresponding with the picture and attitude parameter are measured.
In step S203, in the map, the picture of retrieval and the position to be positioned is apart from nearest picture
According to a preferred embodiment of the present invention, the localization method 200 further include: using phase correlation method calculate it is described to
Confidence level, location parameter offset and attitude parameter between the picture of position location and the nearest picture of the distance deviate.
According to a preferred embodiment of the present invention, when the confidence level being calculated using phase correlation method is lower than preset value,
This is abandoned apart from nearest picture, being retrieved again with the picture of the position to be positioned distance (does not include recently the picture being dropped
Inside) and confidence level be higher than preset value picture.When finding distance recently and confidence level is higher than the picture of preset value, inspection is utilized
The Pictures location that rope arrives, in addition the offset of phase correlation method, so that it may which the then location parameter for obtaining picture to be positioned updates
The position location of equipment positions successfully.After positioning successfully, the position retrieved next time is exactly this position location.
Figure 12 is the block diagram for the computer program product 900 arranged according at least some embodiments of the invention.Signaling bearer is situated between
Matter 902 may be implemented as or including computer-readable medium 906, computer recordable media 908, computer communication media
910 or their combination, configurable processing unit is stored to execute the volume of all or some during being previously described
Cheng Zhiling 904.These instructions may include the one or more for example handled as follows for executing one or more processors
Executable instruction: establishing or obtains the coordinate system in the place;The place is scanned, the picture of calibration point, position to be positioned are obtained
The picture and location parameter corresponding with the picture and attitude parameter set;It is picture based on the calibration point, described undetermined
Picture, the location parameter and the attitude parameter of position position correct the position ginseng of the picture of the position to be positioned
Several and attitude parameter.
Although the detailed description of front elaborates device and/or method by using block diagram, flow chart and/or example
Various examples, but such block diagram, flow chart and/or example include one or more functions and/or operation, art technology
Personnel will be understood that, each function and/or the extensive hardware of operation usable range in such block diagram, flow chart or example, soft
Part, firmware or their substantially any combination individually and/or are jointly implemented.In one example, described herein
It several parts of theme can be via specific integrated circuit (ASIC), field programmable gate array (FPGA), digital signal processor
(DSP) or other integrated formats are implemented.However, it would be recognized by those skilled in the art that disclosed herein exemplary one
A little aspects can equally be implemented in integrated circuits entirely or in part, be implemented as on one or more computers
One or more computer programs of operation are (for example, the one or more journeys run in one or more computer systems
Sequence), the one or more programs for being implemented as running on the one or more processors are (for example, at one or more micro- places
The one or more programs run on reason device), it is implemented as firmware, or be implemented as their substantially any combination,
And according to the disclosure, designs circuit and/or write will be in the ripe of those skilled in the art for the code of software and/or firmware
Practice in technical ability.For example, if the user determine that speed and precision be it is most important, then main hardware and/or firmware may be selected in user
Medium;If flexibility be it is most important, main software embodiment may be selected in user;Alternatively, again alternatively,
The a certain combination of hardware, software and/or firmware may be selected in user.
In addition, it will be appreciated by persons skilled in the art that the mechanism of theme described herein being capable of conduct in a variety of manners
Program product distribution, and the illustrated examples of theme described herein are regardless of for actually realizing the signaling bearer of the distribution
How the concrete type of medium is all suitable for.The example of signal bearing medium includes but is not limited to following: recordable-type media,
Floppy disk, hard disk drive, compact disk (CD), digital video disc (DVD), number tape, computer storage etc.;And transmission
The medium of type, such as number and/or analogue communication medium are (for example, fiber optic cables, waveguide, wired communications links, wireless communication
Link etc.).
It would be recognized by those skilled in the art that describing device and/or method in mode set forth herein, making thereafter
It by the such device and/or method integration is common in the art into data processing system with engineering practice.
That is, at least part of device and/or method described herein can be integrated into data via the experiment of reasonable amount
In processing system.It would be recognized by those skilled in the art that typical data processing system generally comprises one of the following or more
It is a: system unit housing, video display devices, the memory of such as volatile and non-volatile memory, such as microprocessor
With the processor of digital signal processor, the computational entity of such as operating system, driver, graphic user interface and application
One or more interactive devices of program, such as Trackpad or touch screen, and/or including feedback loop and control motor (for example,
For sensing the feedback of position and/or the feedback of rate;For moving and/or adjusting the control motor of component and/or amount) control system
System.Typical data processing system can be implemented using any suitable commercially available component, such as be common in data calculating communication
And/or those of in network calculations communication system.
Finally, it should be noted that the foregoing is only a preferred embodiment of the present invention, it is not intended to restrict the invention, although
Present invention has been described in detail with reference to the aforementioned embodiments, for those skilled in the art, still can be right
Technical solution documented by foregoing embodiments is modified or equivalent replacement of some of the technical features.It is all
Within the spirit and principles in the present invention, any modification, equivalent replacement, improvement and so on should be included in protection of the invention
Within the scope of.
Claims (29)
1. a kind of pair of place carries out the method for building figure, comprising:
Establish or obtain the coordinate system in the place;
The place is scanned, the picture of calibration point, the picture of position to be positioned and position corresponding with picture ginseng are obtained
Several and attitude parameter;
Picture, the location parameter and the attitude parameter of picture, the position to be positioned based on the calibration point, amendment
The location parameter and attitude parameter of the picture of the position to be positioned.
2. the method as described in claim 1, wherein the location parameter includes abscissa and ordinate, it preferably includes vertical
Coordinate, the attitude parameter include course angle, it preferably includes pitch angle and roll angle.
3. such as method of any of claims 1-2, wherein the modified step includes:
The set of tie point is constructed, each tie point includes a width picture, the position corresponding with the width picture
Whether parameter and the attitude parameter and the picture correspond to calibration point;
Based on the set of the tie point, the location parameter and attitude parameter of the picture of the position to be positioned are corrected.
4. method as claimed in claim 3, wherein the modified step includes:
From the set of the tie point, two tie points of the distance no more than predetermined value are obtained as a connection, establish connection
Set;
Two included tie points of each of set to connection connection, calculate between described two tie points
Confidence level is connected, and filters out connection confidence level and is higher than the connection of those of predetermined threshold, as building figure articulation set;
Figure articulation set is built based on described, corrects the location parameter and attitude parameter of the picture of the position to be positioned.
5. method as claimed in claim 4, wherein the amendment step further include:
Gradient descent method is executed in described build on figure articulation set, wherein when executing the initialization step of gradient descent method, it will
The location parameter and attitude parameter of the picture of the tie point of non-calibration point are joined as the primary iteration of the gradient descent method
Number.
6. method as claimed in claim 5, wherein the amendment step further include: the gradient descent method is executed, until repeatedly
It is lower than predetermined threshold for change rate.
7. the method as described in claim 1-6, wherein multiple picture collection is carried out to some or all in calibration point,
And obtain location parameter corresponding with each picture collection and attitude parameter.
8. such as method of any of claims 1-7, further includes: by the coordinate system, the picture of the calibration point, institute
State the picture of position to be positioned, the location parameter of the picture of the calibration point and attitude parameter and revised described undetermined
The location parameter and attitude parameter of the picture of position position are stored into database or in file, establish map, preferably will be described
The set of connection and/or the figure articulation set of building are stored into the database or file.
9. such as method of any of claims 1-8, wherein the coordinate system is physical coordinates system.
10. method as claimed in claim 4, wherein the predetermined value is the half of the length or width of the picture.
11. a kind of automatic guide vehicle for Image Acquisition, comprising:
Pedestal;
Camera, the camera are mounted on the pedestal and are configured to that the picture in the region below the pedestal can be acquired;
Component is measured, the measurement component is mounted on the pedestal, and is configured to can measure or be calculated corresponding with the picture
The automatic guide vehicle location parameter and attitude parameter.
12. automatic guide vehicle as claimed in claim 11 further includes light emitting device, the light emitting device is mounted on the pedestal
It goes up and is configured to that the region below the pedestal can be illuminated, acquire picture for the camera.
13. the automatic guide vehicle as described in claim 11 or 12 further includes the control device being mounted on the pedestal, described
Camera and the measurement component are all coupled to the control device, and the control device, which is configured to control the trolley, to be marched to
Mark point and position to be positioned are to acquire the picture of the mark point and the picture of the position to be positioned.
14. automatic guide vehicle as claimed in claim 13 further includes processing unit, the processing unit and the camera and
The measurement component coupling, and based on the picture and the location parameter and attitude parameter, correct the position to be positioned
The location parameter and attitude parameter for the picture set.
15. automatic guide vehicle as claimed in claim 14, described in the processing unit is configured to correct by the following method
The location parameter and attitude parameter of the picture of position to be positioned:
The set of tie point is constructed, each tie point includes a width picture, the position corresponding with the width picture
Whether parameter and the attitude parameter and the picture correspond to calibration point;
From the set of the tie point, two tie points of the distance no more than predetermined value are obtained as a connection, establish connection
Set;
Two included tie points of each of set to connection connection, calculate between described two tie points
Confidence level is connected, and filters out connection confidence level and is higher than the connection of those of predetermined threshold, as building figure articulation set;
Gradient descent method is executed in described build on figure articulation set, until iteration change rate is lower than predetermined threshold, wherein executing
When the initialization step of gradient descent method, using the location parameter of the picture of the tie point of non-calibration point and attitude parameter as
The primary iteration parameter of the gradient descent method.
16. the automatic guide vehicle as described in any one of claim 11-15 further includes hood, the hood is mounted on
On the pedestal, for the light that light emitting device described in softening issues, the light emitting device is preferably installed around the hood.
17. the automatic guide vehicle as described in any one of claim 11-16, wherein the measurement component is inertial navigation measurement
Component.
18. the automatic guide vehicle as described in any one of claim 11-17, wherein the location parameter includes abscissa and indulges
Coordinate, it preferably includes vertical coordinate, the attitude parameter include course angle, it preferably includes pitch angle and roll angle.
19. the automatic guide vehicle as described in any one of claim 11-18, wherein the measurement component includes that laser SLAM is surveyed
Measure device and/or vision SLAM measuring device.
20. the automatic guide vehicle as described in claims 14 or 15, wherein the processing unit is configured to the coordinate system, institute
State the picture of calibration point, the picture of the position to be positioned, the calibration point picture location parameter and attitude parameter and
The location parameter and attitude parameter of the picture of the revised position to be positioned are stored into database or in file, establish ground
Figure preferably stores the set of the connection and/or the figure articulation set of building into the database or file.
21. a kind of image acquisition and processing system, comprising:
Automatic guide vehicle as claimed in claim 11;With
Processing unit, the processing unit are coupled with the camera and the measurement component, and are based on the picture, Yi Jisuo
Location parameter and attitude parameter are stated, the location parameter and attitude parameter of the picture are corrected.
22. image acquisition and processing system as claimed in claim 20, wherein the processing unit is configured to executable right
It is required that building drawing method described in any one of 1-10.
23. a kind of build figure and positioning system for automatic guide vehicle, comprising:
Camera, the camera are arranged to that the image below the automatic guide vehicle can be acquired;
Light emitting device, the light emitting device are configured to that the lower section of the automatic guide vehicle can be illuminated;
Inertial navigation measures component, and the inertial navigation measurement component Configuration is the location parameter that can measure the automatic guide vehicle
And attitude parameter;
Processing unit, the camera and inertial navigation measurement component are all coupled to the processing unit, the control dress
Set the location parameter for being configured to that the picture is corrected based on described image, the location parameter and attitude parameter and posture ginseng
Number.
24. figure and positioning system are built as claimed in claim 22, wherein the processing unit is configured to can be performed as right is wanted
It asks and builds drawing method described in any one of 1-10.
25. a kind of pair of place carries out the equipment for building figure, comprising:
It is configured to establish or obtain the device of the coordinate system in the place;
Be configured to scan the place, obtain the picture of calibration point and the picture of multiple positions to be positioned and with the figure
The device of piece corresponding location parameter and attitude parameter;
It is configured to correct the picture of the position to be positioned based on the picture, the location parameter and the attitude parameter
The device of location parameter and attitude parameter.
26. a kind of localization method, comprising:
Load obtains the map obtained by method of any of claims 1-10;
Acquire or obtain the picture and location parameter corresponding with the picture and attitude parameter of position to be positioned;According to describedly
The picture of figure, retrieval and the position to be positioned is apart from nearest picture.
27. localization method as claimed in claim 26, further includes: calculate the figure of the position to be positioned using phase correlation method
Confidence level, location parameter offset and attitude parameter between piece and the nearest picture of the distance deviate.
28. localization method as claimed in claim 26, wherein when the confidence level being calculated using phase correlation method is lower than pre-
If abandoning this when value apart from nearest picture, retrieving and be higher than with the picture of the position to be positioned apart from nearest and confidence level again
The picture of preset value.
29. a kind of computer readable storage medium, including the computer executable instructions being stored thereon, the executable instruction
Implement such as the method for any of claims 1-10 for building figure when being executed by processor.
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2019/075741 WO2019154435A1 (en) | 2018-05-31 | 2019-02-21 | Mapping method, image acquisition and processing system, and positioning method |
JP2019531677A JP6977921B2 (en) | 2018-05-31 | 2019-02-21 | Mapping method, image collection processing system and positioning method |
PCT/CN2019/084185 WO2019154444A2 (en) | 2018-05-31 | 2019-04-25 | Mapping method, image acquisition and processing system, and positioning method |
JP2019531456A JP7083472B2 (en) | 2018-05-31 | 2019-04-25 | Map construction method, image collection processing system and positioning method |
Applications Claiming Priority (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810551792 | 2018-05-31 | ||
CN201820865300 | 2018-05-31 | ||
CN201810551792X | 2018-05-31 | ||
CN201820865300X | 2018-05-31 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110006420A true CN110006420A (en) | 2019-07-12 |
CN110006420B CN110006420B (en) | 2024-04-23 |
Family
ID=
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1497244A (en) * | 2002-09-27 | 2004-05-19 | 佳能株式会社 | Information processing method and information processing deivce |
US20040168148A1 (en) * | 2002-12-17 | 2004-08-26 | Goncalves Luis Filipe Domingues | Systems and methods for landmark generation for visual simultaneous localization and mapping |
CN103955550A (en) * | 2012-11-12 | 2014-07-30 | 洛克威尔自动控制技术股份有限公司 | Method and device for computer aided design of man-machine interface cartoon graphic element |
CN104835173A (en) * | 2015-05-21 | 2015-08-12 | 东南大学 | Positioning method based on machine vision |
CN105389819A (en) * | 2015-11-13 | 2016-03-09 | 武汉工程大学 | Robust semi-calibrating down-looking image epipolar rectification method and system |
CN105444741A (en) * | 2015-12-17 | 2016-03-30 | 南京航空航天大学 | Double view window based route characteristic identifying, deviation measuring, and accurate positioning method |
CN106289285A (en) * | 2016-08-20 | 2017-01-04 | 南京理工大学 | Map and construction method are scouted by a kind of robot associating scene |
CN106714110A (en) * | 2017-01-19 | 2017-05-24 | 深圳大学 | Auto building method and system of Wi-Fi position fingerprint map |
CN106767854A (en) * | 2016-11-07 | 2017-05-31 | 纵目科技(上海)股份有限公司 | mobile device, garage map forming method and system |
CN107146255A (en) * | 2017-04-05 | 2017-09-08 | 纵目科技(上海)股份有限公司 | Panoramic picture error calibration method and device |
CN107392848A (en) * | 2017-06-14 | 2017-11-24 | 江西科技师范大学 | Panoramic image display method and device |
CN107607110A (en) * | 2017-07-29 | 2018-01-19 | 刘儿兀 | A kind of localization method and system based on image and inertial navigation technique |
CN211668521U (en) * | 2018-05-31 | 2020-10-13 | 上海快仓智能科技有限公司 | Automatic guide vehicle for image acquisition and processing system |
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1497244A (en) * | 2002-09-27 | 2004-05-19 | 佳能株式会社 | Information processing method and information processing deivce |
US20040168148A1 (en) * | 2002-12-17 | 2004-08-26 | Goncalves Luis Filipe Domingues | Systems and methods for landmark generation for visual simultaneous localization and mapping |
CN103955550A (en) * | 2012-11-12 | 2014-07-30 | 洛克威尔自动控制技术股份有限公司 | Method and device for computer aided design of man-machine interface cartoon graphic element |
CN104835173A (en) * | 2015-05-21 | 2015-08-12 | 东南大学 | Positioning method based on machine vision |
CN105389819A (en) * | 2015-11-13 | 2016-03-09 | 武汉工程大学 | Robust semi-calibrating down-looking image epipolar rectification method and system |
CN105444741A (en) * | 2015-12-17 | 2016-03-30 | 南京航空航天大学 | Double view window based route characteristic identifying, deviation measuring, and accurate positioning method |
CN106289285A (en) * | 2016-08-20 | 2017-01-04 | 南京理工大学 | Map and construction method are scouted by a kind of robot associating scene |
CN106767854A (en) * | 2016-11-07 | 2017-05-31 | 纵目科技(上海)股份有限公司 | mobile device, garage map forming method and system |
CN106714110A (en) * | 2017-01-19 | 2017-05-24 | 深圳大学 | Auto building method and system of Wi-Fi position fingerprint map |
CN107146255A (en) * | 2017-04-05 | 2017-09-08 | 纵目科技(上海)股份有限公司 | Panoramic picture error calibration method and device |
CN107392848A (en) * | 2017-06-14 | 2017-11-24 | 江西科技师范大学 | Panoramic image display method and device |
CN107607110A (en) * | 2017-07-29 | 2018-01-19 | 刘儿兀 | A kind of localization method and system based on image and inertial navigation technique |
CN211668521U (en) * | 2018-05-31 | 2020-10-13 | 上海快仓智能科技有限公司 | Automatic guide vehicle for image acquisition and processing system |
Also Published As
Publication number | Publication date |
---|---|
CN211668521U (en) | 2020-10-13 |
JP2020530598A (en) | 2020-10-22 |
CN110189331A (en) | 2019-08-30 |
CN110189331B (en) | 2022-08-05 |
JP6977921B2 (en) | 2021-12-08 |
JP2020532775A (en) | 2020-11-12 |
JP7083472B2 (en) | 2022-06-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110189331A (en) | Build drawing method, image acquisition and processing system and localization method | |
KR102627352B1 (en) | Methods for calibrating an augmented reality device | |
CN110057352A (en) | A kind of camera attitude angle determines method and device | |
CN104395692B (en) | Three-dimensional measurement method, device, system and image processing apparatus | |
CN107869960B (en) | A kind of aircraft wing deformation measuring device, installation method and test method | |
US9584768B2 (en) | Information processing apparatus, information processing method and computer-readable storage medium | |
CN105791811B (en) | A kind of three-dimensional test mark version and its design and forming method | |
CN108020827A (en) | It is moved into as platform alignment | |
WO2010052558A2 (en) | System and method for the precise integration of virtual objects to interactive panoramic walk-through applications | |
JP5030953B2 (en) | Method and system for determining the relative position of a first object with respect to a second object, a corresponding computer program and a corresponding computer-readable recording medium | |
CN109598781A (en) | The method of puppet 3D frame is obtained from 2D bounding box by regression analysis and uses the learning device and test device of this method | |
CN110310304A (en) | Monocular vision builds figure and localization method, device, storage medium and mobile device | |
CN110793548B (en) | Navigation simulation test system based on virtual-real combination of GNSS receiver hardware in loop | |
CN110645980B (en) | Indoor and outdoor integrated positioning and navigation method and system thereof | |
US20190287257A1 (en) | Method and system for measuring the distance to remote objects | |
CN104913775B (en) | Measurement method, unmanned plane localization method and the device of unmanned plane distance away the ground | |
CN107796370A (en) | For obtaining the method, apparatus and mobile mapping system of conversion parameter | |
CN102721374B (en) | Planar sub-aperture splicing method based on weighted least square method | |
CN107063187A (en) | A kind of height of tree rapid extracting method of total powerstation and unmanned plane image association | |
CN110231832A (en) | Barrier-avoiding method and obstacle avoidance apparatus for unmanned plane | |
JP2019144153A (en) | Reproduction method, reproduction device, and reproduction program of electric wire shape, and evaluation method, evaluation device, and evaluation program of point group accuracy | |
CN109813338A (en) | Fly calibration method, device, electronic equipment and the storage medium of control gyroscope | |
CN115900697B (en) | Object motion trail information processing method, electronic equipment and automatic driving vehicle | |
CN108700883A (en) | Control method and unmanned plane | |
CN109959501A (en) | A kind of optical sensor elements of interior orientation and distort test macro and method |
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 |