CN111950308A - Two-dimensional code positioning method for AGV - Google Patents
Two-dimensional code positioning method for AGV Download PDFInfo
- Publication number
- CN111950308A CN111950308A CN202010681125.0A CN202010681125A CN111950308A CN 111950308 A CN111950308 A CN 111950308A CN 202010681125 A CN202010681125 A CN 202010681125A CN 111950308 A CN111950308 A CN 111950308A
- Authority
- CN
- China
- Prior art keywords
- dimensional code
- positioning
- agv
- pyramid
- picture
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000007781 pre-processing Methods 0.000 claims abstract description 10
- 238000004458 analytical method Methods 0.000 claims abstract description 5
- 238000012937 correction Methods 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 7
- 238000012882 sequential analysis Methods 0.000 claims description 3
- 238000012790 confirmation Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 14
- 238000010586 diagram Methods 0.000 description 7
- 238000012216 screening Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 238000001914 filtration Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/10009—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation sensing by radiation using wavelengths larger than 0.1 mm, e.g. radio-waves or microwaves
- G06K7/10019—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation sensing by radiation using wavelengths larger than 0.1 mm, e.g. radio-waves or microwaves resolving collision on the communication channels between simultaneously or concurrently interrogated record carriers.
- G06K7/10079—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation sensing by radiation using wavelengths larger than 0.1 mm, e.g. radio-waves or microwaves resolving collision on the communication channels between simultaneously or concurrently interrogated record carriers. the collision being resolved in the spatial domain, e.g. temporary shields for blindfolding the interrogator in specific directions
- G06K7/10089—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation sensing by radiation using wavelengths larger than 0.1 mm, e.g. radio-waves or microwaves resolving collision on the communication channels between simultaneously or concurrently interrogated record carriers. the collision being resolved in the spatial domain, e.g. temporary shields for blindfolding the interrogator in specific directions the interrogation device using at least one directional antenna or directional interrogation field to resolve the collision
- G06K7/10099—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation sensing by radiation using wavelengths larger than 0.1 mm, e.g. radio-waves or microwaves resolving collision on the communication channels between simultaneously or concurrently interrogated record carriers. the collision being resolved in the spatial domain, e.g. temporary shields for blindfolding the interrogator in specific directions the interrogation device using at least one directional antenna or directional interrogation field to resolve the collision the directional field being used for pinpointing the location of the record carrier, e.g. for finding or locating an RFID tag amongst a plurality of RFID tags, each RFID tag being associated with an object, e.g. for physically locating the RFID tagged object in a warehouse
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/002—Measuring arrangements characterised by the use of optical techniques for measuring two or more coordinates
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/10544—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation by scanning of the records by radiation in the optical part of the electromagnetic spectrum
- G06K7/10821—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation by scanning of the records by radiation in the optical part of the electromagnetic spectrum further details of bar or optical code scanning devices
- G06K7/10861—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation by scanning of the records by radiation in the optical part of the electromagnetic spectrum further details of bar or optical code scanning devices sensing of data fields affixed to objects or articles, e.g. coded labels
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Health & Medical Sciences (AREA)
- Toxicology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Theoretical Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Automation & Control Theory (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention relates to an improvement of AGV trolley positioning technology, in particular to a two-dimension code positioning method for an AGV trolley, which enables the AGV to quickly position and identify a two-dimension code under a complex working condition and to obtain the current trolley posture without depending on a direction sensor, and comprises the following steps: step one, auxiliary positioning graphs are respectively arranged at four top corners of the two-dimensional code; step two, positioning the two-dimensional code: when the AGV trolley runs to the two-dimensional code position, a special camera carried by the AGV trolley is used for shooting a two-dimensional code picture of the ground, and picture preprocessing is carried out on the two-dimensional code picture; thirdly, positioning the auxiliary positioning graph of the preprocessed picture, accurately positioning according to the auxiliary positioning graph of the two-dimensional code, and analyzing the content of the two-dimensional code; step four: and according to the accurate positioning result, performing X-axis and Y-axis deviation analysis on the two-dimensional code image, and calculating the angle of the two-dimensional code relative to the acquisition camera.
Description
Technical Field
The invention relates to an improvement of an AGV trolley positioning technology, in particular to a two-dimensional code positioning method for an AGV trolley.
Background
One of the core technologies of an AGV (Automated guided vehicle) is a navigation technology, and common navigation technologies include a magnetic navigation technology, a laser navigation technology, an inertial navigation technology, a visual navigation technology, an RFID positioning navigation technology, and the like. Wherein, the magnetic navigation technology is stable but the change and the laying of the path are not easy; laser navigation techniques are accurate but the equipment is expensive; the inertial navigation is greatly influenced by the environment and devices; the visual navigation technology is limited to the reason of algorithm, and has limited adaptability to complex working conditions; the RFID positioning navigation technology needs a specific label, and the price is high;
two-dimensional code navigation has the reasons of accurate positioning, low cost, convenient path modification and the like, and is more and more favored by people.
In a conventional two-dimensional code navigation mode, two-dimensional codes need to be laid at intervals of a certain distance or at specific positions on a moving path of an AGV. In the moving process of the AGV, the current position is positioned by identifying the content of the two-dimensional code, and the current attitude is acquired by utilizing inertial navigation with magnetic pole induction or directly selecting a high-precision course angle sensor. After the current position and posture are located, the AGV can start to the next target point.
The two-dimension code recognition speed of the two-dimension code navigation is limited by the positioning speed and the recognition precision of the two-dimension code; the gesture information recognition is limited by factors such as the accuracy of the sensor and magnetic interference, so the application technology of two-dimensional code navigation in the prior art still needs to be improved.
Disclosure of Invention
The technical problem to be solved by the invention is to overcome the existing defects, and provide a two-dimension code positioning method for an AGV (automatic guided vehicle), so that the AGV can quickly position and identify a two-dimension code under a complex working condition, and the current posture of the AGV can be obtained without depending on a direction sensor.
In order to solve the technical problems, the invention provides the following technical scheme: a two-dimensional code positioning method for AGV navigation comprises the following steps: step one, auxiliary positioning graphs are respectively arranged at four top corners of the two-dimensional code;
step two, positioning the two-dimensional code: when the AGV trolley runs to the two-dimensional code position, a special camera carried by the AGV trolley is used for shooting a two-dimensional code picture of the ground, and picture preprocessing is carried out on the two-dimensional code picture;
thirdly, positioning the auxiliary positioning graph of the preprocessed picture, accurately positioning according to the auxiliary positioning graph of the two-dimensional code, and analyzing the content of the two-dimensional code;
step four: and according to the accurate positioning result, performing X-axis and Y-axis deviation analysis on the two-dimensional code image, and calculating the angle of the two-dimensional code relative to the acquisition camera so as to correct the driving direction of the current AGV.
Preferably, the auxiliary positioning patterns are two arbitrary axisymmetric patterns, when the symmetric patterns are placed, the symmetric axis is coaxial with the diagonal line of the two-dimensional code, and the symmetric patterns of the auxiliary positioning are tangent to the extension line of the adjacent side of the two-dimensional code.
Preferably, the auxiliary positioning graph is nested by N graphs, and the nesting principle is homocentroid.
Preferably, the image preprocessing refers to establishing an image pyramid model to divide an original image into 4 layers, and positioning the image through a template matching algorithm.
Preferably, carrying out shape-based full-resolution template matching on the pyramid upper layer; tracking matching is carried out on the lower layer of the pyramid from top to bottom to obtain a candidate region; and (4) carrying out candidate positioning graph proportion confirmation on the bottom pyramid to obtain an accurate candidate area.
Preferably, during accurate positioning, vertical gray projection is carried out on the accurate candidate area, the obtained projection waveform is analyzed to obtain the L edge and the railway line of the two-dimensional code, and four-point sequential analysis of the two-dimensional code is obtained.
Preferably, after four-point sequentiality is determined, calculating a decoding reference digit according to railway line projection, taking the decoding reference digit as a decoding priority reference basis, and arranging a code source ROI (region of interest); and sending the ROI sequence into a decoding protocol, and obtaining the content of the two-dimensional code through an error correction algorithm.
Preferably, the angle of the two-dimensional code relative to the acquisition camera is accurately calculated for the candidate corresponding to the successfully decoded Data matrix code, and the result is output and used for posture rectification of the AGV.
The invention has the beneficial effects that: according to the two-dimension code positioning method for the AGV trolley, the two-dimension codes with the auxiliary icons arranged on the four vertex angles are placed in the pasting area with the right-angle auxiliary grooves. The two-dimensional code image is subjected to pyramid image matching tracking from top to bottom, the candidate region of the image can be quickly positioned, and the accurate two-dimensional code candidate region can be obtained through candidate region entry screening and sub-pixel positioning. And (3) performing gray projection on the accurate candidate region, analyzing an L edge and a railway line, dividing reference digits of the two-dimensional code, and selecting four sequential candidate regions which are not more than the ROI region of the code source on a projection waveform, and realizing quick and accurate identification of the two-dimensional code by using an error correction algorithm. In addition, the direction of the current trolley relative to the absolute coordinate can be analyzed by calculating the deviation of the accurate candidate area which is successfully decoded in the X and Y directions, and the direction result can be used as posture rectification and direction navigation.
Drawings
FIG. 1 is an auxiliary positioning graph of an embodiment of a two-dimensional code positioning method for an AGV according to the present invention;
FIG. 2 is a graphical illustration of an auxiliary positioning for the two-dimensional code positioning method for an AGV according to the present invention;
FIG. 3 is a schematic diagram of a two-dimensional code with an auxiliary positioning pattern according to an embodiment of the present invention;
FIG. 4 is a flowchart of a two-dimensional code positioning method for AGV navigation according to an embodiment of the present invention;
FIG. 5 is a schematic diagram illustrating AGV attitude calculation according to an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
A two-dimensional code positioning method for an AGV comprises the following steps: step one, auxiliary positioning graphs are respectively arranged at four top corners of the two-dimensional code;
step two, positioning the two-dimensional code: when the AGV trolley runs to the two-dimensional code position, a special camera carried by the AGV trolley is used for shooting a two-dimensional code picture of the ground, and picture preprocessing is carried out on the two-dimensional code picture;
thirdly, positioning the auxiliary positioning graph of the preprocessed picture, accurately positioning according to the auxiliary positioning graph of the two-dimensional code, and analyzing the content of the two-dimensional code;
step four: and according to the accurate positioning result, performing X-axis and Y-axis deviation analysis on the two-dimensional code image, and calculating the angle of the two-dimensional code relative to the acquisition camera so as to correct the driving direction of the current AGV.
The auxiliary positioning patterns are two arbitrary axisymmetric patterns, when the symmetric patterns are placed, the symmetric axis is coaxial with the diagonal line of the two-dimensional code, and the symmetric patterns of the auxiliary positioning are tangent to the adjacent side extension line of the two-dimensional code.
The auxiliary positioning graph is nested by N graphs, and the nesting principle is homocentroid.
The auxiliary graphs are positioned, the auxiliary graphs are nested by N graphs, and the nesting principle is homocentroid. The picture preprocessing comprises the following processes: generating a pyramid image by adopting a 2 x 2 mean filtering method; calculating a vector diagram corresponding to each layer of pyramid images by adopting a 3 x 3Prewit operator; establishing circular matching templates which correspond to the pyramids of each layer and take the radius as the reference;
specifically, the pattern matching template is related to the selected auxiliary positioning pattern, and only N nested concentric circles are used as the example.
The positioning of the auxiliary positioning graph comprises the following processes:
at the highest layer of the pyramid, using the circular templates of the corresponding layer to perform shape-based full-resolution template matching;
bringing the information obtained by the highest pyramid matching into the lower pyramid tracking matching, and performing necessary screening;
the ratio of candidate circular positioning patterns is confirmed at the bottom layer of the pyramid, and the concentric circle ratio can be determined as the positioning pattern if the concentric circle ratio is satisfied;
in particular, a similarity calculation method for template matching of positioning-assisted positioning patterns (haar-like features) is proposed. By way of example, N nested concentric circles are arranged according to a pattern to be positioned, as shown in fig. 1, and the variance between the variance (the variance of pixel gray levels inside a and B) within each layer of concentric circles and the variance between layers (the variance of average gray levels between a and B) of concentric circles are calculated as the final similarity. And traversing the top-level image of the search pyramid by setting respective thresholds of the two variances to obtain the candidate position. And after candidate positions are searched for in the top image of the pyramid, performing shape-based template matching tracking search on the lower layer of the pyramid until a positioning graph is found in the bottom layer of the pyramid.
The accurate positioning of the two-dimension code candidate comprises the following processes: arranging and combining all candidates passing the verification of the positioning graph, and connecting outer boundary points in the connecting line direction once to form quadrilateral candidates; screening the side length proportion and the deformation angle of the candidate quadrangle, and performing sub-pixel positioning on the screened quadrangle to obtain an accurate two-dimensional code candidate area; the analyzing of the two-dimensional code content comprises the following processes: carrying out vertical gray projection with proper width in the accurate quadrilateral candidate region to obtain a corresponding waveform; analyzing an L edge and a railway line of the two-dimensional code based on the winning waveform, namely analyzing the four-point sequence of the two-dimensional code; after four-point sequentiality is determined, calculating a decoding reference digit according to the side projection of the railway line, and taking the decoding reference digit as a decoding priority reference basis; according to the reference digit of the two-dimensional code, sequentially more than four candidate code source ROI areas are selected; sending the obtained ROI sequence into a Datamatrix decoding protocol, and calculating by an error correction algorithm to obtain a character string result;
the image preprocessing refers to establishing an image pyramid model to divide an original image into 4 layers, and positioning the image through a template matching algorithm.
Tracking and matching the pyramid from top to bottom to obtain a candidate region; and carrying out template matching based on the shape on the lower layer of the pyramid to obtain an accurate candidate region.
And performing vertical gray projection on the accurate candidate area during accurate positioning, and analyzing the obtained projection waveform to obtain the L edge and the railway line of the two-dimensional code to obtain four-point sequential analysis of the two-dimensional code.
After the four-point sequentiality is determined, calculating a decoding reference digit according to railway line projection, taking the decoding reference digit as a decoding priority reference basis, and arranging a code source ROI area; and sending the ROI sequence into a decoding protocol, and obtaining the content of the two-dimensional code through an error correction algorithm.
And accurately calculating the angle of the two-dimensional code relative to the acquisition camera for the candidate corresponding to the successfully decoded Data matrix code, and outputting the result, wherein the result is used for posture correction of the AGV.
The picture preprocessing comprises the following processes:
generating a pyramid image by adopting a 2 x 2 mean filtering method;
calculating a vector diagram corresponding to each layer of pyramid images by adopting a 3 x 3Prewit operator;
establishing circular matching templates which correspond to the pyramids of each layer and take the radius as the reference;
specifically, the pattern matching template is related to the selected auxiliary positioning pattern, and only N nested concentric circles are used as the example.
The positioning of the auxiliary positioning graph comprises the following processes:
at the highest layer of the pyramid, using the circular templates of the corresponding layer to perform shape-based full-resolution template matching;
bringing the information obtained by the highest pyramid matching into the lower pyramid tracking matching, and performing necessary screening;
the ratio of candidate circular positioning patterns is confirmed at the bottom layer of the pyramid, and the concentric circle ratio can be determined as the positioning pattern if the concentric circle ratio is satisfied;
in particular, a similarity calculation method for template matching of positioning-assisted positioning patterns (haar-like features) is proposed. By way of example, N nested concentric circles are arranged according to a pattern to be positioned, as shown in fig. 1, and the variance between the variance (the variance of pixel gray levels inside a and B) within each layer of concentric circles and the variance between layers (the variance of average gray levels between a and B) of concentric circles are calculated as the final similarity. And traversing the top-level image of the search pyramid by setting respective thresholds of the two variances to obtain the candidate position. And after candidate positions are searched for in the top image of the pyramid, performing shape-based template matching tracking search on the lower layer of the pyramid until a positioning graph is found in the bottom layer of the pyramid.
The accurate positioning of the two-dimension code candidate comprises the following processes:
arranging and combining all candidates passing the verification of the positioning graph, and connecting outer boundary points in the connecting line direction once to form quadrilateral candidates;
screening the side length proportion and the deformation angle of the candidate quadrangle, and performing sub-pixel positioning on the screened quadrangle to obtain an accurate two-dimensional code candidate area;
the analyzing of the two-dimensional code content comprises the following processes:
carrying out vertical gray projection with proper width in the accurate quadrilateral candidate region to obtain a corresponding waveform;
analyzing an L edge and a railway line of the two-dimensional code based on the winning waveform, namely analyzing the four-point sequence of the two-dimensional code;
after four-point sequentiality is determined, calculating a decoding reference digit according to the side projection of the railway line, and taking the decoding reference digit as a decoding priority reference basis;
according to the reference digit of the two-dimensional code, sequentially more than four candidate code source ROI areas are selected;
sending the obtained ROI sequence into a Data matrix decoding protocol, and calculating by an error correction algorithm to obtain a character string result;
the calculation of the angle of the two-dimensional code relative to the acquisition camera comprises the following processes:
and accurately calculating the angle of the two-dimensional code relative to the acquisition camera for the candidate corresponding to the successfully decoded Data matrix code, and outputting the result, wherein the result can be used for posture correction of the AGV.
When the method is specifically implemented, the four vertex angles of the two-dimensional code are respectively provided with the auxiliary icons, and the specific mode is as follows: FIG. 2 lists some auxiliary positioning icons, which are axisymmetric graphs and are concentrically nested with the centroid as an anchor point; fig. 3 is an example of the positioning icon in fig. 2, in which the symmetry axis of the graph is coaxial with the diagonal line of the two-dimensional code, and the triangle graph is tangent to the extension line of the adjacent side of the two-dimensional code.
Above-mentioned picture sticker that is printed with two-dimensional code can be changed according to actual demand, for example when the route of AGV dolly needs to be changed or cancel, can tear the two-dimensional code at any time and change, the two-dimensional code paste the department need have with absolute coordinate axis equidirectional right angle groove, can not change the two-dimensional code position when making things convenient for the two-dimensional code to change, rectifies to provide the guarantee for hou mian gesture.
With the example shown in fig. 3, according to the flowchart of the positioning method shown in fig. 4, the two-dimensional code positioning method for AGV navigation according to the embodiment of the present invention includes the following steps:
and S1, acquiring the image of the two-dimensional code when the AGV runs to the position of the two-dimensional code.
And S2, preprocessing the image.
In one embodiment of the invention, a 2 x 2 mean filtering method is used to generate pyramid images; calculating a vector diagram corresponding to each layer of pyramid images by adopting a 3 x 3Prewit operator; establishing circular matching templates which correspond to the pyramids of each layer and take the radius as the reference;
particularly, when the auxiliary positioning graph is complex, the vector diagram can also adopt 8-direction or more-direction sobel operators to calculate a smoother vector diagram, and the loss of details of the auxiliary positioning graph can be effectively reduced.
And S3, positioning the auxiliary positioning graph.
In one embodiment of the invention, starting from the pyramid highest level, a circular template of the corresponding level is used for shape-based full-resolution template matching; bringing the information obtained by the highest pyramid matching into the lower pyramid tracking matching, and performing necessary screening; the ratio of candidate circular positioning patterns is confirmed at the bottom layer of the pyramid, and the concentric circle ratio can be determined as the positioning pattern if the concentric circle ratio is satisfied;
in particular, a similarity calculation method (haar-like feature) for template matching of positioning auxiliary positioning patterns is provided. N nested concentric circles are arranged according to a graph to be positioned, and the variance between the variance (the variance of pixel gray levels inside A and B) in each layer of concentric circles and the variance between layers (the variance of average gray levels between A and B) of concentric circles are calculated to be final similarity. And traversing the top-level image of the search pyramid by setting respective thresholds of the two variances to obtain the candidate position. And after candidate positions are searched for in the top image of the pyramid, performing shape-based template matching tracking search on the lower layer of the pyramid until a positioning graph is found in the bottom layer of the pyramid.
And S4, acquiring two-dimension code candidates and accurately positioning.
Specifically, all candidates passing through the verification of the positioning graph are arranged and combined, and outer boundary points in the connecting line direction are sequentially connected to form quadrilateral candidates; screening the side length proportion and the deformation angle of the candidate quadrangle, and performing sub-pixel positioning on the screened quadrangle to obtain an accurate two-dimensional code candidate area;
and S5, analyzing the two-dimensional code content.
Specifically, vertical gray level projection with proper width is carried out in a quadrilateral accurate candidate region to obtain a corresponding waveform; analyzing an L edge and a railway line of the two-dimensional code based on the projection waveform, namely analyzing the four-point sequence of the two-dimensional code; after four-point sequentiality is determined, calculating a decoding reference digit according to the side projection of the railway line, and taking the decoding reference digit as a decoding priority reference basis; according to the reference digit of the two-dimensional code, sequentially more than four candidate code source ROI areas are selected; sending the obtained ROI sequence into a Data matrix decoding protocol, and calculating by an error correction algorithm to obtain a character string result;
and S6, calculating the angle of the two-dimensional code relative to the acquisition camera.
Specifically, as shown in fig. 5, for the candidate corresponding to the successfully decoded Data matrix code, the X-axis and Y-axis deviation analysis of the two-dimensional code image is performed, and the angle of the two-dimensional code with respect to the acquisition camera is calculated to correct the driving direction of the current camera (car). Generally, the size of theta x and theta y perpendicular to the ground of a camera is equal to the size of theta y by default, if the situation strictly requires the attitude angle, a three-dimensional model can be introduced, and a Z axis is additionally arranged according to the difference between the theta x and the theta y, so that the angle calculation precision is improved.
The above embodiments are preferred embodiments of the present invention, and those skilled in the art can make variations and modifications to the above embodiments, therefore, the present invention is not limited to the above embodiments, and any obvious improvements, substitutions or modifications made by those skilled in the art based on the present invention are within the protection scope of the present invention.
Claims (8)
1. A two-dimensional code positioning method for an AGV (automatic guided vehicle) is characterized by comprising the following steps of: the method comprises the following steps: step one, auxiliary positioning graphs are respectively arranged at four top corners of the two-dimensional code;
step two, positioning the two-dimensional code: when the AGV trolley runs to the two-dimensional code position, a special camera carried by the AGV trolley is used for shooting a two-dimensional code picture of the ground, and picture preprocessing is carried out on the two-dimensional code picture;
thirdly, positioning the auxiliary positioning graph of the preprocessed picture, accurately positioning according to the auxiliary positioning graph of the two-dimensional code, and analyzing the content of the two-dimensional code;
step four: and according to the accurate positioning result, performing X-axis and Y-axis deviation analysis on the two-dimensional code image, and calculating the angle of the two-dimensional code relative to the acquisition camera so as to correct the driving direction of the current AGV.
2. The two-dimensional code positioning method for the AGV according to claim 1, wherein: the auxiliary positioning patterns are two arbitrary axisymmetric patterns, when the symmetric patterns are placed, the symmetric axis is coaxial with the diagonal line of the two-dimensional code, and the symmetric patterns of the auxiliary positioning are tangent to the adjacent side extension line of the two-dimensional code.
3. The two-dimensional code positioning method for the AGV according to claim 2, wherein: the auxiliary positioning graph is nested by N graphs, and the nesting principle is homocentroid.
4. The two-dimensional code positioning method for the AGV according to claim 1, wherein: the image preprocessing refers to establishing an image pyramid model to divide an original image into 4 layers, and positioning the image through a template matching algorithm.
5. The two-dimensional code positioning method for the AGV according to claim 4, wherein: carrying out shape-based full-resolution template matching on the pyramid upper layer; tracking matching is carried out on the lower layer of the pyramid from top to bottom to obtain a candidate region; and (4) carrying out candidate positioning graph proportion confirmation on the bottom pyramid to obtain an accurate candidate area.
6. The two-dimensional code positioning method for the AGV according to claim 1, wherein: and performing vertical gray projection on the accurate candidate area during accurate positioning, and analyzing the obtained projection waveform to obtain the L edge and the railway line of the two-dimensional code to obtain four-point sequential analysis of the two-dimensional code.
7. The two-dimensional code positioning method for the AGV according to claim 6, wherein: after the four-point sequentiality is determined, calculating a decoding reference digit according to railway line projection, taking the decoding reference digit as a decoding priority reference basis, and arranging a code source ROI area; and sending the ROI sequence into a decoding protocol, and obtaining the content of the two-dimensional code through an error correction algorithm.
8. The two-dimensional code positioning method for an AGV according to claim 7, wherein: and accurately calculating the angle of the two-dimensional code relative to the acquisition camera for the candidate corresponding to the successfully decoded Data matrix code, and outputting the result, wherein the result is used for posture correction of the AGV.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010681125.0A CN111950308A (en) | 2020-07-15 | 2020-07-15 | Two-dimensional code positioning method for AGV |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010681125.0A CN111950308A (en) | 2020-07-15 | 2020-07-15 | Two-dimensional code positioning method for AGV |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111950308A true CN111950308A (en) | 2020-11-17 |
Family
ID=73341101
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010681125.0A Pending CN111950308A (en) | 2020-07-15 | 2020-07-15 | Two-dimensional code positioning method for AGV |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111950308A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113420580A (en) * | 2021-07-14 | 2021-09-21 | 北京紫光青藤微系统有限公司 | Method and device for positioning auxiliary locator for two-dimensional code, two-dimensional code scanning equipment and storage medium |
CN114510953A (en) * | 2022-01-20 | 2022-05-17 | 深圳市墨甲智能科技有限责任公司 | Position acquisition method and device, electronic equipment and computer readable storage medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109740395A (en) * | 2018-12-17 | 2019-05-10 | 江苏理工学院 | The two dimensional code localization method and system that deep learning is combined with SHAPE DETECTION |
CN110705322A (en) * | 2019-08-30 | 2020-01-17 | 江苏理工学院 | Two-dimensional code positioning method for AGV navigation |
CN110879593A (en) * | 2019-11-11 | 2020-03-13 | 江苏理工学院 | Positioning method, reading method, positioning system and positioning device |
-
2020
- 2020-07-15 CN CN202010681125.0A patent/CN111950308A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109740395A (en) * | 2018-12-17 | 2019-05-10 | 江苏理工学院 | The two dimensional code localization method and system that deep learning is combined with SHAPE DETECTION |
CN110705322A (en) * | 2019-08-30 | 2020-01-17 | 江苏理工学院 | Two-dimensional code positioning method for AGV navigation |
CN110879593A (en) * | 2019-11-11 | 2020-03-13 | 江苏理工学院 | Positioning method, reading method, positioning system and positioning device |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113420580A (en) * | 2021-07-14 | 2021-09-21 | 北京紫光青藤微系统有限公司 | Method and device for positioning auxiliary locator for two-dimensional code, two-dimensional code scanning equipment and storage medium |
CN114510953A (en) * | 2022-01-20 | 2022-05-17 | 深圳市墨甲智能科技有限责任公司 | Position acquisition method and device, electronic equipment and computer readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP3407294B1 (en) | Information processing method, device, and terminal | |
CN107782305B (en) | Mobile robot positioning method based on digital letter recognition | |
CN107727104B (en) | Positioning and map building air navigation aid, apparatus and system while in conjunction with mark | |
CN108489486B (en) | Two-dimensional code and vision-inertia combined navigation system and method for robot | |
Ahn et al. | Circular coded target for automation of optical 3D-measurement and camera calibration | |
US20160246302A1 (en) | Methods and systems for mobile-agent navigation | |
CN110530372B (en) | Positioning method, path determining device, robot and storage medium | |
CN111486849B (en) | Mobile visual navigation method and system based on two-dimensional code road sign | |
CN111598952B (en) | Multi-scale cooperative target design and online detection identification method and system | |
CN106251353A (en) | Weak texture workpiece and the recognition detection method and system of three-dimensional pose thereof | |
CN104197899A (en) | Mobile robot location method and system | |
CN208937054U (en) | Position Fixing Navigation System and robot based on two dimensional code | |
US9336595B2 (en) | Calibration device, method for implementing calibration, and camera for movable body and storage medium with calibration function | |
CN106650873A (en) | Identification code, and automatic guiding vehicle rapid navigation method and system | |
CN108007388A (en) | A kind of turntable angle high precision online measuring method based on machine vision | |
US20100111364A1 (en) | Method of creating three-dimensional model and object recognizing device | |
CN111950308A (en) | Two-dimensional code positioning method for AGV | |
CN110096920A (en) | A kind of high-precision high-speed positioning label and localization method towards visual servo | |
CN115609591B (en) | Visual positioning method and system based on 2D Marker and compound robot | |
JPH08136220A (en) | Method and device for detecting position of article | |
CN109711503A (en) | A kind of robot localization method and device | |
Wang et al. | Autonomous landing of multi-rotors UAV with monocular gimbaled camera on moving vehicle | |
CN110503096A (en) | The bar section tagging scheme and character picture antidote of horizontal double-flag point | |
CN112085708B (en) | Method and equipment for detecting defects of straight line edges in outer contour of product | |
Goronzy et al. | QRPos: Indoor positioning system for self-balancing robots based on QR codes |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201117 |