CN107967437A - A kind of image processing method, device and computer-readable recording medium - Google Patents
A kind of image processing method, device and computer-readable recording medium Download PDFInfo
- Publication number
- CN107967437A CN107967437A CN201711143788.1A CN201711143788A CN107967437A CN 107967437 A CN107967437 A CN 107967437A CN 201711143788 A CN201711143788 A CN 201711143788A CN 107967437 A CN107967437 A CN 107967437A
- Authority
- CN
- China
- Prior art keywords
- agv
- mark
- image processing
- coding
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- 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
- G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
- G06K7/1404—Methods for optical code recognition
- G06K7/1408—Methods for optical code recognition the method being specifically adapted for the type of code
- G06K7/1417—2D bar codes
-
- 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
- G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
- G06K7/1404—Methods for optical code recognition
- G06K7/1439—Methods for optical code recognition including a method step for retrieval of the optical code
- G06K7/1456—Methods for optical code recognition including a method step for retrieval of the optical code determining the orientation of the optical code with respect to the reader and correcting therefore
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
Abstract
The invention discloses a kind of image processing method, comprise the following steps：The image information of AGV vehicle bodies mark is obtained, determines the direction of the mark；The fisrt feature information of coding region in described image information is obtained, wherein, the fisrt feature information includes colouring information；Based on the coding of coding region described in the fisrt feature acquisition of information, the sequence number of the AGV is determined.The invention also discloses a kind of image processing apparatus and computer-readable recording medium.The present invention realizes the coding of the color acquisition coding region of coding region in Direct Recognition image, the sequence number of quick definite AGV, so as to improve the convenience of image procossing and the accuracy rate of image recognition.
Description
Technical field
The present invention relates to technical field of image processing, more particularly to a kind of image processing method, device and computer-readable
Storage medium.
Background technology
AGV (Automatic Guided Vehicle automatically guiding trolleys) is that navigation system is housed by power of battery
Unmanned automated handling vehicle.The distinguishing feature of AGV is unmanned, and using automatic guiding system, AGV can be not required to
In the case of wanting artificial pilotage, along predetermined route automatic running, cargo is transported to destination from starting point automatically.
In the AGV trolley identifying schemes of view-based access control model, segmentation scheme is identified using color, and the scheme of the type is easy
Influenced by ambient light, it is higher to camera imaging quality requirement, and with the increase that need to identify trolley quantity, identify the face used
Color is more and more, also has segmentation scheme using the mark on the method identification trolley based on machine learning, for example, on identification trolley
Digital number, certain difficulty is brought to recognizer.These schemes complexity in image procossing is cumbersome, and identifies accurately
Rate is low.
The above is only used to facilitate the understanding of the technical scheme, and is not represented and is recognized that the above is existing skill
Art.
The content of the invention
It is a primary object of the present invention to provide a kind of image processing method, device and computer-readable recording medium, purport
The technical problem that complexity is cumbersome, recognition accuracy is low when solving in image procossing.
To achieve the above object, the present invention provides a kind of image processing method, the described method comprises the following steps：
The image information of AGV vehicle bodies mark is obtained, determines the direction of the mark；
The fisrt feature information of coding region in described image information is obtained, wherein, the fisrt feature information includes face
Color information；
Based on the coding of coding region described in the fisrt feature acquisition of information, the sequence number of the AGV is determined.
Preferably, described image information includes color, shape and special identifier, the image of the acquisition AGV vehicle bodies mark
The step of information, the direction for determining the mark, includes：
Described image information is obtained, and by the corresponding image binaryzation of described image information, finds the shape of image medium square
Shape, determines non-coding region medium square center；
Based on the grid center by image rectification, with the correction chart picture after being corrected；
The direction of the mark is determined based on the correction chart picture.
Preferably, described the step of determining the direction of the mark based on the correction chart picture, includes：
Obtain the second feature information of non-coding region in the correction chart picture；
Based on the second feature information, when recognizing the special identifier of predeterminated position in the mark, obtain
The direction of the mark.
Preferably, the coding based on coding region described in the fisrt feature acquisition of information, determines the sequence of the AGV
Number the step of include：
Based on the colouring information of each grid in coding region described in the fisrt feature acquisition of information, each grid is determined
The corresponding coding of color；
Combination is ranked up to the coding according to preset order, to obtain coded strings, and is obtained based on the coded strings
The sequence number of the AGV.
Preferably, described and the step of obtaining the sequence number of the AGV based on the coded strings, includes：
The first coding of the first presetting digit capacity in coded strings is obtained, determines the set position of the mark；
The second coding of the second presetting digit capacity in coded strings is obtained, determines the sequence number of the AGV.
Preferably, second coding for obtaining the second presetting digit capacity in coded strings, the step of determining the sequence number of the AGV
Including：
Second coding is obtained, the described second coding is decoded, with corresponding numeral after being decoded；
Using the corresponding numeral after decoding as the sequence number of the AGV.
Preferably, described image processing method further includes：
The image that AGV vehicle bodies identify is obtained into the birds-eye view of the mark by perspective transform, is obtained in the birds-eye view
Centre coordinate；
The actual physics coordinate of the mark is determined based on the centre coordinate.
Preferably, it is described the mark is determined based on the centre coordinate actual physics coordinate the step of after, it is described
Image processing method includes：
Based on the special identifier, the vehicle body direction of AGV is determined；
Vehicle body direction and the corresponding change in coordinate axis direction of the actual physics coordinate based on the AGV determine the course of AGV.
In addition, to achieve the above object, the present invention also provides a kind of image processing apparatus, image processing apparatus includes：Deposit
Reservoir, processor and it is stored in the image processing program that can be run on the memory and on the processor, described image
Processing routine realizes the step of any of the above-described image processing method when being performed by the processor.
In addition, to achieve the above object, it is described computer-readable the present invention also provides a kind of computer-readable recording medium
Image processing program is stored with storage medium, described image processing routine realizes any of the above-described item of image when being executed by processor
The step of processing method.
The image information that the present invention is identified by obtaining AGV vehicle bodies, determines the direction of the mark；Obtain described image letter
The fisrt feature information of coding region in breath, wherein, the fisrt feature information includes colouring information；Based on the fisrt feature
The coding of coding region described in acquisition of information, determines the sequence number of the AGV.The invention also discloses a kind of image processing apparatus and
Computer-readable recording medium.The present invention realizes the volume of the color acquisition coding region of coding region in Direct Recognition image
Code, the sequence number of quick definite AGV, so as to improve the convenience of image procossing and the accuracy rate of image recognition.
Brief description of the drawings
Fig. 1 is that the structure of the affiliated terminal of image processing apparatus in the hardware running environment that the embodiment of the present invention is related to is shown
It is intended to；
Fig. 2 is the flow diagram of image processing method first embodiment of the present invention；
Fig. 3 is the schematic diagram of AGV vehicle bodies mark；
Fig. 4 is the image information that AGV vehicle bodies mark is obtained described in image processing method second embodiment of the present invention, is determined
The refinement flow diagram of the direction step of the mark；
Fig. 5 is the schematic diagram after image binaryzation；
Fig. 6 is the schematic diagram that similar quadrilateral structure is found in image；
Fig. 7 is the schematic diagram for finding peripheral grid center；
Fig. 8 is the schematic diagram after image calibration operation；
Fig. 9 is as determining the mark described in image processing method 3rd embodiment of the present invention based on the correction chart
The refinement flow diagram of direction step；
Figure 10 is based on described in the fisrt feature acquisition of information described in image processing method fourth embodiment of the present invention
The coding of coding region, determines the refinement flow diagram of the sequence number step of the AGV；
Figure 11 is to obtain the AGV's described in the 5th embodiment of image processing method of the present invention and based on the coded strings
The refinement flow diagram of sequence number step；
Figure 12 is the of the second presetting digit capacity in acquisition coded strings described in image processing method sixth embodiment of the present invention
Two codings, determine the refinement flow diagram of the sequence number step of the AGV；
Figure 13 is the flow diagram of the 7th embodiment of image processing method of the present invention；
Figure 14 is the schematic diagram of the mark detected in original image；
Figure 15 is the flow diagram of the 8th embodiment of image processing method of the present invention；
Figure 16 is that mark is transformed to schematic diagram in physical plane coordinate.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
As shown in Figure 1, in the hardware running environment that Fig. 1, which is the embodiment of the present invention, to be related to belonging to image processing apparatus eventually
The structure diagram at end.
Terminal of the embodiment of the present invention can be PC.As shown in Figure 1, the terminal can include：Processor 1001, such as CPU,
Network interface 1004, user interface 1003, memory 1005, communication bus 1002.Wherein, communication bus 1002 is used for realization this
Connection communication between a little components.User interface 1003 can include display screen (Display), input unit such as keyboard
(Keyboard), optional user interface 1003 can also include standard wireline interface and wireless interface.Network interface 1004 is optional
Can include standard wireline interface and wireless interface (such as WI-FI interfaces).Memory 1005 can be high-speed RAM memory,
Can also be stable memory (non-volatile memory), such as magnetic disk storage.Memory 1005 optionally may be used also
To be independently of the storage device of aforementioned processor 1001.
Alternatively, terminal can also include camera, RF (Radio Frequency, radio frequency) circuit, sensor, audio
Circuit, WiFi module etc..Wherein, sensor ratio such as optical sensor, motion sensor and other sensors.Specifically, light
Sensor may include ambient light sensor and proximity sensor, wherein, ambient light sensor can according to the light and shade of ambient light come
The brightness of display screen is adjusted, proximity sensor can close display screen and/or backlight when mobile terminal is moved in one's ear.As
One kind of motion sensor, gravity accelerometer can detect on direction the size of (generally three axis) acceleration, when static
It can detect that size and the direction of gravity, application (such as horizontal/vertical screen switching, related trip available for identification mobile terminal posture
Play, magnetometer pose calibrating), Vibration identification correlation function (such as pedometer, tap) etc.；Certainly, mobile terminal can also configure
The other sensors such as gyroscope, barometer, hygrometer, thermometer, infrared ray sensor, details are not described herein.
It will be understood by those skilled in the art that the restriction of the terminal structure shown in Fig. 1 not structure paired terminal, can wrap
Include than illustrating more or fewer components, either combine some components or different components arrangement.
As shown in Figure 1, as in a kind of memory 1005 of computer-readable storage medium can include operation server, network
Communication module, Subscriber Interface Module SIM and image processing program.
In the terminal shown in Fig. 1, network interface 1004 is mainly used for connecting background server, is carried out with background server
Data communication；User interface 1003 is mainly used for connecting client (user terminal), with client into row data communication；And processor
1001 can be used for calling the image processing program stored in memory 1005.
In the present embodiment, image processing apparatus includes：Memory 1005, processor 1001 and it is stored in the memory
On 1005 and the image processing program that can be run on the processor 1001, wherein, processor 1001 calls memory 1005
During the image processing program of middle storage, following operation is performed：
The image information of AGV vehicle bodies mark is obtained, determines the direction of the mark；
The fisrt feature information of coding region in described image information is obtained, wherein, the fisrt feature information includes face
Color information；
Based on the coding of coding region described in the fisrt feature acquisition of information, the sequence number of the AGV is determined.
Further, processor 1001 can call the image processing program stored in memory 1005, also perform following
Operation：
Described image information is obtained, and by the corresponding image binaryzation of described image information, finds the shape of image medium square
Shape, determines non-coding region medium square center；
Based on the grid center by image rectification, with the correction chart picture after being corrected；
The direction of the mark is determined based on the correction chart picture.
Further, processor 1001 can call the image processing program stored in memory 1005, also perform following
Operation：
Obtain the second feature information of non-coding region in the correction chart picture；
Based on the second feature information, when recognizing the special identifier of predeterminated position in the mark, obtain
The direction of the mark.
Further, processor 1001 can call the image processing program stored in memory 1005, also perform following
Operation：
Based on the colouring information of each grid in coding region described in the fisrt feature acquisition of information, each grid is determined
The corresponding coding of color；
Combination is ranked up to the coding according to preset order, to obtain coded strings, and is obtained based on the coded strings
The sequence number of the AGV.
Further, processor 1001 can call the image processing program stored in memory 1005, also perform following
Operation：
The first coding of the first presetting digit capacity in coded strings is obtained, determines the set position of the mark；
The second coding of the second presetting digit capacity in coded strings is obtained, determines the sequence number of the AGV.
Further, processor 1001 can call the image processing program stored in memory 1005, also perform following
Operation：
Second coding is obtained, the described second coding is decoded, with corresponding numeral after being decoded；
Using the corresponding numeral after decoding as the sequence number of the AGV.
Further, processor 1001 can call the image processing program stored in memory 1005, also perform following
Operation：
The image that AGV vehicle bodies identify is obtained into the birds-eye view of the mark by perspective transform, is obtained in the birds-eye view
Centre coordinate；
The actual physics coordinate of the mark is determined based on the centre coordinate.
Further, processor 1001 can call the image processing program stored in memory 1005, also perform following
Operation：
Based on the special identifier, the vehicle body direction of AGV is determined；
Vehicle body direction and the corresponding change in coordinate axis direction of the actual physics coordinate based on the AGV determine the course of AGV.
The present invention further provides a kind of image processing method.With reference to Fig. 2, Fig. 2 is data processing method first of the present invention
The flow diagram of embodiment.
In the present embodiment, which comprises the following steps：
Step S10, obtains the image information of AGV vehicle bodies mark, determines the direction of the mark；
In the present embodiment, when obtaining the image that camera acquisition arrives, can the information such as color combining, image is carried out
Preliminary analysis, difference is not the region of mark, for example, the structure of large-area colour.Obtain the image information of identified areas, the figure
Picture information includes color, shape and special identifier etc., can be set in positions such as the front of AGV vehicle bodies, rear, side and tops
There is mark, which can be the grid composition of n × m, wherein, n represents row, and m represents row, coding region is designed by technical staff
With non-coding region, the direction of the mark can be represented with user's different colours, shape and special identifier in non-coding region, one
As for, mark white is formed with black, and easily identification, reduces to camera imaging quality requirement, in coding region with not
Represent different codings with color, coding region encoded according to preset order, the preset order include from left to right, from
Top to bottm etc., binary coding composition coded strings, the position of AGV where technical staff can set front two coded representation mark
Put, rear seven coded representations AGV sequence numbers, for example, referring to Fig. 3, which is made of 5 × 5 grid, and each grid size is d
× d, outermost layer are non-coding region, and the grid of the inside 3 × 3 is coding region, and the black box center in the upper right corner has one and half
The white that footpath is 0.5d is circular, is all black box in outermost four apex angles, has among the black box in the upper right corner a white
Color is circular, and for marking the direction of mark, among the black box of bottom two, the mark is shown using 3 Arabic numerals
Numbering, when recognizing the characteristic information of upper right corner black box, then can determine that the mark is in positive direction.
Step S20, obtains the fisrt feature information of coding region in described image information, wherein, the fisrt feature letter
Breath includes colouring information；
In the present embodiment, the different coding that color different in coding region represents, fisrt feature information include color
Information, shape information etc., colouring information include the color of each grid in mark., can be to code area when carrying out image recognition
Domain is equidistantly divided, and for example, referring to Fig. 8, the coding region of the mark is 3 × 3 grids, inside four grids, uses 3
× 3 are equidistantly divided, and are encoded with binary system, and black represents 1, and white represents 0, coding region according to from left to right,
What coded sequence from top to bottom obtained is encoded to 000 010 100.
Further, when mark is identified, the color of each grid of coding region is identified, according to the color of grid
Corresponding coding is obtained, combination is then ranked up to the coding according to preset order, for example, according to the suitable of grid present position
Ordered pair coding is ranked up combination, obtains corresponding coded strings, which is made of the corresponding binary coding of each color.
Step S30, the sequence number of the AGV is determined based on the fisrt feature information.
When in the present embodiment, according to coded strings are got in fisrt feature information, diverse location, no in coded strings is obtained
The coding of isotopic number, the implication that each coded combination represents in the rule analysis coded strings set according to technical staff, for example,
With reference to Fig. 3, the coded strings which obtains are 000 010 100, wherein, in front two, 00 represents front, and 01 represents side,
10 represent top, and 11 represent rears, latter 7 be trolley serial number code, when carrying out image recognition, when getting in coded strings
During the coding of front two, it may be determined that position set by the mark, will after seven it is encoded translated be the decimal system after, obtain metric
Numerical value is 20, then the serial number 20 of AGV.So sequence number of position and the AGV set by being determined to identify according to the coded strings.
The image processing method that the present embodiment proposes, the image information identified by obtaining AGV vehicle bodies, determines the mark
Direction, then extract described image information in coding region feature, to obtain the fisrt feature information of coding region, its
In, the fisrt feature information includes colouring information, is finally based on the volume of coding region described in the fisrt feature acquisition of information
Code, determines the sequence number of the AGV；The color for realizing coding region in Direct Recognition image obtains the coding of coding region, soon
The sequence number of the definite AGV of speed, so as to improve the convenience of image procossing and the accuracy rate of image recognition.
Based on first embodiment, the second embodiment of image processing method of the present invention is proposed, reference Fig. 4, in the present embodiment,
Step S10 includes：
Step S11, obtains described image information, and described image information corresponding image binaryzation is found in image
The shape of grid, determines non-coding region medium square center；
In the present embodiment, binaryzation includes the gray value of the pixel on image being arranged to 0 or 255, will entirely scheme
Significantly there was only black and white visual effect as showing, binaryzation is carried out to image, with reference to Fig. 5, Fig. 5 is after image binaryzation
Schematic diagram, then using Morphological scale-space image, possible connection between each grid is eliminated, using connectivity analysis, more
Side shape approach method, finds the structure of similar quadrangle in image, and similar four are found in image to find with reference to Fig. 6, Fig. 6
The schematic diagram of side shape structure.
Further, when searching out the structure of similar quadrangle, the midpoint of similar quadrilateral structure, convex closure, outer is calculated
Enclose a little, then Polygonal Approximation is used to peripheral point, if polygon is quadrangle, four vertex are that four identified are outer
Enclose grid center, peripheral then be non-coding region, with reference to Fig. 7, Fig. 7 is the schematic diagram for finding peripheral grid center.
Step S12, based on the grid center by image rectification, with the correction chart picture after being corrected；
In the present embodiment, at definite grid pattern center, according to detect four peripheral grid centers and
Position of the center in standard form, using perspective transform, is corrected processing, the correction after being corrected by image
Image, with reference to Fig. 8, Fig. 8 is the schematic diagram after image calibration operation.
Step S13, the direction of the mark is determined based on the correction chart picture.
In the present embodiment, non-coding region is equipped with special identifier in correction chart picture, which includes color, shape
Etc. different with other grids marks, have for example, referring to Fig. 8, in the grid of figure correcting image in the black box of the upper right corner
White circular, other three apex angles of outermost are all black box, and the figure at the most upper angle of the image is then special identifier, works as knowledge
When being clipped to the special identifier, the direction of mark can determine.
The image processing method that the present embodiment proposes, corresponds to by obtaining described image information, and by described image information
Image binaryzation, find image medium square shape, determine non-coding region medium square center, be then based in the grid
Image rectification with the correction chart picture after being corrected, is finally based on the direction that the correction chart picture determines the mark by the heart；It is real
Correction process will be carried out by having showed after image binaryzation, can quickly determine mark direction, improve image procossing efficiency and
The accuracy rate of identification.
Based on second embodiment, the 3rd embodiment of image processing method of the present invention is proposed, reference Fig. 9, in the present embodiment,
Step S13 includes：
Step S131, obtains the second feature information of non-coding region in the correction chart picture；
In the present embodiment, second feature information includes color, shape and the special identifier of non-coding region, the special mark
It is different from other positions that knowledge includes predeterminated position, can be the differences such as color, shape, for example, referring to Fig. 8, upper right corner black side
White in lattice is circular.
Further, in mark, non-coding region can represent the mark with different colours, shape and special identifier
Direction, which is generally combined with black and white, and camera easily identifies, it is of course also possible to use other colors to combine, example
Such as, with reference to Fig. 3, Fig. 3 is 5 × 5 mark, and one layer of outermost is non-coding region, and four apex angles are all black, the black in the upper right corner
There is a white circle in grid.
Step S132, based on the second feature information, when the special mark for recognizing predeterminated position in the mark
During knowledge, the direction of the mark is obtained.
In the present embodiment, in image recognition processes, with reference to Fig. 8, when recognize in black box have a white it is circular when,
The direction of the mark can be obtained.The predeterminated position refers to the position that technical staff is marked in mark with special identifier, should
Special identifier can determine that the present position direction in the mark, for example, when there is white circle in the black box of the upper right corner,
Then think the black box in the front of 5 × 5 grids, so that it is determined that in front of 5 × 5 grids institute towards direction forward, if identification bottom right
When in the black box of angle in the presence of white circle, it may be considered that 5 × 5 grid institute is right, the special mark of 5 × 5 grid towards direction
The position of knowledge and represented institute are set towards direction by technical staff.
The image processing method that the present embodiment proposes, by the second feature for obtaining non-coding region in the correction chart picture
Information, is then based on the second feature information, when recognizing the special identifier of predeterminated position in the mark, obtains
The direction of the mark；Realize and quickly determine the direction of mark by identifying the special identifier of non-characteristic area, so as to carry
The high speed of image procossing.
Based on 3rd embodiment, the fourth embodiment of proposition image processing method of the present invention, with reference to Figure 10, the present embodiment
In, step S30 includes：
Step S31, based on the colouring information of each grid in coding region described in the fisrt feature acquisition of information, determines
The corresponding coding of each grid color；
In the present embodiment, colouring information includes white, black, red or blueness etc., and mark can be by different colours
Grid forms, and different colours can be defined as different codings by technical staff, when the color of each grid in mark is different,
Corresponding coding also differs, and the corresponding coding of each grid can be obtained according to different colours.
It is relatively low to camera imaging mass ratio when preferably, using white boxes and black box, it is easy to image procossing, example
Such as, with reference to Fig. 3, in 5 × 5 grid, one layer of outermost is non-coding region, and the grid of centre 3 × 3 is coding region, by black
Color grid and white boxes form, and black represents 1 in binary system, and white represents binary zero, when recognizing black box
When, then coding 1 can be got, when recognizing white boxes, then can get coding 0.
Step S32, is ranked up combination to the coding according to preset order, to obtain coded strings, and is based on the volume
Sequence obtains the sequence number of the AGV.
In the present embodiment, coded strings include multiple codings, and color in the grid lattice of coding region can be identified together,
Then the corresponding coding of color of each grid is obtained, is finally ranked up according to preset order, which is included from upper
Arrive down, from left to right, finally obtain the coded strings of combination, for example, referring to Fig. 3, to getting each grid in 3 × 3 grids
After the corresponding coding of color, it is ranked up according to preset order, obtained coded strings are 000 010 100.
It is further possible in the grid of coding region, encoded by preset order, preset order include from
Left-to-right, from top to bottom, so in identification process, can be identified successively according to the preset order, for example, referring to Fig. 3,
It is identified according to order from left to right, from top to bottom, most last layer is 000 in 3 × 3 grids of coding region, the second layer
For 010, this is combined to obtain coded strings and is similarly 000 010 100 by third layer 100.
The image processing method that the present embodiment proposes, by based in coding region described in the fisrt feature acquisition of information
The colouring information of each grid, determines the corresponding coding of each grid color, and then the coding is carried out according to preset order
Sequence combination, to obtain coded strings, and based on the sequence number of the coded strings acquisition AGV；Realize by identify color come
The sequence number of quick definite AGV, improves the accuracy and convenience of image recognition.
Based on fourth embodiment, the 5th embodiment of proposition image processing method of the present invention, with reference to Figure 11, the present embodiment
In, step S32 includes：
Step S321, obtains the first coding of the first presetting digit capacity in coded strings, determines the set position of the mark；
In the present embodiment, the first presetting digit capacity includes which position in coded strings, former positions or the rear diverse locations such as several
Or not isotopic number, technical staff can set in coded strings diverse location or the not implication of the coded representation of isotopic number, for example,
In step s 32, the coded strings got are 000 010 100, and the front two of the coding can be set to represent the set of mark
Position, the set position are included positioned at positions such as front, side, rear and the tops of AGV, wherein 00 represents front, 01 represents
Side, 10 represent top, and 11 represent rear, when carrying out image recognition, when obtaining front two coding in coded strings, according to preceding
The numeral of dibit encoding can determine position set by the corresponding mark of the numeral.
Step S322, obtains the second coding of the second presetting digit capacity in coded strings, determines the sequence number of the AGV.
In the present embodiment, technical staff can set in coded strings diverse location or the coding of isotopic number does not determine
The sequence number of AGV, for example, in step s 32, the coded strings got are 000 010 100, when with the front two coded representation mark
When the location of knowing, then the sequence number of seven coded representation AGV after can using, i.e., 0010100, can be automatically by the binary system
Encoded translated is the decimal system, obtains the sequence number of AGV.
It is further possible to using diverse location or isotopic number is not encoded, for example, after can using coded strings
Dibit encoding represents position set by mark, and with the sequence number of the first seven coded representation AGV, the implication represented by the coding is by technology people
Member is set according to demand.
The image processing method that the present embodiment proposes, by obtaining the first coding of the first presetting digit capacity in coded strings, really
The set position of the fixed mark, then obtains the second coding of the second presetting digit capacity in coded strings, determines the sequence of the AGV
Number；Realize and the set position of mark and the sequence number of AGV are quickly determined according to the diverse location and digit of coded strings, so as to improve
The accuracy rate and convenience of identification.
Based on the 5th embodiment, the sixth embodiment of proposition image processing method of the present invention, with reference to Figure 12, the present embodiment
In, step S321 includes：
Step S3211, obtains second coding, the described second coding is decoded, with corresponding after being decoded
Numeral；
Step S3222, using the corresponding numeral after decoding as the sequence number of the AGV.
In the present embodiment, the decoding include by binary second it is encoded translated be metric numeral, can pass through
The second coding in coded strings is intercepted, for example, in step s 32, obtained coded strings are 000 010 100, front two coding
Represent be mark present position, rear seven coded representations be AGV sequence number, then intercept after seven obtain be encoded to
0010100, it is 20 which is converted into the numeral that the decimal system obtains.
Further, if the first seven in coded strings represents the sequence number of AGV, the first seven sequence as AGV can be intercepted
Number, for example, the coded strings got are 000 010 100, then 7 are encoded to 000 010 1 before intercepting, then compile the binary system
It is 5 that code, which is converted into the decimal system, then the serial number 5 of the AGV.
The image processing method that the present embodiment proposes, by obtaining second coding, the described second coding is solved
Code, with corresponding numeral after decode, then using the corresponding digital sequence number as the AGV after decoding；Realize
By being converted into the decimal system to the binary coding of presetting digit capacity, the sequence number of AGV can be fast and accurately obtained.
Based on all of above embodiment, the 7th embodiment of proposition image processing method of the present invention, with reference to Figure 13, this implementation
In example, the recognition methods of the AGV further includes：
Step S40, obtains the birds-eye view of the mark, described in acquisition by the image that AGV vehicle bodies identify by perspective transform
Centre coordinate in birds-eye view；
Step S50, the actual physics coordinate of the mark is determined based on the centre coordinate.
In the present embodiment, birds-eye view is according to Perspective Principles, and ground is overlooked from eminence certain point with high viewpoint perspective
Rise and fall the figure being depicted as, and the image coordinate in birds-eye view has linear relationship with actual physics plane coordinates, with reference to Figure 14, figure
14 be the schematic diagram of the mark detected in original image, and the mark of deformation in artwork, transforming to deformation in birds-eye view can be by school
Just, mark is detected in birds-eye view, obtains centre coordinate, is the actual physics coordinate that can be identified by linear transformation.
The image processing method that the present embodiment proposes, obtains the birds-eye view of the mark, described in acquisition by perspective transform
Centre coordinate in birds-eye view, is then based on the actual physics coordinate that the centre coordinate determines the mark；Realize basis
The birds-eye view of mark determines the actual physics coordinate of mark, and then AGV can be positioned.
Based on the 7th embodiment, the 8th embodiment of proposition image processing method of the present invention, with reference to Figure 15, the present embodiment
In, after step S50, further include：
Step S60, based on the special identifier, determines the vehicle body direction of AGV；
In the present embodiment, mark is equipped with AGV vehicle bodies, has the direction that special identifier represents the mark, institute in the mark
When recognizing the special identifier, then equally can determine the vehicle body direction of the AGV, for example, it is assumed that the top of mark corresponds to
In front of AGV, according to the grid in the upper right corner, confirm AGV front directions.
Step S70, vehicle body direction and the corresponding change in coordinate axis direction of the actual physics coordinate based on the AGV determine
The course of AGV.
In the present embodiment, the image coordinate in birds-eye view has linear relationship with actual physics plane coordinates, with reference to figure
16, Figure 16 be that mark is transformed to schematic diagram in physical plane coordinate, and the mark of deformation in artwork, transforms to shape in birds-eye view
Change can be corrected, and mark is detected in birds-eye view, obtain centre coordinate, be the actual physics that can be identified by linear transformation
Coordinate, grid automatically generates center line up and down in mark, angle, θ is determined according to center line and physical coordinates direction of principal axis, so that it is determined that AGV
Course.
The image processing method that the present embodiment proposes, by based on the special identifier, determining the vehicle body direction of AGV, so
The vehicle body direction based on the AGV and the corresponding change in coordinate axis direction of the actual physics coordinate determine the course of AGV afterwards；Realize
The course of AGV is quickly determined by identification marking, for the identification of vehicle, anticollision, path planning provides foundation.
The present invention also provides a kind of computer-readable recording medium, in the present embodiment, on computer-readable recording medium
Image processing program is stored with, wherein：
The image information of AGV vehicle bodies mark is obtained, determines the direction of the mark；
The fisrt feature information of coding region in described image information is obtained, wherein, the fisrt feature information includes face
Color information；
Based on the coding of coding region described in the fisrt feature acquisition of information, the sequence number of the AGV is determined.
Further, when which is performed by the processor, following steps are also realized：
Described image information is obtained, and by the corresponding image binaryzation of described image information, finds the shape of image medium square
Shape, determines non-coding region medium square center；
Based on the grid center by image rectification, with the correction chart picture after being corrected；
The direction of the mark is determined based on the correction chart picture.
Further, when which is performed by the processor, following steps are also realized：
Obtain the second feature information of non-coding region in the correction chart picture；
Based on the second feature information, when recognizing the special identifier of predeterminated position in the mark, obtain
The direction of the mark.
Further, when which is performed by the processor, following steps are also realized：
Based on the colouring information of each grid in coding region described in the fisrt feature acquisition of information, each grid is determined
The corresponding coding of color；
Combination is ranked up to the coding according to preset order, to obtain coded strings, and is obtained based on the coded strings
The sequence number of the AGV.
Further, when which is performed by the processor, following steps are also realized：
The first coding of the first presetting digit capacity in coded strings is obtained, determines the set position of the mark；
The second coding of the second presetting digit capacity in coded strings is obtained, determines the sequence number of the AGV.
Further, when which is performed by the processor, following steps are also realized：
Second coding is obtained, the described second coding is decoded, with corresponding numeral after being decoded；
Using the corresponding numeral after decoding as the sequence number of the AGV.
Further, when which is performed by the processor, following steps are also realized：
The image that AGV vehicle bodies identify is obtained into the birds-eye view of the mark by perspective transform, is obtained in the birds-eye view
Centre coordinate；
The actual physics coordinate of the mark is determined based on the centre coordinate.
Further, when which is performed by the processor, following steps are also realized：
Based on the special identifier, the vehicle body direction of AGV is determined；
Vehicle body direction and the corresponding change in coordinate axis direction of the actual physics coordinate based on the AGV determine the course of AGV.
It should be noted that herein, term " comprising ", "comprising" or its any other variant are intended to non-row
His property includes, so that process, method, article or system including a series of elements not only include those key elements, and
And other elements that are not explicitly listed are further included, or further include as this process, method, article or system institute inherently
Key element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that including this
Also there are other identical element in the process of key element, method, article or system.
The embodiments of the present invention are for illustration only, do not represent the quality of embodiment.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on such understanding, technical scheme substantially in other words does the prior art
Going out the part of contribution can be embodied in the form of software product, which is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disc, CD), including some instructions use so that a station terminal equipment (can be mobile phone,
Computer, server, air conditioner, or network equipment etc.) perform method described in each embodiment of the present invention.
It these are only the preferred embodiment of the present invention, be not intended to limit the scope of the invention, it is every to utilize this hair
The equivalent structure or equivalent flow shift that bright specification and accompanying drawing content are made, is directly or indirectly used in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
- A kind of 1. image processing method, applied to AGV automatically guiding trolley control systems, it is characterised in that described image processing Method comprises the following steps：The image information of AGV vehicle bodies mark is obtained, determines the direction of the mark；The fisrt feature information of coding region in described image information is obtained, wherein, the fisrt feature information is believed including color Breath；Based on the coding of coding region described in the fisrt feature acquisition of information, the sequence number of the AGV is determined.
- 2. image processing method as claimed in claim 1, described image information includes color, shape and special identifier, it is special The step of sign is, the image information of the acquisition AGV vehicle bodies mark, the direction for determining the mark includes：Described image information is obtained, and by the corresponding image binaryzation of described image information, finds the shape of image medium square, really Determine non-coding region medium square center；Based on the grid center by image rectification, with the correction chart picture after being corrected；The direction of the mark is determined based on the correction chart picture.
- 3. image processing method as claimed in claim 2, it is characterised in that described that the mark is determined based on the correction chart picture The step of direction of knowledge, includes：Obtain the second feature information of non-coding region in the correction chart picture；Based on the second feature information, when recognizing the special identifier of predeterminated position in the mark, described in acquisition The direction of mark.
- 4. image processing method as claimed in claim 3, it is characterised in that described to be based on the fisrt feature acquisition of information institute The coding of coding region is stated, the step of sequence number for determining the AGV includes：Based on the colouring information of each grid in coding region described in the fisrt feature acquisition of information, each grid color is determined Corresponding coding；Combination is ranked up to the coding according to preset order, to obtain coded strings, and based on described in coded strings acquisition The sequence number of AGV.
- 5. image processing method as claimed in claim 4, it is characterised in that it is described and based on the coded strings obtain described in The step of sequence number of AGV, includes：The first coding of the first presetting digit capacity in coded strings is obtained, determines the set position of the mark；The second coding of the second presetting digit capacity in coded strings is obtained, determines the sequence number of the AGV.
- 6. image processing method as claimed in claim 5, it is characterised in that described to obtain the second presetting digit capacity in coded strings The step of second coding, the sequence number for determining the AGV, includes：Second coding is obtained, the described second coding is decoded, with corresponding numeral after being decoded；Using the corresponding numeral after decoding as the sequence number of the AGV.
- 7. the image processing method as described in claim 1-6, it is characterised in that described image processing method further includes：The image that AGV vehicle bodies identify is obtained into the birds-eye view of the mark by perspective transform, in obtaining in the birds-eye view Heart coordinate；The actual physics coordinate of the mark is determined based on the centre coordinate.
- 8. image processing method as claimed in claim 7, it is characterised in that described that the mark is determined based on the centre coordinate After the step of actual physics coordinate of knowledge, described image processing method further includes：Based on the special identifier, the vehicle body direction of AGV is determined；Vehicle body direction and the corresponding change in coordinate axis direction of the actual physics coordinate based on the AGV determine the course of AGV.
- 9. a kind of image processing apparatus, it is characterised in that described image processing unit includes：Memory, processor and it is stored in On the memory and the image processing program that can run on the processor, described image processing routine is by the processor Realized during execution such as the step of method described in any item of the claim 1 to 8.
- 10. a kind of computer-readable recording medium, it is characterised in that be stored with the computer-readable recording medium at image Program is managed, such as image procossing described in any item of the claim 1 to 8 is realized when described image processing routine is executed by processor Method and step.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711143788.1A CN107967437B (en) | 2017-11-17 | 2017-11-17 | Image processing method and device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711143788.1A CN107967437B (en) | 2017-11-17 | 2017-11-17 | Image processing method and device and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107967437A true CN107967437A (en) | 2018-04-27 |
| CN107967437B CN107967437B (en) | 2021-04-20 |
Family
ID=62001230
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711143788.1A Active CN107967437B (en) | 2017-11-17 | 2017-11-17 | Image processing method and device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107967437B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109048072A (en) * | 2018-08-21 | 2018-12-21 | 深圳市创客工场科技有限公司 | Laser processing, device, equipment and computer readable storage medium |
| CN109359645A (en) * | 2018-08-29 | 2019-02-19 | 深圳市易成自动驾驶技术有限公司 | AGV coding maker, detection method and computer readable storage medium |
| CN110766019A (en) * | 2018-07-25 | 2020-02-07 | 深圳市创客工场科技有限公司 | Code recognition method and device, electronic equipment and computer readable storage medium |
| CN113706842A (en) * | 2021-07-20 | 2021-11-26 | 东风柳州汽车有限公司 | In-vehicle article anti-leaving reminding method, device, storage medium and device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160187878A1 (en) * | 2011-03-31 | 2016-06-30 | King Abdulaziz City for Science & Technology | Matrix code symbols for accurate robot tracking |
| CN206312215U (en) * | 2016-10-09 | 2017-07-07 | 浙江国自机器人技术有限公司 | A kind of mobile unit and stock article management system |
| CN107076557A (en) * | 2016-06-07 | 2017-08-18 | 深圳市大疆创新科技有限公司 | Mobile robot recognition positioning method, device, system and mobile robot |
-
2017
- 2017-11-17 CN CN201711143788.1A patent/CN107967437B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160187878A1 (en) * | 2011-03-31 | 2016-06-30 | King Abdulaziz City for Science & Technology | Matrix code symbols for accurate robot tracking |
| CN107076557A (en) * | 2016-06-07 | 2017-08-18 | 深圳市大疆创新科技有限公司 | Mobile robot recognition positioning method, device, system and mobile robot |
| CN206312215U (en) * | 2016-10-09 | 2017-07-07 | 浙江国自机器人技术有限公司 | A kind of mobile unit and stock article management system |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110766019A (en) * | 2018-07-25 | 2020-02-07 | 深圳市创客工场科技有限公司 | Code recognition method and device, electronic equipment and computer readable storage medium |
| CN109048072A (en) * | 2018-08-21 | 2018-12-21 | 深圳市创客工场科技有限公司 | Laser processing, device, equipment and computer readable storage medium |
| CN109359645A (en) * | 2018-08-29 | 2019-02-19 | 深圳市易成自动驾驶技术有限公司 | AGV coding maker, detection method and computer readable storage medium |
| CN109359645B (en) * | 2018-08-29 | 2022-02-22 | 深圳市易成自动驾驶技术有限公司 | AGV encoding marker, detection method and computer readable storage medium |
| CN113706842A (en) * | 2021-07-20 | 2021-11-26 | 东风柳州汽车有限公司 | In-vehicle article anti-leaving reminding method, device, storage medium and device |
| CN113706842B (en) * | 2021-07-20 | 2023-11-03 | 东风柳州汽车有限公司 | Method, equipment, storage medium and device for reminding article in car of leaving behind |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107967437B (en) | 2021-04-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112348815B (en) | Image processing method, image processing apparatus, and non-transitory storage medium | |
| CN107967437A (en) | A kind of image processing method, device and computer-readable recording medium | |
| US10924729B2 (en) | Method and device for calibration | |
| CN109816745B (en) | Human body thermodynamic diagram display method and related products | |
| CN109357673A (en) | Vision navigation method and device based on image | |
| US20030076980A1 (en) | Coded visual markers for tracking and camera calibration in mobile computing systems | |
| CN111832447B (en) | Building drawing component identification method, electronic equipment and related product | |
| KR101165415B1 (en) | Method for recognizing human face and recognizing apparatus | |
| CN108717709A (en) | Image processing system and image processing method | |
| CN113538574B (en) | Pose positioning method, device and equipment and computer readable storage medium | |
| CN108765584A (en) | Laser point cloud data collection augmentation method, apparatus and readable storage medium storing program for executing | |
| KR102375325B1 (en) | Method for detection and recognition of distant high-density visual markers | |
| CN103049731A (en) | Decoding method for point-distributed color coding marks | |
| CN107851308A (en) | system and method for identifying target object | |
| CN109920018A (en) | Black-and-white photograph color recovery method, device and storage medium neural network based | |
| CN108052869B (en) | Lane line recognition method, lane line recognition device and computer-readable storage medium | |
| CN103854020A (en) | Character recognition method and device | |
| CN113435557B (en) | Two-dimensional code generation, decoding and identification method, device and equipment | |
| CN112200230A (en) | Training board identification method and device and robot | |
| US10635958B2 (en) | Hybrid visual tagging using customized colored tiles | |
| CN110288691B (en) | Method, apparatus, electronic device and computer-readable storage medium for rendering image | |
| CN104933430B (en) | A kind of Interactive Image Processing method and system for mobile terminal | |
| JPH1151611A (en) | Device and method for recognizing position and posture of object to be recognized | |
| CN105787541B (en) | four-dimensional code encoding method and system | |
| Han et al. | L-split marker for augmented reality in aircraft assembly |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: An image processing method, device and computer readable storage medium Effective date of registration: 20220623 Granted publication date: 20210420 Pledgee: Industrial and Commercial Bank of China Limited Shenzhen Fuyong sub branch Pledgor: SHENZHEN ECHIEV AUTONOMOUS DRIVING TECHNOLOGY Co.,Ltd. Registration number: Y2022980008778 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Date of cancellation: 20230818 Granted publication date: 20210420 Pledgee: Industrial and Commercial Bank of China Limited Shenzhen Fuyong sub branch Pledgor: SHENZHEN ECHIEV AUTONOMOUS DRIVING TECHNOLOGY Co.,Ltd. Registration number: Y2022980008778 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right |