CN110264531A - A kind of catching for X-comers takes method, apparatus, system and readable storage medium storing program for executing - Google Patents
A kind of catching for X-comers takes method, apparatus, system and readable storage medium storing program for executing Download PDFInfo
- Publication number
- CN110264531A CN110264531A CN201910570335.XA CN201910570335A CN110264531A CN 110264531 A CN110264531 A CN 110264531A CN 201910570335 A CN201910570335 A CN 201910570335A CN 110264531 A CN110264531 A CN 110264531A
- Authority
- CN
- China
- Prior art keywords
- table images
- chessboard table
- value
- filtered
- chessboard
- 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 57
- 238000006243 chemical reaction Methods 0.000 claims abstract description 29
- 238000001914 filtration Methods 0.000 claims description 32
- 230000008569 process Effects 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 11
- 238000011946 reduction process Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 9
- 230000008859 change Effects 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 230000001186 cumulative effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 206010016256 fatigue Diseases 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration by the use of local operators
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
Abstract
The invention discloses a kind of catching for X-comers to take method, apparatus, system and computer readable storage medium, and this method includes obtaining original chessboard table images；Binary conversion treatment is carried out to original chessboard table images, obtains binaryzation chessboard table images；Binaryzation chessboard table images progress angle point is caught and takes analysis, determines the corner location in target area.Then the application takes analysis by catching to binaryzation chessboard table images progress angle point again, obtains the position of angle point in target area by obtaining binaryzation chessboard table images after carrying out binary conversion treatment to original chessboard table images.Calculating speed is fast in use by the application, and can be realized to tessellated identification and angle point crawl is obscured, and the scope of application is wider, more efficient.
Description
Technical field
The present embodiments relate to technical field of image processing, more particularly to a kind of X-comers catch take method,
Device, system and readable storage medium storing program for executing.
Background technique
When analyzing the focusing of camera module or the variation of analysis module parsing power under different distance, chess is usually taken
The SFR (spatial frequency response, spatial frequency response) of disk format is calculated, when carrying out SFR calculating
It is most important for how catching region required for taking, and determines that tessellated corner location is to catch the important prerequisite for taking region, mesh
Before, Angular Point Extracting Method commonly used in the prior art is the method for harris Corner Detection, but this method arithmetic speed is slow, and
And fuzzy gridiron pattern can not be identified.
In consideration of it, how to provide it is a kind of solve above-mentioned technical problem X-comers catch take method, apparatus, system and
Computer readable storage medium becomes those skilled in the art's problem to be solved.
Summary of the invention
Take method, apparatus, system and computer can the purpose of the embodiment of the present invention is that providing a kind of catching for X-comers
Storage medium is read, can be improved calculating speed in use, and can be realized to obscuring tessellated identification and angle point
Crawl, the scope of application are wider, more efficient.
In order to solve the above technical problems, the embodiment of the invention provides a kind of catching for X-comers to take method, comprising:
Obtain original chessboard table images；
Binary conversion treatment is carried out to the original chessboard table images, obtains two-value corresponding with the original chessboard table images
Change chessboard table images；
Binaryzation chessboard table images progress angle point is caught and takes analysis, determines the corner location in target area.
Optionally, before described to the original chessboard table images progress binary conversion treatment, further includes:
The original chessboard table images are filtered, filtered chessboard table images are obtained；
It is described that binary conversion treatment is carried out to the original chessboard table images specifically:
Binary conversion treatment is carried out to the filtered chessboard table images.
Optionally, described that the original chessboard table images are filtered, obtain filtered chessboard table images
Process are as follows:
Noise reduction process is filtered to the original chessboard table images, obtains first filtered chessboard table images；
Radius core is determined according to the black and white block size in the first filtered chessboard table images, and using described half
The diameter verification first filtered chessboard table images carry out secondary filtering processing, the chessboard table images after obtaining secondary filtering.
Optionally, the black and white block size according in the first filtered chessboard table images determines radius core
Process are as follows:
Using the half of the black and white block length in the first filtered chessboard table images as the size of the radius core.
Optionally, described that binary conversion treatment is carried out to the filtered chessboard table images, obtain binaryzation chessboard trrellis diagram
The process of picture are as follows:
The brightness value of each pixel in the first filtered chessboard table images is calculated, and calculates described two
The brightness value of each pixel in secondary filtered chessboard table images；
By the brightness value of each pixel in the first filtered chessboard table images respectively with the secondary filtering
The brightness value of pixel in chessboard table images afterwards in same position is compared；
The chess after brightness value of the pixel in the first filtered chessboard table images is greater than the secondary filtering
When the brightness value of the pixel in disk table images in same position, the brightness value of the pixel is set to 255, it otherwise, will
The brightness value of the pixel is set to 0；
Binaryzation chessboard table images are obtained according to brightness value determining, corresponding with each pixel.
Optionally, described catch to binaryzation chessboard table images progress angle point takes analysis, determines in target area
The process of corner location are as follows:
Black and white block in the binaryzation gridiron pattern objective area in image is traversed, and determines that every group of intersection is black
White piece of each intersection point；
Each intersection point is calculated separately out on the upper left corner of the intersection point, the upper right corner, the lower left corner, the lower right corner
It is cumulative to obtain corresponding with the predeterminable area in the upper left corner first for the sum of the brightness value of each pixel in predeterminable area
Value the second accumulated value corresponding with the predeterminable area in the upper right corner, third corresponding with the predeterminable area in the lower left corner are tired out
4th accumulated value value added and corresponding with the predeterminable area in the lower right corner；
When first accumulated value less than the first preset value, the second accumulated value be greater than the second preset value, the first accumulated value with
The absolute value of the difference of 4th accumulated value is less than third preset value and the second accumulated value and the absolute value of the difference of third accumulated value is small
When the third preset value, using the intersection point as initial angle point；
Or when first accumulated value be greater than second preset value, the second accumulated value be less than first preset value,
The absolute value of the difference of first accumulated value and the 4th accumulated value be less than third preset value, the second accumulated value and third accumulated value it
When absolute value of the difference is less than the third preset value, using the intersection point as initial angle point；
The average coordinates value of angle point is calculated according to the coordinate value of each initial angle point in default angle point region, and
Using the average coordinates value as the position coordinates of angle point.
The embodiment of the present invention provides a kind of catching for X-comers accordingly and takes device, comprising:
Module is obtained, for obtaining original chessboard table images；
Processing module obtains binaryzation chessboard table images for carrying out binary conversion treatment to the original chessboard table images；
Extraction module takes analysis for catching to binaryzation chessboard table images progress angle point, determines in target area
Corner location.
Optionally, further includes:
Filter module obtains filtered chessboard table images for being filtered to the original chessboard table images；
The processing module is specifically used for carrying out binary conversion treatment to the filtered chessboard table images.
The embodiment of the invention also provides a kind of catching for X-comers to take system, comprising:
Memory, for storing computer program；
Processor, that X-comers as described above are realized when for executing the computer program catches the step for taking method
Suddenly.
The embodiment of the invention also provides a kind of computer readable storage medium, deposited on the computer readable storage medium
Computer program is contained, the computer program realizes that catching for X-comers as described above takes method when being executed by processor
The step of.
The embodiment of the invention provides a kind of catching for X-comers to take method, apparatus, system and computer-readable storage
Medium, this method comprises: obtaining original chessboard table images；Binary conversion treatment is carried out to original chessboard table images, obtains binaryzation
Chessboard table images；Binaryzation chessboard table images progress angle point is caught and takes analysis, determines the corner location in target area.
As it can be seen that the application by original chessboard table images carry out binary conversion treatment after obtain binaryzation chessboard table images,
Then analysis is taken by catching to binaryzation chessboard table images progress angle point again, obtains the position of angle point in target area.The application
Calculating speed is fast in use, and can be realized to obscuring tessellated identification and angle point crawl, the scope of application is wider,
It is more efficient.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to institute in the prior art and embodiment
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without creative efforts, can also obtain according to these attached drawings
Obtain other attached drawings.
Fig. 1 is that a kind of X-comers provided in an embodiment of the present invention catch the flow diagram for taking method；
Fig. 2 is a kind of schematic diagram of original chessboard table images provided in an embodiment of the present invention；
Fig. 3 is a kind of first filtered chessboard table images provided in an embodiment of the present invention；
Fig. 4 is the chessboard table images after a kind of secondary filtering provided in an embodiment of the present invention；
Fig. 5 is a kind of binaryzation chessboard table images provided in an embodiment of the present invention；
Fig. 6 is the schematic diagram of one group of intersection black and white block provided in an embodiment of the present invention；
Fig. 7 is the schematic diagram of another group of intersection black and white block provided in an embodiment of the present invention；
Fig. 8 is that a kind of angle point provided in an embodiment of the present invention catches the chessboard table images after the completion of taking；
Fig. 9 is that a kind of X-comers provided in an embodiment of the present invention catch the structural schematic diagram for taking device.
Specific embodiment
The embodiment of the invention provides a kind of catching for X-comers to take method, apparatus, system and computer-readable storage
Medium can be improved calculating speed in use, and can be realized to tessellated identification and angle point crawl is obscured, and fit
It is wider, more efficient with range.
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
Fig. 1 is please referred to, Fig. 1 is that a kind of catching for X-comers provided in an embodiment of the present invention takes the process of method to illustrate
Figure.This method comprises:
S110: original chessboard table images are obtained；
Specifically, in the present embodiment catch take X-comers when, original chessboard table images can be directly acquired, specifically such as
Shown in Fig. 2.
S120: binary conversion treatment is carried out to original chessboard table images, obtains binaryzation chessboard table images；
It should be noted that in the present embodiment two-value can be carried out to original chessboard table images by the adjusting to gray value
Change processing can also carry out binary conversion treatment to original chessboard table images in other way, obtain binaryzation chessboard trrellis diagram
Picture.
Specifically, this method can also include: before carrying out binary conversion treatment to original chessboard table images in S120
Original chessboard table images are filtered, filtered chessboard table images are obtained；
Binary conversion treatment is carried out to original chessboard table images specifically:
Binary conversion treatment is carried out to filtered chessboard table images.
It is understood that more accurate binaryzation chessboard table images in order to obtain, can obtained in the present embodiment
To after original chessboard table images, which is filtered, and filtered chessboard table images are carried out
Binary conversion treatment, so that the binaryzation chessboard table images made are more accurate.
Further, above-mentioned that original chessboard table images are filtered, obtain the mistake of filtered chessboard table images
Journey is specifically as follows:
Noise reduction process is filtered to original chessboard table images, obtains first filtered chessboard table images；
Radius core is determined according to the black and white block size in first filtered chessboard table images, and just using radius verification
Secondary filtered chessboard table images carry out secondary filtering processing, the chessboard table images after obtaining secondary filtering.
Specifically, in the present embodiment when being filtered to original chessboard table images, it can be first to original chessboard table images
It is filtered for the first time, to remove the noise in original chessboard table images, wherein first filtered chessboard table images such as Fig. 3
It is shown, secondary filtering processing then is carried out to first filtered chessboard table images again, the chessboard trrellis diagram after obtaining secondary filtering
As (as shown in Figure 4), wherein in secondary filtering processing, used radius core can be according to first filtered chessboard trrellis diagram
Black and white block size as in is determined, such as the half of the black and white block length in first filtered chessboard table images can be made
For the size of radius core, it is of course also possible to radius core when determining secondary filtering according to other modes, wherein secondary filter
The radius core used when wave is greater than used radius core when first filtering.
Further, in order to further increase the accuracy of binaryzation chessboard table images, in the present embodiment to filtering
Chessboard table images afterwards carry out binary conversion treatment, obtain the process of binaryzation chessboard table images, are specifically as follows:
The brightness value of each pixel in first filtered chessboard table images is calculated, and after calculating secondary filtering
Chessboard table images in each pixel brightness value；
By the brightness value of each pixel in first filtered chessboard table images respectively with the chessboard after secondary filtering
The brightness value of pixel in table images in same position is compared；
Chessboard table images after the brightness value of the pixel in first filtered chessboard table images is greater than secondary filtering
In in same position pixel brightness value when, the brightness value of pixel is set to 255, otherwise, by the brightness of pixel
Value is set to 0；
Binaryzation chessboard table images are obtained according to brightness value determining, corresponding with each pixel.
It should be noted that passing through the gridiron pattern after first filtered chessboard table images and secondary filtering in the present embodiment
Image is analyzed, and binaryzation chessboard table images are further obtained.Specifically by the first filtered chessboard table images of general
The brightness value of each pixel be compared with the brightness value of same position pixel in the chessboard table images after secondary filtering,
Such as by the chessboard table images after the brightness value and secondary filtering of the pixel in first filtered chessboard table images at position 1
The brightness value of pixel at middle position 1 is compared, thus if picture in first filtered chessboard table images at position 1
The brightness value of vegetarian refreshments is greater than the brightness value of the pixel in the chessboard table images after secondary filtering at position 1, then by picture at position 1
The brightness value of vegetarian refreshments is set to 255 (namely pixel is white point at this), otherwise, the brightness value of pixel at position 1 is set to 0
(namely pixel is stain at this) to obtain the specific brightness value of pixel at each position, and then obtains binaryzation
Chessboard table images (as shown in Figure 5).
Wherein it is possible to the data in first filtered chessboard table images are set as psrc, by the chessboard after secondary filtering
Data in table images are set as psrc2, and the data in binaryzation chessboard table images are set as psrc3, then after the first filtering of basis
Chessboard table images in data and the data in chessboard table images after secondary filtering obtain in binaryzation chessboard table images
The program in machine code of data is as follows:
S130: binaryzation chessboard table images progress angle point is caught and takes analysis, determines the corner location in target area.
Specifically, after obtaining binaryzation chessboard table images, it can be by carrying out angle point to the binaryzation chessboard table images
It catches and takes analysis, and then determine each angle point in the target area in the binaryzation chessboard table images and corresponding each angle point
Position.
Further, binaryzation chessboard table images progress angle point is caught in above-mentioned S130 and takes analysis, determine target area
In corner location process, be specifically as follows:
Black and white block in binaryzation gridiron pattern objective area in image is traversed, and determines every group of intersection black and white block
Each intersection point；
Predeterminable area on the upper left corner of intersection point, the upper right corner, the lower left corner, the lower right corner is calculated separately out to each intersection point
The sum of the brightness value of interior each pixel obtains the first accumulated value corresponding with the predeterminable area in the upper left corner, with the upper right corner
Corresponding second accumulated value of predeterminable area, third accumulated value corresponding with the predeterminable area in the lower left corner and the preset areas with the lower right corner
Corresponding 4th accumulated value in domain；
When the first accumulated value is greater than the second preset value, the first accumulated value and the 4th less than the first preset value, the second accumulated value
The absolute value of the difference of accumulated value is less than the absolute value of the difference of third preset value and the second accumulated value and third accumulated value less than the
When three preset values, using intersection point as initial angle point；
Or when the first accumulated value be greater than the second preset value, the second accumulated value less than the first preset value, the first accumulated value with
The absolute value of the difference of 4th accumulated value is less than the absolute value of the difference of third preset value, the second accumulated value and third accumulated value less than the
When three preset values, using intersection point as initial angle point；
The average coordinates value of angle point is calculated according to the coordinate value of each initial angle point in default angle point region, and will be put down
Equal position coordinates of the coordinate value as angle point.
It should be noted that the target area in the present embodiment can be the partial region in binaryzation chessboard table images,
It may be whole region, the specific location of the target area can be determined according to actual needs, wherein each intersection is black
White piece of angle point can be determined according to the above method.
Specifically, may include one or more intersection points for each black and white block, for each intersection point, it can be calculated
The sum of brightness value of each pixel (the first accumulated value) in the predeterminable area of the upper left corner calculates each in its upper right corner predeterminable area
The sum of brightness value of a pixel (the second accumulated value), calculates the brightness value of each pixel in its lower left corner predeterminable area
The sum of (third accumulated value), calculating the sum of brightness value of each pixel in its lower right corner predeterminable area, (the 4th is cumulative
Value), wherein upper left side, upper right side, lower left and lower right respectively can be for positioned at 45 ° of intersection point upper left side, 45 ° of upper right side, a left sides
45 ° of lower section, 45 ° of lower right direction (namely 45 °, 135 °, 225 ° and 315 ° four directions in two-dimentional quadrant), preset model
Enclose can be to have preset length and the line segment including preset quantity pixel, that is, will in the corresponding direction from intersection point
The added luminance of this preset quantity pixel on the line segment in this direction including preset quantity pixel obtains
Corresponding accumulated value, for example, the added luminance of 24 pixels on the preset length line segment for being located at the intersection point upper left corner is obtained
To the first accumulated value, the added luminance of 24 pixels on the preset length line segment for being located at the intersection point upper right corner is obtained second
The added luminance of 24 pixels on the preset length line segment in the lower left corner is obtained third accumulated value, by bottom right by accumulated value
The added luminance of 24 pixels on the preset length line segment at angle obtains the 4th accumulated value.Wherein, preset quantity is specific
Numerical value can be set according to actual needs, and the application is not specifically limited.
It should be noted that if the first accumulated value is less than the first preset value (such as 3600), second for an intersection point
The absolute value of the difference that accumulated value is greater than the second preset value (such as 2000), the first accumulated value and the 4th accumulated value is default less than third
When being worth the absolute value of the difference of (for example, 500) and the second accumulated value and third accumulated value less than third preset value, then explanation should
The upper left side and lower right of intersection point are black patch, and the upper right corner and the lower left corner are white piece, as shown in fig. 6, then can be by intersection point
As initial angle point；
Certainly, if for the intersection point, it is default less than first that the first accumulated value is greater than the second preset value, the second accumulated value
Value, the absolute value of the difference of the first accumulated value and the 4th accumulated value less than third preset value, the second accumulated value and third accumulated value it
When absolute value of the difference is less than third preset value, then illustrates the upper left side of the intersection point and lower right is white piece, the upper right corner and a left side
Inferior horn is black patch, as shown in fig. 7, then using intersection point as initial angle point；
For one group of black and white block there are one or more initial angle points in it, then can be pre- in black and white block intersection selection one
If angle point region, and the coordinate value for presetting according to this each initial angle point in angle point region calculates average coordinates value, and will
Position coordinates of the average coordinates value as angle point corresponding with this group of black and white block.
Specifically, being all made of the above method for the black and white block of every group of intersection in target area determines its angle point, thus really
Make each angle point (as shown in Figure 8) in target area.
Wherein, the specific value of the first preset value in the present embodiment, the second preset value and third preset value can root
It is determined according to actual conditions, the present embodiment does not do particular determination to this.
In addition, the angle position of each angle point in target area can be determined in the present embodiment according to following code program
It sets:
It should also be noted that, the method provided in the present embodiment is suitable for catching the angle point of fuzzy chessboard table images taking,
And the calculating after catching and taking angle point, for subsequent sfr value.
The embodiment of the invention provides a kind of catching for X-comers to take method, this method comprises: obtaining original gridiron pattern
Image；Binary conversion treatment is carried out to original chessboard table images, obtains binaryzation chessboard table images；To binaryzation chessboard table images into
Row angle point, which is caught, takes analysis, determines the corner location in target area.As it can be seen that the application passes through to original chessboard table images two-value
Binaryzation chessboard table images are obtained after change processing, then analysis is taken by catching to binaryzation chessboard table images progress angle point again, obtains
The position of angle point into target area.Calculating speed is fast in use by the application, and can be realized to fuzzy gridiron pattern
Identification and angle point crawl, the scope of application is wider, more efficient.
On the basis of the above embodiments, the embodiment of the present invention provides a kind of catching for X-comers accordingly and takes dress
It sets, specifically please refers to Fig. 9.The device includes:
Module 91 is obtained, for obtaining original chessboard table images；
Processing module 92 obtains binaryzation chessboard table images for carrying out binary conversion treatment to original chessboard table images；
Extraction module 93 takes analysis for catching to binaryzation chessboard table images progress angle point, determines in target area
Corner location.
Further, the device further include:
Filter module obtains filtered chessboard table images for being filtered to original chessboard table images；
Processing module 92 is specifically used for carrying out binary conversion treatment to filtered chessboard table images.
Further, filter module includes:
First filter unit obtains first filtered chess for being filtered noise reduction process to original chessboard table images
Disk table images；
Second filter unit, for determining radius according to the black and white block size in first filtered chessboard table images
Core, and secondary filtering processing, the chessboard after obtaining secondary filtering are carried out using the first filtered chessboard table images of radius verification
Table images.
Further, processing module 32 includes:
Computing unit, for calculating the brightness value of each pixel in first filtered chessboard table images, Yi Jiji
The brightness value of each pixel in chessboard table images after calculating secondary filtering；
Comparing unit, for by the brightness value of each pixel in first filtered chessboard table images respectively with it is secondary
The brightness value of pixel in filtered chessboard table images in same position is compared；
Assignment unit, for after the brightness value of the pixel in first filtered chessboard table images is greater than secondary filtering
Chessboard table images in same position pixel brightness value when, the brightness value of pixel is set to 255, otherwise, will
The brightness value of pixel is set to 0；
Generation unit, for obtaining binaryzation chessboard according to brightness value determine, corresponding with each pixel
Table images.
It should be noted that X-comers provided in the present embodiment catch take device have in above-described embodiment
Catching for provided X-comers takes the identical beneficial effect of method, and to gridiron pattern involved in this present embodiment
Catching for angle point takes the specific introduction of method to please refer to above-described embodiment, and details are not described herein by the application.
On the basis of the above embodiments, the embodiment of the invention also provides a kind of catching for X-comers to take system, should
System includes:
Memory, for storing computer program；
Processor is realized when for executing computer program and catches the step of taking method such as above-mentioned X-comers.
For example, the processor in the present embodiment is for realizing the original chessboard table images of acquisition；To original chessboard table images into
Row binary conversion treatment obtains binaryzation chessboard table images；Binaryzation chessboard table images progress angle point is caught and takes analysis, determines mesh
Mark the corner location in region.
On the basis of the above embodiments, the embodiment of the invention also provides a kind of computer readable storage mediums, calculate
It is stored with computer program on machine readable storage medium storing program for executing, such as above-mentioned X-comers are realized when computer program is executed by processor
Catch the step of taking method.
The computer readable storage medium may include: USB flash disk, mobile hard disk, read-only memory (Read-Only
Memory, ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc. is various to deposit
Store up the medium of program code.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with other
The difference of embodiment, the same or similar parts in each embodiment may refer to each other.For device disclosed in embodiment
For, since it is corresponded to the methods disclosed in the examples, so being described relatively simple, related place is said referring to method part
It is bright.
It should also be noted that, in the present specification, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that the process, method, article or equipment for including a series of elements not only includes that
A little elements, but also including other elements that are not explicitly listed, or further include for this process, method, article or
The intrinsic element of equipment.In the absence of more restrictions, the element limited by sentence "including a ...", is not arranged
Except there is also other identical elements in the process, method, article or apparatus that includes the element.
The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention.
Various modifications to these embodiments will be readily apparent to those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, of the invention
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest scope of cause.
Claims (10)
1. a kind of catching for X-comers takes method characterized by comprising
Obtain original chessboard table images；
Binary conversion treatment is carried out to the original chessboard table images, obtains binaryzation chess corresponding with the original chessboard table images
Disk table images；
Binaryzation chessboard table images progress angle point is caught and takes analysis, determines the corner location in target area.
2. catching for X-comers according to claim 1 takes method, which is characterized in that described to the original chessboard
Table images carry out before binary conversion treatment, further includes:
The original chessboard table images are filtered, filtered chessboard table images are obtained；
It is described that binary conversion treatment is carried out to the original chessboard table images specifically:
Binary conversion treatment is carried out to the filtered chessboard table images.
3. catching for X-comers according to claim 2 takes method, which is characterized in that described to the original gridiron pattern
Image is filtered, and obtains the process of filtered chessboard table images are as follows:
Noise reduction process is filtered to the original chessboard table images, obtains first filtered chessboard table images；
Radius core is determined according to the black and white block size in the first filtered chessboard table images, and uses the radius core
Secondary filtering processing is carried out to the first filtered chessboard table images, the chessboard table images after obtaining secondary filtering.
4. catching for X-comers according to claim 3 takes method, which is characterized in that described according to the first filtering
The black and white block size in chessboard table images afterwards determines the process of radius core are as follows:
Using the half of the black and white block length in the first filtered chessboard table images as the size of the radius core.
5. catching for X-comers according to claim 3 takes method, which is characterized in that described to the filtered chess
Disk table images carry out binary conversion treatment, obtain the process of binaryzation chessboard table images are as follows:
The brightness value of each pixel in the first filtered chessboard table images is calculated, and calculates the secondary filter
The brightness value of each pixel in chessboard table images after wave；
By the brightness value of each pixel in the first filtered chessboard table images respectively and after the secondary filtering
The brightness value of pixel in chessboard table images in same position is compared；
The gridiron pattern after brightness value of the pixel in the first filtered chessboard table images is greater than the secondary filtering
When the brightness value of the pixel in image in same position, the brightness value of the pixel is set to 255, it otherwise, will be described
The brightness value of pixel is set to 0；
Binaryzation chessboard table images are obtained according to brightness value determining, corresponding with each pixel.
6. catching for X-comers according to claim 5 takes method, which is characterized in that described to the binaryzation chessboard
Table images progress angle point, which is caught, takes analysis, determines the process of the corner location in target area are as follows:
Black and white block in the binaryzation gridiron pattern objective area in image is traversed, and determines every group of intersection black and white block
Each intersection point；
Each intersection point is calculated separately out default on the upper left corner of the intersection point, the upper right corner, the lower left corner, the lower right corner
The sum of the brightness value of each pixel in region, obtain the first accumulated value corresponding with the predeterminable area in the upper left corner, with
Corresponding second accumulated value of the predeterminable area in the upper right corner, third accumulated value corresponding with the predeterminable area in the lower left corner and
The 4th accumulated value corresponding with the predeterminable area in the lower right corner；
When first accumulated value is greater than the second preset value, the first accumulated value and the 4th less than the first preset value, the second accumulated value
The absolute value of the difference of accumulated value is less than third preset value and the second accumulated value and the absolute value of the difference of third accumulated value is less than institute
When stating third preset value, using the intersection point as initial angle point；
Or when first accumulated value is greater than second preset value, the second accumulated value is less than first preset value, described
The absolute value of the difference of first accumulated value and the 4th accumulated value is less than the difference of third preset value, the second accumulated value and third accumulated value
When absolute value is less than the third preset value, using the intersection point as initial angle point；
Calculate the average coordinates value of angle point according to the coordinate value of each initial angle point in default angle point region, and by institute
State position coordinates of the average coordinates value as angle point.
7. a kind of catching for X-comers takes device characterized by comprising
Module is obtained, for obtaining original chessboard table images；
Processing module obtains binaryzation chessboard table images for carrying out binary conversion treatment to the original chessboard table images；
Extraction module takes analysis for catching to binaryzation chessboard table images progress angle point, determines the angle in target area
Point position.
8. catching for X-comers according to claim 7 takes device, which is characterized in that further include:
Filter module obtains filtered chessboard table images for being filtered to the original chessboard table images；
The processing module is specifically used for carrying out binary conversion treatment to the filtered chessboard table images.
9. a kind of catching for X-comers takes system characterized by comprising
Memory, for storing computer program；
Processor, realizing the X-comers as described in claim 1 to 6 any one when for executing the computer program
Catch the step of taking method.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program realizes that the X-comers as described in claim 1 to 6 any one are caught when the computer program is executed by processor
The step of taking method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910570335.XA CN110264531A (en) | 2019-06-27 | 2019-06-27 | A kind of catching for X-comers takes method, apparatus, system and readable storage medium storing program for executing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910570335.XA CN110264531A (en) | 2019-06-27 | 2019-06-27 | A kind of catching for X-comers takes method, apparatus, system and readable storage medium storing program for executing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110264531A true CN110264531A (en) | 2019-09-20 |
Family
ID=67922596
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910570335.XA Pending CN110264531A (en) | 2019-06-27 | 2019-06-27 | A kind of catching for X-comers takes method, apparatus, system and readable storage medium storing program for executing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110264531A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112284330A (en) * | 2020-11-18 | 2021-01-29 | 青岛科美创视智能科技有限公司 | Distance measuring system and method based on fisheye camera |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5525883A (en) * | 1994-07-08 | 1996-06-11 | Sara Avitzour | Mobile robot location determination employing error-correcting distributed landmarks |
| CN104036244A (en) * | 2014-06-09 | 2014-09-10 | 西安邮电大学 | Checkerboard pattern corner point detecting method and device applicable to low-quality images |
| CN106709952A (en) * | 2016-11-18 | 2017-05-24 | 南京仁光电子科技有限公司 | Automatic calibration method of display screen |
| CN107231553A (en) * | 2017-05-31 | 2017-10-03 | 信利光电股份有限公司 | Corner location acquisition methods and device |
| CN109300104A (en) * | 2017-07-24 | 2019-02-01 | 比亚迪股份有限公司 | Angular-point detection method, device |
-
2019
- 2019-06-27 CN CN201910570335.XA patent/CN110264531A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5525883A (en) * | 1994-07-08 | 1996-06-11 | Sara Avitzour | Mobile robot location determination employing error-correcting distributed landmarks |
| CN104036244A (en) * | 2014-06-09 | 2014-09-10 | 西安邮电大学 | Checkerboard pattern corner point detecting method and device applicable to low-quality images |
| CN106709952A (en) * | 2016-11-18 | 2017-05-24 | 南京仁光电子科技有限公司 | Automatic calibration method of display screen |
| CN107231553A (en) * | 2017-05-31 | 2017-10-03 | 信利光电股份有限公司 | Corner location acquisition methods and device |
| CN109300104A (en) * | 2017-07-24 | 2019-02-01 | 比亚迪股份有限公司 | Angular-point detection method, device |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112284330A (en) * | 2020-11-18 | 2021-01-29 | 青岛科美创视智能科技有限公司 | Distance measuring system and method based on fisheye camera |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111612781B (en) | Screen defect detection method and device and head-mounted display equipment | |
| CN106934803B (en) | method and device for detecting surface defects of electronic device | |
| CN106485275B (en) | A method of realizing that cover-plate glass is bonded with liquid crystal display positioning | |
| TW202011733A (en) | Method and device for performing target sampling on pictures | |
| CN107092871B (en) | Remote sensing image building detection method based on multiple dimensioned multiple features fusion | |
| US20130243343A1 (en) | Method and device for people group detection | |
| CN108280829A (en) | Welding seam method, computer installation and computer readable storage medium | |
| CN108171104A (en) | A kind of character detecting method and device | |
| CN108323204A (en) | A kind of method and intelligent terminal of detection face flaw point | |
| US20100084470A1 (en) | Two-dimensional barcode localization for camera based devices | |
| Lo et al. | Joint trilateral filtering for depth map super-resolution | |
| CN109740533A (en) | Masking ratio determines method, apparatus and electronic system | |
| CN104809453A (en) | Authentication method based on fingerprints | |
| CN111626163B (en) | Human face living body detection method and device and computer equipment | |
| CN107452028B (en) | Method and device for determining position information of target image | |
| CN109949227A (en) | Image split-joint method, system and electronic equipment | |
| CN109426814A (en) | A kind of positioning of the specific plate of invoice picture, recognition methods, system, equipment | |
| CN109086734A (en) | The method and device that pupil image is positioned in a kind of pair of eye image | |
| CN106971185A (en) | A kind of license plate locating method and device based on full convolutional network | |
| CN106919883B (en) | QR code positioning method and device | |
| CN105427333A (en) | Real-time registration method of video sequence image, system and shooting terminal | |
| CN109447117A (en) | The double-deck licence plate recognition method, device, computer equipment and storage medium | |
| CN105243662B (en) | The determination method and terminal device of a kind of terminal position | |
| CN106909916B (en) | Method for rapidly detecting and identifying sidewalk zebra crossing based on mobile phone platform | |
| CN109102026A (en) | A kind of vehicle image detection method, apparatus and system |
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 |