CN105574840B - Grain face aisle board detecting method based on image and device - Google Patents
Grain face aisle board detecting method based on image and device Download PDFInfo
- Publication number
- CN105574840B CN105574840B CN201410549190.2A CN201410549190A CN105574840B CN 105574840 B CN105574840 B CN 105574840B CN 201410549190 A CN201410549190 A CN 201410549190A CN 105574840 B CN105574840 B CN 105574840B
- Authority
- CN
- China
- Prior art keywords
- image
- radon
- pixel
- changing images
- grain face
- 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.)
- Active
Links
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
An embodiment of the present invention provides a kind of grain face aisle board detecting method based on image, including：The corresponding normalized Radon changing images of grain face image are obtained, the pixel with max pixel value in the normalized Radon changing images is found；When the max pixel value is more than preset normalized Radon changing images pixel threshold, judge in the normalized Radon changing images, it whether there is matched pixel point in the relevant range of the pixel with max pixel value, the pixel value of the matched pixel point is more than the normalized Radon changing images pixel threshold, if in the presence of, it is determined that include grain face walkway board in the grain face image.The present invention passes through the methods of image edge information extraction and Radon transformation, collected grain face image in silo is analyzed, the characteristics of image for meeting grain face aisle plate shape and laying characteristic is found, to fast and effeciently judge whether be equipped with walkway board in the grain face in image.
Description
Technical field
The present invention relates to field of image recognition more particularly to a kind of grain face aisle board detecting methods and dress based on image
It sets.
Background technology
In grain storage management, it is an important procedure after buying securities with all one's capital that grain face walkway board is laid in grain face, in order to
Check that the people of grain feelings walks above in static state keeping.Common laying method is to be parallel to multiple grain face walkway boards with edge
The direction of metope is put, and the access in length and breadth of a plurality of square crossing is formed.The detection of grain face walkway board is grain storage video prison
Control one of committed step during image intelligent understands and the important evidence of silo job state identification.
It is silo static state keeping state that walkway board whether is equipped in the applications such as grain storage video monitoring, in grain face
A kind of important feature.But since grain face walkway board is artificial laying, generally it is unable to the linear edge of formation rule.Also, grain
The color of face walkway board differs, and light is uneven in silo, these all increase the difficulty that grain face walkway board is detected by image mode
Degree.
Therefore, it develops a kind of efficient grain face aisle board detecting method based on image and is one and urgently to be resolved hurrily ask
Topic.
Invention content
The embodiment provides a kind of grain face aisle board detecting method and device based on image, it is effective to realize
Ground judges whether be equipped with walkway board in the grain face in image.
The present invention provides following schemes：
A kind of grain face aisle board detecting method based on image, including：
The corresponding normalized Radon changing images of grain face image are obtained, the normalized Radon Transformation Graphs are found
The pixel with max pixel value as in；
When the max pixel value is more than preset normalized Radon changing images pixel threshold, judge
In the normalized Radon changing images, in the relevant range of the pixel with max pixel value with the presence or absence of
With pixel, the pixel value of the matched pixel point is more than the normalized Radon changing images pixel threshold, and if it exists,
Then determine in the grain face image to include grain face walkway board.
The corresponding normalized Radon changing images of the acquisition grain face image, including：
The corresponding edge image of grain face image is calculated by edge detection method, Radon changes are done to the edge image
It changes, obtains the Radon changing images of the edge image；
It is arranged and complete 1 image of the specific equal resolution of the edge image, Radon transformation is done to complete 1 image,
The Radon changing images of complete 1 image are obtained, the value of each pixel in complete 1 image is 1；
Establish the image between the Radon changing images of the edge image and the Radon changing images of complete 1 image
Correspondence, according to described image correspondence by each pixel in the Radon changing images of the edge image
Pixel value and the pixel value of corresponding pixel points in the Radon changing images of complete 1 image are divided by, and obtain normalized Radon
Changing image.
Between the Radon changing images for establishing the edge image and the Radon changing images of complete 1 image
Image correspondence, including：
It will be in the Radon changing images of pixel and complete 1 image in the Radon changing images of the edge image
Establish correspondence between the pixel of same position, the Radon changing images of the edge image and complete 1 image
Correspondence in Radon changing images between all pixels point constitutes Radon changing images and the institute of the edge image
State the image correspondence between the Radon changing images of complete 1 image.
The method further includes：
Reject the Radon Transformation Graphs that pixel value in the Radon changing images of complete 1 image is less than preset complete 1 image
As the pixel of threshold value.
The method further includes：
When the max pixel value in the normalized Radon changing images is no more than preset described normalized
When Radon changing image pixel thresholds, it is determined that do not include grain face walkway board in the grain face image.
The judgement in the normalized Radon changing images, the pixel with max pixel value
It whether there is matched pixel point in relevant range, the pixel value of the matched pixel point is more than the normalized Radon transformation
Image pixel threshold value, and if it exists, then determine in the grain face image to include grain face walkway board, including：
In the normalized Radon changing images, set as symmetric points using the pixel with max pixel value
It sets in lower regions, the lower regions do not include the pixel with max pixel value, and the lower regions are by maximum
Alternate position spike, minimum position is poor, and maximum angle difference determines that the maximum position is poor, and minimum position difference does not indicate the edge graph
The maximum value and minimum value of the number of pixels of walkway board width as in, the maximum angle difference indicate aisle in the edge image
The maximum value of the angle of inclination difference of plate both sides line segment；
The matched pixel point with max pixel value in the lower regions is found out, judges the pixel of the matched pixel point
Whether value is more than the normalized Radon changing images pixel threshold, if it is, it includes grain to determine in the grain face image
Face walkway board；Otherwise, it determines not including grain face walkway board in the grain face image.
For the walkway board edge line on straight line in the edge image, the normalized Radon changing images
Pixel threshold indicate the marginal point number on the walkway board edge line should at least account for its pixel sum on straight line ratio
Example.
A kind of grain face aisle board checking device based on image, including：
Normalized Radon changing images acquisition module becomes for obtaining the corresponding normalized Radon of grain face image
Change image；
Maximum pixel point processing module has max pixel value for finding in the normalized Radon changing images
Pixel, judge the max pixel value whether be more than preset normalized Radon changing images pixel threshold；
Matched pixel point processing module, for becoming when the max pixel value is more than preset normalized Radon
When changing image pixel threshold value, judge in the normalized Radon changing images, the pixel with max pixel value
Relevant range in whether there is matched pixel point, the pixel value of the matched pixel point is more than the normalized Radon and becomes
Change image pixel threshold value；
Grain face walkway board judgment module, for judging that the matched pixel point exists when the matched pixel point processing module
When, it is determined that include grain face walkway board in the grain face image.
The normalized Radon changing images acquisition module, specifically for being put out cereal by edge detection method calculating
Image corresponding edge image in face does Radon transformation to the edge image, obtains the Radon Transformation Graphs of the edge image
Picture；
It is arranged and complete 1 image of the specific equal resolution of the edge image, Radon transformation is done to complete 1 image,
The Radon changing images of complete 1 image are obtained, the value of each pixel in complete 1 image is 1；
Establish the image between the Radon changing images of the edge image and the Radon changing images of complete 1 image
Correspondence, according to described image correspondence by each pixel in the Radon changing images of the edge image
Pixel value and the pixel value of corresponding pixel points in the Radon changing images of complete 1 image are divided by, and obtain normalized Radon
Changing image.
The normalized Radon changing images acquisition module is specifically used for becoming the Radon of the edge image
Change foundation between the pixel in image and the pixel of same position in the Radon changing images of complete 1 image it is corresponding close
In the Radon changing images of system, the Radon changing images of the edge image and complete 1 image between all pixels point
Correspondence constitutes between the Radon changing images of the edge image and the Radon changing images of complete 1 image
Image correspondence.
The normalized Radon changing images acquisition module is additionally operable to reject the Radon transformation of complete 1 image
Pixel value is less than the pixel of the Radon changing image pixel thresholds of preset complete 1 image in image.
The maximum pixel point processing module is additionally operable to when the maximum picture in the normalized Radon changing images
When element value is no more than the preset normalized Radon changing images pixel threshold, it is determined that in the grain face image
Not comprising grain face walkway board.
The grain face walkway board judgment module is additionally operable in the normalized Radon changing images, with the tool
It is that symmetric points are arranged in lower regions to have the pixel of max pixel value, and the lower regions do not include described with maximum pixel
The pixel of value, the lower regions are poor by maximum position, and minimum position is poor, and maximum angle difference determines that the maximum position is poor,
Minimum position difference does not indicate the maximum value and minimum value of the number of pixels of walkway board width in the edge image, the maximum
Differential seat angle indicates the maximum value of the angle of inclination difference of walkway board both sides line segment in the edge image；
The matched pixel point with max pixel value in the lower regions is found out, judges the pixel of the matched pixel point
Whether value is more than the normalized Radon changing images pixel threshold, if it is, it includes grain to determine in the grain face image
Face walkway board；Otherwise, it determines not including grain face walkway board in the grain face image.
The embodiment of the present invention is believed by image border it can be seen from the technical solution that embodiments of the invention described above provide
The methods of breath extraction and Radon transformation, analyze collected grain face image in silo, and searching meets grain face walkway board shape
The characteristics of image of shape and laying characteristic, to fast and effeciently judge whether be equipped with walkway board in the grain face in image.
Description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, required use in being described below to embodiment
Attached drawing be briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for this
For the those of ordinary skill of field, without having to pay creative labor, other are can also be obtained according to these attached drawings
Attached drawing.
Fig. 1 is a kind of process flow for grain face aisle board detecting method based on image that the embodiment of the present invention one provides
Figure；
Fig. 2 is a kind of process flow of the grain face aisle board detecting method based on image provided by Embodiment 2 of the present invention
Figure；
Fig. 3 is the corresponding edge image of grain face image provided by Embodiment 2 of the present invention；
Fig. 4 is the Radon changing images of the corresponding edge image of grain face image provided by Embodiment 2 of the present invention；
Fig. 5 is the Radon changing images of complete 1 image provided by Embodiment 2 of the present invention；
Fig. 6 is the corresponding normalized Radon changing images of grain face image provided by Embodiment 2 of the present invention；
Fig. 7 is the corresponding normalized Radon changing images of grain face image provided by Embodiment 2 of the present invention；
Fig. 8 is a kind of module map for grain face aisle board checking device based on image that the embodiment of the present invention three provides.
Specific implementation mode
For ease of the understanding to the embodiment of the present invention, done further by taking several specific embodiments as an example below in conjunction with attached drawing
Explanation, and each embodiment does not constitute the restriction to the embodiment of the present invention.
An embodiment of the present invention provides a kind of grain face aisle board detecting method based on image, is carried by image edge information
Take with Radon transformation the methods of, collected grain face image in silo is analyzed, searching meet grain face aisle plate shape and
The characteristics of image of laying characteristic, to fast and effeciently judge whether be equipped with walkway board in the grain face in image.
Embodiment one
The process flow of this embodiment offers a kind of grain face aisle board detecting method based on image is as shown in Figure 1, packet
Include following processing step：
Step S110, the corresponding normalized Radon changing images of grain face image are obtained, are found described normalized
Pixel with max pixel value in Radon changing images；
Step S120, when the max pixel value is more than preset normalized Radon changing images pixel threshold
When, judge in the normalized Radon changing images, is in the relevant range of the pixel with max pixel value
It is no that there are matched pixel point, the pixel value of the matched pixel point is more than the normalized Radon changing images pixel threshold,
If in the presence of, it is determined that include grain face walkway board in the grain face image.
Embodiment two
The process flow of this embodiment offers a kind of grain face aisle board detecting method based on image is as shown in Fig. 2, packet
Include following processing step：
Step S211, edge image is calculated.
Given grain face image calculates grain face figure using edge detection method, preferably Sobel operator edge detections method
As corresponding edge image, which is gray level image or bianry image, and the positive value point in edge image is denoted as marginal point.
One edge image calculated by the grain face image for being equipped with walkway board is as shown in Figure 3.
Step S212, the Radon changing images of edge image are calculated.
Radon transformation is done to the edge image, the Radon changing images of the edge image is obtained, is denoted as Ro.
The meaning of Radon transformation is, in different directions with the straight line of angle to institute on straight line in a gray level image or bianry image
There is the value of pixel to do line integral, obtained gray level image is exactly Radon changing images, and two reference axis of the image are remembered respectively
For position coordinates axis and angle coordinate axis.Fig. 3 is the corresponding edge image of grain face image, the corresponding side of grain face image shown in Fig. 3
The Radon changing images of edge image are as shown in Figure 4.
Step S213, the Radon changing images of complete 1 image are calculated.
It is arranged and complete 1 image of the specific equal resolution of the edge image, Radon transformation is done to complete 1 image,
Obtain the Radon changing images of complete 1 image.
The bianry image of a resolution ratio same as edge image is generated, the value of each pixel of juxtaposition is 1, is denoted as complete 1
Image.The Radon changing images for calculating complete 1 image, are denoted as Rn.Complete 1 image of resolution ratio same as edge image shown in Fig. 1
Radon changing images are as shown in Figure 5.By in Rn be less than threshold value m pixel be set as just infinite, it is just infinite in actual setting can
The number for being more than pixel maximum value in Rn with one replaces, and the value of m is by empirically determined, since the pixel value after transformation indicates transformation
The number of pixel on preceding straight line, the effect of setting threshold value m are that straight line of the pixel sum less than m will be ignored
Radon transformation results reject pixel value in the Radon changing images of complete 1 image and are less than preset complete 1 image
The pixel of Radon changing image threshold values.Radon changing images shown in fig. 5, just infinite available 350 are replaced, the value of m
It is preferred that 50.
Step S214, the corresponding normalized Radon changing images of grain face image are calculated.
Establish the image between the Radon changing images of the edge image and the Radon changing images of complete 1 image
Correspondence, according to described image correspondence by each pixel in the Radon changing images of the edge image
Pixel value and the pixel value of corresponding pixel points in the Radon changing images of complete 1 image are divided by, and obtain normalized Radon
Changing image.
It will be in the Radon changing images of pixel and complete 1 image in the Radon changing images of the edge image
Establish correspondence between the pixel of same position, the Radon changing images of the edge image and complete 1 image
Correspondence in Radon changing images between all pixels point constitutes Radon changing images and the institute of the edge image
State the image correspondence between the Radon changing images of complete 1 image.
The value of corresponding pixel points in the value of each pixel in Ro and Rn is divided by according to above-mentioned image correspondence,
A normalized Radon changing image is obtained, R, i.e. R=Ro/Rn are denoted as.Wherein ,/indicate each pixel in two images
Point does division respectively.The R that Rn is calculated shown in Ro and Fig. 5 as shown in Figure 4 is as shown in Figure 6.
Step S215, the pixel with max pixel value in R is found out, it is pre- to judge whether the max pixel value in R is more than
The normalized Radon changing images pixel threshold th first set, if so, thening follow the steps S216；Otherwise, step is executed
S220。
If max pixel value step S216, in R is more than th, the coordinate of the pixel with maximum value in R is marked
(xm, ym), xm are the points on position coordinates axis, and ym is the point on angle coordinate axis.Wherein, th is by empirically determined, for edge
Walkway board edge line in image on straight line, the value of th, which indicates its marginal point number at least, should account for its institute pixel on straight line
The ratio of point sum.For R shown in fig. 6, i.e., edge image shown in FIG. 1, the value preferably 0.25 of th.
Step S217, matched pixel point is found.
In the normalized Radon changing images R, set as symmetric points using the pixel with max pixel value
It sets in lower regions, the lower regions do not include the pixel with max pixel value, and the lower regions are by maximum
Alternate position spike xl, minimum position difference xl0, maximum angle difference yl determine that the maximum position difference xl, minimum position difference xl0 distinguishes table
Show that the maximum value and minimum value of the number of pixels difference of walkway board both sides in the edge image, the maximum angle difference yl indicate institute
State the maximum value of the angle of inclination difference of walkway board both sides in edge image；
The matched pixel point with max pixel value in the lower regions is found out, judges the pixel of the matched pixel point
Whether value is more than the normalized Radon changing images pixel threshold, if it is, it includes grain to determine in the grain face image
Face walkway board；Otherwise, it determines not including grain face walkway board in the grain face image.
In R with (xm, ym) be symmetric points lower regions L in find out the pixel with maximum value, wherein L is by most
Big this 3 parameters of alternate position spike xl, minimum position difference xl0, maximum angle difference yl determine that the value of parameter is by empirically determined.For Fig. 6
Shown in R, xl, xl0, the value of yl respectively preferably 30,10,10.Xl and xl0 indicates walkway board width in the edge image respectively
Number of pixels maximum value and minimum value, the yl indicates that the angle of inclination of walkway board both sides line segment in the edge image is poor
Maximum value.Image shown in Fig. 7 is that the part sectional drawing of Fig. 6 adds a circle and two rectangle shadow region field marks, in round
Heart point indicates (xm, ym), and corresponding L has two parts, by upper and lower two rectangle shadow regions indicate, above rectangle upper left
Angular coordinate be (xm-xl, ym-yl), bottom right angular coordinate be (xm-xl0, ym+yl), below rectangle top left co-ordinate be (xm+
Xl0, ym-yl), bottom right angular coordinate is (xm+xl, ym+yl), and first coordinate is ordinate in above-mentioned coordinate, i.e. position is sat
Mark, first coordinate is abscissa, i.e. angle coordinate, and using the upper left corner of image shown in Fig. 6 as coordinate origin.
Those skilled in the art will be understood that the determination of the range of above-mentioned lower regions L is only for example, other it is existing or
The range for the above-mentioned lower regions L being likely to occur from now on is such as applicable to the embodiment of the present invention, should also be included in protection of the present invention
Within range, and it is incorporated herein by reference herein.
Step S218, judge whether the pixel value of matched pixel point is more than threshold value th, if so, thening follow the steps S219；
Otherwise, step S220 is executed.
Step S219；Determine in the grain face image to include grain face walkway board, output testing result is to have walkway board, is detected
Terminate.
Step S220 is determined and is not included grain face walkway board in the grain face image, and output testing result is no walkway board, inspection
Survey terminates.
Embodiment three
This embodiment offers a kind of grain face aisle board checking device based on image, specific implementation structure such as Fig. 8 institutes
Show, can specifically include following module：
Normalized Radon changing images acquisition module 81, for obtaining the corresponding normalized Radon of grain face image
Changing image；
Maximum pixel point processing module 82 has maximum pixel for finding in the normalized Radon changing images
The pixel of value, judges whether the max pixel value is more than preset normalized Radon changing images pixel threshold
Value；
Matched pixel point processing module 83, for being more than preset normalized Radon when the max pixel value
When changing image pixel threshold, judge in the normalized Radon changing images, the pixel with max pixel value
It whether there is matched pixel point in the relevant range of point, the pixel value of the matched pixel point is more than the normalized Radon
Changing image pixel threshold；
Grain face walkway board judgment module 84 judges that the matched pixel point is deposited for working as the matched pixel point processing module
When, it is determined that in the grain face image include grain face walkway board.
Further, the normalized Radon changing images acquisition module, specifically for passing through edge detection method
The corresponding edge image of grain face image is calculated, Radon transformation is done to the edge image, obtains the edge image
Radon changing images；
It is arranged and complete 1 image of the specific equal resolution of the edge image, Radon transformation is done to complete 1 image,
Obtain the Radon changing images of complete 1 image；
Establish the image between the Radon changing images of the edge image and the Radon changing images of complete 1 image
Correspondence, according to described image correspondence by each pixel in the Radon changing images of the edge image
Pixel value and the pixel value of corresponding pixel points in the Radon changing images of complete 1 image are divided by, and obtain normalized Radon
Changing image.
Further, the normalized Radon changing images acquisition module is specifically used for the edge image
It pixel in Radon changing images and is established between the pixel of same position in the Radon changing images of complete 1 image
All pixels point in the Radon changing images of correspondence, the Radon changing images of the edge image and complete 1 image
Between correspondence, constitute the Radon changing images of the Radon changing images and complete 1 image of the edge image
Between image correspondence.
Further, the normalized Radon changing images acquisition module is additionally operable to reject complete 1 image
Pixel value is less than the pixel of preset complete 1 image pixel threshold value in Radon changing images.
Further, maximum pixel point processing module is additionally operable to when the maximum in the normalized Radon changing images
When pixel value is not more than the preset normalized Radon changing images pixel threshold, it is determined that the grain face image
In do not include grain face walkway board.
Further, the grain face walkway board judgment module is additionally operable in the normalized Radon changing images
In, it is arranged in lower regions by symmetric points of the pixel with max pixel value, the lower regions do not include described
Pixel with max pixel value, the lower regions are poor by maximum position, and minimum position is poor, and maximum angle difference determines, institute
State that maximum position is poor, minimum position difference does not indicate in the edge image maximum value of the number of pixels of walkway board width and most
Small value, the maximum angle difference indicate the maximum value of the angle of inclination difference of walkway board both sides line segment in the edge image；
The matched pixel point with max pixel value in the lower regions is found out, judges the pixel of the matched pixel point
Whether value is more than the normalized Radon changing images pixel threshold, if it is, it includes grain to determine in the grain face image
Face walkway board；Otherwise, it determines not including grain face walkway board in the grain face image.
The detailed process and preceding method of the detection of the grain face walkway board based on image are carried out with the device of the embodiment of the present invention
Embodiment is similar, and details are not described herein again.
In conclusion the embodiment of the present invention by image edge information extraction and Radon convert the methods of, to being adopted in silo
The grain face image collected is analyzed, and the characteristics of image for meeting grain face aisle plate shape and laying characteristic is found, to quickly have
Effect ground judges whether be equipped with walkway board in the grain face in image.
The embodiment of the present invention fast and effeciently detects whether be equipped with away in grain face by analyzing grain face image
Guidance tape, solves the test problems of this important symbol object of grain face walkway board, and testing result can be used as silo job state
The important evidence of the work such as identification.
One of ordinary skill in the art will appreciate that：Attached drawing is the schematic diagram of one embodiment, module in attached drawing or
Flow is not necessarily implemented necessary to the present invention.
As seen through the above description of the embodiments, those skilled in the art can be understood that the present invention can
It is realized by the mode of software plus required general hardware platform.Based on this understanding, technical scheme of the present invention essence
On in other words the part that contributes to existing technology can be expressed in the form of software products, the computer software product
It can be stored in a storage medium, such as ROM/RAM, magnetic disc, CD, including some instructions are used so that a computer equipment
(can be personal computer, server either network equipment etc.) executes the certain of each embodiment of the present invention or embodiment
Method described in part.
Each embodiment in this specification is described in a progressive manner, identical similar portion between each embodiment
Point just to refer each other, and each embodiment focuses on the differences from other embodiments.Especially for device or
For system embodiment, since it is substantially similar to the method embodiment, so describing fairly simple, related place is referring to method
The part of embodiment illustrates.Apparatus and system embodiment described above is only schematical, wherein the conduct
The unit that separating component illustrates may or may not be physically separated, the component shown as unit can be or
Person may not be physical unit, you can be located at a place, or may be distributed over multiple network units.It can root
According to actual need that some or all of module therein is selected to achieve the purpose of the solution of this embodiment.Ordinary skill
Personnel are without creative efforts, you can to understand and implement.
The foregoing is only a preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto,
Any one skilled in the art in the technical scope disclosed by the present invention, the change or replacement that can be readily occurred in,
It should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with scope of the claims
Subject to.
Claims (11)
1. a kind of grain face aisle board detecting method based on image, which is characterized in that including：
The corresponding edge image of grain face image is calculated by edge detection method, Radon transformation is done to the edge image, is obtained
Take the Radon changing images of the edge image；
Complete 1 image for having equal resolution with the edge image is set, Radon transformation is done to complete 1 image, obtains institute
The Radon changing images of complete 1 image are stated, the value of each pixel in complete 1 image is 1；
The image established between the Radon changing images of the edge image and the Radon changing images of complete 1 image corresponds to
Relationship, according to described image correspondence by the pixel of each pixel in the Radon changing images of the edge image
The pixel value of value and corresponding pixel points in the Radon changing images of complete 1 image is divided by, and obtains normalized Radon transformation
Image；
Find the pixel with max pixel value in the normalized Radon changing images；
When the max pixel value is more than preset normalized Radon changing images pixel threshold, judge described
In normalized Radon changing images, with the presence or absence of matching picture in the relevant range of the pixel with max pixel value
The pixel value of vegetarian refreshments, the matched pixel point is more than the normalized Radon changing images pixel threshold, and if it exists, then really
Include grain face walkway board in the fixed grain face image.
2. the grain face aisle board detecting method according to claim 1 based on image, which is characterized in that described establishes institute
The image correspondence between the Radon changing images of edge image and the Radon changing images of complete 1 image is stated, including：
Pixel in the Radon changing images of the edge image is identical with the Radon changing images of complete 1 image
Correspondence, the Radon of the Radon changing images of the edge image and complete 1 image are established between the pixel of position
Correspondence in changing image between all pixels point constitutes the Radon changing images and described complete 1 of the edge image
Image correspondence between the Radon changing images of image.
3. the grain face aisle board detecting method according to claim 1 based on image, which is characterized in that the method is also
Including：
Reject the Radon changing image thresholds that pixel value in the Radon changing images of complete 1 image is less than preset complete 1 image
The pixel of value.
4. the grain face aisle board detecting method according to claim 1 based on image, which is characterized in that the method is also
Including：
When the max pixel value in the normalized Radon changing images is no more than preset described normalized
When Radon changing image pixel thresholds, it is determined that do not include grain face walkway board in the grain face image.
5. the grain face aisle board detecting method according to any one of claims 1 to 4 based on image, which is characterized in that institute
The judgement stated is in the normalized Radon changing images, in the relevant range of the pixel with max pixel value
With the presence or absence of matched pixel point, the pixel value of the matched pixel point is more than the normalized Radon changing images pixel threshold
Value, and if it exists, then determine in the grain face image to include grain face walkway board, including：
In the normalized Radon changing images, using the pixel with max pixel value as in symmetric points setting
Lower region, the lower regions do not include the pixel with max pixel value, and the lower regions are poor by maximum position,
Minimum position is poor, and maximum angle difference determines that the maximum position is poor, and minimum position difference does not indicate aisle in the edge image
The maximum value and minimum value of the number of pixels of plate width, the maximum angle difference indicate two side line of walkway board in the edge image
The maximum value of the angle of inclination difference of section；
The matched pixel point with max pixel value in the lower regions is found out, judges that the pixel value of the matched pixel point is
It is no to be more than the normalized Radon changing images pixel threshold, it is walked comprising grain face in the grain face image if it is, determining
Guidance tape；Otherwise, it determines not including grain face walkway board in the grain face image.
6. the grain face aisle board detecting method according to claim 5 based on image, which is characterized in that for the edge
Walkway board edge line in image on straight line, the normalized Radon changing images pixel threshold indicate the aisle
Marginal point number on plate edge line should at least account for its pixel sum on straight line ratio.
7. a kind of grain face aisle board checking device based on image, which is characterized in that including：
Normalized Radon changing images acquisition module, for obtaining the corresponding normalized Radon Transformation Graphs of grain face image
Picture；The normalized Radon changing images acquisition module calculates grain face image pair specifically for passing through edge detection method
The edge image answered does Radon transformation to the edge image, obtains the Radon changing images of the edge image；
Complete 1 image for having equal resolution with the edge image is set, Radon transformation is done to complete 1 image, obtains institute
The Radon changing images of complete 1 image are stated, the value of each pixel in complete 1 image is 1；
The image established between the Radon changing images of the edge image and the Radon changing images of complete 1 image corresponds to
Relationship, according to described image correspondence by the pixel of each pixel in the Radon changing images of the edge image
The pixel value of value and corresponding pixel points in the Radon changing images of complete 1 image is divided by, and obtains normalized Radon transformation
Image；
Maximum pixel point processing module, for finding the picture with max pixel value in the normalized Radon changing images
Vegetarian refreshments, judges whether the max pixel value is more than preset normalized Radon changing images pixel threshold；
Matched pixel point processing module, for being more than preset normalized Radon Transformation Graphs when the max pixel value
When as pixel threshold, judge in the normalized Radon changing images, the phase of the pixel with max pixel value
It closes and whether there is matched pixel point in region, the pixel value of the matched pixel point is more than the normalized Radon Transformation Graphs
As pixel threshold；
Grain face walkway board judgment module is used in the presence of the matched pixel point processing module judges the matched pixel point,
Then determine in the grain face image to include grain face walkway board.
8. the grain face aisle board checking device according to claim 7 based on image, it is characterised in that：
The normalized Radon changing images acquisition module is specifically used for the Radon changing images of the edge image
In pixel and complete 1 image Radon changing images in same position pixel between establish correspondence, it is described
Corresponding pass in the Radon changing images of the Radon changing images of edge image and complete 1 image between all pixels point
System, constitutes the image pair between the Radon changing images of the edge image and the Radon changing images of complete 1 image
It should be related to.
9. the grain face aisle board checking device according to claim 7 based on image, it is characterised in that：
The normalized Radon changing images acquisition module is additionally operable to reject the Radon changing images of complete 1 image
Middle pixel value is less than the pixel of the Radon changing image pixel thresholds of preset complete 1 image.
10. the grain face aisle board checking device according to claim 7 based on image, it is characterised in that：
The maximum pixel point processing module is additionally operable to when the max pixel value in the normalized Radon changing images
When no more than the preset normalized Radon changing images pixel threshold, it is determined that do not wrapped in the grain face image
Walkway board containing grain face.
11. according to grain face aisle board checking device of claim 7 to 10 any one of them based on image, it is characterised in that：
The grain face walkway board judgment module is additionally operable in the normalized Radon changing images, is had most with described
The pixel of big pixel value is that lower regions are arranged in symmetric points, and the lower regions do not include the picture with max pixel value
Vegetarian refreshments, the lower regions are poor by maximum position, and minimum position is poor, and maximum angle difference determines that the maximum position is poor, minimum bit
Maximum value and minimum value that difference does not indicate the number of pixels of walkway board width in the edge image are set, the maximum angle is poor
Indicate the maximum value of the angle of inclination difference of walkway board both sides line segment in the edge image；
The matched pixel point with max pixel value in the lower regions is found out, judges that the pixel value of the matched pixel point is
It is no to be more than the normalized Radon changing images pixel threshold, it is walked comprising grain face in the grain face image if it is, determining
Guidance tape；Otherwise, it determines not including grain face walkway board in the grain face image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410549190.2A CN105574840B (en) | 2014-10-16 | 2014-10-16 | Grain face aisle board detecting method based on image and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410549190.2A CN105574840B (en) | 2014-10-16 | 2014-10-16 | Grain face aisle board detecting method based on image and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105574840A CN105574840A (en) | 2016-05-11 |
| CN105574840B true CN105574840B (en) | 2018-09-18 |
Family
ID=55884934
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410549190.2A Active CN105574840B (en) | 2014-10-16 | 2014-10-16 | Grain face aisle board detecting method based on image and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105574840B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110531772B (en) * | 2019-09-12 | 2022-12-20 | 四川阿泰因机器人智能装备有限公司 | Control method and system of grain leveling robot |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1691064A (en) * | 2004-04-26 | 2005-11-02 | 三丰株式会社 | Image processing apparatus using morphology |
| CN102542277A (en) * | 2012-01-06 | 2012-07-04 | 中国人民解放军第二炮兵装备研究院第三研究所 | Method for detecting ship trail of ocean synthetic aperture radar image |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7524061B2 (en) * | 2005-10-12 | 2009-04-28 | Siemens Corporate Research, Inc. | System and method for robust optic disk detection in retinal images using vessel structure and radon transform |
| CN101540040B (en) * | 2008-03-21 | 2012-12-12 | 深圳迈瑞生物医疗电子股份有限公司 | Method and device for automatically detecting boundary of beam-limiting device |
-
2014
- 2014-10-16 CN CN201410549190.2A patent/CN105574840B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1691064A (en) * | 2004-04-26 | 2005-11-02 | 三丰株式会社 | Image processing apparatus using morphology |
| CN102542277A (en) * | 2012-01-06 | 2012-07-04 | 中国人民解放军第二炮兵装备研究院第三研究所 | Method for detecting ship trail of ocean synthetic aperture radar image |
Non-Patent Citations (1)
| Title |
|---|
| 基于Radon变换的机织物纬斜检测方法;宫元九;《电子测量技术》;20140228;第37卷(第2期);58-63页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105574840A (en) | 2016-05-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yeum et al. | Vision‐based automated crack detection for bridge inspection | |
| CN109215020A (en) | Ultra-high-tension power transmission line fault recognition method based on computer vision | |
| CN106447669B (en) | The adhesion particle image concave point dividing method differentiated based on round masking-out area ratio | |
| Maini et al. | Study and comparison of various image edge detection techniques | |
| CN108022233A (en) | A kind of edge of work extracting method based on modified Canny operators | |
| CN105654097B (en) | The detection method of quadrangle marker in image | |
| Abate et al. | BIRD: Watershed based iris detection for mobile devices | |
| CN110097542A (en) | Detection method, device and the storage medium of chip bubble | |
| US20160364601A1 (en) | Image processing apparatus image processing method, and control program to perform face-detection processing | |
| CN107452035B (en) | Method and apparatus for analyzing lane line image and computer readable medium thereof | |
| CN107392139A (en) | A kind of method for detecting lane lines and terminal device based on Hough transformation | |
| WO2019190405A1 (en) | Method and apparatus for detecting condition of a bolt on a bolted structure | |
| CN111062918B (en) | Abnormality detection method and device based on computer vision | |
| CN110199317A (en) | Automatic detection, counting and measurement using handheld device to plank | |
| CN110188730A (en) | Face datection and alignment schemes based on MTCNN | |
| CN110458855A (en) | Image extraction method and Related product | |
| CN108537787A (en) | A kind of quality judging method of facial image | |
| CN110147748A (en) | A kind of mobile robot obstacle recognition method based on road-edge detection | |
| CN105574840B (en) | Grain face aisle board detecting method based on image and device | |
| CN115512134A (en) | Express item stacking abnormity early warning method, device, equipment and storage medium | |
| CN106530481A (en) | Method and device for detecting abnormal transmission of paper money | |
| CN108052921A (en) | A kind of method for detecting lane lines, device and terminal | |
| CN107292238A (en) | Contour of building recognition methods with end point is constrained based on spatial topotaxy | |
| CN107766847A (en) | A kind of method for detecting lane lines and device | |
| CN116805332A (en) | Section steel posture distinguishing method based on Hough transformation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |