CN103093456B - Corn ear character index computing method based on images - Google Patents
Corn ear character index computing method based on images Download PDFInfo
- Publication number
- CN103093456B CN103093456B CN201210572760.0A CN201210572760A CN103093456B CN 103093456 B CN103093456 B CN 103093456B CN 201210572760 A CN201210572760 A CN 201210572760A CN 103093456 B CN103093456 B CN 103093456B
- Authority
- CN
- China
- Prior art keywords
- image
- corn
- corn ear
- ear
- images
- 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)
Abstract
The invention relates to image processing technology, and particularly discloses a corn ear character index computing method. The corn ear character index computing method comprises the steps of obtaining color images CIi (i= 1,2, 3 and 4) of corn ears, transforming the color images to grayscale images SIi and binary images BIi, rectifying axial and radial distortion to obtain rectified color images CI2i, grayscale images HIi and binary images BI2i, segmenting the images HIi to obtain binary images BI3i which only contain corn kernels, spicing the images BI3i to obtain a panorama BI4 of the kernels, conducting morphological operation to the images BI3i to work out the barren tip area of the corn ears and the barren tip length of the corn ears, working out the number of kernels per row according to the images BI3i, and working out ear row number according to the images BI4. Through the rectification of the axial and the radial distortion, true forms of the corn ears and the kernels are recovered and accuracy of parameter computing is guaranteed. At the same time, an integral solution if provided for the computing of corn ear various character indexes.
Description
Technical field
The present invention relates to technical field of image processing, particularly a kind of computing method of corn ear character index.
Background technology
The economical character of corn ear is the routine measurement project in research and production, on corn yield existence impact in various degree.In order to fully understand the influence degree of fruit ear quantitative character to output, specifying the formation effect of every characteristic index to output, needing to carry out Measurement accuracy to a large amount of fruit ear sample.At present, for grain number per spike, row grain number, the characteristic index such as tassel row number and bald sharp length of corn ear, general employing manual measurement and statistical method obtain, process is loaded down with trivial details, error is larger, especially capable grain number and tassel row number etc. have the index of statistical significance, and its measurement result is subject to the experience influence of survey crew.
Carrying out precision corn ear test based on image, is that a kind of fusion calculation machine vision technique and computer image processing technology carry out determination and analysis to corn ear, and then the technological means of quick obtaining Ear Characters characteristic.Based on the species test method simple, intuitive, convenient and swift of fruit ear image, greatly can reduce human cost, improve corn seed investigating efficiency, advance the precision of corn seed investigating work flow, standardization, realize the ALARA Principle of species test flow process, can review with visual.The method of the existing properties and characteristics parameter based on image calculating corn ear, mainly for single traits index, implementation method lacks unified, integrated solution.As " the machine vision research of counting corncob line number " (Han Zhongzhi etc., Maize Sciences, 2010) machine vision method is utilized automatically to detect tassel row number index, the tassel row number distribution characteristics of corn ear is calculated by gathering corn ear cross-sectional image, the shortcoming of the method is to need to carry out destructiveness sampling to fruit ear, destroys valuable sample and has influence on the mensuration of other Ear Characters parameters.
Along with computing machine and infotech are in the widespread use of agriculture field, the corn ear robotization species test based on image processing techniques has become a kind of trend.At present, for the important character index of corn ear, comprise grain number per spike, tassel row number, row grain number and bald sharp rate etc., still there is no the computing method of complete set.The existing corn ear character computing method based on image, carry out for single index often, lack the integrative solution that simultaneously can calculate the characteristic indexs such as grain number per spike, tassel row number, row grain number and bald sharp rate.
Summary of the invention
(1) technical matters to be solved
The object of the present invention is to provide a kind of corn ear character index calculating method based on image, with solve existing Ear Characters index calculating method single, only carry out calculating for wherein a certain index, there is destructive problem in sampling method.
(2) technical scheme
In order to solve the problems of the technologies described above, the present invention proposes a kind of corn ear character index calculating method based on image, said method comprising the steps of:
S1, by every the mode of 90 degree shootings image, the coloured image CI of acquisition corn ear
i, and i=1,2,3,4,
By described coloured image CI
ibe converted into gray level image SI
i, and by described gray level image SI
ibe converted into the bianry image BI only comprising corn ear
i;
S2, respectively to described coloured image CI
i, described gray level image SI
iand described bianry image BI
icarry out axial distortion correction and Lens Distortion Correction, obtain the coloured image CI2 after correcting
i, gray level image HI after correction
iand the bianry image BI2 after correcting
i;
S3, to described gray level image HI
isplit, only comprised the bianry image BI3 of corn kernel
i,
By described bianry image BI3
isplice, obtain seed panorama sketch BI4, described seed panorama sketch BI4 comprises all seeds on described corn ear three-dimensional surface;
S4, to described bianry image BI3
icarry out morphology operations, calculate the bald sharp region of described corn ear, and calculate the bald sharp length of described corn ear,
According to described bianry image BI3
i, calculate the row grain number of described corn ear,
According to described seed panorama sketch BI4, calculate the tassel row number of described corn ear.
Optionally, in step S1, by described gray level image SI
ibe converted into the bianry image BI only comprising corn ear
ispecifically comprise:
Determine described gray level image SI
ithe boundary pixel intensity of middle corn ear and background to described gray level image SI
icarry out binaryzation, use dilation operation to fill vacancy, use the isolated island in etching operation deleted image and recover the border of corn ear, thus obtaining described bianry image BI
i.
Optionally, in step S2, described axial distortion correction and described Lens Distortion Correction specifically comprise:
Based on described bianry image BI
iset up the OBB bounding box of corn ear in each image, and set up fruit ear local coordinate system according to described OBB bounding box, calculate axial distortion correction parameter and Lens Distortion Correction parameter, according to described axial distortion correction parameter and described Lens Distortion Correction parameter respectively to described coloured image CI
i, described gray level image SI
iand described bianry image BI
icorrect.
Optionally, step S3 comprises further:
To described gray level image HI
iafter splitting, utilize the color characteristic of corn kernel and shape facility to screen the corn kernel be partitioned into, thus obtain described bianry image BI3
i, wherein,
The color characteristic of described corn kernel is by described coloured image CI2
iobtain, the shape facility of described corn kernel is by described bianry image BI2
iobtain.
Optionally, in step S3, by described bianry image BI3
icarry out splicing specifically comprising:
By described bianry image BI3
ilaunch according to fruit ear three-dimensional surface, set up the mapping relations between identical corn kernel on each image, and extract the corn kernel of structural integrity as the corn kernel on described seed panorama sketch BI4 from each image.
Optionally, in step S4, to described bianry image BI3
icarry out morphology operations specifically to comprise:
To described bianry image BI3
icarry out dilation operation, until all corn kernels in image merge formation simply connected region, record dilation pixel number, then utilizes erosion operation to recover the border of corn kernel, then by the image that obtains and described bianry image BI2
icarry out difference operation, do not comprised the region of corn kernel, and obtain described bald sharp region further.
Optionally, in step S4, the row grain number calculating described corn ear specifically comprises:
According to described bianry image BI3
iin the coordinate of each corn kernel in described fruit ear local coordinate system, set up point set S
i, the starting point A of setting row grain counting number
iwith terminal B
i, and by described starting point A
iwith described terminal B
ijoin described point set S
iin,
By described point set S
iconnect into planar triangulations T
i, and calculate described planar triangulations T
iin from described starting point A
ito described terminal B
ishortest path P
i, described shortest path P
iin except described starting point A
iwith described terminal B
ithe number of grid node is in addition described bianry image BI3
irow grain number, described bianry image BI3
ithe mean value of row grain number be the row grain number of described corn ear.
Optionally, in step S4, the tassel row number calculating described corn ear specifically comprises:
According to described seed panorama sketch BI4, calculate the grain number per spike of described corn ear, described grain number per spike is the tassel row number of described corn ear divided by the business that described row grain number obtains.
Optionally, in step S4, the tassel row number calculating described corn ear specifically comprises:
According to described seed panorama sketch BI4, calculate the girth of described corn ear and the mean breadth of corn kernel, described girth is the tassel row number of described corn ear divided by the business that the mean breadth of described corn kernel obtains.
Optionally, in step S4, the tassel row number calculating described corn ear specifically comprises:
According to the center position of each corn kernel in described seed panorama sketch BI4, set up point set S ', the starting point A ' of setting tassel row number counting and terminal B ', and described starting point A ' and described terminal B ' joined in described point set S ',
Described point set S ' is connected into planar triangulations T ', and calculating from described starting point A ' to the shortest path P ' of described terminal B ' in described planar triangulations T ', the number of the grid node in described shortest path P ' except described starting point A ' and described terminal B ' is the tassel row number of described corn ear.
(3) beneficial effect
Compared with the existing technology, the technical scheme tool that the present invention proposes has the following advantages:
1, recover the morphological feature of fruit ear and seed based on axial/radial distortion correction, improve the accuracy rate of the computing method based on corn kernel CF.
2, based on the result that seed is split and spliced, provide the computing method of new grain number per spike, bald sharp length, row grain number and tassel row number, for the character parameter of corn ear calculates the solution providing integration, make the calculating of the every character parameter of fruit ear simply clear and definite, for the robotization species test of corn ear provides solution.
Accompanying drawing explanation
Fig. 1 is the basic flow sheet of the corn ear character index calculating method based on image that the present invention proposes.
Fig. 2 is the schematic diagram of the corn ear image in one embodiment of the invention.
Fig. 3 is the schematic diagram of the row grain number calculating method in one embodiment of the invention.
Fig. 4 is the schematic diagram of the tassel row number computing method in one embodiment of the invention.
Embodiment
Below in conjunction with drawings and Examples, the specific embodiment of the present invention is described in further detail.
The present invention proposes a kind of corn ear character index calculating method based on image, as shown in Figure 1, said method comprising the steps of:
S1, by every the mode of 90 degree shootings image, the coloured image CI of acquisition corn ear
i, and i=1,2,3,4,
By described coloured image CI
ibe converted into gray level image SI
i, and by described gray level image SI
ibe converted into the bianry image BI only comprising corn ear
i;
S2, respectively to described coloured image CI
i, described gray level image SI
iand described bianry image BI
icarry out axial distortion correction and Lens Distortion Correction, obtain the coloured image CI2 after correcting
i, gray level image HI after correction
iand the bianry image BI2 after correcting
i;
S3, to described gray level image HI
isplit, only comprised the bianry image BI3 of corn kernel
i,
By described bianry image BI3
isplice, obtain seed panorama sketch BI4, described seed panorama sketch BI4 comprises all seeds on described corn ear three-dimensional surface;
S4, to described bianry image BI3
icarry out morphology operations, calculate the bald sharp region of described corn ear, and calculate the bald sharp length of described corn ear,
According to described bianry image BI3
i, calculate the row grain number of described corn ear,
According to described seed panorama sketch BI4, calculate the tassel row number of described corn ear.
Below by specific embodiment, the preferred implementation of each step is described in detail.
In step sl, first to gather and pre-service the image of corn ear.
Under certain illumination condition, along the direction perpendicular to corn ear central shaft on solid background, every 90 degree of shooting piece images, 4 coloured images of acquisition are expressed as CI
i(be respectively CI
1, CI
2, CI
3and CI
4), be translated into the gray level image SI that codomain is 255
i, and the bianry image BI only being comprised corn ear is calculated in combining form student movement further
i.
Wherein, image taking ensures that illumination condition is identical as far as possible, and shooting direction is as far as possible perpendicular to corn ear central shaft, and it is 90 degree that adjacent image shooting angle ensures.
Convert coloured image to gray level image, conversion method is: gray scale=(R × 30+G × 59+B × 11)/100.
The bianry image of corn ear, refer to the boundary pixel intensity first determining fruit ear and background, for to Binary Sketch of Grey Scale Image, then dilation operation is used to fill fruit ear vacancy, use the isolated island in etching operation deleted image and the border of recovering fruit ear, in the bianry image finally obtained, only comprise corn ear.
Wherein, fruit ear threshold value can use OSTU method to obtain; Use morphology operations, should ensure that the number of pixels of accumulative dilation and corrosion is equal, to recover the outline edge of fruit ear; Judge that the method only comprising fruit ear in bianry image is, utilize the fruit ear size calculated, judge fruit ear region in conjunction with priori, delete other noise region.
In step s 2, need to carry out axis and Lens Distortion Correction to image.
Based on the binary map BI of fruit ear
i, set up the OBB bounding box of each fruit ear, set up fruit ear local coordinate system based on this, calculate axis and Lens Distortion Correction parameter, thus obtain the fruit ear coloured image CI2 after correcting
i, gray level image HI
iwith bianry image BI2
i.
Wherein, OBB bounding box refers to the rectangle of pressing close to fruit ear border most, and it is high that its height on long axis direction is fringe, is that fringe is wide at the width of short-axis direction.
Fruit ear local coordinate system, refers to the central axis direction Y using the long axis direction of bounding box as corn ear, and set up new coordinate system using bounding box minor axis as X-axis, coordinate origin is positioned at the central point of minor axis.
Axial distortion correction, is the angle calculating fruit ear bounding box Y direction and picture altitude direction, fruit ear is rotated to vertical direction, then calculates the altitude datum of fruit ear, by each fruit ear region Scaling/be amplified to specified altitude assignment.Altitude datum is that the mean value directly calculating fruit ear height on 4 images obtains; Uniform zoom refers to while highly zooming to altitude datum, fruit ear width convergent-divergent on year-on-year basis, and zoom factor is the ratio of fruit ear height before altitude datum and convergent-divergent.New images after convergent-divergent adopts linear interpolation method to generate from former figure.
Lens Distortion Correction, utilize the three-dimensional shape features of fruit ear to set up corresponding relation on fruit ear image between each point in each pixel and three-dimensional fruit ear surface, thus fruit ear image is radially launched, make each pixel on image have identical physical size with the fruit ear surface node of its expression.Wherein, radial direction (along picture traverse direction) on the radial transverse section referring to fruit ear center of fruit ear; Radial development method is, thinks that current fruit ear image is the perspective view of three-dimensional fruit ear, and after launching, image is the two dimensional image after the tiling of three-dimensional fruit ear surface image.Wherein, fruit ear center is by fruit ear binary map BI
iin edge pixel feature determine.
Utilize bianry image to calculate distortion correction parameter, thus obtain the coloured image CI2 after correcting
i, gray level image HI
iwith bianry image BI2
i.
In step s3, seed segmentation and splicing are carried out to image.
Image after distortion correction has recovered the full-size(d) of corn kernel on fruit ear to a certain extent, in conjunction with seed coat color characteristic sum shape facility to fruit ear gray level image HI
isplit, only comprised the bianry image BI3 of corn kernel
i.
Wherein, image partition method can adopt any effective corn kernel dividing method; The seed result be partitioned into adopts its color characteristic and shape facility to screen, and color characteristic is from image CI2
imiddle acquisition, Seed shape feature is from image BI2
imiddle acquisition.Wherein, by distortion correction above, on image, Seed shape feature can reflect the true shape of seed, makes the screening based on Seed shape more accurate.
Seed splice, be by from segmentation after seed image BI3
iaccording to fruit ear three-dimensional surface launch, be spliced into a width seed panorama sketch BI4 from often opening the most complete seed of information extraction seed image.Seed panorama sketch contains all seed information on fruit ear three-dimensional surface.Joining method sets up the mapping relations after different segmentation on image between identical seed, extracts that seed distortion is minimum, the most complete seed of structure is as the seed on panorama sketch BI4 from often opening image.
In step s 4 which, the image obtained is utilized to calculate the characteristic index such as bald sharp length, row grain number, grain number per spike, tassel row number of corn ear.
Bald sharp region is defined as the region not growing corn kernel at fruit ear top, and bald sharp length is this region height in vertical direction.At present, the method calculating bald sharp length is generally split separately for the bald sharp region in image, because bald sharp proterties, color, size variation differ greatly, lacks the bald point that effective method is partitioned into various fruit ear type always.The present invention is based on the seed image BI3 be partitioned into
i, using the hole between morphology operations filling seed, is single connected region by corn kernel region merging technique, then with fruit ear image BI2
idifference operation, is not comprised the region of seed, and the part being positioned at fruit ear top is in this region judged to be bald sharp region, and calculates the parameters such as bald sharp area, bald sharp length thus.
Wherein, the process of morphology operations specifically comprises: to image BI3
iapplication dilation operation, until all seeds merge formation simply connected region, record dilation pixel number; Then apply erosion operation and recover seed border; Again by the image that obtains and original contour image subtraction, obtain bald sharp region.
Difference operation, refers to from fruit ear binary map BI2
iin deduct corn kernel region, do not grown the region of corn kernel.
Fig. 2 shows the bald sharp region extracted from 4 input pictures.
Row grain number is defined as the average corn kernel number of often going on fruit ear image.Because seed spread pattern is various, artificial counting, mainly by micro-judgment, lacks robotization and standardized computing method.The present invention is based on the seed image BI3 be partitioned into
i, establish the row grain counting number method meeting human vision custom.
First image BI3 is calculated
ithe centroid coordinate of upper each seed, is input to point set S
iin; Starting point and the terminal (generally getting the OBB bounding box of image and two intersection points of Y-axis after correcting) of capable grain counting number are set, and are joined center point set S
iin.Then, by point set S
iconnect into planar triangulations, the calculating of row grain number is converted into and calculates at the shortest path of given grid interior joint, in this path, be the row grain number of fruit ear from the number of the grid node (that is, not comprising starting point and terminal) of process between origin-to-destination.
Wherein, from point set S
igenerate triangle gridding and adopt Delaunay method.Delaunay method can be split into triangular mesh from the set of loose point, and wherein triangle meets two criterions: empty circle characteristic sum maximizes minimum corner characteristics.
Shortest path between specifying at 2 in Calculation Plane grid, uses BellmanFord method.BellmanFord method is a kind of dynamic programming algorithm solving signal source shortest path.First construct an original two-dimensional matrix, matrix size equals node number, and in matrix, each element value is initially assigned maximum value, represents that this path is obstructed.Then extract the vertex index on every bar limit in grid, calculate the weight connected between summit, wherein connection weight is based on 2 distances, and adds self-defining weight regulatory factor.Weight regulatory factor, to make path searching meet user define feature, between origin-to-destination, an initial straight is generated in the present invention, each point is calculated on the angle of itself and this initial straight and limit to the vertical range of initial straight to every bar limit, using on angle, vertical range, limit, 2 distances are as this limit weight, and assignment is to matrix correspondence position.And then utilize BellmanFord method to calculate node serial numbers all from the path of origin-to-destination process.
Due to individual fruit ear image distorts minimum, that the most complete tassel row number of seed information is generally 3-4 is capable, therefore all can calculate at least 2 shortest paths to often opening image, for adding up the mean value of trip grain number.To the method for often opening fruit ear image calculating many groups row grain number be: record the grid node (except starting point and terminal) that each path computing obtains, be maximum value by all Grid Edges be connected with these nodes assignment in array, block path searching, shortest path again between zequin and terminal, namely obtains other row grain number indexs in image.
Fig. 3 is the schematic diagram calculating row grain number from 4 input pictures respectively, and the row grain number of the corn ear finally obtained is the mean value of these image line grain numbers.
Based in the fruit ear species test of image, tassel row number is the most difficult index accurately determined.Tassel row number is defined as the seed line number that fruit ear is independently embarked on journey on the surface.Due to fruit ear kind and individual difference, on fruit ear, seed arrangement mode has diversified feature, causes the determination of tassel row number very difficult.The present invention establishes tassel row number and calculates decision model, and characteristic use three kinds of methods of this models coupling seed calculate tassel row number, and give applicable elements.
First method: tassel row number 1=grain number per spike/row grain number.The key of the method is accurately to calculate grain number per spike and row grain number, and wherein grain number per spike calculates from seed panorama sketch BI4, and row grain number is from image BI3
iin obtain.
Second method: tassel row number 2=fruit ear girth/seed mean breadth.Wherein, fruit ear girth directly calculates from image BI4; The computing method of seed mean breadth are, first the average area of seed on fruit ear is calculated, i.e. seed average area=(fruit ear area-bald sharp area-inactive area area)/grain number per spike, then from image BI4, calculate the length breadth ratio of seed, calculate seed mean breadth in conjunction with two parameters above.Wherein, inactive area refers to the region except seed and bald point on fruit ear, utilizes the computing method in similar bald sharp region to obtain.
The third method, similar to the computing method of row grain number, calculate the central point of all seeds in seed panorama sketch, starting point and terminal (generally getting the mid point of OBB bounding box along two limits of Y-axis of image after correcting) are then set on panorama sketch, these nodes are generated triangle gridding according to Delaunay criterion, again adopt BellmanFord method to calculate the grid node number of shortest path process between origin-to-destination, it can be used as tassel row number 3.Fig. 4 is that the third calculates the schematic diagram of the method for tassel row number.
Above-mentioned three kinds of methods calculate tassel row number from different perspectives, and wherein, first method make use of fruit ear seed global statistics information, and applicable elements is that the row grain number of fruit ear is more or less the same; Second method considers the shape facility of seed, and applicable elements is that in fruit ear, seed size is basically identical; The third method is then applicable to any Kernel-Type, needs the weight factor regulating Mesh connection.Finally, which kind of tassel row number computing method is adopted to need to determine in image processing process according to the feature of current fruit ear and seed thereof.
The above is only the preferred embodiment of the present invention; it should be pointed out that for the person of ordinary skill of the art, under the prerequisite not departing from the technology of the present invention principle; can also make some improvement and replacement, these improve and replace and also should be considered as protection scope of the present invention.
Claims (9)
1., based on a corn ear character index calculating method for image, it is characterized in that, said method comprising the steps of:
S1, by every the mode of 90 degree shootings image, the coloured image CI of acquisition corn ear
i, and i=1,2,3,4,
By described coloured image CI
ibe converted into gray level image SI
i, and by described gray level image SI
ibe converted into the bianry image BI only comprising corn ear
i;
S2, respectively to described coloured image CI
i, described gray level image SI
iand described bianry image BI
icarry out axial distortion correction and Lens Distortion Correction, obtain the coloured image CI2 after correcting
i, gray level image HI after correction
iand the bianry image BI2 after correcting
i;
S3, to described gray level image HI
isplit, only comprised the bianry image BI3 of corn kernel
i,
By described bianry image BI3
isplice, obtain seed panorama sketch BI4, described seed panorama sketch BI4 comprises all seeds on described corn ear three-dimensional surface;
S4, to described bianry image BI3
icarry out morphology operations, calculate the bald sharp region of described corn ear, and calculate the bald sharp length of described corn ear,
According to described bianry image BI3
i, calculate the row grain number of described corn ear,
According to described seed panorama sketch BI4, calculate the tassel row number of described corn ear;
In step S4, the row grain number calculating described corn ear specifically comprises:
According to described bianry image BI3
iin the coordinate of each corn kernel in described fruit ear local coordinate system, set up point set S
i, the starting point A of setting row grain counting number
iwith terminal B
i, and by described starting point A
iwith described terminal B
ijoin described point set S
iin,
By described point set S
iconnect into planar triangulations T
i, and calculate described planar triangulations T
iin from described starting point A
ito described terminal B
ishortest path P
i, described shortest path P
iin except described starting point A
iwith described terminal B
ithe number of grid node is in addition described bianry image BI3
irow grain number, described bianry image BI3
ithe mean value of row grain number be the row grain number of described corn ear.
2. the corn ear character index calculating method based on image according to claim 1, is characterized in that, in step S1, by described gray level image SI
ibe converted into the bianry image BI only comprising corn ear
ispecifically comprise:
Determine described gray level image SI
ithe boundary pixel intensity of middle corn ear and background to described gray level image SI
icarry out binaryzation, use dilation operation to fill vacancy, use the isolated island in etching operation deleted image and recover the border of corn ear, thus obtaining described bianry image BI
i.
3. the corn ear character index calculating method based on image according to claim 1, is characterized in that, in step S2, described axial distortion correction and described Lens Distortion Correction specifically comprise:
Based on described bianry image BI
iset up the OBB bounding box of corn ear in each image, and set up fruit ear local coordinate system according to described OBB bounding box, calculate axial distortion correction parameter and Lens Distortion Correction parameter, according to described axial distortion correction parameter and described Lens Distortion Correction parameter respectively to described coloured image CI
i, described gray level image SI
iand described bianry image BI
icorrect.
4. the corn ear character index calculating method based on image according to claim 1, it is characterized in that, step S3 comprises further:
To described gray level image HI
iafter splitting, utilize the color characteristic of corn kernel and shape facility to screen the corn kernel be partitioned into, thus obtain described bianry image BI3
i, wherein,
The color characteristic of described corn kernel is by described coloured image CI2
iobtain, the shape facility of described corn kernel is by described bianry image BI2
iobtain.
5. according to the corn ear character index calculating method based on image one of claim 1-4 Suo Shu, it is characterized in that, in step S3, by described bianry image BI3
icarry out splicing specifically comprising:
By described bianry image BI3
ilaunch according to fruit ear three-dimensional surface, set up the mapping relations between identical corn kernel on each image, and extract the corn kernel of structural integrity as the corn kernel on described seed panorama sketch BI4 from each image.
6. the corn ear character index calculating method based on image according to claim 1, is characterized in that, in step S4, to described bianry image BI3
icarry out morphology operations specifically to comprise:
To described bianry image BI3
icarry out dilation operation, until all corn kernels in image merge formation simply connected region, record dilation pixel number, then utilizes erosion operation to recover the border of corn kernel, then by the image that obtains and described bianry image BI2
icarry out difference operation, do not comprised the region of corn kernel, and obtain described bald sharp region further.
7. the corn ear character index calculating method based on image according to claim 1, is characterized in that, in step S4, the tassel row number calculating described corn ear specifically comprises:
According to described seed panorama sketch BI4, calculate the grain number per spike of described corn ear, described grain number per spike is the tassel row number of described corn ear divided by the business that described row grain number obtains.
8. the corn ear character index calculating method based on image according to claim 1, is characterized in that, in step S4, the tassel row number calculating described corn ear specifically comprises:
According to described seed panorama sketch BI4, calculate the girth of described corn ear and the mean breadth of corn kernel, described girth is the tassel row number of described corn ear divided by the business that the mean breadth of described corn kernel obtains.
9. the corn ear character index calculating method based on image according to claim 1, is characterized in that, in step S4, the tassel row number calculating described corn ear specifically comprises:
According to the center position of each corn kernel in described seed panorama sketch BI4, set up point set S ', the starting point A ' of setting tassel row number counting and terminal B ', and described starting point A ' and described terminal B ' joined in described point set S ',
Described point set S ' is connected into planar triangulations T ', and calculating from described starting point A ' to the shortest path P ' of described terminal B ' in described planar triangulations T ', the number of the grid node in described shortest path P ' except described starting point A ' and described terminal B ' is the tassel row number of described corn ear.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210572760.0A CN103093456B (en) | 2012-12-25 | 2012-12-25 | Corn ear character index computing method based on images |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210572760.0A CN103093456B (en) | 2012-12-25 | 2012-12-25 | Corn ear character index computing method based on images |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103093456A CN103093456A (en) | 2013-05-08 |
| CN103093456B true CN103093456B (en) | 2015-06-03 |
Family
ID=48205987
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210572760.0A Active CN103093456B (en) | 2012-12-25 | 2012-12-25 | Corn ear character index computing method based on images |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103093456B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10186029B2 (en) | 2014-09-26 | 2019-01-22 | Wisconsin Alumni Research Foundation | Object characterization |
| CN106709505A (en) * | 2016-11-23 | 2017-05-24 | 中国农业大学 | Dictionary learning-based grain type classification method and system for corn grains |
| CN106934796B (en) * | 2017-02-15 | 2018-11-30 | 山东大学 | The high-speed belt conveyor rock slag video analytic system and method that rock tunnel(ling) machine carries |
| CN108764294B (en) * | 2018-04-28 | 2021-04-30 | 青岛农业大学 | Line number automatic detection method based on corn ear symmetry |
| CN110490868B (en) * | 2019-08-23 | 2023-05-30 | 陈�峰 | Nondestructive counting method based on computer vision corn cob grain number |
| CN111680552B (en) * | 2020-04-28 | 2023-10-03 | 北京控制工程研究所 | Feature part intelligent recognition method |
| CN111950436A (en) * | 2020-08-07 | 2020-11-17 | 中国农业大学 | Corn ear phenotype measuring method and system |
| CN112611715A (en) * | 2020-11-11 | 2021-04-06 | 无锡臻永科技有限公司 | Rotary type subentry detection system and method |
| CN112577956A (en) * | 2020-12-04 | 2021-03-30 | 中国农业大学 | Corn seed test system and method based on intelligent device photographing function |
| CN115294482B (en) * | 2022-09-26 | 2022-12-20 | 山东常生源生物科技股份有限公司 | Edible fungus yield estimation method based on unmanned aerial vehicle remote sensing image |
| CN115345880B (en) * | 2022-10-18 | 2023-03-24 | 浙江托普云农科技股份有限公司 | Corn ear character estimation method and device based on corn ear unilateral scanning map |
| CN115496756B (en) * | 2022-11-16 | 2023-01-17 | 湖南农业大学 | Rice quality detection method and device based on three-dimensional image processing and electronic equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101853524A (en) * | 2010-05-13 | 2010-10-06 | 北京农业信息技术研究中心 | Method for generating corn ear panoramic image by using image sequence |
| CN101957313A (en) * | 2010-09-21 | 2011-01-26 | 吉林大学 | Method and device for computer visual inspection classification of quality of fresh corn ears |
-
2012
- 2012-12-25 CN CN201210572760.0A patent/CN103093456B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101853524A (en) * | 2010-05-13 | 2010-10-06 | 北京农业信息技术研究中心 | Method for generating corn ear panoramic image by using image sequence |
| CN101957313A (en) * | 2010-09-21 | 2011-01-26 | 吉林大学 | Method and device for computer visual inspection classification of quality of fresh corn ears |
Non-Patent Citations (3)
| Title |
|---|
| 《基于生长模型的玉米三维可视化研究》;郭新宇等;《农业工程学报》;20070531;第23卷(第3期);全文 * |
| 《基于龚线平行特征的视觉导航多垄线识别》;陈娇等;《农业工程学报》;20091231;第109页右栏第2.2节及图7 * |
| 《计数玉米穗行数的机器视觉研究》;韩仲志等;《玉米科学》;20100415;第18卷(第2期);第147页右栏第1.2.3节预处理及图1 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103093456A (en) | 2013-05-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103093456B (en) | Corn ear character index computing method based on images | |
| CN109146948B (en) | Crop growth phenotype parameter quantification and yield correlation analysis method based on vision | |
| US20190279420A1 (en) | Automated roof surface measurement from combined aerial lidar data and imagery | |
| Niederheiser et al. | Deriving 3D point clouds from terrestrial photographs-Comparison of different sensors and software | |
| Rottensteiner et al. | Results of the ISPRS benchmark on urban object detection and 3D building reconstruction | |
| Pound et al. | Automated recovery of three-dimensional models of plant shoots from multiple color images | |
| CA2858166C (en) | Method and system for characterising plant phenotype | |
| CN106651900B (en) | A kind of overhead strawberry three-dimensional modeling method in situ based on contours segmentation | |
| CN102800127B (en) | Light stream optimization based three-dimensional reconstruction method and device | |
| CN109883401B (en) | Method and system for measuring visual field of city mountain watching | |
| CN114998536A (en) | Model generation method and device based on novel basic mapping and storage medium | |
| WO2019198412A1 (en) | Forest resources information calculation method and forest resources information calculation device | |
| WO2016082797A1 (en) | Method for modeling and registering three-dimensional scene structure based on single image | |
| Santos et al. | 3D plant modeling: localization, mapping and segmentation for plant phenotyping using a single hand-held camera | |
| Gibbs et al. | Active vision and surface reconstruction for 3D plant shoot modelling | |
| CN107807387B (en) | Acquisition methods when seismic first break neural network based is walked | |
| JP7156515B2 (en) | Point cloud annotation device, method and program | |
| CN105447868A (en) | Automatic checking method for aerial data of mini unmanned air vehicle | |
| Pound et al. | A patch-based approach to 3D plant shoot phenotyping | |
| CN106097433A (en) | Object industry and the stacking method of Image model and system | |
| CN103954970A (en) | Terrain detail acquisition method | |
| Ando et al. | Robust surface reconstruction of plant leaves from 3D point clouds | |
| CN103077559A (en) | Cluster three-dimensional rebuilding method based on sequence image | |
| CN104751479A (en) | Building extraction method and device based on TIN data | |
| CN103743750B (en) | A kind of generation method of distribution diagram of surface damage of heavy calibre optical element |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |