CN103093456A - Corn ear character index computing method based on images - Google Patents
Corn ear character index computing method based on images Download PDFInfo
- Publication number
- CN103093456A CN103093456A CN2012105727600A CN201210572760A CN103093456A CN 103093456 A CN103093456 A CN 103093456A CN 2012105727600 A CN2012105727600 A CN 2012105727600A CN 201210572760 A CN201210572760 A CN 201210572760A CN 103093456 A CN103093456 A CN 103093456A
- 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.)
- Granted
Links
Images
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 fully to understand the fruit ear quantitative character to the influence degree of output, the formation effect of clear and definite every characteristic index to output need to be carried out Measurement accuracy to a large amount of fruit ear samples.At present, the characteristic indexs such as grain number per spike, row grain number, tassel row number and bald sharp length for corn ear, general manual measurement and the statistical method of adopting obtained, process is loaded down with trivial details, error is larger, especially row grain number and tassel row number etc. have the index of statistical significance, and its measurement result is subject to the experience impact of survey crew.
Carrying out the species test of precision corn ear 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 of fruit ear image, convenient and swift, can greatly reduce human cost, improve corn seed investigating efficient, advance precision, the standardization of corn seed investigating work flow, realize managing, can reviewing with visual of species test flow process.The method of existing properties and characteristics parameter based on the image calculation corn ear is mainly for the single traits index, lacks unified, integrated solution on implementation method.As " the machine vision research of counting corncob line number " (Han Zhongzhi etc., Maize Sciences, 2010) utilize machine vision method automatically to detect the tassel row number index, calculate the tassel row number distribution characteristics of corn ear by gathering the corn ear cross-sectional image, the shortcoming of the method is and need to carries out destructiveness sampling to fruit ear, destroyed valuable sample and had influence on the mensuration of other Ear Characters parameters.
Along with the widespread use at agriculture field of computing machine and infotech, become a kind of trend based on the corn ear robotization species test of image processing techniques.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 complete computing method of cover.Existing image-based corn ear character computing method are carried out for single index often, lack the integrative solution of characteristic indexs such as can calculating simultaneously 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 image-based corn ear character index calculating method, with solve existing Ear Characters index calculating method single, only for a certain index wherein calculate, 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 image-based corn ear character index calculating method, said method comprising the steps of:
S1, the mode by taking an image every 90 degree are obtained the coloured image CI of corn ear
i, and i=1,2,3,4,
With described coloured image CI
iBe converted into gray level image SI
i, and with described gray level image SI
iBe converted into the bianry image BI that only comprises 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, the coloured image CI2 after being proofreaied and correct
i, the gray level image HI after correction
iAnd the bianry image BI2 after proofreading and correct
i
S3, to described gray level image HI
iCut apart, obtain only comprising the bianry image BI3 of corn kernel
i,
With 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 point zone 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, with described gray level image SI
iBe converted into the bianry image BI that only comprises corn ear
iSpecifically comprise:
Determine described gray level image SI
iThe boundary pixel intensity of middle corn ear and background and to described gray level image SI
iCarry out binaryzation, use dilation operation to fill vacancy, use the isolated island in corrosion operation deleted image and the border of recovering corn ear, thereby obtain 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 the 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
iProofread and correct.
Optionally, step S3 further comprises:
To described gray level image HI
iAfter cutting apart, utilize the color characteristic of corn kernel and shape facility that the corn kernel that is partitioned into is screened, thereby 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, with described bianry image BI3
iSplice specifically and comprise:
With described bianry image BI3
iLaunch according to the 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
iCarrying out morphology operations specifically comprises:
To described bianry image BI3
iCarry out dilation operation, form a simply connected region until all corn kernels in image merge, record the expansion number of pixels, the border that then utilizes erosion operation to recover corn kernel, then with the image and the described bianry image BI2 that obtain
iCarry out difference operation, obtain not comprising the zone of corn kernel, and it is regional further to obtain described bald point.
Optionally, in step S4, the row grain number that calculates 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 point B
i, and with described starting point A
iWith described terminal point B
iJoin described point set S
iIn,
With 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 point B
iShortest path P
i, described shortest path P
iIn except described starting point A
iWith described terminal point B
iThe number of grid node in addition is described bianry image BI3
iA row 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 that calculates described corn ear specifically comprises:
According to described seed panorama sketch BI4, calculate the grain number per spike of described corn ear, the business that described grain number per spike obtains divided by described row grain number is the tassel row number of described corn ear.
Optionally, in step S4, the tassel row number that calculates 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, the business that described girth obtains divided by the mean breadth of described corn kernel is the tassel row number of described corn ear.
Optionally, in step S4, the tassel row number that calculates 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 ', set starting point A ' and the terminal point B ' of tassel row number counting, and described starting point A ' and described terminal point B ' are joined in described point set S ',
Described point set S ' is connected into planar triangulations T ', and calculating the shortest path P ' from described starting point A ' to described terminal point 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 point B ' is the tassel row number of described corn ear.
(3) beneficial effect
Compare with prior art, the technical scheme that the present invention proposes has following advantage:
1, recover the morphological feature of fruit ear and seed based on the axial/radial distortion correction, improved the accuracy rate based on the computing method of corn kernel CF.
The result of 2, cutting apart and splicing based on seed, the computing method of new grain number per spike, bald sharp length, row grain number and tassel row number are provided, for calculating, the character parameter of corn ear provides integrated solution, 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.
Description of drawings
Fig. 1 is the basic flow sheet of the image-based corn ear character index calculating method that proposes of the present invention.
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 image-based corn ear character index calculating method, as shown in Figure 1, said method comprising the steps of:
S1, the mode by taking an image every 90 degree are obtained the coloured image CI of corn ear
i, and i=1,2,3,4,
With described coloured image CI
iBe converted into gray level image SI
i, and with described gray level image SI
iBe converted into the bianry image BI that only comprises 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, the coloured image CI2 after being proofreaied and correct
i, the gray level image HI after correction
iAnd the bianry image BI2 after proofreading and correct
i
S3, to described gray level image HI
iCut apart, obtain only comprising the bianry image BI3 of corn kernel
i,
With 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 point zone 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 elaborated.
In step S1, at first to gather the image of corn ear and pre-service.
Under certain illumination condition, along the direction perpendicular to the corn ear central shaft, take piece image every 90 degree on solid background, 4 coloured images of acquisition are expressed as CI
i(be respectively CI
1, CI
2, CI
3And CI
4), be translated into codomain and be 255 gray level image SI
i, and further the bianry image BI that obtains only comprising corn ear is calculated in the combining form student movement
i
Wherein, image taking guarantees that as far as possible illumination condition is identical, takes direction as far as possible perpendicular to the corn ear central shaft, and the adjacent image shooting angle guarantees to be 90 degree.
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 at first determine the boundary pixel intensity of fruit ear and background, be used for Binary Sketch of Grey Scale Image, then use dilation operation to fill the fruit ear vacancy, use the isolated island in corrosion operation deleted image and the border of recovering fruit ear, only comprise corn ear in the bianry image that obtains at last.
Wherein, the fruit ear threshold value can use the OSTU method to obtain; Use morphology operations, should guarantee that the number of pixels of accumulative total dilation and corrosion equates, to recover the outline edge of fruit ear; The method that only comprises fruit ear in the judgement bianry image is that the fruit ear size that utilization calculates in conjunction with priori judgement fruit ear zone, is deleted other noise region.
In step S2, need to carry out axially and Lens Distortion Correction image.
Binary map BI based on fruit ear
i, set up the OBB bounding box of each fruit ear, set up the fruit ear local coordinate system based on this, calculate axially and the Lens Distortion Correction parameter, thus the fruit ear coloured image CI2 after being proofreaied and correct
i, gray level image HI
iWith bianry image BI2
i
Wherein, the rectangle that the OBB bounding box refers to press close to most the fruit ear border, it is high that its height on long axis direction is fringe, is that fringe is wide at the width of short-axis direction.
The fruit ear local coordinate system refers to set up new coordinate system with minor axis of bounding box as X-axis with the long axis direction of the bounding box central axis direction Y as corn ear, and coordinate origin is positioned at the central point of minor axis.
Axial distortion correction is the angle that calculates fruit ear bounding box Y direction and picture altitude direction, and fruit ear is rotated to vertical direction, then calculates the altitude datum of fruit ear, with the regional Scaling of each fruit ear/be amplified to specified altitude assignment.Altitude datum is that the mean value that directly calculates fruit ear height on 4 images obtains; Uniform zoom refers to that when highly zooming to altitude datum, the fruit ear width is 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, to utilize the three-dimensional shape features of fruit ear to set up the corresponding relation between each point of each pixel and three-dimensional fruit ear surface on the fruit ear image, thereby the fruit ear image is radially launched, make the fruit ear surface node of each pixel and its expression on image have identical physical size.Wherein, fruit ear radially referred to radial direction (along the picture traverse direction) on the transverse section at fruit ear center; The 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 three-dimensional fruit ear surface image tiling.Wherein, the fruit ear center is by fruit ear binary map BI
iIn the edge pixel feature determine.
Utilize bianry image to calculate the distortion correction parameter, thus the coloured image CI2 after being proofreaied and correct
i, gray level image HI
iWith bianry image BI2
i
In step S3, image is carried out seed cut apart and splicing.
Image after distortion correction has recovered the full-size(d) of corn kernel on the fruit ear to a certain extent, in conjunction with seed coat color feature and shape facility to fruit ear gray level image HI
iCut apart, obtain only comprising the bianry image BI3 of corn kernel
i
Wherein, image partition method can adopt any effective corn kernel dividing method; The seed result that is partitioned into adopts its color characteristic and shape facility to screen, and color characteristic is from image C I2
iMiddle acquisition, the Seed shape feature is from image B I2
iMiddle acquisition.Wherein, by top distortion correction, on image, the Seed shape feature can reflect the true shape of seed, and it is more accurate to make based on the screening of Seed shape.
Seed splicing is with the seed image B I3 after cut apart
iIn launch according to the fruit ear three-dimensional surface, the most complete seed of information extraction is spliced into a width seed panorama sketch BI4 from every seed image.The seed panorama sketch has comprised all seed information on the fruit ear three-dimensional surface.Joining method is to set up difference to cut apart the mapping relations between identical seed on rear image, extracts seed distortion minimum, the most complete seed of structure as the seed on panorama sketch BI4 from every image.
In step S4, utilize the bald sharp length of the image calculation corn ear that obtains, the characteristic indexs such as grain number, grain number per spike, tassel row number of going.
Bald sharp zone definitions is the zone of the corn kernel of not growing at the fruit ear top, and bald sharp length is this zone height in vertical direction.At present, the method for calculating bald sharp length is generally to cut apart separately for the bald sharp zone in image, because bald sharp proterties, color, size variation differ greatly, lacks the bald point that effective method is partitioned into various fruit ear types always.The present invention is based on the seed image B I3 that has been partitioned into
i, use morphology operations to fill hole between seed, single connected region is merged in the corn kernel zone, then with fruit ear image B I2
iDifference operation obtains not comprising the zone of seed, and the part that is positioned at the fruit ear top in this zone is judged to be bald point zone, and calculates thus the parameters such as bald sharp area, bald sharp length.
Wherein, the process of morphology operations specifically comprises: to image B I3
iUse dilation operation, form a simply connected region until all seeds merge, record the expansion number of pixels; Then use erosion operation and recover the seed border; With the image and the original contour image subtraction that obtain, obtain bald point regional again.
Difference operation refers to from fruit ear binary map BI2
iIn deduct the corn kernel zone, the zone of the corn kernel that obtains not growing.
Fig. 2 has shown the bald point zone that extracts from 4 input pictures.
Row grain number is defined as the average corn kernel number on every row on the fruit ear image.Because the seed spread pattern is various, artificial counting lacks robotization and standardized computing method mainly by micro-judgment.The present invention is based on the seed image B I3 that is partitioned into
i, set up the row grain counting number method that meets the human vision custom.
At first calculate image B I3
iThe shape centre coordinate of upper each seed is input to point set S
iIn; Starting point and the terminal point (generally getting the OBB bounding box of image after proofreading and correct and two intersection points of Y-axis) of row grain counting number are set, and it is joined center point set S
iIn.Then, with point set S
iConnect into planar triangulations, the calculating of row grain number is converted into the shortest path that calculates node in given grid, be the row grain number of fruit ear in this path from the number of the grid node (that is, not comprising starting point and terminal point) of process between origin-to-destination.
Wherein, from point set S
iGenerate triangle gridding and adopt the Delaunay method.The Delaunay method can be gathered from loose point be split into triangular mesh, and wherein triangle satisfies two criterions: empty circle feature and the minimum corner characteristics of maximization.
Shortest path between specifying at 2 in the Calculation Plane grid uses the BellmanFord method.The BellmanFord method is a kind of dynamic programming algorithm of finding the solution single source shortest path.At first construct an original two-dimensional matrix, matrix size equals the node number, and in matrix, each element value initially is assigned maximum value, represents that this path is obstructed.Then extract the vertex index on every limit in grid, calculate the weight that connects between the summit, wherein connection weight is take 2 distances as main, and adds self-defining weight regulatory factor.The weight regulatory factor, in order to make path searching meet user's defined feature, in the present invention from generating an initial straight between origin-to-destination, each point is calculated on the angle of itself and this initial straight and limit to the vertical range of initial straight in every limit, as this limit weight, assignment is to the matrix correspondence position with 2 distances on angle, vertical range, limit.And then utilize the BellmanFord method to calculate all node serial numbers from the path of origin-to-destination process.
Capable because on individual fruit ear image, distortion is minimum, the most complete tassel row number of seed information is generally 3-4, therefore all can calculate at least 2 shortest paths to every image, be used for the mean value of statistics trip grain number.The method of every fruit ear image calculation being organized more row grain number is: record the grid node (except starting point and terminal point) that each path computing obtains, all Grid Edges that will be connected with these nodes assignment in array is maximum value, the blocking-up path searching, shortest path between zequin and terminal point again namely obtains in image other row grains and counts index.
Fig. 3 calculates respectively the schematic diagram of row grain number from 4 input pictures, the row grain number of the corn ear that finally obtains is the mean value of these image line grain numbers.
In the species test of image-based fruit ear, tassel row number is the most difficult index of accurately determining.Tassel row number is defined as the seed line number of independently embarking on journey on the fruit ear surface.Due to fruit ear kind and individual difference, on fruit ear, the seed arrangement mode has diversified characteristics, causes the definite very difficult of tassel row number.The present invention has set up tassel row number and has calculated decision model, and three kinds of methods of the characteristic use of this models coupling seed are calculated tassel row number, and have provided 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 B I3
iIn obtain.
Second method: tassel row number 2=fruit ear girth/seed mean breadth.Wherein, the fruit ear girth directly calculates from image B I4; The computing method of seed mean breadth are, at first calculate the average area of seed on fruit ear, it is seed average area=(fruit ear area-bald sharp area-inactive area area)/grain number per spike, then calculate the length breadth ratio of seed from image B I4, go out the seed mean breadth in conjunction with top two calculation of parameter.Wherein, inactive area refers on fruit ear except the zone of seed and bald point, utilizes the computing method in similar bald point zone to obtain.
The third method, similar to the computing method of row grain number, calculate the central point of all seeds in the seed panorama sketch, starting point and terminal point (generally getting the OBB bounding box of image after proofreading and correct along the mid point on two limits of Y-axis) then are set on panorama sketch, these nodes are generated triangle gridding according to the Delaunay criterion, again adopt the BellmanFord method to calculate from the grid node number of shortest path process between origin-to-destination, with it as tassel row number 3.Fig. 4 is the third schematic diagram that calculates the method for tassel row number.
Above-mentioned three kinds of methods calculate tassel row number from different perspectives, and wherein, first method has been utilized 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 has been considered the shape facility of seed, and applicable elements is that in fruit ear, seed size is basically identical; The third method is fit to any seed type, the weight factor that needs to regulate Mesh connection.Finally, adopt which kind of tassel row number computing method 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; should be pointed out that for the person of ordinary skill of the art, under the prerequisite that does not break away from the technology of the present invention principle; can also make some improvement and replacement, these improvement and replacement also should be considered as protection scope of the present invention.
Claims (10)
1. an image-based corn ear character index calculating method, is characterized in that, said method comprising the steps of:
S1, the mode by taking an image every 90 degree are obtained the coloured image CI of corn ear
i, and i=1,2,3,4,
With described coloured image CI
iBe converted into gray level image SI
i, and with described gray level image SI
iBe converted into the bianry image BI that only comprises 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, the coloured image CI2 after being proofreaied and correct
i, the gray level image HI after correction
iAnd the bianry image BI2 after proofreading and correct
i
S3, to described gray level image HI
iCut apart, obtain only comprising the bianry image BI3 of corn kernel
i,
With 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 point zone 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.
2. image-based corn ear character index calculating method according to claim 1, is characterized in that, in step S1, with described gray level image SI
iBe converted into the bianry image BI that only comprises corn ear
iSpecifically comprise:
Determine described gray level image SI
iThe boundary pixel intensity of middle corn ear and background and to described gray level image SI
iCarry out binaryzation, use dilation operation to fill vacancy, use the isolated island in corrosion operation deleted image and the border of recovering corn ear, thereby obtain described bianry image BI
i
3. image-based corn ear character index calculating method 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 the 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
iProofread and correct.
4. image-based corn ear character index calculating method according to claim 1, is characterized in that, step S3 further comprises:
To described gray level image HI
iAfter cutting apart, utilize the color characteristic of corn kernel and shape facility that the corn kernel that is partitioned into is screened, thereby 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. one of according to claim 1-4 described image-based corn ear character index calculating methods, is characterized in that, in step S3, with described bianry image BI3
iSplice specifically and comprise:
Described bianry image BI3i is launched according to the 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. image-based corn ear character index calculating method according to claim 1, is characterized in that, in step S4, described bianry image BI3i carried out morphology operations specifically comprise:
To described bianry image BI3
iCarry out dilation operation, form a simply connected region until all corn kernels in image merge, record the expansion number of pixels, the border that then utilizes erosion operation to recover corn kernel, then with the image and the described bianry image BI2 that obtain
iCarry out difference operation, obtain not comprising the zone of corn kernel, and it is regional further to obtain described bald point.
7. image-based corn ear character index calculating method according to claim 3, is characterized in that, in step S4, the row grain number that calculates 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 point B
i, and with described starting point A
iWith described terminal point B
iJoin described point set S
iIn,
With 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 point B
iShortest path P
i, described shortest path P
iIn except described starting point A
iWith described terminal point B
iThe number of grid node in addition is described bianry image BI3
iA row grain number, described bianry image BI3
iThe mean value of row grain number be the row grain number of described corn ear.
8. image-based corn ear character index calculating method according to claim 1, is characterized in that, in step S4, the tassel row number that calculates described corn ear specifically comprises:
According to described seed panorama sketch BI4, calculate the grain number per spike of described corn ear, the business that described grain number per spike obtains divided by described row grain number is the tassel row number of described corn ear.
9. image-based corn ear character index calculating method according to claim 1, is characterized in that, in step S4, the tassel row number that calculates 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, the business that described girth obtains divided by the mean breadth of described corn kernel is the tassel row number of described corn ear.
10. image-based corn ear character index calculating method according to claim 1, is characterized in that, in step S4, the tassel row number that calculates 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 ', set starting point A' and the terminal point B ' of tassel row number counting, and described starting point A' and described terminal point B ' are joined in described point set S ',
Described point set S ' is connected into planar triangulations T ', and calculating the shortest path P ' from described starting point A' to described terminal point 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 point 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 true CN103093456A (en) | 2013-05-08 |
| CN103093456B 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) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN106934796A (en) * | 2017-02-15 | 2017-07-07 | 山东大学 | High-speed belt conveyor rock slag video analytic system and method that rock tunnel(ling) machine is carried |
| CN108764294A (en) * | 2018-04-28 | 2018-11-06 | 青岛农业大学 | Line number automatic testing method based on corn ear symmetry |
| US10186029B2 (en) | 2014-09-26 | 2019-01-22 | Wisconsin Alumni Research Foundation | Object characterization |
| CN110490868A (en) * | 2019-08-23 | 2019-11-22 | 陈�峰 | A kind of lossless method of counting based on computer vision corn grain number per spike |
| CN111680552A (en) * | 2020-04-28 | 2020-09-18 | 北京控制工程研究所 | Intelligent feature part identification method |
| CN111950436A (en) * | 2020-08-07 | 2020-11-17 | 中国农业大学 | Corn ear phenotype measuring method and system |
| 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 |
| 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 |
| CN115294482A (en) * | 2022-09-26 | 2022-11-04 | 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 |
| CN115345880A (en) * | 2022-10-18 | 2022-11-15 | 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 |
| CN115496756A (en) * | 2022-11-16 | 2022-12-20 | 湖南农业大学 | Rice quality detection method and device based on three-dimensional image processing and electronic equipment |
| CN118072046A (en) * | 2024-04-19 | 2024-05-24 | 云南大学 | Chrysanthemum similar variety fine grain identification method, device, equipment and storage medium |
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 |
|---|
| 郭新宇等: "《基于生长模型的玉米三维可视化研究》", 《农业工程学报》, vol. 23, no. 3, 31 May 2007 (2007-05-31), pages 121 - 125 * |
| 陈娇等: "《基于龚线平行特征的视觉导航多垄线识别》", 《农业工程学报》, 31 December 2009 (2009-12-31) * |
| 韩仲志等: "《计数玉米穗行数的机器视觉研究》", 《玉米科学》, vol. 18, no. 2, 15 April 2010 (2010-04-15) * |
Cited By (19)
| 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 |
| CN106934796A (en) * | 2017-02-15 | 2017-07-07 | 山东大学 | High-speed belt conveyor rock slag video analytic system and method that rock tunnel(ling) machine is carried |
| 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 |
| CN108764294A (en) * | 2018-04-28 | 2018-11-06 | 青岛农业大学 | Line number automatic testing method based on corn ear symmetry |
| 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 |
| CN110490868A (en) * | 2019-08-23 | 2019-11-22 | 陈�峰 | A kind of lossless method of counting based on computer vision corn grain number per spike |
| CN111680552A (en) * | 2020-04-28 | 2020-09-18 | 北京控制工程研究所 | Intelligent feature part identification method |
| 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 |
| CN115294482A (en) * | 2022-09-26 | 2022-11-04 | 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 |
| CN115345880A (en) * | 2022-10-18 | 2022-11-15 | 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 |
| CN115496756A (en) * | 2022-11-16 | 2022-12-20 | 湖南农业大学 | Rice quality detection method and device based on three-dimensional image processing and electronic equipment |
| 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 |
| CN118072046A (en) * | 2024-04-19 | 2024-05-24 | 云南大学 | Chrysanthemum similar variety fine grain identification method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103093456B (en) | 2015-06-03 |
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 | |
| US11514644B2 (en) | Automated roof surface measurement from combined aerial LiDAR data and imagery | |
| Rottensteiner et al. | Results of the ISPRS benchmark on urban object detection and 3D building reconstruction | |
| Mei et al. | 3D tree modeling from incomplete point clouds via optimization and L 1-MST | |
| CA2858166C (en) | Method and system for characterising plant phenotype | |
| Pound et al. | Automated recovery of three-dimensional models of plant shoots from multiple color images | |
| Niederheiser et al. | Deriving 3D point clouds from terrestrial photographs comparison of different sensors and software | |
| CN108010092A (en) | A kind of city high density area Solar use potential evaluation method based on low altitude photogrammetry | |
| CN114998536A (en) | Model generation method and device based on novel basic mapping and storage medium | |
| CN104599314A (en) | Three-dimensional model reconstruction method and system | |
| CN107807387B (en) | Acquisition methods when seismic first break neural network based is walked | |
| CN103969656A (en) | Building modeling method and device based on airborne laser radar | |
| US12106438B2 (en) | Point cloud annotation device, method, and program | |
| KR20100067673A (en) | Geospatial modeling system providing building generation based upon user input on 3d model and related methods | |
| CN102708587A (en) | Method and system for acquiring three-dimensional building information rapidly | |
| CN105447868A (en) | Automatic checking method for aerial data of mini unmanned air vehicle | |
| CN103839286B (en) | The true orthophoto of a kind of Object Semanteme constraint optimizes the method for sampling | |
| CN109961510B (en) | High-cut-slope geological rapid recording method based on three-dimensional point cloud reconstruction technology | |
| CN111814715B (en) | Ground object classification method and device | |
| CN106097433A (en) | Object industry and the stacking method of Image model and system | |
| CN114663787A (en) | Single-tree segmentation method fusing unmanned aerial vehicle CHM and RGB images | |
| Zhu et al. | 3D reconstruction of plant leaves for high-throughput phenotyping | |
| Sánchez-Lopera et al. | Classification of lidar bare-earth points, buildings, vegetation, and small objects based on region growing and angular classifier | |
| Li et al. | Multi-source data fusion improves time-series phenotype accuracy in maize under a field high-throughput phenotyping platform |
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 |