CN103632157A - A method for counting seeds of a wheatear portion per wheat - Google Patents
A method for counting seeds of a wheatear portion per wheat Download PDFInfo
- Publication number
- CN103632157A CN103632157A CN201210304177.1A CN201210304177A CN103632157A CN 103632157 A CN103632157 A CN 103632157A CN 201210304177 A CN201210304177 A CN 201210304177A CN 103632157 A CN103632157 A CN 103632157A
- Authority
- CN
- China
- Prior art keywords
- image
- wheatear
- wheatear portion
- area
- kernal number
- 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 Processing (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a method for counting seeds of a wheatear portion per wheat. The method comprises the following steps: S1, collecting a front view of the wheatear portion by utilizing a CCD camera and performing pretreatment on the collected front view; S2, carrying out mathematical morphology analysis, wherein the mathematical morphology is a new method applied to the field of image processing and pattern recognition; S3, extracting wheatear portion characteristic parameters, wherein the characteristics of the wheatear portion are extracted so as to establish correlationship between correlated characteristic parameters of the wheatear portion and the number of the seeds; and S4, performing mathematic model testing, which is for testing the correlationships between area characteristics as well as long axis characteristics of the wheatear portion and the number of the seeds so as to ensure the practicality of the two models. Through the method, mathematic models between the wheatear portion image area characteristics as well as long axis length characteristics and the number of the seeds are established through extracting the wheatear portion image area characteristics as well as long axis length characteristics, so that the number of the seeds of the wheatear portion can be accurately, rapidly and objectively counted, and compared with the manual work, the method greatly helps to improve the efficiency of seed counting.
Description
Technical field
The present invention relates to a kind of method of utilizing digital image processing techniques to count out individual plant wheatear portion kernal number.
Background technology
The quantity of all plump seeds of fringe portion when wheatear portion kernal number is exactly wheat maturation.
Ultimate capacity in Wheat Production process is the thing that agricultural producer pays close attention to most all the time, is actually the management processing in postpartum of being convenient to wheat, accurately know as early as possible wheat yield assess be all the time the producer and agricultural management department in the urgent need to.Therefore between wheat paddock, seed number concrete on the wheat head need to be accurately known when wheat seed is ripe in output estimation.When agronomy Breeding and cultivation expert carries out laboratory species test, also wish to know fast wheatear portion seed quantity, accelerate wheat breeding work.On the kernal number basis on the wheat head by counting, according to the mass of 1000 kernel of this kind and other correlation parameters, thus can be comparatively fast and infer exactly land for growing field crops wheat yield.
Present stage agricultural survey product method is as follows: sampling point area and investigation content.Theoretical survey while producing, gets 1 square metre at every, investigation mu spike number; In each sampling point, get at random 20 fringes, investigation grain number per spike; Mass of 1000 kernel is calculated by the long-term mass of 1000 kernel of this kind.
Theoretical yield calculates according to following formula: per mu yield (kg/acre)=mu spike number * grain number per spike * mass of 1000 kernel * 0.85.
Hence one can see that, to wheatear portion kernal number, be that theoretical yield is measured one of important basic step, present stage, wheatear portion kernal number was all to obtain by artificial counting method, thereby obtain the output of wheat, this method counting is time-consuming, effort, in counting process, there is equally certain error, technician is produced in different surveys may obtain different results, and subjectivity impact is larger, the shortcomings such as poor accuracy.
Therefore develop a kind of wheatear of machine counting fast and accurately portion kernal number and there is realistic meaning, and to reach machine counting wheatear portion kernal number, first need to determine that wheatear portion kernal number carries out the method for Auto-counting, accurately obtaining on the basis of wheatear portion kernal number, according to the per mu yield of the mass of 1000 kernel of wheat seed and mu spike number acquisition wheat.The characteristic parameters such as wheatear portion kernal number and wheat head properties and characteristics cob length and fringe portion area are relevant, so the present invention is counted and obtained wheatear portion kernal number and have theoretical foundation by digital image processing.
Summary of the invention
(1) technical matters that will solve
The technical problem to be solved in the present invention is: a kind of method of utilizing digital image processing techniques to count out wheatear portion kernal number is provided, by the method for Digital Image Processing, calculate area and the cob length of wheat head seed region, set up the correlationship between fringe portion seed region area and cob length and its fringe portion seed number.
(2) technical scheme
For achieving the above object, the invention provides the method for counting of a kind of wheatear portion kernal number, the method comprising the steps of:
S1. utilize the front elevation of CCD camera collection wheatear portion, and the front elevation collecting is carried out to pre-service;
The concrete steps of S1 comprise: Image Acquisition, and gray processing is processed, binary conversion treatment, wherein pre-service comprises gray processing processing and two steps of binary conversion treatment.
S1.1 Image Acquisition is mainly to utilize the front elevation of CCD camera collection wheatear portion, and the device that gathers wheatear portion image has, CCD camera, and objective table, computing machine etc., illumination condition is natural lighting.Wherein objective table table top is white base plate, and CCD camera is suspended on objective table top by frame, thereby frame links into an integrated entity objective table and CCD camera.Under natural lighting, individual plant wheatear is placed on objective table according to front, objective table table top is the uniform white negative of color, gets same angle CCD camera and takes pictures from top, gets same light intensity, same angle (vertically), same focal length, sustained height while gathering image.
S1.2 gray processing is processed: coloured image is carried out to gray processing processing, obtain the gray level image of the wheat head, obtained the histogram of image by gray level image.
S1.3 binary conversion treatment: the threshold value of determining background area and the distribution of wheat head area grayscale by histogram, adopt Otsu method to select to maximize the threshold value of inter-class variance, thereby wheat head region and background area are separated, obtain the distinct image of the wheat head and background area.
S2. mathematical morphology analyse: pretreated front view is looked like to carry out morphology processing, adopt in mathematical morphology analyse opening operation to process and reasonably remove the part that structural element is little; Padding is carried out in each cavity, utilize area-method by the whole impurity eliminations of the object that is less than area P;
The concrete steps of S2 comprise: the combinatorial operation of dilation and erosion, image is filled and impurity elimination is processed
The combinatorial operation of S2.1 dilation and erosion: adopted opening operation (first this computing corrodes image, then expands at the image to after corrosion, and same structural element is used in twice operation) to process image in image processing process.
The awn of wheat after morphology processing in the image of (opening operation) or assorted point have obvious minimizing, than the part that structural element is little, reasonably remove.
S2.2 image is filled and impurity elimination is processed: bianry image is carried out to padding.For bianry image, change the background pixel of connection 0 value into foreground pixel 1 value, until reach the border of object.An important application of padding is that image is filled out to hole operation, and padding is carried out in each hole.Utilize area-method to remove unnecessary object, by the whole impurity eliminations of the object that is less than area P simultaneously.In image processing process, be this time to the bianry image after opening operation fill, impurity elimination operation.
Clear in image after processing, clear.Remaining wheat head part only, the awn of wheat, assorted point etc. are rationally removed, for the extraction of subsequent characteristics parameter provides advantage.
S3. wheatear portion characteristic parameter extraction: wheatear portion image features is the basic description of wheatear portion image fundamental characteristics, be the theoretical foundation of setting up the mathematical model between wheatear portion relevant feature parameters and kernal number, the present invention only extracts the area features of wheatear portion and cob length characteristic.
The concrete step of S3 wheatear portion characteristic parameter extraction comprises: wheatear portion area features parameter extraction and wheatear portion cob length characteristic are extracted
S3.1 area features parameter extraction: through filling and the bianry image of impurity elimination be that only to remain the wheat head be partly the region of pixel value 1, utilizing image processing techniques calculating pixel value is that the number of pixels of 1 part is wheat head area partly.
S3.2 cob length characteristic is extracted: wheat head image cob length is by connecting two obtainable nose sections of point on ellipse.
S4. set up mathematical model: utilize least square method to set up mathematical model between wheatear portion characteristic parameter and its kernal number.
S4 sets up mathematical model between wheatear portion characteristic parameter and its kernal number and comprises step: the mathematical model on wheatear portion area features parameter and the actual wheat head between kernal number, the mathematical model on wheatear portion cob length characteristic parameter and the actual wheat head between kernal number.
S4.1 sets up the correlationship between area features parameter and its kernal number: by least square method, set up image and process to calculate the mathematical model between kernal number on the area features parameter that obtains and the actual wheat head.
S4.2 sets up the correlationship between cob length parameter and its kernal number: by least square method, set up image and process to calculate the mathematical model between kernal number on the cob length characteristic parameter that obtains and the actual wheat head.
S5. mathematical model check: the mathematical model between wheatear portion area features and cob length characteristic and its kernal number is verified, guaranteed the practicality of these two kinds of models.
Related Mathematical Models verification step between S5 wheatear portion's kernal number and its feature comprises: the mathematical model checking between wheatear portion area features and its kernal number, the mathematical model checking between wheatear portion cob length characteristic and its kernal number.
Model between S5.1 wheatear portion area features parameter and kernal number is tested: the seed quantity of check sample of usining is weighed the seed quantity of the wheatear obtaining by mathematical model as standard.Using the seed quantity of the actual checking wheat samples collection obtaining as setting up correlationship curve between actual value and the wheatear portion seed quantity predicted value that obtains by mathematical model, and both difference degrees relatively.
S5.2 wheatear cob length characteristic parameter is tested with the model between kernal number: method identical in employing and S5.1 is tested to the model between wheatear cob length and kernal number.
(3) beneficial effect
The present invention passes through wheatear portion front elevation image gray processing and binary conversion treatment, use Mathematical Morphology Method that the awn of wheat and the wheat head are cut apart, thereby obtain, only there is wheatear portion principal part image, thereby can continue to utilize image processing method to extract fringe portion area features and cob length characteristic.By the wheatear portion area features that extracted and cob length characteristic parameter, set up the Related Mathematical Models between the kernal number that itself and artificial counting obtain, further higher by modelling verification method proof gained mathematical model precision, can effectively replace artificial counting.
Accompanying drawing explanation
Fig. 1 wheatear kernal number number system course of work
The wheatear portion front view picture that Fig. 2 gathers
The gray processing of Fig. 3 coloured image is processed
Fig. 4 grey level histogram
Fig. 5 gray-scale map is to binary picture
Binary map after the combinatorial operation of Fig. 6 dilation and erosion
Image after Fig. 7 filling and impurity elimination
Embodiment
The wheatear portion seed method of counting that the present invention proposes, is described in detail as follows in conjunction with the accompanying drawings and embodiments.
For quick obtaining wheatear portion area features parameter and cob length characteristic parameter, set up the correlationship between area features parameter and cob length characteristic parameter and its kernal number, therefore key point has two, one is quick obtaining wheatear portion's area features and cob length characteristic parameter, another is that these two characteristic parameters and its fringe portion kernal number are set up to mathematical model, thereby has set up basis for quick obtaining wheatear portion kernal number.
Shown in Fig. 1, the method for counting according to a kind of quick obtaining wheatear of the present invention portion kernal number comprises step:
S1. utilize the front elevation of CCD camera collection wheatear portion, and the front elevation collecting is carried out to pre-service;
The concrete steps of S1 comprise: Image Acquisition, gray processing is processed, binary conversion treatment
S1.1 Image Acquisition: Image Acquisition is mainly to utilize the front elevation of CCD camera collection wheatear portion, the device that gathers wheatear portion image has, CCD camera, objective table, computing machine etc., illumination condition is natural lighting.Wherein objective table table top is white base plate, and CCD camera is suspended on objective table top by frame, thereby frame links into an integrated entity objective table and CCD camera.Under natural lighting, individual plant wheatear is placed on objective table according to front, objective table table top is the uniform white negative of color, gets same angle CCD camera and takes pictures from top, gets same light intensity, same angle (vertically), same focal length, sustained height while gathering image.According to said method, obtain and be illustrated in figure 2 wheatear portion front view picture.
The pre-service of wheatear portion front elevation picture comprises gray processing processing and two steps of binary conversion treatment.
S1.2 gray processing is processed: coloured image is carried out to gray processing processing, obtain the gray level image of the wheat head, wheatear portion front view picture is processed and is obtained image as shown in Figure 3 through gray processing, and as can be seen from the figure gray level image has been preserved the details in wheat head region, edge clear effectively.By gray level image, obtained the histogram of gray level image.The histogram of gray level image 3 as shown in Figure 4.In histogram, the gray distribution features of wheat head region and background area is distinguished obviously, is easy to separately.
S1.3 binary conversion treatment: the threshold value of determining background area and the distribution of wheat head area grayscale by histogram, adopt Otsu method to select to maximize the threshold value of inter-class variance, thereby wheat head region and background area are separated, obtain the distinct image of the wheat head and background area.Through binary conversion treatment gained binary image as shown in Figure 5.
S2. mathematical morphology analyse: pretreated front view is looked like to carry out morphology processing, adopt in mathematical morphology analyse opening operation to process and reasonably remove the part that structural element is little; Padding is carried out in each cavity, utilize area-method by the whole impurity eliminations of the object that is less than area P; Edge extraction based on mathematical morphology is processed and is better than the Boundary extracting algorithm based on differentiating, low to noise susceptibility, the edge smoother of simultaneously extracting.Morphological filter based on mathematical morphology can utilize morphological operator filtering noise effectively by means of the geometric properties information of priori, can retain the original information in image again.
The concrete steps of S2 comprise: the combinatorial operation of dilation and erosion, image is filled and impurity elimination
The combinatorial operation of S2.1 dilation and erosion
In image processing process, adopted opening operation (first this computing corrodes image, then expands at the image to after corrosion, and same structural element is used in twice operation) to process image.That this time in processing procedure, adopt is circular configuration element (disk), and radius R gets 7, and result as shown in Figure 6.
The awn of wheat after morphology processing in the image of (opening operation) or assorted point have obvious minimizing, than the part that structural element is little, reasonably remove, and wheatear portion fringe stalk is also removed through this computing simultaneously.
S2.2 image is filled and impurity elimination
Bianry image is carried out to padding.For bianry image, change the background pixel of connection 0 value into foreground pixel 1 value, until reach the border of object.An important application of padding is that image is filled out to hole operation, and padding is carried out in each hole.Utilize area-method to remove unnecessary object, by the whole impurity eliminations of the object that is less than area P simultaneously.In image processing process, be this time to the bianry image after opening operation fill, impurity elimination operation, result is as shown in Figure 7.
Clear in image after processing, clear.Remaining wheat head part only, the awn of wheat, assorted point etc. are rationally removed, for the extraction of subsequent characteristics parameter provides advantage.
S3. wheatear portion characteristic parameter extraction: wheatear portion image features is the basic description of wheatear portion image fundamental characteristics, be the theoretical foundation of setting up the mathematical model between wheatear portion relevant feature parameters and kernal number, the present invention only extracts the area features of wheatear portion and cob length characteristic.
The concrete step of S3 wheatear portion characteristic parameter extraction comprises: wheatear portion area features amount is calculated and wheatear portion cob length characteristic is extracted
S3.1 area features parameter extraction: through filling and the bianry image of impurity elimination be that only to remain the wheat head be partly the region of pixel value 1, utilizing image processing techniques calculating pixel value is that the number of pixels of 1 part is wheat head area partly.Computation bound interior pixels number is as the area of its image Grain parts.
S3.2 cob length characteristic parameter extraction: wheat head image cob length is by connecting two obtainable nose sections of point on ellipse.
S4. set up mathematical model: set up mathematical model the correlationship between wheatear portion image characteristic parameters and its time kernal number, utilize least square method to set up mathematical model between wheatear portion characteristic parameter and its kernal number.
S4.1 sets up the correlationship between area features parameter and its kernal number: by least square method, set up the mathematical model between kernal number on area features parameter that image process to calculate obtains and the actual wheat head.
In order to count the seed number on the wheat head, this method adopts the size of the same kind wheat head image of identification, sets up the relation between wheat head seed number and its image area, adopts 100 strain wheatear heads as the sample of setting up mathematical model.The dependent linearity model of setting up between wheat head image area characteristic parameter and wheatear kernal number by the method is: y=-1.7871+0.0007x, R=0.9583.
S4.2 sets up the correlationship between cob length parameter and its kernal number: by least square method, set up image and process to calculate the mathematical model between kernal number on the cob length characteristic parameter that obtains and the actual wheat head.
In order to count the seed number on the wheat head, this method adopts the same kind wheat head image cob length scale of identification, sets up the relation between wheat head seed number and its image cob length, adopts 100 strain wheatear heads as the sample of setting up mathematical model.The relative coefficient R that sets up wheatear cob length characteristic parameter and its seed quantity by the method is 0.9474, and mathematical model expression formula is Y=0.1089X-24.958, illustrates that wheatear cob length and its seed quantity have very significant linear relationship.
S5. mathematical model check: the mathematical model between wheatear portion area features and cob length characteristic and its kernal number is verified, guaranteed the practicality of these two kinds of models.
Related Mathematical Models verification step between S5.1 wheatear portion's kernal number and its feature comprises: the mathematical model checking between wheatear portion area features and its kernal number, the mathematical model checking between wheatear portion cob length characteristic and its kernal number.In this invention, adopted 40 verification samples (surpass test specimen 1/3rd) to test to above-mentioned mathematical model, 40 samples and test specimen belong to same kind, and utilize same image capturing system, the method that image processing method adopts when setting up mathematical model is consistent.
S5.1 tests to the model between wheatear area and kernal number
Coefficient R between wheatear portion kernal number actual value and predicted value is 0.9781, close to 1, illustrates that this model can obtain by Digital Image Processing the seed quantity of wheatear.
The wheat samples of error between 12%-16% only accounts for 2.50% (i.e. a sample) of total verification sample, the error rate major part of 40 verification samples concentrates on 0-4%, 4%-8%, 8%-12%, by Tu Ke get, error rate accounts for 97.5% of total verification sample at the wheat samples below 12%.
S4.2 tests to the model between wheatear cob length and kernal number
Adopt identical method to test to the model between wheatear cob length and kernal number.
Coefficient R between wheatear portion kernal number actual value and predicted value is 0.9501, close to 1, illustrates that this model can obtain by Digital Image Processing the seed quantity of wheatear.
The wheat samples of error between 12%-16% accounts for 12.50% (i.e. 5 samples) of total verification sample, the error rate major part of 40 verification samples concentrates on 0-4%, 4%-8%, 8%-12%, analysis can obtain, and error rate accounts for 87.5% of total verification sample at the wheat samples below 12%.The number percent going out with respect to a upper model testing is lower.
From above-mentioned two kinds of model testing results, find out, the model testing result between wheatear portion area and kernal number is better than the model testing result between wheatear shaft length and kernal number.
Above wheatear portion kernal number method of counting is for awned wheat fringe portion, and applicable equally for awnless wheat fringe portion kernal number method of counting.
Claims (6)
1. a wheatear portion kernal number method of counting, the method comprising the steps of:
S1. utilize the front view picture of CCD camera collection wheatear portion, and the front view collecting is looked like to carry out pre-service;
S2. pretreated front view is looked like to carry out morphology processing, adopt opening operation processing in mathematical morphology analyse reasonably to remove the part that structural element is little; Padding is carried out in each cavity, utilize area-method by the whole impurity eliminations of the object that is less than area P;
S3. extract wheatear portion image area feature and cob length characteristic parameter;
S4. set up the Related Mathematical Models between wheatear portion image area feature and cob length characteristic parameter and kernal number;
S5. the mathematical model between wheatear portion area features and cob length characteristic and its kernal number is verified, guaranteed the practicality of these two kinds of models.
2. the wheatear portion kernal number method of counting as described in right 1, is characterized in that, the described pre-service in step S1 comprises step:
S1.1 gray processing is processed: coloured image is carried out to gray processing processing, obtain the gray level image of the wheat head, obtained the histogram of gray level image by gray level image.
S1.2 binary conversion treatment: adopt Otsu method to select to maximize the histogram thresholding of inter-class variance, thereby obtain the image that wheat head region and background area are separated.
3. the wheatear portion kernal number method of counting as described in right 1, is characterized in that, the described morphology processing in step S2 comprises step:
The image that S2.1 processes two-value has adopted opening operation, and first opening operation corrodes image, then at the image to after corrosion, expands, and twice operation used same structural elements usually to process image.Through opening operation, than the part that structural element is little, reasonably remove.
S2.2 carries out padding for bianry image, changes the background pixel of connection 0 value into foreground pixel 1 value, until reach the border of object.Utilize area-method to remove unnecessary object, by the whole impurity eliminations of the object that is less than area P simultaneously.Through filling and removal of impurities is processed, bianry image is remaining wheat head part only, i.e. the rationally removal such as the awn of wheat, wheat stalk and assorted point, for the extraction of subsequent characteristics parameter provides advantage.
4. the wheatear portion kernal number method of counting as described in right 1, is characterized in that, the described fringe portion image characteristics extraction in step S3 comprises step:
S3.1 area features amount is extracted: the bianry image through filling and impurity elimination is the region that only surplus wheat head partial pixel value is 1, and calculating pixel value is the area that the number of pixels of 1 part is wheat head part.
S3.2 cob length characteristic is extracted: cob length is by connecting two obtainable nose segment length of point on ellipse.
5. the wheatear portion kernal number method of counting as described in right 1, is characterized in that, the described mathematical model of setting up in step S4 comprises step:
S4.1 utilizes least square method to set up mathematical model between area features amount that image process to calculate obtains and actual wheatear portion kernal number.
S4.2 utilizes least square method to set up mathematical model between cob length characteristic amount that image process to calculate obtains and actual wheatear portion kernal number.
6. the wheatear portion kernal number method of counting as described in right 1, is characterized in that, the described checking mathematical model in step S5 comprises step:
When above-mentioned mathematical model is tested, check sample and test specimen belong to same kind, and utilize same image capturing system, and the method that image processing method adopts when setting up mathematical model is consistent.
S5.1 tests to the model between wheatear portion area and kernal number
The actual seed quantity of obtaining checking wheat samples of usining is set up correlationship curve as between actual value and the wheatear portion seed quantity predicted value that obtains by mathematical model, and both difference degrees of comparison.
S5.2 tests to the model between wheatear cob length and kernal number
Adopt identical method to test to the model between wheatear cob length and kernal number.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210304177.1A CN103632157B (en) | 2012-08-24 | 2012-08-24 | Individual plant wheat fringe portion kernal number method of counting |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210304177.1A CN103632157B (en) | 2012-08-24 | 2012-08-24 | Individual plant wheat fringe portion kernal number method of counting |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103632157A true CN103632157A (en) | 2014-03-12 |
CN103632157B CN103632157B (en) | 2018-01-05 |
Family
ID=50213185
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210304177.1A Active CN103632157B (en) | 2012-08-24 | 2012-08-24 | Individual plant wheat fringe portion kernal number method of counting |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103632157B (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104021369A (en) * | 2014-04-30 | 2014-09-03 | 南京农业大学 | Grain counting method for spike of single rice based on digital image processing technology |
CN105427275A (en) * | 2015-10-29 | 2016-03-23 | 中国农业大学 | Filed environment wheat head counting method and device |
CN105574853A (en) * | 2015-12-07 | 2016-05-11 | 中国科学院合肥物质科学研究院 | Method and system for calculating number of wheat grains based on image identification |
CN107064146A (en) * | 2017-05-15 | 2017-08-18 | 柳州环山科技有限公司 | A kind of computer based wheat spike number measurement apparatus |
CN107590812A (en) * | 2017-09-01 | 2018-01-16 | 南京农业大学 | Wheat fringe portion small ear identifies method of counting |
WO2018073093A1 (en) * | 2016-10-19 | 2018-04-26 | Bayer Cropscience Aktiengesellschaft | Determining the grain weight of an ear |
CN109447945A (en) * | 2018-09-21 | 2019-03-08 | 河南农业大学 | Wheat Basic Seedling rapid counting method based on machine vision and graphics process |
CN113011296A (en) * | 2021-03-08 | 2021-06-22 | 中国农业科学院农产品加工研究所 | Method and system for rapidly identifying purity of wheat variety |
CN113470104A (en) * | 2021-07-21 | 2021-10-01 | 浙江托普云农科技股份有限公司 | Wheat ear grain counting and measuring method and system based on gray value comparison |
CN113936056A (en) * | 2021-10-20 | 2022-01-14 | 广东皓行科技有限公司 | Image recognition method, yield estimation method and electronic device |
CN115375694A (en) * | 2022-10-27 | 2022-11-22 | 浙江托普云农科技股份有限公司 | Portable rice whole ear measuring method based on image recognition and application thereof |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0072237B1 (en) * | 1981-08-11 | 1987-04-29 | De La Rue Systems Limited | Apparatus for scanning a sheet |
EP1089553A1 (en) * | 1999-10-01 | 2001-04-04 | Seiko Epson Corporation | Colour image processing apparatus and method |
CN101281112A (en) * | 2008-04-30 | 2008-10-08 | 浙江理工大学 | Image type automatic analysis method for mesh adhesion rice corn |
CN101673414A (en) * | 2009-10-19 | 2010-03-17 | 北京农业信息技术研究中心 | Three-dimensional morphological virtual modeling method of corn silk |
CN101944231A (en) * | 2010-08-19 | 2011-01-12 | 北京农业智能装备技术研究中心 | Method for extracting wheatear morphological parameters |
CN102072883A (en) * | 2010-07-07 | 2011-05-25 | 北京农业智能装备技术研究中心 | Device and method for detecting comprehensive quality of crop seeds |
CN102132139A (en) * | 2008-08-22 | 2011-07-20 | 先锋国际良种公司 | Methods for counting corn silks or other plural elongated strands and use of the count for characterizing the strands or their origin |
-
2012
- 2012-08-24 CN CN201210304177.1A patent/CN103632157B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0072237B1 (en) * | 1981-08-11 | 1987-04-29 | De La Rue Systems Limited | Apparatus for scanning a sheet |
EP1089553A1 (en) * | 1999-10-01 | 2001-04-04 | Seiko Epson Corporation | Colour image processing apparatus and method |
CN101281112A (en) * | 2008-04-30 | 2008-10-08 | 浙江理工大学 | Image type automatic analysis method for mesh adhesion rice corn |
CN102132139A (en) * | 2008-08-22 | 2011-07-20 | 先锋国际良种公司 | Methods for counting corn silks or other plural elongated strands and use of the count for characterizing the strands or their origin |
CN101673414A (en) * | 2009-10-19 | 2010-03-17 | 北京农业信息技术研究中心 | Three-dimensional morphological virtual modeling method of corn silk |
CN102072883A (en) * | 2010-07-07 | 2011-05-25 | 北京农业智能装备技术研究中心 | Device and method for detecting comprehensive quality of crop seeds |
CN101944231A (en) * | 2010-08-19 | 2011-01-12 | 北京农业智能装备技术研究中心 | Method for extracting wheatear morphological parameters |
Non-Patent Citations (2)
Title |
---|
陈娇等: "基于垄线平行特征的视觉导航多垄线识别", 《农业工程学报》 * |
韩仲志等: "计数玉米穗行数的机器视觉研究", 《玉米科学》 * |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104021369A (en) * | 2014-04-30 | 2014-09-03 | 南京农业大学 | Grain counting method for spike of single rice based on digital image processing technology |
CN105427275A (en) * | 2015-10-29 | 2016-03-23 | 中国农业大学 | Filed environment wheat head counting method and device |
CN105427275B (en) * | 2015-10-29 | 2017-11-24 | 中国农业大学 | Crop field environment wheat head method of counting and device |
CN105574853A (en) * | 2015-12-07 | 2016-05-11 | 中国科学院合肥物质科学研究院 | Method and system for calculating number of wheat grains based on image identification |
CN105574853B (en) * | 2015-12-07 | 2018-05-15 | 中国科学院合肥物质科学研究院 | The method and system that a kind of wheat head grain number based on image recognition calculates |
WO2018073093A1 (en) * | 2016-10-19 | 2018-04-26 | Bayer Cropscience Aktiengesellschaft | Determining the grain weight of an ear |
CN109863530A (en) * | 2016-10-19 | 2019-06-07 | 巴斯夫农化商标有限公司 | Determine the grain weight of grain ear |
US10984548B2 (en) | 2016-10-19 | 2021-04-20 | Basf Agro Trademarks Gmbh | Yield prediction for a cornfield |
US11010913B2 (en) | 2016-10-19 | 2021-05-18 | Basf Agro Trademarks Gmbh | Determining the grain weight of an ear |
CN107064146A (en) * | 2017-05-15 | 2017-08-18 | 柳州环山科技有限公司 | A kind of computer based wheat spike number measurement apparatus |
CN107590812B (en) * | 2017-09-01 | 2021-07-02 | 南京农业大学 | Wheat ear identification and counting method |
CN107590812A (en) * | 2017-09-01 | 2018-01-16 | 南京农业大学 | Wheat fringe portion small ear identifies method of counting |
CN109447945A (en) * | 2018-09-21 | 2019-03-08 | 河南农业大学 | Wheat Basic Seedling rapid counting method based on machine vision and graphics process |
CN113011296A (en) * | 2021-03-08 | 2021-06-22 | 中国农业科学院农产品加工研究所 | Method and system for rapidly identifying purity of wheat variety |
CN113470104A (en) * | 2021-07-21 | 2021-10-01 | 浙江托普云农科技股份有限公司 | Wheat ear grain counting and measuring method and system based on gray value comparison |
CN113936056A (en) * | 2021-10-20 | 2022-01-14 | 广东皓行科技有限公司 | Image recognition method, yield estimation method and electronic device |
CN115375694A (en) * | 2022-10-27 | 2022-11-22 | 浙江托普云农科技股份有限公司 | Portable rice whole ear measuring method based on image recognition and application thereof |
Also Published As
Publication number | Publication date |
---|---|
CN103632157B (en) | 2018-01-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103632157A (en) | A method for counting seeds of a wheatear portion per wheat | |
CN104021369A (en) | Grain counting method for spike of single rice based on digital image processing technology | |
CN101944231B (en) | Method for extracting wheatear morphological parameters | |
CN109447945B (en) | Quick counting method for basic wheat seedlings based on machine vision and graphic processing | |
CN103745478B (en) | Machine vision determination method for wheat germination rate | |
CN102288606B (en) | Pollen viability measuring method based on machine vision | |
Stajnko et al. | Modelling apple fruit yield using image analysis for fruit colour, shape and texture | |
CN111462058B (en) | Method for rapidly detecting effective rice ears | |
CN102855485B (en) | The automatic testing method of one grow wheat heading | |
CN108037123B (en) | Precision detection method for sowing performance parameters of hybrid rice bowl body tray | |
CN107564000A (en) | Hericium erinaceus Non-Destructive Testing stage division based on computer vision | |
CN109827957A (en) | A kind of rice leaf SPAD value estimating and measuring method based on computer vision and system | |
CN105005813A (en) | Insect pest analyzing and counting method and system | |
CN113096178A (en) | Pig weight estimation method, device, equipment and storage medium | |
CN106023235B (en) | A kind of method that the effective seed number of crops measures | |
CN112580671A (en) | Automatic detection method and system for multiple development stages of rice ears based on deep learning | |
CN114596509A (en) | Machine vision-based rice seedling leaf age period identification method | |
CN104268890B (en) | A kind of Seed-Setting Percentage in Rice measuring method | |
CN111932551A (en) | Missing transplanting rate detection method of rice transplanter | |
CN116824405A (en) | Green-peel walnut target detection method based on improved YOLOv8 under unmanned aerial vehicle aerial photographing visual angle | |
CN110619417B (en) | Theoretical yield measurement method based on image characteristics of rice canopy spike in field | |
CN106172082A (en) | For the method analyzing poultry growth performance automatic measurement system noisy data | |
CN109115771A (en) | Sugarcane technical maturity automatic observation process | |
CN103136439B (en) | Plant illness discrimination method and system thereof | |
Zhao et al. | Grading system of tomato grafting machine based on machine vision |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |