CN102172119A - Monitoring system for precise seeding machine - Google Patents
Monitoring system for precise seeding machine Download PDFInfo
- Publication number
- CN102172119A CN102172119A CN 201110051140 CN201110051140A CN102172119A CN 102172119 A CN102172119 A CN 102172119A CN 201110051140 CN201110051140 CN 201110051140 CN 201110051140 A CN201110051140 A CN 201110051140A CN 102172119 A CN102172119 A CN 102172119A
- Authority
- CN
- China
- Prior art keywords
- seeding
- image
- camera
- sigma
- speed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Abstract
The invention discloses a monitoring system for a precise seeding machine. The system comprises a computer, a camera and a seeding device, wherein the computer is provided with MATLAB software. The image collecting speed of the camera is set according to the seeding speed of the seeding device, and collected images are applied to the MATLAB software and processed and computed, thus coordinates for the images of a target can be calculated, and the seeding condition of the precise seeding machine can be determined according to collected coordinate data. The monitoring system has a simple structure, ensures the accurate monitoring result and can be used for monitoring the seeding amount and the reseeding and seed leakage conditions in real time.
Description
Technical field
The present invention relates to a kind of agricultural technology field, specifically be a kind of utilize computer vision technique to detect the sead feeder seeding to finish after the precision metering device machine monitoring system of seed end-state in the plane.
Background technology
Precision metering device machinery can reduce by artificial seeding's workload and grain weight, but because some crops have super seed, seeding quantity is generally one in every cave, and kind of a spacing is had strict demand.As broadcast leakage occurs and will have a strong impact on emergence rate, and then influence crop yield, therefore the seeding state of sead feeder is monitored and have very important significance.But up to now, Shang Weijian has the seeding state of pair sead feeder to carry out the relevant report of device for monitoring or method.
Summary of the invention
Technical problem to be solved by this invention provides a kind of can the monitoring the seeding state of sead feeder, and accurate monitoring precision metering device machine monitoring system.
The present invention solves the problems of the technologies described above with following technical scheme: precision metering device machine monitoring system of the present invention comprises computer, camera, the seeding unit that MATLAB software is housed, camera is connected with computer and remains constant with the distance of seeding unit, the top of seeding unit connects inoculating hood, the below connects discharging tube, the below of discharging tube is provided with can be by the conveyer belt of camera, and conveyer belt is made horizontal uniform motion by driven by motor and relative seeding unit; The operating procedure of described precision metering device machine monitoring system is as follows: 1) start sead feeder, set the speed of IMAQ according to seeding speed, calculated by formula T=(240-1000V t)/1000V t, wherein: the T-frame period;
The V-line speed, unit is m/s;
T=0.017s is for gathering the single-frame images required time;
2) frame period that draws according to aforementioned calculation is selected the collection speed image of camera, starts camera then and begins to gather image;
3) then to the tool box of the image that collects utilization MATLAB software
Z=imsubtract(X,Y)
K=im2bw(Z,0)
Obtain bianry image K, wherein image X takes good background image before seeding begins, and image Y is the seeding images that photographs after seeding begins, and image K is the bianry image after the computing;
4) at last to the target among the image K, i.e. the drop point of seed calculates object coordinates by following formula:
Wherein,
B[i, j] be the mark value of this point, m, n are respectively gauge point pixel i, and the sum of j is brought into formula x=v/k y=u/k to data,
Known camera inner parameter k and image coordinate (v, u), just obtain successively each object coordinate figure (x, y),, thereby finish the seeding state of sead feeder is monitored.
The present invention compares with traditional image processing method, owing to the MATLAB software that adopts does not need to programme substantially again, but directly realizes calling of program by function, has saved a lot of times like this.In addition, involved in the present invention to all data and mathematical formulae also can call and calculate the result by MATLAB software, this is that other image processing softwares are not available.The present invention combines with seeding unit monitoring device based on computer vision by utilizing MATLAB software, the reliability and the sensitivity of the seed-metering performance monitoring of seeding unit have been improved, reduce human factor, and solved the high problem of field site test expense, improved the automaticity of seeding unit process of the test.
Description of drawings
Fig. 1 is the hardware configuration schematic diagram of precision metering device machine monitoring system of the present invention;
Fig. 2 be the MATLAB software toolkit Z=imsubtract that adopts of the present invention (X, Y), the schematic diagram of X image among the K=im2bw (Z, 0);
Fig. 3 be the MATLAB software toolkit Z=imsubtract that adopts of the present invention (X, Y), the schematic diagram of Y image among the K=im2bw (Z, 0);
Fig. 4 be the MATLAB software toolkit Z=imsubtract that adopts of the present invention (X, Y), the schematic diagram of the bianry image K that K=im2bw (Z, 0) draws after computing.
Embodiment
The invention will be further described below in conjunction with accompanying drawing:
As shown in Figure 1, precision metering device machine monitoring system of the present invention comprises notebook computer 1, camera 2, the magnetic shake formula seeding unit 4 that MATLAB software is housed, camera 2 is connected with notebook computer 1 and remains constant with the distance of magnetic shake formula seeding unit 4, the top of magnetic shake formula seeding unit 4 connects inoculating hood 3, the below connects discharging tube 5, the below of discharging tube 5 is provided with can be by the Rubber Conveyor Belt Scrap 6 of camera 2, and Rubber Conveyor Belt Scrap 6 is driven by motor 7 and relative magnetic shake formula seeding unit 4 is made horizontal uniform motion.
Below be the embodiment that uses precision metering device machine monitoring system of the present invention, specific operation process is as follows:
The transmission speed of 1, startup sead feeder, and setting Rubber Conveyor Belt Scrap 6 is 0.5m/s, sets the speed of IMAQ then according to seeding speed, and by formula T=(240-1000V t)/1000V t
Wherein: the T-frame period;
The V-line speed, unit is m/s;
T=0.017s is for gathering the single-frame images required time;
Calculate, the interframe of IMAQ is divided into 27;
2, select the speed of camera collection image according to frame period, specifically selected for use major parameter to see Table 1 camera and carried out IMAQ;
Table 1 camera major parameter
3) then to the tool box of the image that collects utilization MATLAB software
Z=imsubtract(X,Y)
K=im2bw(Z,0)
Obtain bianry image K, wherein X takes good background image (seeing shown in Figure 2) before seeding begins, and Y is the seeding images (seeing shown in Figure 3) that photographs after seeding begins, and K is the bianry image (seeing shown in Figure 4) after the computing;
4) at last to the target among the image K, i.e. the drop point of seed calculates object coordinates by following formula:
Wherein,
B[i, j] be the mark value of this point, m, n are respectively gauge point pixel i, and the sum of j is brought into formula x=v/k y=u/k to data,
Computational process is as follows:
I=imread (' figure x.bmp ');
J=imread (' figure y.bmp ');
y=imsubtract(J,25);
z=imsubtract(I,y);
BW=im2bw(z,0);
L=bwlabel(BW,4);
[i,j]=find(L==0);
X=v/2.5 y=u/2.5, adjacent x, y subtracts each other, and obtains showing the monitoring spacing X among the 5-1, the data of Y.
The seed grain that table 5-1 application system monitoring of the present invention draws is apart from result and actual measured results contrast table
L1 | L2 | L3 | L4 | L5 | L6 | L7 | L8 | |
X monitors spacing (mm) | 61 | 58 | 62 | 55 | 60 | 57 | 57 | 60 |
Y monitors spacing (mm) | 2 | 2 | 1 | 2 | 3 | 2 | 1 | 2 |
X surveys (mm) | 62 | 58 | 61 | 54 | 60 | 57 | 58 | 59 |
Y surveys (mm) | 2 | 2 | 1 | 1 | 3 | 2 | 1 | 2 |
The experimental data of analytical table 5-1 can obviously be found out, the data that Computing is come out and the data of actual measurement are very approaching, according to
Can calculate the data goodness of fit η of directions X kind spacing
x=98.93%,
The data goodness of fit η of Y direction kind spacing
y=91.67%.
F ratio and significance test:
The data of the spacing among the his-and-hers watches 5-1 on the directions X are carried out error analysis, test data can be divided into theoretical value and error two parts, theoretical value is not having due result under the error disturbed condition exactly, it can be estimated with the mean value of repeated test result under the same level, but the X actual measurement is theoretical value in table 5-1.
Wherein, r: number of levels, n
iRepeat number.
Because the X actual measurement is theoretical value, so can be the mean value of X actual measurement as repeated test result under the same level.
S
Mistake=(61-62)
2+ (58-58)
2+ (62-61)
2+ (55-54)
2
+(60-60)
2+(57-57)
2+(57-58)
2+(60-59)
2=5
Promptly
Test data is not as there being sum of errors factor level effects, and whole test datas all should be the same, for
So test data x
IjCan reflect total fluctuation with the difference of overall average.Get they square after addition promptly get the total deviation sum of squares.
Data substitution formula (5.27) is got S
Always=83.5, S
Cause=78.5
Known that the sum of errors factor level respectively after the influence to index, also needs the sum of errors total deviation is compared, whether remarkable with error in judgement to the influence of index.But can not be by directly comparing S
MistakeAnd S
AlwaysSize carry out.Because their size is not only relevant with the size of data that participates in calculating.And generally calculate S
MistakeAnd S
AlwaysThe number difference of contained data in the time of therefore will comparing, at first will be eliminated the influence of data number.The degree of freedom notion is proposed for this reason.Degree of freedom is represented by f
Generally: f
Always=overall test number of times-1
f
Cause=factor level number-1
f
Mistake=f
Always-f
Cause=n-r
S/f----mean deviation sum of squares (all side and)
Because equal sides and eliminated the influence of data numbers, so can be by S relatively
Mistake/ f
MistakeAnd S
Always/ f
Always, come error in judgement whether bigger than normal and produce mistake.
Order: F=(S
Always/ f
Always)/(S
Mistake/ f
Mistake) (5.28)
If F is big, illustrate that the data that calculator calculates compare with the data of actual measurement, error is very little.Otherwise it is opposite.Data substitution formula (5.28) F
x=(83.5/15)/(5/8) ≈ 8.907
Table look-up: F
0.01(f
Always, f
Mistake)=F
0.01(15,8)=5.52
F
x=8.907>F
0.01=5.52
Therefore, the data error that calculator calculates is very little, and confidence level is very high.
The data of the spacing among the his-and-hers watches 5-1 on the Y direction are carried out error analysis, get according to table 5-1 and formula (5.25), (5.26), (5.27), (5.28)
S
Mistake=1
S
Always=8.0625
F
y=(8.0625/15)/(1/8)=4.30
Table look-up: F
0.01(f
Always, f
Mistake)=F
0.01(15,8)=5.52
F
0.025(f
Always, f
Mistake)=F
0.025(15,8)=4.10
F
0.025=4.10<F
y=4.30<F
0.01=5.52
Therefore, the data error that calculator calculates is little, and is with a high credibility.
Integrate, the data error of table 5-1 is little, with a high credibility, thus the accuracy height of explanation precision metering device machine monitoring system of the present invention.
Claims (1)
1. precision metering device machine monitoring system, it is characterized in that, it comprises computer, camera, the seeding unit that MATLAB software is housed, camera is connected with computer and remains constant with the distance of seeding unit, the top of seeding unit connects inoculating hood, the below connects discharging tube, and the below of discharging tube is provided with can be by the conveyer belt of camera, and conveyer belt is made horizontal uniform motion by driven by motor and relative seeding unit; The operating procedure of described precision metering device machine monitoring system is as follows:
1) starts sead feeder, set the speed of IMAQ, calculate by formula T=(240-1000Vt)/1000Vt, wherein: the T-frame period according to seeding speed;
The V-line speed, unit is m/s;
T=0.017s is for gathering the single-frame images required time;
2) frame period that draws according to aforementioned calculation is selected the speed of camera collection image, starts camera then and begins to gather image;
3) then to the tool box of the image that collects utilization software MATLAB
Z=imsubtract(X,Y)
K=im2bw(Z,0)
Obtain bianry image K, wherein image X takes good background image before seeding begins, and image Y is the seeding images that photographs after seeding begins, and image K is the bianry image after the computing;
4) at last to the target among the image K, i.e. the drop point of seed calculates object coordinates by following formula:
Wherein,
B[i, j] be the mark value of this point, m, n are respectively gauge point pixel i, and the sum of j is brought into formula x=v/k y=u/k to data,
(v, u), (x y), monitors the seeding state of sead feeder thereby finish just to obtain the coordinate figure of each object successively for known camera inner parameter k and image coordinate.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 201110051140 CN102172119A (en) | 2011-03-03 | 2011-03-03 | Monitoring system for precise seeding machine |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 201110051140 CN102172119A (en) | 2011-03-03 | 2011-03-03 | Monitoring system for precise seeding machine |
Publications (1)
Publication Number | Publication Date |
---|---|
CN102172119A true CN102172119A (en) | 2011-09-07 |
Family
ID=44515516
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN 201110051140 Pending CN102172119A (en) | 2011-03-03 | 2011-03-03 | Monitoring system for precise seeding machine |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102172119A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102630429A (en) * | 2012-04-24 | 2012-08-15 | 广西大学 | Bud injury preventing system for sugarcane cutting |
CN105960902A (en) * | 2016-06-14 | 2016-09-28 | 河北阔海农业机械有限公司 | Air-sweeping type drill seeder |
CN108801665A (en) * | 2018-03-27 | 2018-11-13 | 昆明理工大学 | A kind of no-till maize mass monitoring system based on LabVIEW |
CN110375979A (en) * | 2019-08-27 | 2019-10-25 | 山东农业大学 | Garlic planter spoon formula takes kind of broadcast leakage replay experimental bench and a detection method |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101361423A (en) * | 2008-09-01 | 2009-02-11 | 中国农业大学 | Self-cleaning sowing device and real-time monitoring method thereof |
EP2047735A1 (en) * | 2007-10-09 | 2009-04-15 | Deere & Company | Seeding machine and row unit of a seeding machine |
CN101441455A (en) * | 2008-12-19 | 2009-05-27 | 华南农业大学 | System for monitoring seed sowing state of seed sowing device of rice direct seeding machine |
CN101715668A (en) * | 2009-12-22 | 2010-06-02 | 中国农业机械化科学研究院 | Planter, planting monitoring equipment and method thereof |
WO2010144801A2 (en) * | 2009-06-12 | 2010-12-16 | Great Plains Manufacturing, Incorporated | Air-assisted planting system having a single fan with pressure-responsive splitting of air streams for conveying and metering functions |
-
2011
- 2011-03-03 CN CN 201110051140 patent/CN102172119A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2047735A1 (en) * | 2007-10-09 | 2009-04-15 | Deere & Company | Seeding machine and row unit of a seeding machine |
CN101361423A (en) * | 2008-09-01 | 2009-02-11 | 中国农业大学 | Self-cleaning sowing device and real-time monitoring method thereof |
CN101441455A (en) * | 2008-12-19 | 2009-05-27 | 华南农业大学 | System for monitoring seed sowing state of seed sowing device of rice direct seeding machine |
WO2010144801A2 (en) * | 2009-06-12 | 2010-12-16 | Great Plains Manufacturing, Incorporated | Air-assisted planting system having a single fan with pressure-responsive splitting of air streams for conveying and metering functions |
CN101715668A (en) * | 2009-12-22 | 2010-06-02 | 中国农业机械化科学研究院 | Planter, planting monitoring equipment and method thereof |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102630429A (en) * | 2012-04-24 | 2012-08-15 | 广西大学 | Bud injury preventing system for sugarcane cutting |
CN105960902A (en) * | 2016-06-14 | 2016-09-28 | 河北阔海农业机械有限公司 | Air-sweeping type drill seeder |
CN108801665A (en) * | 2018-03-27 | 2018-11-13 | 昆明理工大学 | A kind of no-till maize mass monitoring system based on LabVIEW |
CN110375979A (en) * | 2019-08-27 | 2019-10-25 | 山东农业大学 | Garlic planter spoon formula takes kind of broadcast leakage replay experimental bench and a detection method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102172119A (en) | Monitoring system for precise seeding machine | |
BR102017022222B1 (en) | METHODS FOR REDUCING AND CORRECTING POLARIZATION OF SENSING SYSTEM AND AGRICULTURAL MACHINERY | |
CN102385318B (en) | Method and device for control of tillage-free seeding machine seeding quantity | |
CN104457936B (en) | Potted plant growing trend dynamic detection device and detection method thereof | |
CN105095958B (en) | A kind of silk cocoon method of counting | |
AU2016337264A1 (en) | Computer-generated accurate yield map data using expert filters and spatial outlier detection | |
CN106163261A (en) | Agricultural tool and agricultural tool operator's supervising device, system and method | |
CN102750584B (en) | On-corncob corn niblet counting method | |
CN103039154B (en) | Method and device for performing high-precision determination of corn ear variety based on images | |
CN102636486B (en) | Method for automatically detecting three-true-leaf period of cotton | |
CN209802305U (en) | system for be used for crops output aassessment | |
CN103688684A (en) | Adjusting device and adjusting method for grading sieve piece opening of combine harvester | |
CN102577742A (en) | Real-time acre counting method based on GPS (Global Positioning System) | |
CN105411618A (en) | Method and system for adjusting positions of radioactive source | |
CN113317032A (en) | Method, system and device for monitoring harvest yield of combined harvester | |
CN106264588A (en) | The detection of positron emission tomography detection efficient, bearing calibration and device | |
CN102865814A (en) | Plant population three-dimensional reconstruction error measurement method | |
Liu et al. | Development and application experiments of a grain yield monitoring system | |
CN115226612B (en) | Intelligent distribution system for water resource allocation management | |
Ding et al. | Design and experiment of performance testing system of multi-channel seed-metering device based on time intervals | |
Yin et al. | Design and experiment of multi-information collection system for grain combine harvesters | |
CN102507238B (en) | Sowing precision detection system and method based on soil matrix | |
CN110400097A (en) | A kind of a kind of information-based method of soil testing and fertilizer recommendation | |
Yin et al. | Development and application of subsoiling monitoring system based on edge computing using IoT architecture | |
CN107764382A (en) | The grain yield investigating system of unmanned plane measuring and calculating wheat paddock based on Beidou navigation |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20110907 |