CN100536653C - Crop water-requesting information determination based on computer vision - Google Patents
Crop water-requesting information determination based on computer vision Download PDFInfo
- Publication number
- CN100536653C CN100536653C CNB2005100410454A CN200510041045A CN100536653C CN 100536653 C CN100536653 C CN 100536653C CN B2005100410454 A CNB2005100410454 A CN B2005100410454A CN 200510041045 A CN200510041045 A CN 200510041045A CN 100536653 C CN100536653 C CN 100536653C
- Authority
- CN
- China
- Prior art keywords
- crop
- fruit
- cane
- image
- size
- 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.)
- Expired - Fee Related
Links
- 235000013399 edible fruits Nutrition 0.000 claims abstract description 36
- 230000002262 irrigation Effects 0.000 claims abstract description 23
- 238000003973 irrigation Methods 0.000 claims abstract description 23
- 238000000034 method Methods 0.000 claims abstract description 18
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 17
- 238000001914 filtration Methods 0.000 claims abstract description 9
- 238000005259 measurement Methods 0.000 claims description 28
- 238000012545 processing Methods 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 4
- 239000013558 reference substance Substances 0.000 claims 1
- 238000012800 visualization Methods 0.000 abstract 1
- 241000196324 Embryophyta Species 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 6
- 210000000056 organ Anatomy 0.000 description 4
- 239000000523 sample Substances 0.000 description 4
- 238000011160 research Methods 0.000 description 3
- 241000207199 Citrus Species 0.000 description 2
- 240000008042 Zea mays Species 0.000 description 2
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 description 2
- 235000002017 Zea mays subsp mays Nutrition 0.000 description 2
- 235000020971 citrus fruits Nutrition 0.000 description 2
- 235000005822 corn Nutrition 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 230000012010 growth Effects 0.000 description 2
- 239000003621 irrigation water Substances 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000008635 plant growth Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 239000002689 soil Substances 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 244000068988 Glycine max Species 0.000 description 1
- 235000010469 Glycine max Nutrition 0.000 description 1
- 235000007688 Lycopersicon esculentum Nutrition 0.000 description 1
- 239000006002 Pepper Substances 0.000 description 1
- 240000003768 Solanum lycopersicum Species 0.000 description 1
- 241000209140 Triticum Species 0.000 description 1
- 235000021307 Triticum Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000011326 mechanical measurement Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000000053 physical method Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 235000013311 vegetables Nutrition 0.000 description 1
Images
Landscapes
- Length Measuring Devices By Optical Means (AREA)
- Image Processing (AREA)
Abstract
A method based on the computer visualization for detecting the information about the water demand of crops in order to save water in intelligent irrigation system is disclosed. Its system is composed of a black reference with known sizes, image acquisition equipment, image acquisition card and computer. Said method includes such steps as arranging said block reference close to stem or fruit (seed) of crops, taking the image, filtering noise, separating the reference and object to be detected, calculating the numbers of their pixels, and calculating the water demand.
Description
Affiliated technical field
The present invention relates to water-saving irrigation field and sensor observation and control technology, particularly relate to a kind of detection method that detects the intelligent water-saving irrigation of crop cane and the variation of fruit micro-dimension based on computer vision technique.
Background technology
Present irrigation system all is the control parameter of the parameters such as temperature of humidity, environment with soil as irrigation system, be not direct parameter, so control accuracy is low, and the problem of bringing is that the irrigation water resource has been caused very big waste.
At the problems referred to above, the nondestructive plant moisture precise detection technology based on physical method is proposed, realize the closed-loop control irrigation system, the utilization ratio that improves China's water resource is had very important significance.The existing researcher of China just used LVDT-5 type (differential transformer type) displacement transducer corn, citrus etc. is measured at the nineties initial stage in 20th century, had obtained 15.6% and 21.4% water-saving result respectively.But LVDT is used for the mechanical manufacturing field industry measurement, and Measurement Resolution and precision can meet the demands, but indexs such as ergometry, volume and anti-environmental disturbances ability but can't satisfy the actual requirement to plant measurement.China fruit tree forest workers measures the citrus size with outside micrometer, in vegetative period, when finding that fruit size does not increase, just fruit tree is in time poured water, and this method wastes time and energy.Recently, the scientist of Hebrew Univ Jerusalem Israel also tests the irrigation system of tomato at application micron order vane thickness sensor, has obtained water-saving rate 35%, has increased production 40% effect, but also do not reached the degree of practicability at present.Current, also there is the scholar being engaged in abroad and utilizes in-plant infrared remote sensing image to detect crop need regimen condition, this technical costs is very expensive, and do not reach the degree of practicability, Chinese patent 03150690.9 " changing the intelligent water-saving irrigation system that detects based on the plant organ micro-dimension ", the trace of measuring plant organ by mechanical device changes, need to obtain water information to control irrigation system, then can reach the purpose of water saving, the method of this mechanical measurement needs to use the mechanical probe contact measurement, and each measurement all will be placed on probe on the former measuring position exactly, perhaps probe is placed on fruit or the blade in real time, the former operating difficulties, the latter is because the long-time mechanical probe of placing, and this can influence plant growth, and gaging pressure is difficult to control, pressure is excessive then to damage the crop organ by pressure, influences certainty of measurement, and pressure is too small, loose contact can make to measure and be forbidden.
The develop rapidly of current computer vision technique, certainty of measurement is more and more higher, and we propose to utilize this technology non-cpntact measurement crop cane to change or the fruit growth situation, need water information thereby detect crop, and the control irrigation system reaches the purpose of water-saving irrigation.This technology is to meet the novel sensor that plant detects demand.This research can have fabulous novelty and practicality early for China's water-saving irrigation service.
Summary of the invention
The purpose of this invention is to provide and a kind ofly detect the intelligent water-saving that crop cane and fruit micro-dimension change based on computer vision technique and irrigate detection method, realize non-cpntact measurement, do not influence the purpose of plant growth and real water-saving irrigation.
In order to achieve the above object, the technical solution used in the present invention is as follows:
Scheme 1: it is made up of image capture device, image pick-up card and calculator; Utilize image capture device to gather the cane image of crop, in order to solve the miscellaneous problem of demarcation in the measurement, we propose to utilize the method for object of reference, not only simple to operate but also certainty of measurement height, just select the suitably object of reference of known dimensions of size, object of reference is placed on crop cane to be measured in the identical same plane of distance of camera lens, existing crop cane to be measured in the image of Cai Jiing like this, the object of reference that known dimensions is arranged again, pass through image processing algorithm, at first be partitioned into crop cane and object of reference, calculate the pixel count that occupies on their diametric(al) then respectively, both ratio is equal to the dimension ratio of their true diameter, so just can measure the cane of crop, thereby obtain crop and need the regimen condition, reach the purpose of water-saving irrigation.
Scheme 2: it is made up of image capture device, image pick-up card and calculator; Utilize image capture device to gather the fruit image of crop, in order to solve the miscellaneous problem of demarcation in the measurement, we propose to utilize the method for object of reference, not only simple to operate but also certainty of measurement height, just select the suitably object of reference of known dimensions of size, object of reference is placed on crop and fruit to be measured in the identical same plane of distance of camera lens, existing crop and fruit to be measured in the image of Cai Jiing like this, the object of reference that known dimensions is arranged again, pass through image processing algorithm, at first be partitioned into crop and fruit and object of reference, calculate the pixel count that occupies on their diametric(al) then respectively, both ratio is equal to the dimension ratio of their true diameter, so just can measure the fruit diameter of crop, thereby obtain crop and need the regimen condition, reach the purpose of water-saving irrigation.
Scheme 3: it is made up of image capture device, image pick-up card and calculator; Utilize image capture device to gather the fruit image of crop, in order to solve the miscellaneous problem of demarcation in the measurement, we propose to utilize the method for object of reference, not only simple to operate but also certainty of measurement height, just select the suitably object of reference of known dimensions of size, object of reference is placed on crop and fruit to be measured in the identical same plane of distance of camera lens, existing crop and fruit to be measured in the image of Cai Jiing like this, the object of reference that known dimensions is arranged again, pass through image processing algorithm, at first be partitioned into crop and fruit and object of reference, calculate the pixel count that their zone contains then respectively, both ratio is equal to their area ratio, so just can measure the fruit size of crop, thereby obtain crop and need the regimen condition, reach the purpose of water-saving irrigation.
Scheme 4: it is made up of image capture device, image pick-up card and calculator; Utilize image capture device to gather cane or the fruit image of crop, in order to solve the miscellaneous problem of demarcation in the measurement, we propose to utilize the method for object of reference, not only simple to operate but also certainty of measurement height, just select the suitably object of reference of known dimensions of size, if the object of reference size of selecting is greater than determinand, then object of reference is placed on the back of determinand, if the object of reference size of selecting is less than determinand, then object of reference is placed on the front of determinand, existing crop and fruit to be measured in the image of Cai Jiing like this, the object of reference that known dimensions is arranged again by above-mentioned 3 kinds of image processing algorithms, so just can be measured the size of cane or the fruit of crop, thereby obtain crop and need the regimen condition, reach the purpose of water-saving irrigation.
Scheme 5: it is made up of image capture device, image pick-up card and calculator; When the cane of crop or fruit size are excessive, measuring principle according to preceding 4 kinds of schemes, just require image capture device resolution than higher, the measurement device cost will increase sharply or can't realize measuring like this, we adopt following method for this reason: utilize image capture device to gather cane or the fruit image of crop, in order to solve the miscellaneous problem of demarcation in the measurement, we propose to utilize the method for object of reference, not only simple to operate but also certainty of measurement height, just select the object of reference of the suitable known dimensions of size, if the object of reference size of selecting is greater than determinand, then object of reference is placed on the back of determinand, if the object of reference size of selecting is less than determinand, then object of reference is placed on the front of determinand, then under the same terms, gather the image of object of reference and determinand left and right sides edges at two ends part respectively, divide again and utilize image processing algorithm to try to achieve the pixel count that object of reference and determinand edge differ in two width of cloth images respectively, the pixel quantity that just differs with their two ends of both diameter differences is directly proportional with value like this, just can obtain the crop cane to be measured or the diameter of fruit, thereby obtain crop and need the regimen condition, reach the purpose of water-saving irrigation.
The present invention compares with background technology, and the beneficial effect that has is:
(1) realize non-cpntact measurement, simple to operate, the certainty of measurement height does not influence the crop normal growth, reaches the expection water-saving rate identical with Chinese patent 03150690.9;
(2) the applicable crops object is extensive, can be installed in the indoor and outdoor irrigation systems such as intelligent greenhouse and modern agriculture base, is suitable for various vegetables, corn, wheat, soybean and fruit sapling etc.;
Obviously, compare with the variation of soil moisture, form or the physiological change of plant organ such as leaf, stem, fruit etc., then can be more direct, more comprehensively, quicker, react the situation of the moisture in the plant corpus more delicately.Like this, diagnosis of plant needs water, can be converted into the research of the certainty of measurement and the mutual corresponding rule of micro-displacement sensor.The irrigation system of Zu Chenging is an optimal control system like this, can improve the utilization ratio of irrigation water, promptly reaches the purpose of water saving.
Description of drawings
Fig. 1 is a measuring system composition frame chart of the present invention;
Fig. 2 crop cane image;
Fig. 3 measures the processing method block diagram of crop cane or fruit.
(a) is crop cane and the object of reference image of gathering among Fig. 2; (b) be through filtering, cut apart and remove the crop cane behind impurity point and the filling cavity and the bianry image of object of reference
Embodiment
In order to understand technical scheme of the present invention better, embodiments of the present invention are described further below in conjunction with the embodiment that measures the crop cane.
According to concrete measuring object is the crop cane, according to shown in Figure 1, makes up measurement mechanism.Select suitable image capture device (PUNIX-7DSP camera) and image pick-up card (MatroxII-MC4) accordingly according to crop cane size.According to the split-run test of collection image, the black object of reference that we select easier realization to cut apart, the image of collection is shown in Fig. 2 (a).
Processing method block diagram as shown in Figure 3, at first image is carried out filtering and remove noise raising certainty of measurement, try to achieve image histogram then, automatically determine according to histogram that segmentation threshold is cut apart image and obtain object of reference and crop cane, remove impure point and filling cavity again, the pixel ratio that calculates crop cane and object of reference at last obtains crop cane situation of change, whether needs water thereby obtain crop, instruct irrigation system, to reach the purpose of water saving.The concrete implementation detail of each several part is as follows:
1. utilize medium filtering to remove noise
The basic thought of medium filtering is that the intermediate value with the neighborhood of pixel points gray value replaces this gray values of pixel points, and this method can keep the image border details removing impulsive noise again in the time of salt-pepper noise.We adopt 3 * 3 windows that the image of gathering has been carried out filtering.
2. threshold value determines automatically
We determine the threshold value of split image with the method for asking extreme value, promptly try to achieve the histogram functions f (n) of image earlier, and n is a gray level 1～255, respectively to f (n) ask single order derived function f ' (n) and second order derived function f " (n).As the first derivative f ' of wherein certain some k (k)=0 time, expression k point is the stationary point, at this moment,
If f " (k)〉0, then the k point is a minimum, is the lowest point between histogrammic two crests; " (k)＜0, then the k point is a maximum, is histogrammic crest as if f.
Because the data of numerical imaging are that the then single order derived function that disperses is:
The second order derived function is:
According to experiment, this research splits object of reference with first minimum and second minimum, with second and the 3rd minimum the crop cane is split again.
3. the filling in the removal of impure point and cavity
After object of reference and crop cane split, contain the cavity in the object, contain more assorted point in the image simultaneously, this can influence the measurement of back, whether we are by having in adjacent eight pixels of judging each pixel more than five and this pixel different value, if then this pixel grey scale is adjusted into the color value of most pixels.
4. calculate the diametric pixel count of object of reference and cane and obtain cane
In order further to improve certainty of measurement, we utilize method of least squares to come the edge of match object of reference and crop cane, try to achieve out their diameter ratio then, just can obtain crop cane size, need aqueous condition thereby obtain crop.
With an edge is example, and establishing the edge pixel number is N,
Calculate the geometric center coordinate of this edge edge:
Slope calculations:
Calculate intercept: C
a=Y
a-B
a* X
a(3)
The edge fitting linear equation is: Y=B
a* X+C
a(4)
Then, another edge fitting equation is: Y=B
b* X+C
b(5)
Because two the edge is approximate parallel, is B=(B so get slope
a+ B
bThe common slope at an edge)/2 two.Certain that cross an edge is wherein like this a bit made the vertical line at this edge, obtains and point that another edge intersects, and calculating distance between two points is exactly the pixel quantity of the diameter correspondence of object of reference or crop cane.Just can obtain the diameter ratio of object of reference and crop cane, known according to the diameter of object of reference, so can obtain the cane diameter, the situation of change of crop cane reflects that crop needs water information, irrigates using water wisely thereby instruct in one day.
Claims (1)
1. based on the crop water-requesting information determination of computer vision, detection system is made up of the suitable reference substance of size, image capture device, image pick-up card and calculator; It is characterized in that object of reference is placed near the crop cane and fruit to be measured, obtain crop cane size and fruit size, obtain crop and need water information by corresponding image processing algorithm, thus the control irrigation system, and described image processing algorithm comprises:
(1) medium filtering is removed noise: adopt the medium filtering of 3 * 3 windows that the image of gathering is carried out filtering removal noise, improve certainty of measurement;
(2) determining automatically of threshold value: the threshold value of determining split image with the method for asking extreme value, promptly try to achieve the histogram functions of image earlier, calculate its single order derived function and second order derived function again, judge all minimums, with first minimum and second minimum object of reference is split, with second and the 3rd minimum crop cane or fruit are split again;
(3) filling in the removal of impure point and cavity: after object of reference and crop cane or fruit split, by whether having in adjacent eight pixels of judging each pixel more than five and this pixel different value, if then this pixel grey scale is adjusted into the color value of most pixels;
(4) pixel count that calculates object of reference and cane or fruit obtains cane or fruit size: utilize method of least squares to come the edge of match object of reference and crop cane, try to achieve out their diameter ratio then, just can obtain the size of crop cane or fruit, thereby obtain crop and need aqueous condition, perhaps when crop cane and fruit are bigger, by measuring the size that pixel quantity that object of reference and determinand edges at two ends differ obtains crop cane or fruit, thereby obtain crop and need water information, control irrigation system, reach the purpose of water saving.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2005100410454A CN100536653C (en) | 2005-07-15 | 2005-07-15 | Crop water-requesting information determination based on computer vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2005100410454A CN100536653C (en) | 2005-07-15 | 2005-07-15 | Crop water-requesting information determination based on computer vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN1895025A CN1895025A (en) | 2007-01-17 |
| CN100536653C true CN100536653C (en) | 2009-09-09 |
Family
ID=37607794
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB2005100410454A Expired - Fee Related CN100536653C (en) | 2005-07-15 | 2005-07-15 | Crop water-requesting information determination based on computer vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN100536653C (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102156108B (en) * | 2010-12-15 | 2013-05-08 | 四川大学 | Method and device for calibrating rainbow ring radius of secondary rainbow |
| CN102524024B (en) * | 2012-02-16 | 2013-04-03 | 四川农业大学 | Crop irrigation system based on computer vision |
| CN102550374B (en) * | 2012-03-18 | 2013-04-03 | 四川农业大学 | Crop irrigation system combined with computer vision and multi-sensor |
| US9488630B2 (en) | 2013-11-08 | 2016-11-08 | Dow Agrosciences Llc | Integrated remote aerial sensing system |
| GB201719058D0 (en) | 2017-11-17 | 2018-01-03 | Ocado Innovation Ltd | Control device and method for a robot system |
| CN109559342B (en) * | 2018-03-05 | 2024-02-09 | 北京佳格天地科技有限公司 | Method and device for measuring animal body length |
| CN109373897B (en) * | 2018-11-16 | 2020-07-31 | 广州市九州旗建筑科技有限公司 | Measuring method based on laser virtual scale |
| JP2022038669A (en) * | 2020-08-27 | 2022-03-10 | オムロン株式会社 | Tool for measuring plant dimensions and method for measuring plant dimensions |
| CN114494396B (en) * | 2021-12-28 | 2023-06-09 | 广州极飞科技股份有限公司 | Job object height determining method, apparatus, device and storage medium |
| CN115457030B (en) * | 2022-10-27 | 2023-03-24 | 浙江托普云农科技股份有限公司 | Crop stem thickness measuring method and device based on image technology and application thereof |
-
2005
- 2005-07-15 CN CNB2005100410454A patent/CN100536653C/en not_active Expired - Fee Related
Non-Patent Citations (2)
| Title |
|---|
| 利用计算机视觉技术实现对温室植物生长的无损检测. 李长缨，滕光辉，赵春江等.农业工程学报，第19卷第3期. 2003 |
| 利用计算机视觉技术实现对温室植物生长的无损检测. 李长缨，滕光辉，赵春江等.农业工程学报，第19卷第3期. 2003 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN1895025A (en) | 2007-01-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100536653C (en) | Crop water-requesting information determination based on computer vision | |
| CN102550374B (en) | Crop irrigation system combined with computer vision and multi-sensor | |
| CN102524024B (en) | Crop irrigation system based on computer vision | |
| CN103512494B (en) | Visual inspection system and method for scale micro changes of plant fruits | |
| CN105739575B (en) | A kind of data fusion method of facilities vegetable environmental parameter | |
| CN105403245A (en) | Sunlight greenhouse wireless sensor multi-data fusion method | |
| CN112258331B (en) | Crop planting growth and environment intelligent monitoring analysis system based on big data | |
| CN109948596A (en) | A method of rice identification and crop coverage measurement are carried out based on vegetation index model | |
| CN102663397B (en) | Automatic detection method of wheat seedling emergence | |
| CN102855485B (en) | The automatic testing method of one grow wheat heading | |
| CN108537851B (en) | Detection method of soil humidity and application thereof | |
| CN113948220B (en) | Anthrax pathogen infection stage detection method with pre-analysis capability | |
| CN116429988B (en) | Dynamic remote sensing monitoring device for ocean plant carbon sink | |
| CN102663396B (en) | Method for automatically detecting rice milky ripe stage | |
| CN112819846A (en) | Multi-load remote sensing image-based rice yield estimation method for cloudy and rainy areas | |
| CN111881864A (en) | Wisdom farming crops growth full-period full-dynamic monitoring management system | |
| CN102592118B (en) | Automatic detection method for time emergence of seedling of corns | |
| CN101413935A (en) | Method for (in-situ) determining steam scatter amount of crops | |
| Tian et al. | The detection system for greenhouse tomato disease degree based on android platform | |
| CN109006749B (en) | Row resistance-based field canopy density detection system and calibration method thereof | |
| WO2022049552A8 (en) | Method and system for tracking, monitoring and predicting the health of a plant heritage | |
| CN108200804B (en) | Visual sensing grain flow online detection device and detection method | |
| Zhou et al. | Modelling spatio-temporal pattern of landuse change using multi-temporal remotely sensed imagery | |
| CN109543729A (en) | Time series data land cover classification method based on characteristic parameter cluster | |
| CN211740296U (en) | Sloping field soil and water conservation monitoring devices |
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 | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20090909 Termination date: 20120715 |