CN113673279A - Plant growth identification method and system - Google Patents
Plant growth identification method and system Download PDFInfo
- Publication number
- CN113673279A CN113673279A CN202010405941.9A CN202010405941A CN113673279A CN 113673279 A CN113673279 A CN 113673279A CN 202010405941 A CN202010405941 A CN 202010405941A CN 113673279 A CN113673279 A CN 113673279A
- Authority
- CN
- China
- Prior art keywords
- unit
- distance
- control unit
- photographing
- pixel
- 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
- 230000008635 plant growth Effects 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 34
- 230000012010 growth Effects 0.000 claims abstract description 36
- 238000005286 illumination Methods 0.000 claims abstract description 34
- 235000013399 edible fruits Nutrition 0.000 claims abstract description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000005259 measurement Methods 0.000 claims description 6
- 238000001228 spectrum Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 238000005265 energy consumption Methods 0.000 abstract description 4
- 230000000694 effects Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 7
- 230000029553 photosynthesis Effects 0.000 description 4
- 238000010672 photosynthesis Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000003306 harvesting Methods 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000035784 germination Effects 0.000 description 1
- 230000001678 irradiating effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01G—HORTICULTURE; CULTIVATION OF VEGETABLES, FLOWERS, RICE, FRUIT, VINES, HOPS OR SEAWEED; FORESTRY; WATERING
- A01G7/00—Botany in general
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Biodiversity & Conservation Biology (AREA)
- Botany (AREA)
- Ecology (AREA)
- Forests & Forestry (AREA)
- Environmental Sciences (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention relates to a plant growth identification method and a system thereof, wherein at least one photographic unit transmits a shot picture to a control unit to calculate the pixel distance of each unit, then the photographic unit shoots plants, the control unit identifies characteristic points of buds, flowers or fruits of the plants in the shot picture, the control unit calculates the pixel distance and the height of each characteristic point, counts the number and the area of a plurality of characteristic points to calculate the growth rate and the yield of the plants, and updates the data of the growth height, the growth rate, the yield and the like of the plants at regular time to dynamically modulate the illumination intensity of the illumination unit to the plants, thereby automatically designing the plant growth identification system to achieve the effects of effectively saving labor cost, lighting energy consumption, improving the yield and the quality of the plants and the like.
Description
Technical Field
The present invention relates to a method and a system for identifying plant growth, and more particularly, to a method and a system for automatically cultivating plants to effectively save labor cost and energy consumption for illumination and improve plant yield and quality.
Background
Accordingly, the cultivation of plants is affected by the natural environment and climate such as temperature, sunlight and water, so that the problems of poor yield of plants are likely to occur.
Because of one of the major factors that the illumination quantity affects the growth of plants, the artificial light source is often used in greenhouse cultivation and indoor cultivation to imitate the sunlight irradiation effect to facilitate the photosynthesis of plants, the distance between the artificial light source and the plants directly affects the photosynthesis of the plants, if the distance between the light source and the plants is too large, the illumination intensity is insufficient, and the photosynthesis of the plants is reduced, otherwise, if the distance between the light source and the plants is too small, the illumination intensity is increased, and the plants are also affected to cause growth adverse circumstances. The existing regulation of the illumination intensity and the illumination time of the artificial light source still relies on manual experience judgment, and besides the problems that the control cannot be accurate and the improper energy loss is easily caused, the artificial light source regularly arrives at a greenhouse to take care of each plant every day to regulate the illumination condition suitable for the growth of the plant, and much manpower and time are consumed, so that the manpower cost and the working hour waste are caused. In addition, the harvesting time and yield of the plants can only be estimated through manual experience, so that the problem of inaccurate harvesting estimation is easy to occur, and when the harvesting estimation is inaccurate, the quality and the yield are influenced, so that the economic value is reduced or the market price is not proper and fluctuates, and the income of farmers and the development of market economy are influenced.
Accordingly, the present inventors have made various studies in view of the shortcomings of the conventional plant cultivation, which are caused by the dependence on manpower and personal experience, and have made the present invention by means of the manufacturing and design experience and knowledge in the related fields over the years.
Disclosure of Invention
The invention relates to a plant growth identification method and a system thereof, mainly aiming at utilizing deep photography combined with artificial intelligence learning to identify plant characteristics so as to improve the accuracy of plant growth rate and yield estimation; the secondary purpose is to improve the precision of the frequency spectrum and the illumination intensity of the light source irradiating the plants, so as to save the illumination energy consumption and improve the yield and the quality of the plants.
To achieve the above objective, the present inventors have developed a plant growth recognition system comprising:
at least one fixing unit, which is erected in a plant growing area;
at least one photographing unit, which is arranged on the fixing unit;
at least one control unit, which connects the control unit and the camera unit by wire or wireless signal, and carries a plant growth identification artificial intelligence program in the control unit, the plant growth identification artificial intelligence program includes a unit pixel distance operation module, a characteristic point learning identification module, a characteristic point pixel distance operation module, a characteristic point height operation module, a characteristic point area operation module, a characteristic point statistic module and a plant growth rate and yield operation module, so that the control unit connects the plant growth identification artificial intelligence program and each module operates.
The plant growth identification system as described above, wherein the plant growth identification system further comprises at least one lighting unit, the lighting unit is disposed on the fixing unit, and the control unit is connected to the lighting unit via a wired or wireless signal, and the artificial intelligence program for plant growth identification further comprises a dynamic illumination modulation module, so that the control unit is interactively connected to the lighting unit via the dynamic illumination modulation module.
The inventor further provides a method for identifying plant growth, comprising the following steps:
A. positioning the photographic unit by keeping the lens of at least one photographic unit downward and horizontal to be vertical to the ground and fixing the height position;
B. the unit pixel distance calculation, the photographic unit transmits the shot picture to a control unit connected with the photographic unit so as to calculate the actual distance represented by each unit pixel in the photographic picture of the photographic unit by the control unit;
C. picking up characteristic points, namely shooting the plants below the shooting unit by the shooting unit, transmitting the shooting picture to the control unit, identifying the characteristic points of buds, flowers or fruits of the plants in the shooting picture by the control unit, and respectively marking the positions and the areas of the characteristic points by square frames;
D. calculating the pixel distance of the characteristic points, namely multiplying the pixel distance of each captured characteristic point frame by the pixel distance of each unit pixel obtained in the step B by the control unit to calculate and obtain the actual distance of each characteristic point pixel;
E. calculating the height of the characteristic points by matching the pixel distance of each characteristic point obtained in the step D with a triangle by the control unit to obtain the height of each characteristic point;
F. calculating the area of the characteristic points, namely multiplying the length and width distances of each characteristic point pixel obtained in the step D by the control unit to obtain the projection area of each characteristic point, and performing area proportion conversion on the projection area of each characteristic point in cooperation with the height of each characteristic point obtained in the step E to obtain the actual area of each characteristic point;
G. the control unit carries out the summation statistics of the quantity of a plurality of characteristic points of the plant shot by the shooting unit and the summation statistics of the area of the plurality of characteristic points;
H. and calculating the growth rate and yield, namely calculating the yield of each characteristic point of the plant shot by the shooting unit by the control unit by using an area and yield regression formula, and calculating the growth rate of each characteristic point of the plant shot by the shooting unit by using a growth rate formula.
The method for identifying plant growth as described above, wherein the method for identifying plant growth is followed by a step of updating plant growth data at regular time after the step of calculating growth rate and yield, and the control unit drives the camera unit to upload the shooting picture to the control unit at fixed time, so that the control unit calculates growth height, growth rate and yield of the plant shot by the camera unit at each fixed time.
The plant growth identification method as described above, wherein the plant growth identification method is followed by a step of dynamically modulating the illumination intensity after the step of updating the plant growth data at regular time, so that the control unit dynamically modulates the spectrum and the illumination intensity of the illumination unit connected with the control unit to the plant below the control unit according to the plant growth height, the growth rate and the yield data obtained at each fixed time.
The method for identifying plant growth as described above, wherein the step of calculating the unit pixel distance is to make the camera unit shoot a subject on the ground, and then transmit the picture of the subject to the control unit, so that the control unit calculates the length and width of the subject by using the formula of x ═ a × z/f and y ═ b × z/f, where x is the length of the subject, y is the width of the subject, a is the length of a photosensitive element in the camera unit, b is the width of the photosensitive element in the camera unit, f is the focal length of the camera unit, and z is the vertical distance from the camera unit to the ground, the vertical distance z from the camera unit to the ground is measured by the camera unit, the control unit extracts the parameters of the length, a width, b, and the focal length, f of the photosensitive element in the camera unit, and then the formula of x ═ z/f and y ═ b × z/f is substituted into the formula, the length and width of the object are calculated, and then the length and width of the object are divided by the pixel resolution of the photographic unit respectively to obtain the actual distance represented by each unit pixel in the photographic picture of the photographic unit.
The method for identifying plant growth as described above, wherein the step of calculating the unit pixel distance includes placing a calibration label with a known length and width on the ground, shooting the calibration label by the shooting unit, sending the shooting picture of the calibration label to the control unit, measuring the pixel occupied by the calibration label in the shooting picture by the control unit, and dividing the length and width of the calibration label by the pixel occupied by the calibration label in the shooting picture to obtain the actual distance represented by each unit pixel in the shooting picture of the shooting unit.
The method for identifying plant growth as described above, wherein the step of calculating the height of the feature point is performed by the control unit using the e carried therein2＝z2+c2Calculating the height of the characteristic point of each plant by using the trigonometric formula, wherein z is the vertical distance from the photographing unit to the ground, c is the pixel distance of the characteristic point, e is the distance from the photographing unit to the ground after the plant characteristic point is projected, the vertical distance z from the photographing unit to the ground is measured by the photographing unit, the pixel distance c of the characteristic point is obtained by the step D, and the known vertical distance z from the photographing unit to the ground and the pixel distance c of the characteristic point are substituted into the step e2＝z2+c2In the formula (2), the distance e of the projection of the photographing unit to the ground through the plant characteristic point is calculated and obtained, and then the distance e is utilizedThe characteristic point height h can be obtained by substituting the known vertical distance z from the shooting unit to the ground, the distance e from the shooting unit to the ground through the plant characteristic point and the distance d from the shooting unit to the plant characteristic point into the formula h-z x (e-d)/d.
The method for identifying plant growth as described above, wherein the step of calculating the area of the feature point uses the loaded a ═ sx[ (z-h)/z by the control unit]2Calculating the actual area of the feature point, wherein a is the area of the feature point, s is the projected area of the feature point, z is the vertical distance from the photographing unit to the ground, h is the height of the feature point, the projected area of the feature point s is obtained by multiplying the pixel length and width distance of the feature point obtained in step D, the vertical distance z from the photographing unit to the ground is obtained by measuring the photographing unit, the height h of the feature point is obtained in step E, and then the projected area of the known feature point s, the vertical distance z from the photographing unit to the ground and the height h of the feature point are substituted into the a ═ s × [ (z-h)/z]2In the formula (2), the characteristic point area a can be obtained.
The method for identifying plant growth as described above, wherein the method for identifying plant growth further comprises a step of calibrating the depth of the camera unit, which is performed after the camera unit of step a is positioned, wherein the method for calibrating the depth of the camera unit measures the distance z1 between the camera unit and the ground, measures the distance z2 between the camera unit and the ground by using a tape measure, inputs the values of z1 and z2 into the camera unit or the control unit, and automatically corrects the proportional error of the depth measurement of the camera unit after the camera unit or the control unit calculates the proportion of z2/z 1; or the distance z between the photographing unit and the ground is measured by the photographing unit, a calibration label with a known height h is placed on the ground, the distance d between the photographing unit and the calibration label is measured by the photographing unit, and then the values of z, h and d are input into the photographing unit or the control unit, so that the ratio of h/(z-d) is calculated by the photographing unit or the control unit, and then the ratio error of the depth measurement of the photographing unit is automatically corrected.
Therefore, by utilizing the plant growth identification method and the system design thereof, the growth rate and the yield of the cultivated plant can be accurately estimated, so as to be beneficial to maintaining the development of market economy, the illumination intensity of the plant can be accurately regulated and dynamically regulated by the illumination unit, the situation that the illumination intensity is insufficient or too strong is easily caused by artificial experience judgment is avoided, the improper energy loss is prevented, the yield and the growth quality of the plant are improved, and in addition, the plant is cultivated automatically, so that the benefits of effectively saving the labor cost, the working hour expenditure and the like for caring the plant can be achieved.
Drawings
Fig. 1 is an overall front view of the present invention.
FIG. 2 is a system architecture diagram of the present invention.
FIG. 3 is a flow chart of the present invention.
FIG. 4 is a schematic diagram of the depth calibration of the camera unit of the present invention.
FIG. 5 is a schematic diagram illustrating a unit pixel distance operation according to the present invention.
FIG. 6 is a schematic diagram illustrating the distance calculation of two unit pixels according to the present invention.
FIG. 7 is a schematic diagram of feature point extraction according to the present invention.
FIG. 8 is a schematic diagram illustrating feature point height calculation according to the present invention.
FIG. 9 is a schematic diagram of the characteristic point area operation of the present invention.
Description of the symbols:
1 fixing unit
2 camera unit
21: lens
22 photosensitive element
3: lamp unit
4 control unit
Plant growth identification artificial intelligence program
51 unit pixel distance operation module
52, characteristic point learning and identifying module
53 characteristic point pixel distance operation module
54 characteristic point height operation module
55 characteristic point area operation module
56 characteristic point statistic module
57 plant growth rate and yield operation module
58 dynamic illumination modulation module
6: object to be photographed
7: calibration label
8 plant
9: square frame
Detailed Description
In order to more fully and clearly disclose the technical means and effects achieved by the present invention, the following detailed description is provided with reference to the accompanying drawings and numbers:
first, referring to fig. 1 and 2, a plant growth identification system of the present invention mainly includes:
at least one fixing unit 1, wherein the fixing unit 1 can be a bracket to be erected in a plant growing area;
at least one camera unit 2, wherein the camera unit 2 is assembled on the fixing unit 1, the camera unit 2 is a depth camera, a depth measuring program is loaded in the camera unit 2, and the camera unit 2 is provided with 2 RGB lenses 21 and is internally provided with a photosensitive element 22;
at least one lighting unit 3, which makes the lighting unit 3 set on the fixed unit 1 and above the photographic unit 2, the lighting unit 3 can be LED lamp;
at least a control unit 4, the control unit 4 can be a desktop computer or notebook computer, etc., the control unit 4 is connected with the camera unit 2 and the lighting unit 3 by wire or by wireless signals such as 3G, 4G, WiFi, Bluetooth, etc., and the control unit 4 is loaded with a plant growth identification artificial intelligence program 5, the plant growth identification artificial intelligence program 5 includes a unit pixel distance operation module 51, a feature point learning identification module 52, a feature point pixel distance operation module 53, a feature point height operation module 54, a feature point area operation module 55, a feature point statistic module 56, a plant growth rate and yield operation module 57 and a dynamic illumination modulation module 58, etc., so that the control unit 4 is connected with the plant growth identification artificial intelligence program 5, and each module operates.
Accordingly, when the present invention is implemented, please refer to fig. 3, and the method includes the following steps:
A. a positioning photographing unit for fixing the photographing unit 2 at a height position of the fixing unit 1, and making the lens 21 of the photographing unit 2 face downwards and kept horizontal to be vertical to the ground;
B. the depth calibration of the photographing unit comprises two methods, namely, measuring the distance z1 between the photographing unit 2 and the ground, measuring the distance z2 between the photographing unit 2 and the ground by using a measuring tape, inputting the numerical values of z1 and z2 into the photographing unit 2 or the control unit 4, calculating the proportion of z2/z1 by using a depth measuring program arranged in the photographing unit 2 or the control unit 4, and automatically correcting the proportion error of the depth measurement of the photographing unit 2; referring to fig. 4, in the second method, the distance z between the photographing unit 2 and the ground is measured, a calibration label 7 with a known height h is placed on the ground, the distance d between the photographing unit 2 and the calibration label 7 is measured, and then the values of z, h and d are input into the photographing unit 2 or the control unit 4, so that the photographing unit 2 or the control unit 4 is internally provided with a depth measurement program to calculate the ratio of h/(z-d), and then the ratio error of the depth measurement of the photographing unit 2 is automatically corrected;
C. calculating the unit pixel distance includes two methods, please refer to fig. 5, one is that the photographing unit 2 photographs any object 6 on the ground, and then the photographing picture of the object 6 is transmitted to the control unit 4, and the control unit 4 calculates the length and width of the object 6 by using the formula of (a × z)/f and (b × z)/f preset by the unit pixel distance calculating module 51 loaded in the plant growth identification artificial intelligence program 5, wherein x is the length of the object 6, y is the width of the object 6, a is the length of the photosensitive element 22 of the photographing unit 2, b is the width of the photosensitive element 22 of the photographing unit 2, f is the focal length of the photographing unit 2, z is the vertical distance from the photographing unit 2 to the ground, and the vertical distance z from the photographing unit 2 to the ground is measured by the photographing unit 2, the unit pixel distance calculating module 51 captures parameters such as the length a, the width b, and the focal length f of the photosensitive element 22 of the photographing unit 2, and then substitutes the parameters into the above-mentioned formulas of x ═ x z/f and y ═ b × z/f to calculate the length x and the width y of the object 6, and then divides the length x and the width y of the object 6 by the pixel resolution of the photographing unit 2, so as to obtain the actual distance represented by each unit pixel in the photographing screen of the photographing unit 2; referring to fig. 6, the second method is to place a calibration label 7 with a known length and width on the ground, then shoot the calibration label 7 by the shooting unit 2, then transmit the shooting picture of the calibration label 7 to the control unit 4, measure the occupied pixels of the calibration label 7 in the shooting picture by the unit pixel distance operation module 51, and then divide the length and width of the calibration label 7 by the occupied pixels of the calibration label 7 in the shooting picture, so as to obtain the actual distance represented by each unit pixel in the shooting picture of the shooting unit 2;
D. picking up the characteristic points, please refer to fig. 7, in which the photographing unit 2 photographs the plant 8 located therebelow, and then transmits the photographing picture to the control unit 4, so that the control unit 4 recognizes the characteristic points of the plant 8, such as buds, flowers or fruits, in the photographing picture by using the characteristic point learning and recognizing module 52 loaded in the plant growth recognizing artificial intelligence program 5, and marks the position and area of the characteristic points by a frame 9;
E. calculating the pixel distance of the characteristic point, namely enabling the control unit 4 to utilize a characteristic point pixel distance operation module 53 loaded in the plant growth identification artificial intelligence program 5 to multiply the pixel distance of each characteristic point box 9 acquired by the characteristic point learning identification module 52 by the pixel distance of each unit pixel obtained in the step C so as to calculate and obtain the actual distance of each characteristic point pixel;
F. please refer to fig. 8, the height of the feature point is calculated by the control unit 4 using the height calculation module 54 of the feature point loaded in the artificial intelligence program 5 for identifying the plant growth of the control unit to preset e2＝z2+c2The trigonometric formula of (a) to calculate the height of the feature point of each plant 8, wherein z is the vertical distance from the photographing unit 2 to the ground, c is the pixel distance of the feature point, and e is the height of the photographing unit 2 passing through the plant 8The distance from the projection of the feature point to the ground, the vertical distance z from the photographing unit 2 to the ground can be obtained by the photographing unit 2, the pixel distance c of the feature point is obtained in step E, and then the known vertical distance z from the photographing unit 2 to the ground and the pixel distance c of the feature point are substituted into step E2＝z2+c2The distance e projected from the photographing unit 2 to the ground via the feature point of the plant 8 can be calculated, and then the feature point height calculating module 54 is used to preset h ═ z × (e-d)/d, wherein z is the vertical distance from the photographing unit 2 to the ground, e is the distance from the photographing unit 2 to the ground through the feature point of the plant 8, d is the distance from the photographing unit 2 to the feature point of the plant 8, h is the height of the feature point, the distance d between the photographing unit 2 and the feature point of the plant 8 can be obtained by the photographing unit 2, and the known vertical distance z between the photographing unit 2 and the ground, the distance e between the photographing unit 2 projected to the ground through the feature point of the plant 8, and the distance d between the photographing unit 2 and the feature point of the plant 8 are substituted into the formula h ═ z × (e-d)/d, so as to obtain the feature point height h;
G. please refer to fig. 9, so that the control unit 4 uses the area a ═ sx[ (z-h)/z preset in the feature point area calculation module 55 of the plant growth identification artificial intelligence program 5 by using the control unit 4]2Calculating the actual area of the feature point, wherein a is the area of the feature point, s is the projected area of the feature point, z is the vertical distance from the photographing unit 2 to the ground, h is the height of the feature point, the projected area s of the feature point is the pixel length and width distance of the feature point obtained in step E, the vertical distance z from the photographing unit 2 to the ground can be measured by the photographing unit 2, the height h of the feature point is obtained in step F, and then the projected area s of the known feature point, the vertical distance z from the photographing unit 2 to the ground and the height h of the feature point are substituted into a ═ sx[ (z-h)/z]2In the formula (a), the area a of the feature point can be calculated;
H. counting the number and area of the feature points, so that the control unit 4 can use the feature point counting module 56 loaded in the plant growth identification artificial intelligence program 5 to count the total number of the feature points of the plant 8 shot by the shooting unit 2 and the total number of the area of the feature points;
I. calculating the growth rate and yield by the control unit 4 using the regression formula of the plant growth rate and yield preset by the plant growth recognition artificial intelligence program 5, the regression formula of the area and yield is obtained by experiment collection, the yield actually obtained by collecting the areas of a plurality of feature points is collected, the areas and yields of the plurality of feature points are summed up, the yield value obtained by averaging the areas of each unit of feature points is calculated to derive the regression formula of the area and yield, the growth rate of the plant 8 is also obtained by experiment collection, the growth rate formula of the characteristic points of the bud, flower or fruit of the plant 8 shot by the camera unit 2 is observed, the time required by the bud, flower or fruit is derived from the time of planting to the germination, or the time required by the flower bud to the fruit production, the growth rate formula of the bud, flower or fruit can be derived, then, the growth rate formula is utilized to calculate the growth rate of each characteristic point of the plant 8 shot by the shooting unit 2;
J. and updating the plant growth data at regular time, namely driving the shooting unit 2 to upload the shot pictures to the control unit 4 by the control unit 4 in fixed time so that each module of the plant growth identification artificial intelligence program 5 of the control unit 4 repeats the steps to calculate the growth height, the growth rate and the yield of the plant 8 shot by the shooting unit 2 in each fixed time.
K. The dynamic illumination modulation module 58 carried in the plant growth identification artificial intelligence program 5 of the control unit 4 dynamically modulates the frequency spectrum and illumination intensity of the illumination unit 3 connected with the control unit to the plant 8 below the control unit according to the growth height, speed and yield data of the plant 8 obtained in each fixed time, so that the illumination intensity is increased when the growth height of the plant 8 is lower, and the illumination intensity is relatively reduced when the growth height of the plant 8 is higher, so that the cultivation of the plant 8 is optimized, and the energy consumption is saved.
Therefore, by using the plant growth identification method and the system design thereof of the invention, the growth rate and the yield of the cultivated plant 8 can be accurately estimated, the improper fluctuation of the market price is avoided, the development of market economy is facilitated, the invention also enables the plant growth identification artificial intelligence program 5 loaded in the control unit 4 to accurately control the illumination intensity of the illumination unit 3 to the plant 8 according to the data of the growth height, the growth rate, the yield and the like of the characteristic points of the plant 8, such as buds, flowers, fruits and the like, which are shot by the shooting unit 2, thereby avoiding the situation that the illumination intensity is insufficient or too strong easily happens by artificial experience judgment, facilitating the photosynthesis of the plant 8, and accordingly, the yield and the growth quality of the plant 8 can be improved besides preventing the improper loss of energy, the plant 8 is cultivated automatically, and the labor cost and the expenditure for caring the plant 8 can be effectively saved, so as to improve the industrial competitiveness.
Claims (10)
1. A plant growth identification system, comprising:
at least one fixing unit, which is erected in a plant growing area;
at least one photographic unit, which is arranged on the fixed unit;
at least one control unit, which connects the control unit and the camera unit by wire or wireless signal, and carries a plant growth identification artificial intelligence program in the control unit, the plant growth identification artificial intelligence program includes a unit pixel distance operation module, a characteristic point learning identification module, a characteristic point pixel distance operation module, a characteristic point height operation module, a characteristic point area operation module, a characteristic point statistic module and a plant growth rate and yield operation module, so that the control unit connects the plant growth identification artificial intelligence program and each module operates.
2. The system according to claim 1, further comprising at least one lighting unit, wherein the lighting unit is disposed on the fixing unit, and the control unit is connected to the lighting unit via a wired or wireless signal, and the artificial intelligence program further comprises a dynamic illumination modulation module, so that the control unit is interactively connected to the lighting unit via the dynamic illumination modulation module.
3. A method for identifying plant growth, comprising the steps of:
A. positioning the photographic unit by keeping the lens of at least one photographic unit downward and horizontal to be vertical to the ground and fixing the height position;
B. the unit pixel distance calculation comprises the steps that the shooting unit transmits a shot picture to a control unit connected with the shooting unit, so that the control unit calculates the actual distance represented by each unit pixel in the shooting picture of the shooting unit;
C. picking up the characteristic points, namely shooting the plants below the photographic unit by the photographic unit, transmitting the photographic picture to the control unit, identifying the characteristic points of buds, flowers or fruits of the plants in the photographic picture by the control unit, and respectively marking the positions and the areas of the characteristic points by square frames;
D. calculating the pixel distance of the characteristic points, namely multiplying the pixel distance of each captured characteristic point frame by the pixel distance of each unit pixel obtained in the step B by the control unit to calculate and obtain the actual distance of each characteristic point pixel;
E. calculating the height of the characteristic points by matching the pixel distance of each characteristic point obtained in the step D with a triangle by the control unit to obtain the height of each characteristic point;
F. calculating the area of the characteristic points, namely multiplying the length and width distances of each characteristic point pixel obtained in the step D by the control unit to obtain the projection area of each characteristic point, and performing area proportion conversion on the projection area of each characteristic point in cooperation with the height of each characteristic point obtained in the step E to obtain the actual area of each characteristic point;
G. the control unit carries out the sum statistics of the number of a plurality of characteristic points of the plant shot by the shooting unit and the sum statistics of the areas of the plurality of characteristic points;
H. and calculating the growth rate and yield, namely calculating the yield of each characteristic point of the plant shot by the shooting unit by the control unit by using an area and yield regression formula, and calculating the growth rate of each characteristic point of the plant shot by the shooting unit by using a growth rate formula.
4. The method of claim 3, wherein the step of plant growth data timing update is performed after the step of growth rate and yield calculation, and the control unit drives the camera unit to upload the shooting pictures to the control unit at fixed time, so that the control unit calculates the growth height, growth rate and yield of the plant shot by the camera unit at each fixed time.
5. The method for identifying plant growth according to claim 4, wherein the step of updating the plant growth data at regular time is followed by a step of dynamically modulating the illumination intensity, so that the control unit dynamically modulates the spectrum and illumination intensity of the illumination unit connected thereto for the plants therebelow according to the plant growth height, growth rate and yield data obtained at each fixed time.
6. The method according to claim 3, wherein the step of calculating the unit pixel distance comprises the step of photographing an object on the ground by the photographing unit, and transmitting a photographing picture of the object to the control unit, so that the control unit calculates the length and width of the object by using the formula of x ═ z/f and y ═ b × z/f, wherein x is the length of the object, y is the width of the object, a is the length of a photosensitive element arranged in the photographing unit, b is the width of the photosensitive element arranged in the photographing unit, f is the focal length of the photographing unit, z is the vertical distance from the photographing unit to the ground, the vertical distance (z) from the photographing unit to the ground is measured by the photographing unit, and the parameters of the length (a), the width (b) and the focal length (f) of the photosensitive element of the photographing unit are captured by the control unit, and then substituting the formulas of x ═ a × z)/f and y ═ b × z)/f to calculate the length and width of the object, and dividing the length and width of the object by the pixel resolution of the shooting unit respectively to obtain the actual distance represented by each unit pixel in the shooting picture of the shooting unit.
7. The method according to claim 3, wherein the step of calculating the distance of the unit pixel comprises placing a calibration label with a known length and width on the ground, capturing the calibration label by the capturing unit, transmitting a capturing image of the calibration label to the control unit, measuring the pixel occupied by the calibration label in the capturing image by the control unit, and dividing the length and width of the calibration label by the pixel occupied by the calibration label in the capturing image to obtain the actual distance represented by each unit pixel in the capturing image of the capturing unit.
8. The method according to claim 3, wherein the step of calculating the height of the feature point is performed by the control unit using e carried therein2＝z2+c2Calculating the height of the feature point of each plant, wherein z is the vertical distance from the photographing unit to the ground, c is the pixel distance of the feature point, e is the distance from the photographing unit to the ground after the plant feature point is projected, the vertical distance (z) from the photographing unit to the ground is measured by the photographing unit, the pixel distance (c) of the feature point is obtained by the step D, and the known vertical distance (z) from the photographing unit to the ground and the known pixel distance (c) of the feature point are substituted into the e2＝z2+c2The distance (d) between the photographing unit and the plant characteristic point is measured by the photographing unit, and the known vertical distance (z) between the photographing unit and the ground, the distance (e) between the photographing unit and the plant characteristic point and the distance (d) between the photographing unit and the plant characteristic point are substituted into the formula h ═ z × (e-d)/dAnd (5) obtaining the feature point height (h).
9. The method according to claim 3, wherein the step of calculating the area of the feature point uses the loaded a ═ s x [ (z-h)/z ] by the control unit]2Calculating the actual area of the feature point, wherein a is the area of the feature point, s is the projected area of the feature point, z is the vertical distance from the photographing unit to the ground, and h is the height of the feature point, the projected area(s) of the feature point is obtained by multiplying the pixel length and width distance of the feature point obtained in the step D, the vertical distance (z) from the photographing unit to the ground is obtained by measuring the photographing unit, the height (h) of the feature point is obtained in the step E, and then the projected area(s) of the feature point, the vertical distance (z) from the photographing unit to the ground and the height (h) of the feature point are known and substituted into a ═ sx[ (z-h)/z]2In the formula (a), the characteristic point area (a) can be obtained.
10. The method as claimed in claim 3, further comprising a camera unit depth calibration step, wherein the camera unit depth calibration step is performed after the camera unit is positioned in step A, the camera unit depth calibration method comprises measuring a distance (z1) between the camera unit and the ground by the camera unit, measuring a distance (z2) between the camera unit and the ground by a tape measure, and inputting values of the distance (z1) and the distance (z2) into the camera unit or the control unit, so that the camera unit or the control unit calculates a distance (z 2)/distance (z1) ratio to automatically correct a ratio error of the camera unit in the depth measurement; or the distance (z) between the photographing unit and the ground is measured by the photographing unit, a calibration label with a known height (h) is placed on the ground, the distance (d) between the photographing unit and the calibration label is measured by the photographing unit, then the numerical values of the distance (z), the height (h) and the distance (d) are input into the photographing unit or the control unit, and after the ratio of the height (h)/(distance (z) -distance (d)) is calculated by the photographing unit or the control unit, the ratio error of the depth measurement of the photographing unit is automatically corrected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010405941.9A CN113673279A (en) | 2020-05-14 | 2020-05-14 | Plant growth identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010405941.9A CN113673279A (en) | 2020-05-14 | 2020-05-14 | Plant growth identification method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113673279A true CN113673279A (en) | 2021-11-19 |
Family
ID=78537142
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010405941.9A Pending CN113673279A (en) | 2020-05-14 | 2020-05-14 | Plant growth identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113673279A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116399401A (en) * | 2023-04-14 | 2023-07-07 | 浙江年年发农业开发有限公司 | Agricultural planting system and method based on artificial intelligence |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103793686A (en) * | 2014-01-16 | 2014-05-14 | 中国农业大学 | Method for early-prediction of fruit tree yield |
| CN104697501A (en) * | 2015-03-08 | 2015-06-10 | 无锡桑尼安科技有限公司 | Apple orchard yield measuring system |
| CN106575419A (en) * | 2014-07-16 | 2017-04-19 | 株式会社理光 | Information processing device, method for generating control signal, information processing system, and program |
| US20170161560A1 (en) * | 2014-11-24 | 2017-06-08 | Prospera Technologies, Ltd. | System and method for harvest yield prediction |
| CN108271581A (en) * | 2018-01-22 | 2018-07-13 | 安徽东华农业科技开发股份有限公司 | A kind of box movable plant factor |
| CN109784300A (en) * | 2019-01-28 | 2019-05-21 | 中国平安财产保险股份有限公司四川分公司 | A kind of crops science survey production method and system |
-
2020
- 2020-05-14 CN CN202010405941.9A patent/CN113673279A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103793686A (en) * | 2014-01-16 | 2014-05-14 | 中国农业大学 | Method for early-prediction of fruit tree yield |
| CN106575419A (en) * | 2014-07-16 | 2017-04-19 | 株式会社理光 | Information processing device, method for generating control signal, information processing system, and program |
| US20170161560A1 (en) * | 2014-11-24 | 2017-06-08 | Prospera Technologies, Ltd. | System and method for harvest yield prediction |
| CN104697501A (en) * | 2015-03-08 | 2015-06-10 | 无锡桑尼安科技有限公司 | Apple orchard yield measuring system |
| CN108271581A (en) * | 2018-01-22 | 2018-07-13 | 安徽东华农业科技开发股份有限公司 | A kind of box movable plant factor |
| CN109784300A (en) * | 2019-01-28 | 2019-05-21 | 中国平安财产保险股份有限公司四川分公司 | A kind of crops science survey production method and system |
Non-Patent Citations (1)
| Title |
|---|
| 张亚静;邓烈;李民赞;赵瑞娇;何绍兰;易时来;: "基于图像处理的柑橘测产方法", 农业机械学报, no. 1 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116399401A (en) * | 2023-04-14 | 2023-07-07 | 浙江年年发农业开发有限公司 | Agricultural planting system and method based on artificial intelligence |
| CN116399401B (en) * | 2023-04-14 | 2024-02-09 | 浙江年年发农业开发有限公司 | Agricultural planting system and method based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11440659B2 (en) | Precision agriculture implementation method by UAV systems and artificial intelligence image processing technologies | |
| CN106406403B (en) | A kind of agriculture managing and control system based on augmented reality | |
| US20210345567A1 (en) | Method and system for plant stress determination and irrigation based thereon | |
| JP6295452B2 (en) | Crop development support device and program thereof | |
| EP3421973A1 (en) | Moisture content observation device, moisture content observation method, and cultivating device | |
| WO2021226907A1 (en) | Plant growth identification method and system therefor | |
| JP2012183021A (en) | Vegetation control device and plant growing system | |
| CN110121264A (en) | Grow the image-taking system and method for cabin assembly line | |
| KR20190106388A (en) | Plant growing system providing growing recipe | |
| CN108427457A (en) | A kind of greenhouse control system based on augmented reality application | |
| CN110286092A (en) | A kind of plant growth trend analysis system | |
| CN109634332A (en) | A kind of intelligent control system of modern greenhouse | |
| CN110024648A (en) | The accurate implantation methods of bulbus fritillariae cirrhosae based on deep neural network | |
| CN113597941A (en) | Greenhouse intelligent environment regulation and control system and device | |
| CN113673279A (en) | Plant growth identification method and system | |
| CN109655108A (en) | A kind of field planting real-time monitoring system and method based on Internet of Things | |
| KR101726944B1 (en) | Apparatus and method for collecting growth information of crop | |
| CN116458422A (en) | Planting system for regulating and controlling plant growth period multi-stage illumination | |
| TWI736227B (en) | Plant growth identification method and system | |
| JP6338184B2 (en) | Environmental control system for plant cultivation | |
| JP6745459B2 (en) | Water content observation device, water content observation method, and cultivation device | |
| KR20210065607A (en) | Method of determining status of plant growth and apparatus for growing plant using the same | |
| CN110064601B (en) | Seedling detection and classification system and classification method for vegetable grafting | |
| KR102201595B1 (en) | Method for diagnosing growth state employing analyzing of image of strawberry | |
| CN111869532A (en) | Automatic orchid cultivation system and cultivation method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20211119 |
|
| WD01 | Invention patent application deemed withdrawn after publication |