A computer vision blade area measurement device and method
Through computer vision technology, combined with spraying and weighing modules, the convolutional neural network and microelectronic weighing modules are used to solve the problem of poor accuracy and repeatability of the existing blade area measurement methods, and high-precision and simple blade area measurement are achieved.
Patent Information
- Application Number
- CN202311811737.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-12-27
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2043-12-27
AI Technical Summary
The existing leaf area measurement methods have problems such as low accuracy, poor repeatability and great destructiveness. They cannot quickly, accurately and easily obtain leaf area, which affects the formulation of high-yield and efficient cultivation strategies for crops.
Using computer vision technology, the area of the spraying module is calculated by spraying pigments, the weighing module is weighing the weight and the computer intelligent module is calculated, and the boundary is identified by convolutional neural network units and the microelectronic weighing module is accurately measured to calculate the blade area.
It realizes accurate measurement of irregular object area, with high precision and simple operation, suitable for continuous measurement.
Smart Images

Figure CN118168499B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of area measurement, and in particular to a blade area measurement device and method based on computer vision. Background Art
[0002] Leaves are important physiological organs of crops. Photosynthesis, respiration, and transpiration are all performed by leaves. Changes in leaf area can reflect the accumulation of photosynthetic products in leaves and the utilization of nutrients such as light, temperature, water, and fertilizer by crop plants. Therefore, the ability to quickly, accurately, simply, and non-destructively obtain leaf area can promote the formulation of high-yield and high-efficiency cultivation strategies for crops.
[0003] Traditional leaf area measurement methods include the empirical formula method, the nine-grid method, and the weighing method. The empirical formula method estimates the area value by using the length and width of the leaf and the empirical coefficient, and the accuracy is not high. The nine-grid method is to spread the leaf on a flat plate with fixed-size grids and calculate the number of grids covered by the leaf. The judgment of the area of the grid that cannot be completely covered by the leaf edge is too subjective, and the measurement results are not repeatable. The weighing method is to take a leaf area of known area on the leaf, weigh it, and convert the area value by weight ratio. This method is destructive and cannot be continued on the same leaf. Summary of the invention
[0004] In view of the deficiencies in the prior art, the object of the present invention is to provide a blade area measurement device and method based on computer vision to solve the problems existing in the above-mentioned background technology.
[0005] The embodiment of the present invention is implemented as follows: a blade area measurement device based on computer vision, the device comprising:
[0006] A spraying module, used to spray paint while moving;
[0007] A weighing module, used to weigh the weight of the blade L alone, used to weigh the weight of the pigment on the upper surface of the weighing module alone, and used to weigh the total weight of the pigment on the upper surface of the weighing module, the blade L, and the pigment on the upper surface of the blade L;
[0008] The computer intelligent module is used to measure the area of the upper surface of the weighing module, to control the spraying module to spray paint along the boundary of the weighing module at a certain speed, to calculate the weight of the paint per unit area on the upper surface of the weighing module, and to calculate the area of the blade L based on the weight of the paint on the upper surface of the blade L and the weight of the paint per unit area on the upper surface of the weighing module.
[0009] As a further solution of the present invention: the spraying module comprises:
[0010] A pigment delivery module, used for delivering liquid pigment;
[0011] A spray valve module is used to spray the paint on the upper surface of the weighing module;
[0012] The moving module is used to drive the spray valve module to move at a constant speed along the upper surface of the weighing module.
[0013] As a further solution of the present invention: the pigment delivery module includes a pigment storage tank, a liquid pump and a flexible hose, the liquid inlet end of the liquid pump is connected to the pigment storage tank, the liquid outlet end of the liquid pump is connected to the flexible hose, and the pigment storage tank stores liquid pigment with a certain viscosity;
[0014] The spray valve module comprises a spray pipe, a spray valve and a bracket, one end of the spray pipe is connected to a flexible hose, the spray valve is fixedly connected to the other end of the spray pipe, and the surface of the spray pipe is fixedly connected to a bracket;
[0015] The mobile module includes a driving motor, a threaded rod, a nut seat and a limit rod, wherein the driving motor, the threaded rod and the limit rod are all connected to the surface of the frame, the driving motor is connected to the threaded rod, the nut seat is not only threadedly connected to the surface of the threaded rod, but also movably sleeved on the surface of the limit rod, and the nozzle is fixedly installed on the surface of the nut seat. When the driving motor drives the threaded rod to rotate, the rotating threaded rod drives the spray valve to perform reciprocating linear motion through the nut seat and the nozzle.
[0016] As a further solution of the present invention: the weighing module comprises:
[0017] A carrier plate is used to place the blade L, and the spray valve sprays the paint onto the upper surface of the carrier plate;
[0018] A microelectronic weighing module, wherein the carrier plate is installed above the microelectronic weighing module and is used to weigh the weight M0 of the carrier plate; when the spray valve sprays the pigment on the upper surface of the carrier plate, it is used to weigh the total weight M1 of the carrier plate and the pigment; when the blade L is placed on the upper surface of the carrier plate, it is used to weigh the total weight M2 of the blade L and the carrier plate; when the blade L is placed on the upper surface of the carrier plate, it is used to weigh the total weight M3 of the blade L, the carrier plate and the pigment; after the blade L is taken away, it is used to weigh the total weight M4 of the carrier plate and the remaining pigment.
[0019] A calculation module, used for calculating the weight of the pigment on the surface of the carrier plate when no blade is placed, △M1=M1-M0, used for calculating the weight of the blade L, △M2=M2-M0, used for calculating the weight of the pigment on the surface of the blade L, △M3=M3-M4-△M2;
[0020] As a further solution of the present invention: the computer intelligence module also includes:
[0021] A camera unit, used for collecting image information of the carrier plate;
[0022] An image recognition unit, used to recognize the boundary of the loading plate according to the image information of the loading plate, wherein the boundary of the loading plate is a rectangle or a circle, and is used to calculate the area S1 of the loading plate;
[0023] A convolutional neural network unit is used to drive the spray valve multiple times to simulate spraying paint along the border of the carrier plate, and output the average value △M1 of the weight of the paint on the surface of the carrier plate;
[0024] The data processing unit is used to receive the weight data △M1 and △M3 transmitted by the calculation module, to calculate the weight m=△M1 / S1 of the pigment per unit area of the carrier plate, and to calculate the area S2=△M3 / m of the blade L.
[0025] Another object of an embodiment of the present invention is to provide a leaf area measurement method based on computer vision, the method comprising the following steps:
[0026] S100, using a spraying module to evenly spray the pigment on the upper surface of the weighing module, and separately collecting the total weight of the pigment on the upper surface of the weighing module;
[0027] S200, placing the blade L on the upper surface of the weighing module, and collecting the weight of the blade L separately;
[0028] S300, placing the blade L on the upper surface of the weighing module, using the spraying module to evenly spray the paint on the weighing module and the upper surface of the blade L, collecting the total weight of the paint on the upper surface of the weighing module, the blade L, and the paint on the upper surface of the blade L, after taking away the blade L with the paint, collecting the weight of the paint on the upper surface of the weighing module, and outputting the weight of the paint on the upper surface of the blade L;
[0029] S400, collecting the area of the upper surface of the weighing module, calculating the pigment weight per unit area using the total weight of the pigment on the upper surface of the weighing module and the area of the upper surface of the weighing module, and calculating the area of blade L according to the pigment weight on the upper surface of blade L and the pigment weight per unit area.
[0030] As a further solution of the present invention: the step of using the spraying module to evenly spray the pigment on the upper surface of the weighing module and separately collecting the total weight of the pigment on the upper surface of the weighing module specifically includes:
[0031] S110, using a liquid pump to spray the pigment in the pigment storage tank through the flexible hose, the spray pipe and the spray valve, using a driving motor to drive the threaded rod to rotate, and then driving the spray valve through the nut seat and the spray pipe to make a linear motion along the boundary of the carrier plate, so that the spray valve makes a linear motion to spray the pigment on the upper surface of the carrier plate;
[0032] S120, using a microelectronic weighing module to weigh the weight M0 of the carrier plate, and when the spray valve sprays the pigment on the upper surface of the carrier plate, using the microelectronic weighing module to weigh the total weight M1 of the carrier plate and the pigment;
[0033] S130, outputting the weight of the pigment when no blade is placed on the surface of the carrier plate, △M1=M1-M0, based on M0 and M1.
[0034] As a further solution of the present invention: the step of placing the blade L on the upper surface of the weighing module and separately collecting the weight of the blade L specifically includes:
[0035] S210, using a microelectronic weighing module to weigh the total weight M2 of the blade L and the carrier plate;
[0036] S220, output the weight of the blade L according to M0 and M2: ΔM2=M2-M0.
[0037] As a further solution of the present invention: the computer intelligent module further comprises: placing the blade L on the upper surface of the weighing module, using the spraying module to evenly spray the pigment on the weighing module and the upper surface of the blade L, collecting the total weight of the pigment on the upper surface of the weighing module, the blade L and the pigment on the upper surface of the blade L, after removing the blade L with the pigment, collecting the weight of the pigment on the upper surface of the weighing module, and outputting the weight of the pigment on the upper surface of the blade L, specifically comprising:
[0038] S310, placing the blade L on the surface of the carrier plate, and using a movable spray valve to evenly spray the paint on the carrier plate and the upper surface of the blade L;
[0039] S320, weighing the total weight M3 of the carrier plate, the pigment and the leaf L using a microelectronic weighing module;
[0040] S330, removing the leaf L with the pigment from the surface of the carrier plate, and weighing the total weight M4 of the carrier plate and the remaining raw materials using a microelectronic weighing module;
[0041] S340, calculating the weight of the pigment on the surface of the blade L according to ΔM2, M3 and M4: ΔM3=M3-M4-ΔM2.
[0042] As a further solution of the present invention: the step of placing the blade L on the upper surface of the weighing module and separately collecting the weight of the blade L specifically includes: collecting the area of the upper surface of the weighing module, calculating the weight of the pigment per unit area by using the total weight of the pigment on the upper surface of the weighing module and the area of the upper surface of the weighing module, and calculating the area of the blade L according to the weight of the pigment on the upper surface of the blade L and the weight of the pigment per unit area, specifically includes:
[0043] S410, using a camera unit to collect a boundary image of the object carrier;
[0044] S420, uploading the boundary image of the loading plate to the image recognition unit, and outputting the area S of the loading plate;
[0045] S430, using the convolutional neural network unit to repeatedly drive the spray valve along the boundary of the carrier plate to simulate spraying paint, averaging △M1 based on the multiple measurements, and outputting the average △M1 of the weight of the paint on the surface of the carrier plate;
[0046] S440 is used to receive the weight data △M1 and △M3 transmitted by the calculation module, to calculate the weight of the pigment per unit area m=△M1 / S1, and to calculate the area of the blade L S2=△M3 / m.
[0047] Compared with the prior art, the beneficial effects of the present invention are as follows: the present application utilizes a convolutional neural network unit to repeatedly drive the spray valve along the boundary of the carrier plate to simulate spraying paint to calculate the area S1 of the carrier plate and the average weight of the paint on the surface of the carrier plate. When the weight △M3 of the paint on the surface of the blade is weighed using a microelectronic weighing module, the area S2 of the blade can be calculated as △M3 / m, thereby achieving the purpose of calculating the area of irregular objects, and has the characteristics of simple measurement and high accuracy. BRIEF DESCRIPTION OF THE DRAWINGS
[0048] Figure 1 The figure is a structural schematic diagram of a leaf area measurement device based on computer vision.
[0049] Figure 2 The figure is a schematic diagram of the structure of a pigment delivery module and a spray valve module in a blade area measurement device based on computer vision.
[0050] Figure 3 The figure is a schematic diagram of the structure of a mobile module in a computer vision blade area measurement device.
[0051] Figure 4 The present invention is a schematic diagram of the structure of a carrier plate and a pigment on the surface of the carrier plate in a computer vision leaf area measurement device.
[0052] Figure 5 FIG. 3 is a structural diagram of a computer intelligent module 300 in a blade area measurement device based on computer vision.
[0053] Figure 6 The figure is a flow chart of a leaf area measurement method based on computer vision.
[0054] Figure 7 The present invention is a flow chart of a computer vision leaf area measurement method, in which a spraying module is used to evenly spray a pigment on the upper surface of a weighing module, and the total weight of the pigment on the upper surface of the weighing module is separately collected.
[0055] Figure 8 The present invention is a flow chart of placing a blade L on the upper surface of a weighing module and separately collecting the weight of the blade L in a blade area measurement method based on computer vision.
[0056] Fig. 9 In a computer vision leaf area measurement method, a leaf L is placed on the upper surface of a weighing module, and a paint is evenly sprayed on the weighing module and the upper surface of the leaf L using a spraying module. The total weight of the paint on the upper surface of the weighing module, the leaf L, and the paint on the upper surface of the leaf L is collected. After the leaf L with the paint is taken away, the weight of the paint on the upper surface of the weighing module is collected, and a flowchart of the paint weight on the upper surface of the leaf L is output.
[0057] Fig.10 The present invention is a flow chart of collecting the area of the upper surface of a weighing module in a computer vision leaf area measurement method, calculating the pigment weight per unit area using the total weight of the pigment on the upper surface of the weighing module and the area of the upper surface of the weighing module, and calculating the area of leaf L based on the pigment weight on the upper surface of leaf L and the pigment weight per unit area. DETAILED DESCRIPTION
[0058] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.
[0059] The specific implementation of the present invention is described in detail below in conjunction with specific embodiments.
[0060] like Figure 1 As shown, an embodiment of the present invention provides a leaf area measurement device based on computer vision, the device comprising:
[0061] A spraying module 100, used for spraying paint while moving;
[0062] The weighing module 200 is used to weigh the weight of the blade L alone, to weigh the weight of the pigment on the surface of the weighing module 200 alone, and to weigh the total weight of the pigment on the surface of the weighing module, the blade L, and the pigment on the surface of the blade L;
[0063] The computer intelligent module 300 is used to measure the area of the upper surface of the weighing module 200, to control the spraying module 200 to spray paint along the boundary of the weighing module 200 at a certain speed, to calculate the weight of the paint per unit area on the upper surface of the weighing module 200, and to calculate the area of the blade L based on the weight of the paint on the upper surface of the blade L and the weight of the paint per unit area on the upper surface of the weighing module 200.
[0064] In the embodiment of the present invention, the device further comprises a frame, and the spraying module 100, the weighing module 200 and the computer intelligence module 300 are all connected to the frame.
[0065] like Figures 1 to 3 As shown, as a preferred embodiment of the present invention, the spraying module 100 includes:
[0066] A pigment delivery module 101, used for delivering liquid pigment;
[0067] The spray valve module 102 is used to spray the paint on the upper surface of the weighing module 200;
[0068] The moving module 103 is used to drive the spray valve module 102 to move at a constant speed along the upper surface of the weighing module 200.
[0069] It should be noted that the pigment delivery module 101 includes a pigment storage tank 1011, a liquid pump 1012 and a flexible hose 1013. The liquid inlet end of the liquid pump 1012 is connected to the pigment storage tank 1011, and the liquid outlet end of the liquid pump 1012 is connected to the flexible hose 1013. The pigment storage tank 1011 stores liquid pigment with a certain viscosity.
[0070] The spray valve module 102 includes a spray pipe 1021, a spray valve 1022 and a bracket 1023. One end of the spray pipe 1021 is connected to the flexible hose 1013, and the spray valve 1022 is fixedly connected to the other end of the spray pipe 1021. The surface of the spray pipe 1021 is fixedly connected to the bracket 1023.
[0071] The mobile module 103 includes a driving motor 1031, a threaded rod 1032, a nut seat 1033 and a limiting rod. The driving motor 1031, the threaded rod 1032 and the limiting rod are all connected to the surface of the frame. The driving motor 1031 is connected to the threaded rod 1032. The nut seat 1033 is not only threadedly connected to the surface of the threaded rod 1032, but also movably sleeved on the surface of the limiting rod. The nozzle 102 is fixedly installed on the surface of the nut seat 1033. When the driving motor 1031 drives the threaded rod 1032 to rotate, the rotating threaded rod 1032 drives the spray valve 1022 to perform reciprocating linear motion through the nut seat 1033 and the nozzle 102.
[0072] The spray valve module 102 may use a wind shield when spraying, or may complete the measurement work in a relatively sealed housing.
[0073] like Figures 1 to 5 As shown, as a preferred embodiment of the present invention, the weighing module 200 includes:
[0074] The carrier plate 201 is used to place the blades L, and the spray valve 1022 sprays the paint on the upper surface of the carrier plate 201 .
[0075] The microelectronic weighing module 202, the carrier plate 201 is installed above the microelectronic weighing module 202, and is used to weigh the weight M0 of the carrier plate 201; when the spray valve 1022 sprays the pigment on the upper surface of the carrier plate 201, it is used to weigh the total weight M1 of the carrier plate 201 and the pigment; when the blade L is placed on the upper surface of the carrier plate 201, it is used to weigh the total weight M2 of the blade L and the carrier plate 201; when the blade L is placed on the upper surface of the carrier plate 201, it is used to weigh the total weight M3 of the blade L, the carrier plate 201 and the pigment; after the blade L is taken away, it is used to weigh the total weight M4 of the carrier plate 201 and the remaining pigment.
[0076] The calculation module 203 is used to calculate the weight of the pigment on the surface of the carrier plate 201 when no blade is placed (ΔM1=M1-M0), the weight of the blade L (ΔM2=M2-M0), and the weight of the pigment on the surface of the blade L (ΔM3=M3-M4-ΔM2).
[0077] In the embodiment of the present invention, when the rotating threaded rod 1032 drives the spray valve 1022 to move along the carrier plate 201 at a certain speed through the nut seat 1033 and the spray pipe 102, the thickness of the pigment sprayed on the carrier plate 201 is 1 mm, and the pigment is selected to be of a type with a large viscosity. When the pigment is sprayed on the surface of the carrier plate 201, it will not flow, so as to prevent the pigment from flowing out from the surface of the carrier plate 201. The carrier plate 201 is a PVC board, and the microelectronic weighing module 202 is a high-precision electronic scale that can accurately weigh light objects. The calculation module 203 has a certain calculation ability, which can not only automatically obtain weighing data, but also calculate the difference between two weighing data, and also has the function of automatically transmitting data;
[0078] The carrier plate 201 is an independent component. A new carrier plate 201 is required for each measurement. The carrier plate 201 can be used again after the pigment on its surface is cleaned.
[0079] like Figures 1 to 6 As shown, as a preferred embodiment of the present invention, the computer intelligence module 300 also includes:
[0080] The camera unit 301 is used to collect image information of the carrier plate 201;
[0081] An image recognition unit 302, used to recognize the boundary of the carrier plate 201 according to the image information of the carrier plate 201, wherein the boundary of the carrier plate is a rectangle or a circle, and is used to calculate the area S1 of the carrier plate 201;
[0082] The convolutional neural network unit 303 is used to drive the spray valve 1022 multiple times to simulate spraying paint along the border of the carrier plate 201, and output the average weight of the paint on the surface of the carrier plate 201.
[0083] The data processing unit 304 is used to receive the weight data △M1 and △M3 transmitted by the calculation module 203, and is used to calculate the weight of the pigment per unit area of the carrier plate 201, and is used to calculate the area S2 of the blade L = △M3 / m.
[0084] It can be understood that the camera unit 301 is a CCD camera group, and the CCD camera group is connected to the spray valve module 102. When the moving module 103 drives the spray valve module 102 to move from one end of the carrier 201 to the other end, the CCD camera group can collect pictures or video information of the carrier 201 in real time, and can transmit the captured pictures of the carrier 201 to the image recognition unit 302. The image recognition unit 302 can use picture recognition technology (specifically, the light and dark relationship presented in the picture) to identify the boundary of the carrier 201. After the boundary of the carrier 201 is identified, the convolutional neural network unit 303 simulates the moving module 103 driving the spray valve module 102 to spray paint along the boundary of the carrier 201 for multiple times, so as to determine the moving speed of the moving module 103 driving the spray valve module 102, so that the spray valve module 102 can ensure that the paint can be evenly distributed within the boundary of the carrier 201 according to a certain thickness when the speed is certain.
[0085] The reason for using paint is to facilitate the camera unit 301 to identify whether the paint is sprayed along the boundary of the carrier plate 201. The reason for spraying the paint along the boundary of the carrier plate 201 is, on the one hand, to prevent the paint from being wasted by spraying on the outside, and on the other hand, to prevent the paint from being sprayed on the outside and being inconvenient to clean.
[0086] like Figure 6 As shown, an embodiment of the present invention further provides a leaf area measurement method based on computer vision, the method comprising the following steps:
[0087] S100, using the spraying module 100 to evenly spray the pigment on the upper surface of the weighing module 200, and separately collecting the total weight of the pigment on the upper surface of the weighing module 200;
[0088] S200, placing the blade L on the upper surface of the weighing module 200, and collecting the weight of the blade L separately;
[0089] S300, placing the blade L on the upper surface of the weighing module 200, using the spraying module 100 to evenly spray the paint on the weighing module 200 and the upper surface of the blade L, collecting the total weight of the paint on the upper surface of the weighing module 200, the blade L, and the paint on the upper surface of the blade L, after taking away the blade L with the paint, collecting the weight of the paint on the upper surface of the weighing module 200, and outputting the weight of the paint on the upper surface of the blade L;
[0090] S400, collecting the area of the upper surface of the weighing module 200, calculating the pigment weight per unit area using the total weight of the pigment on the upper surface of the weighing module 200 and the area of the upper surface of the weighing module 200, and calculating the area of the blade L according to the pigment weight on the upper surface of the blade L and the pigment weight per unit area.
[0091] like Figure 7 As shown, as a preferred embodiment of the present invention, the step of using the spraying module 100 to evenly spray the pigment on the upper surface of the weighing module 200 and separately collecting the total weight of the pigment on the upper surface of the weighing module 200 specifically includes:
[0092] S110, using the liquid pump 1012 to spray the paint in the paint storage tank 1011 through the flexible hose 1013, the nozzle 1021 and the spray valve 1022, using the driving motor 1031 to drive the threaded rod 1032 to rotate, and then driving the spray valve 1022 to make a linear motion along the boundary of the carrier plate 201 through the nut seat 1033 and the nozzle 102, so that the spray valve 1022 makes a linear motion to spray the paint on the upper surface of the carrier plate 201;
[0093] S120, using the microelectronic weighing module 202 to weigh the weight M0 of the carrier plate 201, and when the spray valve 1022 sprays the pigment on the upper surface of the carrier plate 201, using the microelectronic weighing module 202 to weigh the total weight M1 of the carrier plate 201 and the pigment;
[0094] S130, outputting the weight of the pigment when no blade is placed on the surface of the carrier plate 201 according to M0 and M1, △M1=M1-M0.
[0095] like Figure 8 As shown, as a preferred embodiment of the present invention, the step of placing the blade L on the upper surface of the weighing module 200 and separately collecting the weight of the blade L specifically includes:
[0096] S210, using the microelectronic weighing module 202 to weigh the total weight M2 of the blade L and the carrier plate 201;
[0097] S220, output the weight of the blade L according to M0 and M2: ΔM2=M2-M0.
[0098] In the embodiment of the present invention, the stem portion of the blade L needs to be removed in advance.
[0099] like Fig. 9As shown, as a preferred embodiment of the present invention, the steps of placing the blade L on the upper surface of the weighing module 200, spraying the pigment evenly on the upper surface of the weighing module 200 and the blade L using the spraying module 100, collecting the total weight of the pigment on the upper surface of the weighing module 200, the blade L, and the pigment on the upper surface of the blade L, and after taking away the blade L with the pigment, collecting the pigment weight on the upper surface of the weighing module 200, and outputting the pigment weight on the upper surface of the blade L specifically include:
[0100] S310, placing the blade L on the surface of the carrier plate 201, and using the movable spray valve 1022 to evenly spray the paint on the carrier plate 201 and the upper surface of the blade L;
[0101] S320, using the microelectronic weighing module 202 to weigh the total weight M3 of the carrier plate 201, the pigment and the leaves L;
[0102] S330, removing the leaf L with the pigment from the surface of the carrier plate 201, and weighing the total weight M4 of the carrier plate 201 and the remaining raw materials using the microelectronic weighing module 202;
[0103] S340, calculating the weight of the pigment on the surface of the blade L according to ΔM2, M3 and M4: ΔM3=M3-M4-ΔM2.
[0104] In the embodiment of the present invention, when removing the blade L with the pigment from the surface of the carrier plate 201 , care should be taken not to damage the pigment on the surface of the carrier plate 201 .
[0105] like Fig.10 As shown, as a preferred embodiment of the present invention, the step of collecting the area of the upper surface of the weighing module 200, calculating the pigment weight per unit area by using the total weight of the pigment on the upper surface of the weighing module 200 and the area of the upper surface of the weighing module 200, and calculating the area of the blade L according to the pigment weight on the upper surface of the blade L and the pigment weight per unit area, specifically includes:
[0106] S410, using the camera unit 301 to collect a boundary image of the object carrier 201;
[0107] S420, uploading the boundary image of the carrier plate 201 to the image recognition unit 302, and outputting the area S1 of the carrier plate 201;
[0108] S430, using the convolutional neural network unit 303 to repeatedly drive the spray valve 1022 along the boundary of the carrier plate 201 to simulate spraying paint, and calculate the average value of △M1 measured multiple times, and output the average value of the paint weight on the surface of the carrier plate 201
[0109] S440, for receiving the weight data ΔM1 and ΔM3 transmitted by the calculation module 203, for calculating the weight of the pigment per unit area, for calculating the area S2 = ΔM3 / m of the blade L.
[0110] In the embodiment of the present invention, the blade L needs to be treated with medicine or directly flattened with a pressing block so that the blade L can be laid flat on the surface of the carrier plate 201. After the measurement is completed, the pigment on the surface of the carrier plate 201 and the blade L is cleaned with a cleaning agent.
[0111] In summary, the present application utilizes the convolutional neural network unit 303 to repeatedly drive the spray valve 1022 along the boundary of the carrier plate 201 to simulate the spraying of paint to calculate the area S1 of the carrier plate 201 and the average weight of the paint on the surface of the carrier plate 201. When the weight △M3 of the paint on the surface of the blade L is weighed using the microelectronic weighing module 202, the area S2 of the blade L can be calculated as △M3 / m, thereby achieving the purpose of calculating the area of irregular objects, and has the characteristics of simple measurement and high accuracy.
[0112] The above only describes in detail the preferred embodiments of the present invention, which is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
[0113] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.
[0114] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
[0115] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the disclosure in the specification and examples. This application is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.
Claims
1. A computer vision leaf area measurement device, characterized in that: The computer vision blade area measurement device comprises: A spraying module, used to spray paint while moving; A weighing module, used to weigh the weight of the blade L alone, used to weigh the weight of the pigment on the upper surface of the weighing module alone, and used to weigh the total weight of the pigment on the upper surface of the weighing module, the blade L, and the pigment on the upper surface of the blade L; The computer intelligent module is used to measure the area of the upper surface of the weighing module, to control the spraying module to spray paint along the boundary of the weighing module at a certain speed, to calculate the weight of the paint per unit area on the upper surface of the weighing module, and to calculate the area of the blade L based on the weight of the paint on the upper surface of the blade L and the weight of the paint per unit area on the upper surface of the weighing module.
2. A computer vision leaf area measurement device according to claim 1, characterized in that: The spraying module comprises: A pigment delivery module, used for delivering liquid pigment; A spray valve module is used to spray the paint on the upper surface of the weighing module; The moving module is used to drive the spray valve module to move at a constant speed along the upper surface of the weighing module.
3. A computer vision leaf area measurement device according to claim 2, characterized in that: The pigment delivery module includes a pigment storage tank, a liquid pump and a flexible hose, wherein the liquid inlet end of the liquid pump is connected to the pigment storage tank, the liquid outlet end of the liquid pump is connected to the flexible hose, and the pigment storage tank stores liquid pigment with a certain viscosity; The spray valve module comprises a spray pipe, a spray valve and a bracket, one end of the spray pipe is connected to a flexible hose, the spray valve is fixedly connected to the other end of the spray pipe, and the surface of the spray pipe is fixedly connected to a bracket; The mobile module includes a driving motor, a threaded rod, a nut seat and a limit rod, wherein the driving motor, the threaded rod and the limit rod are all connected to the surface of the frame, the driving motor is connected to the threaded rod, the nut seat is not only threadedly connected to the surface of the threaded rod, but also movably sleeved on the surface of the limit rod, and the nozzle is fixedly installed on the surface of the nut seat. When the driving motor drives the threaded rod to rotate, the rotating threaded rod drives the spray valve to perform reciprocating linear motion through the nut seat and the nozzle.
4. The computer vision leaf area measurement device according to claim 3, characterized in that: The weighing module comprises: A carrier plate, used for placing the blade L, and the spray valve sprays the paint onto the upper surface of the carrier plate; A microelectronic weighing module, wherein the carrier plate is installed above the microelectronic weighing module, and is used to weigh the weight M0 of the carrier plate; when the spray valve sprays the pigment on the upper surface of the carrier plate, it is used to weigh the total weight M1 of the carrier plate and the pigment; when the blade L is placed on the upper surface of the carrier plate, it is used to weigh the total weight M2 of the blade L and the carrier plate; when the blade L is placed on the upper surface of the carrier plate, it is used to weigh the total weight M3 of the blade L, the carrier plate and the pigment; after the blade L is taken away, it is used to weigh the total weight M4 of the carrier plate and the remaining pigment; The calculation module is used to calculate the weight of the pigment when no blade is placed on the surface of the carrier plate △M1=M1-M0, to calculate the weight of the blade L △M2=M2-M0, and to calculate the weight of the pigment on the surface of the blade L △M3=M3-M4-△M2.
5. The leaf area measurement device based on computer vision according to claim 4, characterized in that: The computer intelligence module also includes: A camera unit, used for collecting image information of the carrier plate; An image recognition unit, used to recognize the boundary of the loading plate according to the image information of the loading plate, wherein the boundary of the loading plate is a rectangle or a circle, and is used to calculate the area S1 of the loading plate; A convolutional neural network unit is used to drive the spray valve multiple times to simulate spraying paint along the border of the carrier plate, and output the average value △M1 of the weight of the paint on the surface of the carrier plate; The data processing unit is used to receive the weight data △M1 and △M2 transmitted by the calculation module, to calculate the weight m=△M1 / S1 of the pigment per unit area of the carrier plate, and to calculate the area S2=△M2 / m of the blade L.
6. A leaf area measurement method based on computer vision, characterized in that: The method comprises the following steps: S100, using a spraying module to evenly spray the pigment on the upper surface of the weighing module, and separately collecting the total weight of the pigment on the upper surface of the weighing module; S200, placing the blade L on the upper surface of the weighing module, and collecting the weight of the blade L separately; S300, placing the blade L on the upper surface of the weighing module, using the spraying module to evenly spray the paint on the weighing module and the upper surface of the blade L, collecting the total weight of the paint on the upper surface of the weighing module, the blade L, and the paint on the upper surface of the blade L, after taking away the blade L with the paint, collecting the weight of the paint on the upper surface of the weighing module, and outputting the weight of the paint on the upper surface of the blade L; S400, collecting the area of the upper surface of the weighing module, calculating the pigment weight per unit area using the total weight of the pigment on the upper surface of the weighing module and the area of the upper surface of the weighing module, and calculating the area of blade L according to the pigment weight on the upper surface of blade L and the pigment weight per unit area.
7. The leaf area measurement method based on computer vision according to claim 6, characterized in that: The step of using the spraying module to evenly spray the pigment on the upper surface of the weighing module and separately collecting the total weight of the pigment on the upper surface of the weighing module specifically includes: S110, using a liquid pump to spray the pigment in the pigment storage tank through the flexible hose, the spray pipe and the spray valve, using a driving motor to drive the threaded rod to rotate, and then driving the spray valve through the nut seat and the spray pipe to make a linear motion along the boundary of the carrier plate, so that the spray valve makes a linear motion to spray the pigment on the upper surface of the carrier plate; S120, using a microelectronic weighing module to weigh the weight M0 of the carrier plate, and when the spray valve sprays the pigment on the upper surface of the carrier plate, using the microelectronic weighing module to weigh the total weight M1 of the carrier plate and the pigment; S130, outputting the weight of the pigment when no blade is placed on the surface of the carrier plate, △M1=M1-M0, based on M0 and M1.
8. The leaf area measurement method based on computer vision according to claim 7, characterized in that: The step of placing the blade L on the upper surface of the weighing module and separately collecting the weight of the blade L specifically includes: S210, using a microelectronic weighing module to weigh the total weight M2 of the blade L and the carrier plate; S220, output the weight of the blade L according to M0 and M2: ΔM2=M2-M0.
9. The leaf area measurement method based on computer vision according to claim 8, characterized in that: The steps of placing the blade L on the upper surface of the weighing module, spraying the pigment evenly on the weighing module and the upper surface of the blade L using the spraying module, collecting the total weight of the pigment on the upper surface of the weighing module, the blade L, and the pigment on the upper surface of the blade L, and after removing the blade L with the pigment, collecting the weight of the pigment on the upper surface of the weighing module, and outputting the weight of the pigment on the upper surface of the blade L specifically include: S310, placing the blade L on the surface of the carrier plate, and using a movable spray valve to evenly spray the paint on the carrier plate and the upper surface of the blade L; S320, weighing the total weight M3 of the carrier plate, the pigment and the leaf L using a microelectronic weighing module; S330, removing the leaf L with the pigment from the surface of the carrier plate, and weighing the total weight M4 of the carrier plate and the remaining raw materials using a microelectronic weighing module; S340, calculating the weight of the pigment on the surface of the blade L according to ΔM2, M3 and M4: ΔM3=M3-M4-ΔM2.
10. The leaf area measurement method based on computer vision according to claim 9, characterized in that: The step of placing the blade L on the upper surface of the weighing module and separately collecting the weight of the blade L specifically includes: collecting the area of the upper surface of the weighing module, calculating the weight of the pigment per unit area by using the total weight of the pigment on the upper surface of the weighing module and the area of the upper surface of the weighing module, and calculating the area of the blade L according to the weight of the pigment on the upper surface of the blade L and the weight of the pigment per unit area, specifically including: S410, using a camera unit to collect a boundary image of the object carrier; S420, uploading the boundary image of the loading plate to the image recognition unit, and outputting the area S of the loading plate; S430, using the convolutional neural network unit to repeatedly drive the spray valve along the boundary of the carrier plate to simulate spraying paint, averaging △M1 based on the multiple measurements, and outputting the average △M1 of the weight of the paint on the surface of the carrier plate; S440, for receiving weight data △M1 and △M2 transmitted by the calculation module, for calculating the weight of the pigment per unit area m=△M1 / S1, for calculating the area of the blade L S2=△M2 / m.
Citation Information
Patent Citations
Nondestructive measuring method for leaf area of broad leaved plant
CN101799283A
Device and method for measuring leaf area based on computer vision
CN102200433A
Method for measuring amount of oil applied on surfaces of aluminum plates per unit area
CN104483001A
Weight measuring device and measuring method of per unit area blade
CN109211375A
Glue amount calculating system based on corrugated paper board production
CN110360961A
