Plant area growth vigour recognition method and system

Abstract

A plant growth vigour recognition method, comprising: receiving a plant area input by a user, determining a detection point according to the plant area, and collecting the relative height of the detection point by an unmanned aerial vehicle S100; establishing a plant area model according to the relative height, determining a detection path in the plant area model, and sending the detection path to the unmanned aerial vehicle S200; receiving plant images obtained by the unmanned aerial vehicle under the detection path, and recognising the plant images to obtain a growth vigour report S300; and acquiring environmental parameters of the plant area to modify a recognition process according to the environmental parameters S400. A growth vigour deviation attributable to environmental parameters may be used to modify the neural network recognition model (S401-403, Fig.5).

Description

TECHNICAL FIELD The present invention relates to the technical field of plant growth vigour judgment, and in particular, to a plant area growth vigour recognition method and system. BACKGROUND Plants are one of the most important life forms on the earth, and provide human beings with a variety of resources and services such as food, oxygen, drugs, fibre, wood, and the like. Without plants, human beings will not survive. Without plants, human beings will face the danger of serious air pollution and hypoxia. The carbon dioxide in the atmosphere will continue to increase, which will lead to the intensification of the greenhouse effect and the rise of the earth's temperature. At the same time, the oxygen in the atmosphere will continue to decrease, making it difficult for human beings to breathe. Therefore, human beings need to protect plants consciously. Under the background of the prior art, the process of protecting the plant area is generally actively completed by workers in cooperation with the unmanned aerial vehicle, and the operation subject of this process is the workers. The flexibility is high, but the workload is heavy, so that the process is suitable for overall detection, but not for rapid detection. Thus, how to provide a rapid detection scheme with high convenience is the technical problem to be solved by the technical solution of the present invention. SUMMARY An object of the present invention is to provide a plant area growth vigour recognition method and system to solve the problems set forth in the above background art. To achieve the above object, the present invention provides the following technical solutions: a plant area growth vigour recognition method, including: receiving a plant area input by a user, determining a detection point according to the plant area, and collecting the relative height of the detection point by an unmanned aerial vehicle; wherein the fluctuation range of the absolute height of the unmanned aerial vehicle during a height collection process is smaller than a preset data condition; establishing a plant area model according to the relative height, determining a detection path in the plant area model, and sending the detection path to the unmanned aerial vehicle; receiving plant images acquired by the unmanned aerial vehicle under the detection path, and recognising the plant images to obtain a growth vigour report; and acquiring environmental parameters of the plant area by preset sensors, and modifying a recognition process according to the environmental parameters. As a further solution of the present invention, the step of receiving a plant area input by a user, determining a detection point according to the plant area, and collecting the relative height of the detection point by an unmanned aerial vehicle includes: receiving boundary coordinates input by the user, and fitting the plant area according to the boundary coordinates; acquiring device parameters of a display device, determining a model precision range according to the device parameters, receiving selection information of the user, and determining final precision within the model precision range based on the selection information; determining the detection point according to the final precision; and sending a working instruction pointing to the detection point to the unmanned aerial vehicle, and receiving the relative height of the detection point fed back by the unmanned aerial vehicle; wherein the relative height is obtained by a ranging module built in the unmanned aerial vehicle. As a further solution of the present invention, the step of establishing a plant area model according to the relative height, determining a detection path in the plant area model, and sending the detection path to the unmanned aerial vehicle includes: creating a reference three-dimensional model according to boundary coordinates; counting all relative heights based on the coordinates of the detection point to obtain three-dimensional coordinate points; connecting and fitting the three-dimensional coordinate points to establish the plant area model; and displaying the plant area model, receiving the detection path input by the user, and sending the detection path to the unmanned aerial vehicle. As a further solution of the present invention, the step of displaying the plant area model, receiving the detection path input by the user, and sending the detection path to the unmanned aerial vehicle includes: displaying the plant area model, and receiving an area marker input by the user; creating a detection path based on the area marker, and receiving adjustment information input by the user; and determining a final path according to the adjustment information, and sending the final path to the unmanned aerial vehicle; wherein the area marker at least includes a partition area and a must-pass area; a preset reference object corresponds to one of the must-pass areas. As a further solution of the present invention, the step of receiving plant images acquired by the unmanned aerial vehicle under the detection path, and recognising the plant images to obtain a growth vigour report includes: receiving the plant images acquired by the unmanned aerial vehicle under the detection path, and classifying the plant images according to the area markers; reading a plant image corresponding to the reference object, and calculating a change layer by comparing the plant image with a standard image corresponding to the reference object; wherein parameters of pixel points in the change layer include hue, saturation and brightness; the change layer is a mean feature of all image comparison processes; modifying a plant image corresponding to a non-reference object based on the change layer, to obtain a modified image; and inputting the modified image into a trained neural network recognition model to output the growth vigour report. As a further solution of the present invention, the step of acquiring environmental parameters of the plant area by preset sensors, and modifying a recognition process according to the environmental parameters includes: acquiring the environmental parameters of the plant area based on the preset sensors; counting all growth vigour reports, calculating a growth vigour deviation, and verifying the growth vigour deviation according to the environmental parameters; wherein the growth vigour deviation is used to represent a gap with a standard growth vigour; and modifying the change layer and the neural network recognition model according to the verification result. The technical solution of the present invention also provides a plant area growth vigour recognition system, including: a height collection module, for receiving a plant area input by a user, determining a detection point according to the plant area, and collecting the relative height of the detection point by an unmanned aerial vehicle; wherein the fluctuation range of the absolute height of the unmanned aerial vehicle during a height collection process is smaller than a preset data condition; a path sending module, for establishing a plant area model according to the relative height, determining a detection path in the plant area model, and sending the detection path to the unmanned aerial vehicle; an image recognition module, for receiving plant images acquired by the unmanned aerial vehicle under the detection path, and recognising the plant images to obtain a growth vigour report; and a recognition process modification module, for acquiring environmental parameters of the plant area by preset sensors, and modifying a recognition process according to the environmental parameters. As a further solution of the present invention, the height collection module includes: receiving boundary coordinates input by the user, and fitting the plant area according to the boundary coordinates; acquiring device parameters of a display device, determining a model precision range according to the device parameters, receiving selection information of the user, and determining final precision within the model precision range based on the selection information; determining the detection point according to the final precision; and sending a working instruction pointing to the detection point to the unmanned aerial vehicle, and receiving the relative height of the detection point fed back by the unmanned aerial vehicle; wherein the relative height is obtained by a ranging module built in the unmanned aerial vehicle. As a further solution of the present invention, the path sending module includes: a reference model creating unit, for creating a reference three-dimensional model according to the boundary coordinates; a three-dimensional point determination unit, for counting all relative heights based on the coordinates of the detection point to obtain three-dimensional coordinate points; a point fitting unit, for connecting and fitting the three-dimensional coordinate points to establish the plant area model; and a path receiving unit, for displaying the plant area model, receiving the detection path input by the user, and sending the detection path to the unmanned aerial vehicle. As a further solution of the present invention, the path receiving unit includes: a marker receiving subunit, for displaying the plant area model, and receiving an area marker input by the user; an adjustment subunit, for creating a detection path based on the area marker, and receiving adjustment information input by the user; and a selection subunit, for determining a final path according to the adjustment information, and sending the final path to the unmanned aerial vehicle; wherein the area marker at least includes a partition area and a must-pass area; a preset reference object corresponds to one of the must-pass areas. Compared with the prior art, the present invention has the beneficial effects that the height data is acquired by the unmanned aerial vehicle, the plant area model is created, and the detection path is determined based on the plant area model, so that the unmanned aerial vehicle can continuously acquire plant images under the detection path; then the plant images are recognised by the existing neural network model, and the growth vigour report is output; in this process, sensors are introduced to modify the recognition process; the recognition efficiency is greatly improved on the premise of ensuring the recognition precision. BRIEF DESCRIPTION OF THE DRAWINGS In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings required to be used in the description of the embodiments or the prior art will be briefly introduced below. It is obvious that the accompanying drawings in the following description are merely some embodiments of the present invention. FIG. lisa flowchart of a plant area growth vigour recognition method. FIG. 2 is a first sub-flowchart of the plant area growth vigour recognition method. FIG. 3 is a second sub-flowchart of the plant area growth vigour recognition method. FIG. 4 is a third sub-flowchart of the plant area growth vigour recognition method. FIG. 5 is a fourth sub-flowchart of the plant area growth vigour recognition method. FIG. 6 is a block diagram of the composition structure of a plant area growth vigour recognition system. DETAILED DESCRIPTION In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clear, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present invention and are not intended to limit the present invention. FIG. 1 is a flowchart of a plant area growth vigour recognition method. In an embodiment of the present invention, the plant area growth vigour recognition method includes: Step SI00: receiving a plant area input by a user, determining a detection point according to the plant area, and collecting the relative height of the detection point by an unmanned aerial vehicle; wherein the fluctuation range of the absolute height of the unmanned aerial vehicle during a height collection process is smaller than a preset data condition; Step S200: establishing a plant area model according to the relative height, determining a detection path in the plant area model, and sending the detection path to the unmanned aerial vehicle; Step S300: receiving plant images acquired by the unmanned aerial vehicle under the detection path, and recognising the plant images to obtain a growth vigour report; and Step S400: acquiring environmental parameters of the plant area by preset sensors, and modifying a recognition process according to the environmental parameters. In one example of the technical solution of the present invention, firstly, the height of the whole plant area is collected by the unmanned aerial vehicle, and a plant area model can be established according to the collected height, wherein the establishment process of the plant area model can adopt the existing three-dimensional modeling software; after the plant area model is created, a detection path is selected in the plant area model, and the detection path is sent to the unmanned aerial vehicle, so that the unmanned aerial vehicle can collect plant images along the detection path, recognise the plant images and output a growth vigour report; this process can adopt the existing classifier based on the neural network model, with the input being images, and the output being growth vigour reports. On this basis, the technical solution of the present invention further introduces a modification process, in which environmental parameters, such as the content of key components (oxygen content, etc.) in air are obtained by sensors, the theoretical situation of the growth vigour report is calculated according to the content of the key components, and the growth vigour report is adjusted according to the theoretical situation, so as to update the recognition process. It is worth mentioning that the working height of the unmanned aerial vehicle needs to be determined in advance, and the unmanned aerial vehicle needs to keep this height all the time when it is moving (only small fluctuations are allowed). FIG. 2 is a first sub-flowchart of the plant area growth vigour recognition method. The step of receiving a plant area input by a user, determining a detection point based on the plant area, and collecting the relative height of the detection point by an unmanned aerial vehicle includes: Step S101: receiving boundary coordinates input by the user, and fitting the plant area according to the boundary coordinates; Step SI02: acquiring device parameters of a display device, determining a model precision range according to the device parameters, receiving selection information of the user, and determining final precision within the model precision range based on the selection information; Step SI03: determining the detection point according to the final precision; and Step SI04: sending a working instruction pointing to the detection point to the unmanned aerial vehicle, and receiving the relative height of the detection point fed back by the unmanned aerial vehicle; wherein the relative height is obtained by a ranging module built in the unmanned aerial vehicle. The above specifically explains the height collection process of the unmanned aerial vehicle. First, the boundary coordinates input by the user are received to determine the range of the plant area. Then, the device parameters of the display device are obtained, which are mainly the data processing ability of the CPU; the stronger the data processing ability, the higher the upper limit of the model precision range. Furthermore, the lower limit of the model precision range is determined by the workers, as long as the subjective sensation of the workers is not affected. Finally, the model precision range is displayed, and the selection information input by the user is received to determine the final precision; the higher the precision, the more detection points are needed, and the relationship between the precision and the number of the detection points is determined in advance by the workers. FIG. 3 is a second sub-flowchart of the plant area growth vigour recognition method. The step of establishing a plant area model according to the relative height, determining a detection path in the plant area model, and sending the detection path to the unmanned aerial vehicle includes: Step S201: creating a reference three-dimensional model according to the boundary coordinates; Step S202: counting all relative heights based on the coordinates of the detection point to obtain three-dimensional coordinate points; Step S203: connecting and fitting the three-dimensional coordinate points to establish the plant area model; and Step S204: displaying the plant area model, receiving the detection path input by the user, and sending the detection path to the unmanned aerial vehicle. The above specifically defines the generation process of the detection path. The plane range of the reference three-dimensional model is created according to the boundary coordinates; then the height information is inserted into the created reference three-dimensional model to obtain the three-dimensional coordinate points; all the three-dimensional coordinate points are connected and fitted, to establish the plant area model; after being established, the plant area model is presented to the user, and the detection path input by the user is received, and sent to the unmanned aerial vehicle; the unmanned aerial vehicle will constantly acquire images under this path. As a preferred embodiment of the technical solution of the present invention, the step of displaying the plant area model, receiving the detection path input by the user, and sending the detection path to the unmanned aerial vehicle includes: displaying the plant area model and receiving an area marker input by the user; creating a detection path based on the area marker, and receiving adjustment information input by the user; and determining a final path according to the adjustment information, and sending the final path to the unmanned aerial vehicle; wherein the area marker at least includes a partition area and a must-pass area; a preset reference object corresponds to one of the must-pass areas. The above further defines the determination process of the detection path. In the technical solution of the present invention, the detection path is mainly input by the user. On this basis, the present invention adds an automatic generation process for reducing the workload of the workers. The specific solution is as follows. The area marker input by the user is received, wherein the area marker is used to describe the function of each area in the plant area model, including the plant area and the reference area, wherein the reference area is used as a must-pass area, that is, when a detection path is generated, the detection path must pass through the must-pass area. Further, the present invention also introduces a partition area that is used to adjust the detection path, and the partition area will automatically avoid the partition area. Some detection paths are created based on the must-pass area and the partition area. The goal of creating the detection path is to make the collection area as large as possible and the path length as small as possible. FIG. 4 is a third sub-flow diagram of the plant area growth vigour recognition method. The step of receiving plant images acquired by the unmanned aerial vehicle under the detection path, and recognising the plant images to obtain a growth vigour report includes: Step S301: receiving the plant images acquired by the unmanned aerial vehicle under the detection path, and classifying the plant images according to the area markers; Step S302: reading a plant image corresponding to the reference object, and calculating a change layer by comparing the plant image with a standard image corresponding to the reference object; wherein parameters of pixel points in the change layer include hue, saturation and brightness; the change layer is a mean feature of all image comparison processes; Step S303: modifying a plant image corresponding to a non-reference object based on the change layer, to obtain a modified image; and Step S304: inputting the modified image into a trained neural network recognition model to output the growth vigour report. The above provides a specific growth vigour report generation process, and its benchmark solution is to convert the images into the growth vigour report according to the trained neural network model; the user creates a sample set and trains the neural network recognition model, and the greater the number of elements in the sample set, the greater the capability of the neural network recognition model. On this basis, the change layer is determined according to the reference object introduced into the present invention, the change layer represents the environmental impact during the shooting process, and the actual image of the reference object is compared with the standard image to obtain the change layer; the changing layer can be understood as a filter, so as to modify all other images. FIG. 5 is a fourth sub-flowchart of the plant area growth vigour recognition method. The step of acquiring environmental parameters of the plant area by preset sensors, and modifying a recognition process according to the environmental parameters includes: Step S401: acquiring the environmental parameters of the plant area based on the preset sensors; Step S402: counting all growth vigour reports, calculating a growth vigour deviation, and verifying the growth vigour deviation according to the environmental parameters; wherein the growth vigour deviation is used to represent a gap with a standard growth vigour; and Step S403: modifying the change layer and the neural network recognition model according to the verification result. Environmental parameters are a superordinate concept, and are used to refer to the environmental characteristics of the plant area. The key point is that the characteristics that are different from other areas, such as temperature, humidity and negative oxygen ion content can all be regarded as one of the environmental parameters. The overall growth status of the plant area can be determined from these parameters; the recognition process of the growth vigour report can be adjusted according to the overall growth status, and the goals of adjustment include modifying the change layer and the neural network recognition model. FIG. 6 is a block diagram of the composition structure of a plant area growth vigour recognition system. In an embodiment of the present invention, the system 10 includes: a height collection module 11, for receiving a plant area input by a user, determining a detection point according to the plant area, and collecting the relative height of the detection point by an unmanned aerial vehicle; wherein the fluctuation range of the absolute height of the unmanned aerial vehicle during a height collection process is smaller than a preset data condition; a path sending module 12, for establishing a plant area model according to the relative height, determining a detection path in the plant area model, and sending the detection path to the unmanned aerial vehicle; an image recognition module 13, for receiving plant images acquired by the unmanned aerial vehicle under the detection path, and recognising the plant images to obtain a growth vigour report; and a recognition process modification module 14, for acquiring environmental parameters of the plant area by preset sensors, and modifying a recognition process according to the environmental parameters. Further, the height collection module 11 includes: receiving boundary coordinates input by the user, and fitting the plant area according to the boundary coordinates; acquiring device parameters of a display device, determining a model precision range according to the device parameters, receiving selection information of the user, and determining final precision within the model precision range based on the selection information; determining the detection point according to the final precision; and sending a working instruction pointing to the detection point to the unmanned aerial vehicle, and receiving the relative height of the detection point fed back by the unmanned aerial vehicle; wherein the relative height is obtained by a ranging module built in the unmanned aerial vehicle. Furthermore, the path sending module 12 includes: a reference model creating unit, for creating a reference three-dimensional model according to the boundary coordinates; a three-dimensional point determination unit, for counting all relative heights based on the coordinates of the detection point to obtain three-dimensional coordinate points; a point fitting unit, for connecting and fitting the three-dimensional coordinate points to establish the plant area model; and a path receiving unit, for displaying the plant area model, receiving the detection path input by the user, and sending the detection path to the unmanned aerial vehicle. Specifically, the path receiving unit includes: a marker receiving subunit, for displaying the plant area model, and receiving an area marker input by the user; an adjustment subunit, for creating a detection path based on the area marker, and receiving adjustment information input by the user; and a selection subunit, for determining a final path according to the adjustment information, and sending the final path to the unmanned aerial vehicle; wherein the area marker at least includes a partition area and a must-pass area; a preset reference object corresponds to one of the must-pass areas. The functions that can be realised by the plant area growth vigour recognition method described above are all accomplished by a computer device, which includes one or more processors and one or more memories, wherein at least one program code is stored in the one or more memories, and the program code is loaded and executed by the one or more processors to realise the functions of the plant area growth vigour recognition method. The processor fetches the instructions one by one from the memory, analyses the instructions, then completes the corresponding operations according to the instruction requirements, and produces a series of control commands, so that all parts of the computer can automatically, continuously and coordinately act as an organic whole, and realise the input of the program, the input of the data, the operation and the output of the results; the arithmetic operation or logical operation generated in this process is completed by the operator; the memory includes a read-only memory (ROM), which is used to store computer programs; a protection device is arranged outside the memory. Exemplarily, the computer program can be partitioned into one or more modules that are stored in the memory and executed by the processor to carry out the present invention. The one or more modules can be a series of computer program instruction sections capable of performing specific functions, the instruction sections being used to describe the execution of a computer program in a terminal device. Those skilled in the art can appreciate that the above description of the service device is merely an example and does not constitute a limitation to the terminal device, can include more or fewer components than the above description, or combine certain components, or different components, for example, can include input / output devices, network access devices, buses, and the like. The processor can be a central processing unit (CPU), other general purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, or the like. The general purpose processor can be a microprocessor, or the processor can be any conventional processor or the like. The processor is the control centre of the terminal device described above, with various interfaces and lines connecting the various parts of the overall user terminal. The above-mentioned memory can be used to store computer programs and / or modules, and the above-mentioned processor implements various functions of the above-mentioned terminal device by running or executing the computer programs and / or modules stored in the memory, and calling data stored in the memory. The memory can mainly include a storage program area and a storage data area, wherein the storage program area can store an operating system, application programs required for at least one function (such as an information collection template presentation function, and a product information release function), and the like; the storage data area can store data created according to the use of the berth status display system (e.g., product information collection templates corresponding to different product categories, and product information required to be released by different product providers), and the like. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory such as a hard disk, a memory, a plug-in type hard disk, a smart memory card (SMC), a secure digital (SD) card, a flash card, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage device. It should be noted that in this document, the term "including" or any other variation thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article or device. Without further restrictions, an element defined by the phrase "including a" does not exclude the existence of other identical elements in the process, method, article or device including the element. The above is only the preferred embodiment of the present invention, which does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the description and drawings of the present invention, or directly or indirectly used in other related technical fields, are equally included in the patent protection scope of the present invention.

Claims

1. A plant area growth vigour recognition method, characterized by comprising:receiving a plant area input by a user, determining a detection point according to the plant area, and collecting a relative height of the detection point by an unmanned aerial vehicle; wherein a fluctuation range of an absolute height of the unmanned aerial vehicle during a height collection process is smaller than a preset data condition;establishing a plant area model according to the relative height, determining a detection path in the plant area model, and sending the detection path to the unmanned aerial vehicle;receiving plant images acquired by the unmanned aerial vehicle under the detection path, and recognising the plant images to obtain a growth vigour report; andacquiring environmental parameters of the plant area by preset sensors, and modifying a recognition process according to the environmental parameters;wherein the step of receiving a plant area input by a user, determining a detection point according to the plant area, and collecting a relative height of the detection point by an unmanned aerial vehicle comprises:receiving boundary coordinates input by the user, and fitting the plant area according to the boundary coordinates;acquiring device parameters of a display device, determining a model precision range according to the device parameters, receiving selection information of the user, and determining final precision within the model precision range based on the selection information;determining the detection point according to the final precision; andsending a working instruction pointing to the detection point to the unmanned aerial vehicle, and receiving the relative height of the detection point fed back by the unmanned aerial vehicle; wherein the relative height is obtained by a ranging modulebuilt in the unmanned aerial vehicle;wherein the step of establishing a plant area model according to the relative height, determining a detection path in the plant area model, and sending the detection path to the unmanned aerial vehicle comprises:creating a reference three-dimensional model according to the boundary coordinates;counting all relative heights based on the coordinates of the detection point to obtain three-dimensional coordinate points;connecting and fitting the three-dimensional coordinate points to establish the plant area model; anddisplaying the plant area model, receiving the detection path input by the user, and sending the detection path to the unmanned aerial vehicle;wherein the step of displaying the plant area model, receiving the detection path input by the user, and sending the detection path to the unmanned aerial vehicle comprises:displaying the plant area model, and receiving an area marker input by the user;creating a detection path based on the area marker, and receiving adjustment information input by the user; anddetermining a final path according to the adjustment information, and sending the final path to the unmanned aerial vehicle;wherein the area marker at least comprises a partition area and a must-pass area; a preset reference object corresponds to one of the must-pass areas;wherein the step of receiving plant images acquired by the unmanned aerial vehicle under the detection path, and recognising the plant images to obtain a growth vigour report comprises:receiving the plant images acquired by the unmanned aerial vehicle under thedetection path, and classifying the plant images according to the area markers;reading a plant image corresponding to the reference object, and calculating a change layer by comparing the plant image with a standard image corresponding to the reference object; wherein parameters of pixel points in the change layer comprise hue, saturation and brightness; the change layer is a mean feature of all image comparison processes;modifying a plant image corresponding to a non-reference object based on the change layer, to obtain a modified image; andinputting the modified image into a trained neural network recognition model to output the growth vigour report.

2. The plant area growth vigour recognition method according to claim 1, characterized in that the step of acquiring environmental parameters of the plant area by preset sensors, and modifying a recognition process according to the environmental parameters comprises:acquiring the environmental parameters of the plant area based on the preset sensors;counting all growth vigour reports, calculating a growth vigour deviation, and verifying the growth vigour deviation according to the environmental parameters; wherein the growth vigour deviation is used to represent a gap with a standard growth vigour; andmodifying the change layer and the neural network recognition model according to a verification result.

Images