CN115963821A

CN115963821A - Automatic production operation method, device, equipment and medium for outdoor vegetables

Info

Publication number: CN115963821A
Application number: CN202211644149.4A
Authority: CN
Inventors: 吴华瑞; 朱华吉; 缪祎晟; 韩笑; 郭旺; 张宁
Original assignee: Research Center of Information Technology of Beijing Academy of Agriculture and Forestry Sciences
Current assignee: Research Center of Information Technology of Beijing Academy of Agriculture and Forestry Sciences
Priority date: 2022-12-20
Filing date: 2022-12-20
Publication date: 2023-04-14

Abstract

The invention provides an automatic production operation method, device, equipment and medium for outdoor vegetables, which relate to the field of agricultural production and comprise the following steps: identifying the current operation scene of a target plot, and determining a target operation link, wherein the target operation link is a soil preparation link, a ridging link, a transplanting link or a harvesting link; matching a target operation strategy from a preset strategy library, wherein the target operation strategy comprises indicating installation of a target agricultural implement, indicating setting of target operation parameters, indicating execution of a target planning path and target operation actions; and under the condition that the target agricultural implement is installed on the working vehicle, setting target working parameters according to a target working strategy, and controlling the working vehicle to execute a target working action in a target plot according to a target planned path. The invention can provide reference basis for the operation method and the operation standard of unmanned production, further realize that the agricultural machinery is instructed to carry out production operation according to the current operation requirement under the condition of unmanned or few-person supervision, improve the crop production efficiency and reduce the labor cost.

Description

Automatic production operation method, device, equipment and medium for outdoor vegetables

Technical Field

The invention relates to the field of agricultural production, in particular to an automatic production operation method, device, equipment and medium for outdoor vegetables.

Background

At present, the existing unmanned crop production research mostly researches automation technology or equipment around a certain production link, agricultural technicians do not form a unified standardized flow, the unified standard of unmanned agricultural machinery continuous operation is lacked, the operation quality and efficiency cannot be guaranteed, and the operation time is difficult to accurately predict.

Disclosure of Invention

The invention provides an automatic production operation method, device, equipment and medium for outdoor vegetables, which are used for solving the technical problem that operation links cannot be automatically matched according to operation scenes in the existing operation and further corresponding operation strategies are adopted, and provide a technical scheme for automatic production operation.

In a first aspect, the present invention provides an automatic production method for open field vegetables, comprising:

identifying a current operation scene of a target plot, and determining a target operation link matched with the current operation scene, wherein the target operation link is a soil preparation link, a ridging link, a transplanting link or a harvesting link;

matching a target operation strategy corresponding to the target operation link from a preset strategy library, wherein the target operation strategy comprises instructions for installing a target agricultural implement, instructions for setting target operation parameters, instructions for executing a target planning path and target operation actions;

and under the condition that the target agricultural implement is installed on the working vehicle, setting target working parameters according to the target working strategy, and controlling the working vehicle to execute target working actions in a target plot according to a target planned path.

According to the automatic production operation method of the open field vegetables, provided by the invention, the current operation scene of the target plot is identified, and the target operation link matched with the current operation scene is determined, wherein the method comprises the following steps:

acquiring and identifying a current operation scene in a target plot, wherein the current operation scene is a plot image or a plot video;

under the conditions that soil air drying, soil moisture loss, ground weed rate larger than a preset value, uneven land or no ridge or crop exists on the current ground in the current operation scene, determining the target operation link as a soil preparation link;

determining the target operation link as a ridging link under the condition that the ground soil in the current operation scene is identified to be ploughed;

determining the target operation link as a transplanting link under the condition that the ridging of the ground of the current operation scene is recognized;

and under the condition that the crop maturity in the current operation scene is identified to be greater than a preset maturity, determining the target operation link as a harvesting link.

According to the automatic production operation method of the open field vegetables, the target operation strategy corresponding to the target operation link is matched from the preset strategy library, and the method comprises the following steps: matching a land preparation operation strategy from a preset strategy library under the condition that the target operation link is a land preparation link;

the land preparation operation strategy is used for indicating the installation of a land preparation machine on the operation vehicle;

the land preparation system is also used for indicating and setting land preparation operation parameters, wherein the land preparation operation parameters comprise that the moving speed of the operation vehicle is a first speed;

and the control system is also used for indicating the operation vehicle to drive to the starting point of the soil preparation planning path, controlling the soil preparation machine to descend, controlling the soil preparation machine to prepare soil, controlling the soil preparation machine to lift, and traversing all soil preparation points on the soil preparation planning path to complete operation.

According to the automatic production operation method of the open field vegetables, the target operation strategy corresponding to the target operation link is matched from the preset strategy library, and the method comprises the following steps: matching a ridging operation strategy from a preset strategy library under the condition that the target operation link is a ridging link;

the ridging operation strategy is used for indicating that a ridging machine is installed on the operation vehicle;

the ridging machine is also used for indicating and setting ridging operation parameters, wherein the ridging operation parameters comprise that the moving speed of the operation vehicle is a second speed, and the operation width of the ridging machine is a first preset width;

and the ridging machine is controlled to descend and ridging is controlled after the operation vehicle is instructed to run to the starting point of the ridging planning path, the ridging machine is controlled to ascend after ridging of a ridge corresponding to the starting point is completed, and the ridging machine is controlled to execute ridging according to the running of the ridging planning path to the next starting point of the ridge, so that the ridging planning path is traversed until ridging operation is completed.

According to the automatic production operation method of the open field vegetables, the target operation strategy corresponding to the target operation link is matched from the preset strategy library, and the method comprises the following steps: matching a transplanting operation strategy from a preset strategy library under the condition that the target operation link is a transplanting link;

the transplanting operation strategy is used for indicating that a transplanting machine is installed on the operation vehicle;

the transplanting operation parameter is also used for indicating and setting the transplanting operation parameter, and the transplanting operation parameter comprises the duckbill quantity, the duckbill distance and the transplanting depth of the transplanting machine;

and the transplanting machine is controlled to descend and transplant, after the transplanting of the ridges corresponding to the starting points is finished, the transplanting machine is controlled to be lifted, the transplanting is executed according to the transplanting planning path to the starting point of the next ridge, and the transplanting planning path is traversed until the transplanting operation is finished.

According to the automatic production operation method of the open field vegetables, the target operation strategy corresponding to the target operation link is matched from the preset strategy library, and the method comprises the following steps: matching a harvesting operation strategy from a preset strategy library under the condition that the target operation link is a harvesting link;

the harvesting operation strategy is used for indicating that a harvesting machine is installed on the operation vehicle;

the system is also used for indicating and setting the harvesting operation parameters, wherein the harvesting operation parameters comprise that the moving speed of the operation vehicle is a second speed, and the operation width of the harvester is a second preset width;

the control system is also used for indicating the operation vehicle to drive to the starting point of the harvesting planning path, controlling the harvesting machine to descend, controlling the harvesting machine to harvest, after the harvesting of the ridge corresponding to the starting point is finished, controlling the harvesting machine to lift, driving to the starting point of the next ridge according to the harvesting planning path to execute harvesting, traversing the harvesting planning path until the harvesting operation is finished.

According to the automatic production operation method of the open field vegetables, before the current operation scene of the target plot is identified, the method further comprises the following steps:

acquiring positioning information of an operation vehicle;

in a preset map, determining a land parcel where the current position of the operation vehicle is located according to the positioning information of the operation vehicle, and determining the land parcel where the current position of the operation vehicle is located as the target land parcel.

According to the automatic production operation method of the open vegetable, before the positioning information of the operation vehicle is obtained, the method comprises the following steps:

converting the edge track graph of each land block into polygons, and collecting longitude and latitude information of all vertexes corresponding to each polygon;

mapping all vertexes corresponding to each polygon to an initial map according to the longitude and latitude information of each vertex;

and reconstructing each land parcel according to all vertexes corresponding to each polygon in the initial map, and determining the preset map.

In a second aspect, the present invention provides an automatic production device for open field vegetables, comprising:

an identification unit: the system comprises a field management system, a field management system and a field management system, wherein the field management system is used for identifying a current operation scene of a target plot and determining a target operation link matched with the current operation scene, and the target operation link is a soil preparation link, a ridging link, a transplanting link or a harvesting link;

a matching unit: the system comprises a target operation strategy database, a target planning path database and a target operation strategy database, wherein the target operation strategy database is used for matching a target operation strategy corresponding to the target operation link from a preset strategy library, and the target operation strategy comprises instructions for installing a target agricultural implement, instructions for setting target operation parameters, instructions for executing the target planning path and target operation actions;

a control unit: and the target operation control system is used for setting target operation parameters according to the target operation strategy and controlling the operation vehicle to execute target operation actions in a target plot according to a target planning path under the condition that the target agricultural implement is installed on the operation vehicle.

In a third aspect, the present invention further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any one of the above-mentioned methods for automatically producing outdoor vegetables.

In a fourth aspect, the present invention further provides a non-transitory computer readable storage medium, having a computer program stored thereon, which when executed by a processor, implements the method for automatically producing outdoor vegetables according to any one of the above methods.

The automatic production operation method, the device, the equipment and the medium for the open field vegetables can identify a target operation link matched with a current operation scene of a target plot, and adopt a proper target operation strategy according to the target operation link, so that under the condition that the target farm implements are installed on the operation vehicle, target operation parameters are set according to the target operation strategy, and the operation vehicle is controlled to execute target operation actions in the target plot according to a target planning path. The invention aims to realize continuous standard operation of the unmanned farm, solve the problems of unclear unmanned operation flow and inconsistent operation parameters in the prior art, provide a reference basis for an unmanned production operation method and an operation standard, further instruct an agricultural machine to autonomously perform production operation according to the current operation requirement under the condition of unmanned or less-person supervision, improve the crop production efficiency and reduce the labor cost.

Drawings

In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.

FIG. 1 is a schematic flow chart of an automated open field vegetable production method according to the present invention;

FIG. 2 is a schematic flow chart of a target job segment determination provided by the present invention;

FIG. 3 is a second schematic flow chart of the method for automatically producing outdoor vegetables according to the present invention;

fig. 4 is a third schematic flow chart of the automatic production method of outdoor vegetables according to the present invention;

FIG. 5 is a schematic signal processing diagram of the automated production method for outdoor vegetables according to the present invention;

FIG. 6 is a schematic structural diagram of an automatic production device for outdoor vegetables according to the present invention;

fig. 7 is a schematic structural diagram of an electronic device provided in the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

The unmanned tractor carries various types of agricultural equipment to carry out the operations of land tillage, ridging and transplanting, crop harvesting and the like, so that the cost of the machine can be saved, and the mechanized crop production and popularization are facilitated. However, the unmanned production process involves a plurality of continuous operation links, and agricultural equipment and agricultural parameters which need to be installed on the unmanned tractor and unmanned tractor path planning can be completely different under different operation links. For example, in the land preparation link, a land preparation machine is required to be mounted behind an unmanned tractor, and the operation path is not restricted except for the land obstacle and the operation efficiency requirement. However, in the ridging link, the unmanned tractor needs to be replaced with a ridging machine for carrying farm implements, the ridging in a plot needs to be considered in the planning process of the operation path of the unmanned tractor, and at present, a technical scheme which can integrate various operation links and realize autonomous operation according to actual operation requirements does not exist, in order to solve the technical problems, the invention provides an automatic production operation method, a device, equipment and a medium for outdoor vegetables, and fig. 1 is one of the flow diagrams of the automatic production operation method for outdoor vegetables provided by the invention, and provides an automatic production operation method for outdoor vegetables, which comprises the following steps:

identifying a current operation scene of a target land parcel, and determining a target operation link matched with the current operation scene, wherein the target operation link is a land preparation link, a ridging link, a transplanting link or a harvesting link;

In step 101, a current operation scene of a target plot is identified, and a target operation link matched with the current operation scene is determined, wherein the target operation link is a land preparation link, a ridging link, a transplanting link or a harvesting link, the target plot is a plot prepared for a working vehicle to perform crop production operation, and can be determined according to actual positioning of the working vehicle, or can be determined according to a received indication instruction, or can be determined by matching plot characteristics of the plot where the working vehicle is located through preset identification characteristics in a preset program.

Those skilled in the art understand that the crop in the present invention can be alternatively the open vegetable such as cabbage, pepper and radish, even the automatic production flow of the open vegetable such as cabbage, pepper and radish.

The current operation scene of the target land block can be soil characteristics, ground characteristics and crop maturity characteristics in the scene, and the current operation scene can be obtained by carrying out image recognition on the target land block to obtain a recognition image corresponding to the target land block, carrying out characteristic extraction according to a semantic segmentation model on the recognition image, or determining each scene characteristic in the current operation scene according to the proportion and distribution arrangement condition of three primary colors in each pixel point corresponding to the recognition image; the current operation scene of the target land parcel can also be directly obtained according to a receiving instruction, wherein the receiving instruction is an instruction for confirming the current operation scene issued after an observer observes the target land parcel.

The technical personnel in the field understand that the target operation link is a soil preparation link, a ridging link, a transplanting link or a harvesting link, namely, the invention can autonomously carry out corresponding operations of the soil preparation link, the ridging link, the transplanting link or the harvesting link of the agricultural machinery through the operation vehicle under the condition of no supervision of people or few people, thereby improving the operation efficiency.

Specifically, the land preparation link is land preparation, namely ploughing the land according to a land preparation machine on the operation vehicle so as to better provide a growing environment for crops; the ridging link can increase the thickness of a plowing layer, improve the ground temperature, increase the fertilizer and water retention capacity of soil, facilitate irrigation and drainage, and resist drought and waterlogging, and realizes ridging of a land block through a ridging machine on an operation vehicle; the transplanting link is to transplant the seedlings in the seedbed to a land, and the transplanting of the crops is mainly realized by a transplanter on an operation vehicle; the harvesting step is a process of collecting and transporting the crops from the field by adopting a harvester on an operation vehicle when the crops reach a mature standard after growing to a certain stage.

In step 102, matching a target operation strategy corresponding to the target operation link from a preset strategy library, wherein the target operation strategy comprises an instruction for installing a target agricultural implement, an instruction for setting target operation parameters, an instruction for executing a target planning path and a target operation action, the preset strategy library is preset and stores strategy libraries of corresponding relations of the operation link and the operation strategy in different land blocks, and the preset strategy library can be preset according to managers, and can also be used for determining different path plans according to different ridge lengths, different ridge surface widths, different ridge intervals, different ridge numbers, different tractor-ploughing channel positions and land block positions and the like in different land blocks, and determining different operation strategies according to different path plans in different land blocks.

The target operation strategy comprises the steps of indicating installation of a target agricultural implement, indicating setting of target operation parameters, indicating execution of a target planning path and target operation actions, indicating installation of the target agricultural implement, indicating setting of the target operation parameters, indicating execution of the target planning path and the target operation actions, displaying on a display screen on an operation vehicle, acquiring real-time working state information of the agricultural machine aiming at agricultural operation of the operation vehicle, wherein the real-time working state information comprises agricultural machine posture (turning and straight going), operation links (plowing and soil preparation, ridging, transplanting and harvesting) and operation track data information, and displaying on the operation vehicle.

Optionally, displaying that the target agricultural implement needs to be installed on the display screen, and under such a condition, if the working vehicle fails to install the target agricultural implement, always performing a picture prompt on the display screen; when the target agricultural implement is installed, jumping to another display screen, displaying a prompt for inputting the operation parameters in the other display screen, when the target operation parameters are input, displaying the target planning path and the target operation action, and if the target operation parameters are not input correctly, keeping the prompt for inputting the target operation parameters on the display screen.

In step 103, when the target agricultural implement is installed on the working vehicle, target working parameters are set according to the target working strategy, and the working vehicle is controlled to execute a target working action in a target land according to a target planned path. According to the target operation link, the target agricultural implement is selected and loaded on the operation vehicle, and the target operation parameters in the target operation strategy are input into the operation vehicle, so that the target planning path in the target operation strategy moves in the target plot and the target operation action is carried out.

The invention can respond to the requirement of an operation link under the current operation scene, acquire land parcel information and crop data agricultural machinery parameter information from a memory, and formulate an unmanned tractor operation strategy under the current operation link, wherein the operation strategy comprises land parcel planning, agricultural machinery parameter matching, operation path planning and target operation rule execution. According to the unmanned tractor, the operation rules in multiple operation links are formulated by collecting real-time crop production operation scene parameters, and the operation of the unmanned tractor is controlled according to the current operation scene and the operation rules, so that the problems that the crop production operation depends on manual operation and the operation specification is poor are solved, the unmanned tractor can independently perform crop planting operation according to the current operation requirement under the cooperation of unmanned driving, internet of things and a big data processing technology, the field crop production efficiency is improved, and the labor cost is reduced.

Optionally, the matching of the target operation policy corresponding to the target operation link from the preset policy library includes: matching a soil preparation operation strategy from a preset strategy library under the condition that the target operation link is a soil preparation link;

The invention selects the working parameters of agricultural implements meeting the working requirements according to the working links obtained by the acquisition, analysis and identification of the working scene data, and comprises agricultural implement type matching, agricultural implement parameter matching and working path planning, when the current working link obtained by the acquisition, analysis and identification of the working scene data is a land preparation link, the working vehicle matches the agricultural implement type to be a land preparation machine, the agricultural implement parameter matching of the working vehicle is the moving speed of an unmanned tractor, the working path planning of the working vehicle is calculated by a crop unmanned working production system integrated on the working vehicle according to a planned machine plough way and a working land block, and the working vehicle executes the following target working rules: the operation car goes to the operation starting point in planning operation orbit, and the operation car starts, start after the soil preparation machine descends, begin the soil preparation and accomplish the soil preparation, the soil preparation machine promotes, carries out the operation return stroke.

Optionally, the matching of the target operation policy corresponding to the target operation link from the preset policy library includes: matching a ridging operation strategy from a preset strategy library under the condition that the target operation link is a ridging link;

still be used for instructing the operation car to go to ridging planning route starting point after, control the ridger and descend, control the ridger and ridging, after the ridging of the corresponding ridge of starting point is accomplished, control the ridger and promote, according to ridging planning route goes to next ridge starting point and carries out the ridging, traverses ridging planning route, until accomplishing the ridging operation.

Optionally, in response to the requirement of an operation link in a current operation scene, the method acquires the land parcel information and crop data agricultural machinery parameter information from a memory, and formulates an unmanned tractor operation strategy in the current operation link, wherein the operation strategy comprises land parcel planning, agricultural machinery parameter matching, operation path planning and target operation execution rules, the land parcel planning calculates the ridge forming length, the ridge surface width, the ridge interval, the ridge number, the tractor plowing path position and the land parcel position according to the land parcel size and crop data in the ridge forming operation link, and the longest ridge length, the ridge surface width and the ridge interval which meet the requirements of the planted crop number, the crop planting density and the seedling spacing are obtained through data analysis and calculation. If the maximum length of the operation vehicle is determined under the condition of carrying agricultural implements and the minimum length required for turning around can also be determined, the tractor-ploughing road width and the tractor-ploughing road length can be determined according to the parameters, and then plot planning is realized.

Optionally, work as the operation scene data acquisition analysis discernment obtains current operation link for the ridging link, the operation car matches the agricultural implement type and is the ridger, the ridger parameter matches, including ridger operation broad width, operation car translation rate, the ridger operation broad width is first preset broad width, first preset broad width suits with ridge face width, operation car translation rate is the second speed, first speed in the soil preparation operation parameter can with the second speed is the same, also can with the second speed is different.

The operation path planning of the operation vehicle is that the operation path is planned by a plot planning result integrated on the operation vehicle, and the operation vehicle executes the following target operation rules according to the corresponding ridging planning path: the operation vehicle runs to a ridging planning path, namely a heading starting point in a planning operation track; starting the working vehicle; the ridger descends; starting ridging; finishing ridging of a ridge, and lifting the ridger; turning according to the planned operation path; if the operation is not finished, entering the starting point of the next ridge according to the planned operation path, and repeating the steps until the operation return stroke is executed after the ridge forming is finished.

Optionally, the matching of the target operation policy corresponding to the target operation link from the preset policy library includes: matching a transplanting operation strategy from a preset strategy library under the condition that the target operation link is a transplanting link;

and the transplanting machine is controlled to descend and transplant, after the transplanting of the ridge corresponding to the starting point is finished, the transplanting machine is controlled to lift, the transplanting is executed according to the transplanting planning path, and the transplanting planning path is traversed until the transplanting operation is finished.

Optionally, when the current operation link obtained by the operation scene data acquisition, analysis and identification is a transplanting link, the operation vehicle matches the type of farm implements to be a transplanter, the parameters of the transplanter are matched, and the parameters include the transplanting duckbill number of the transplanter, the duckbill distance of the transplanter and the transplanting depth, the operation track planning of the operation vehicle can be determined by a path planning system integrated on the operation vehicle according to ridge distribution in a plot, and can also be obtained from a preset strategy library, and then the operation path planning is performed according to a transplanting planning path in a transplanting operation strategy.

When the current operation link obtained by the operation scene data acquisition, analysis and identification is a transplanting link, the operation vehicle executes transplanting operation actions according to a transplanting planning path: the operation vehicle runs to the ground head starting point in the planned operation track; starting an agricultural machine; descending the transplanter; starting a transplanter; keeping the height of the press wheel for automatic transplanting; beginning to transplant; when the transplanting on the ridge is finished, the ridger is lifted; turning according to the transplanting planning path; if the operation is not finished, entering the next ridge according to the transplanting planning path, repeating the steps until the transplanting operation on all paths is finished, and executing the operation return stroke.

Optionally, the matching of the target operation policy corresponding to the target operation link from the preset policy library includes: matching a harvesting operation strategy from a preset strategy library under the condition that the target operation link is a harvesting link;

the system is also used for indicating and setting harvesting operation parameters, wherein the harvesting operation parameters comprise that the moving speed of an operation vehicle is a second speed, and the operation width of the harvester is a second preset width;

and the control system is also used for indicating the operation vehicle to drive to the starting point of the harvesting planning path, controlling the harvester to descend, controlling the harvester to harvest, after the harvesting of the ridge corresponding to the starting point is finished, controlling the harvester to lift, driving to the starting point of the next ridge according to the harvesting planning path to execute the harvesting, traversing the harvesting planning path until the harvesting operation is finished.

Optionally, when the operation scene data is collected, analyzed and identified to obtain a current operation link as a harvesting link, the harvesting link is matched with the type of farm implements to be a harvesting machine, the parameters of the harvesting machine are matched and include the operation width of the harvesting machine and the moving speed of the operation vehicle, the operation track planning of the operation vehicle can be determined by planning a harvesting planning path through the ridge position, the ridge number and the crop density, which are obtained by the operation scene data collection, analysis and identification, the current operation link is a harvesting link, the operation vehicle executes the operation collecting action according to the harvesting planning path, and the harvesting operation is executed as follows: the operation vehicle drives to the ground head starting point in the harvesting planning path track; starting an agricultural machine; starting a harvester; the harvester descends; keeping the height of the harvester for automatic harvesting; starting harvesting; when the current ridge is harvested, the harvester is lifted; turning according to the planned operation path; if the operation is not finished, entering the next ridge according to the harvesting planning path, repeating the steps until all harvesting work is finished, and executing the operation return stroke.

The invention realizes automatic crop planting, management, harvesting and the like by integrating various intelligent and communication technologies. At present, intelligent agricultural machinery for field grain crops can reach a highly autonomous state, but special crops such as crops and the like are still dependent on manpower due to the fact that planting management tasks are complex, and the levels of mechanization and automation are low for a long time. However, with the development of technologies such as internet of things, automatic driving, big data decision and the like, the invention can combine various types of crop operation flows with other automatic farm management activities, and convert the past large amount of labor operation work into supervision operation work through the comprehensive interconnection of agricultural technicians, agricultural machines and crops to construct an unmanned crop production and management system close to a full-automatic factory mode.

The automatic production operation method, the device, the equipment and the medium for the open field vegetables can identify a target operation link matched with a current operation scene of a target plot, and adopt a proper target operation strategy according to the target operation link, so that under the condition that the target farm implements are installed on the operation vehicle, target operation parameters are set according to the target operation strategy, and the operation vehicle is controlled to execute target operation actions in the target plot according to a target planning path. The invention aims to realize continuous standard operation of the unmanned farm, solve the problems of unclear unmanned operation flow and non-uniform operation parameters in the prior art, provide a reference basis for an unmanned production operation method and an operation standard, further realize independent production operation of an agricultural machine according to the current operation requirement under the condition of unmanned or few-person supervision, improve the crop production efficiency and reduce the labor cost.

Fig. 2 is a schematic flow chart of determining a target operation link, which identifies a current operation scene of a target parcel and determines a target operation link matching the current operation scene, according to the present invention, where the method includes:

and under the condition that the crop maturity in the current operation scene is identified to be greater than the preset maturity, determining the target operation link as a harvesting link.

In step 1011, a current operation scene in the target land parcel is obtained and identified, wherein the current operation scene is a land parcel image or a land parcel video, the present invention obtains and identifies the current operation scene in the target land parcel according to the target operation vehicle, the target operation vehicle can be understood as an agricultural machine to be operated in a real-time operation scene, and the current operation scene is the operation surrounding environment information of the current agricultural machine when the current agricultural machine is to operate in real time. The agricultural machine carried by the working vehicle adopts fixed working parameters when carrying out automatic operation, and the controlled working process is a process of automatically operating and controlling the working vehicle by a computer and executing a working target rule according to an expected track by the agricultural machine on the working vehicle.

Optionally, the work vehicle collects a current work scenario in a current work environment. The acquisition information corresponding to the current operation scene is determined according to the ambient environment information in the current plot environment acquired by the acquisition equipment. For example, the information acquisition devices may be cameras, GPS/beidou positioning devices, millimeter wave radar devices and infrared devices mounted on the unmanned tractor, and are respectively used for acquiring the current position of the agricultural machinery, the boundary coordinates of the land parcel, the positions of obstacles in the land parcel, and the sizes of the obstacles.

The invention uses computer vision technology to identify scene, the computer vision technology converts the shot object into image signal through the image shooting device, transmits to the special image processing system, obtains the form information of the shot object, converts into digital signal according to the information of pixel distribution, brightness, color, etc, and extracts the characteristic of the object by various operations to obtain the result of discrimination. The CCD camera in the image shooting device can record the object to be identified and explained in the form of an image, the CCD camera is a photoelectric sensor, optical signals reflecting the object and the background are recorded in the form of electric signals, an image collecting card inserted into the computer can convert the electric signals collected by the camera into digital signals, and the image is digitized, so that the computer can carry out various necessary processing on the digital signals, and optionally, an illumination system is adopted to provide proper illumination for image collection, thereby being beneficial to the processing and analysis of the image.

In the invention, the operation vehicle acquires a real-time current operation scene according to a plurality of information acquisition devices, performs time-sharing identification according to a plurality of information in the current operation scene, and determines the characteristic information of the real-time operation scene. For example: when the plurality of information acquisition devices are a plurality of cameras, the method acquires the plot images or the plot videos corresponding to the real-time operation scene where the operation vehicle is located, the type of the planted crops, the number of the planted crops, the planting density of the crops, the height of the seedlings, the planting distance of the seedlings, the height of the mature crops, the planting distance of the mature crops and the like, analyzes and identifies the acquired data to obtain the characteristic information of the real-time operation scene, and determines the operation link according to the characteristic information of the real-time operation scene.

In step 1012, under the conditions that soil air-drying, soil moisture loss, a ground weed rate larger than a preset value, uneven land or no ridge or crop exists on the current ground in the current operation scene, determining the target operation link as a soil preparation link, wherein the soil air-drying is a condition of dry soil, and soil preparation is needed at the moment to eliminate the condition of air-drying soil; soil moisture loss refers to the process of soil moisture loss in farmland, and soil preparation is needed at the moment to increase soil moisture; the uneven ground means that the ground has obvious height difference at different positions, and soil preparation is needed at the moment to level the ground; if the weed rate on the ground is greater than a preset value, the weed rate on the ground is large, and soil preparation is needed to eliminate weeds; under the condition that the current ground is free of ridges and crops, in order to prepare for subsequent ridging and transplanting, soil preparation operation needs to be carried out on the current ground.

Optionally, the soil volume water content can be detected by a multispectral camera, whether soil air-drying and soil moisture loss exist in the current operation scene or not is identified, the soil moisture content detection method needs to detect four spectral channels of a green wave band (500-600 nm), a red wave band (600-700 nm), a red wave band (700-730 nm) and a near infrared wave band (700 nm-1.3 um), the same target is shot through a plurality of lenses provided with different optical filters, information radiated or reflected by the same target on different narrow spectral bands is received by the lenses simultaneously, pictures of several different spectral bands of the target can be obtained, and farmland soil moisture detection actual measurement is carried out.

Optionally, the method adopts a computer image processing technology to analyze the characteristic quantity of the weeds in the field of the crop seedling stage, identifies the weeds in the field, determines the position and the growth condition of the weeds, adopts a double-peak method to filter out a soil background, identifies the weeds according to the projection area, the leaf length and the leaf width, and determines the weed density according to the projection area of the weeds, thereby effectively identifying the slender monocotyledon weeds in the field of the corn seedling stage.

In step 1013, when it is recognized that the ground soil in the current operation scene is plowed, it is determined that the target operation link is a ridging link, where the plowed ground soil refers to a ground condition after ground preparation processing has been performed on the ground, and at this time, it is determined that the target operation link is a ridging link.

In step 1014, when it is recognized that the ground of the current operation scene is ridged, it is determined that the target operation link is a transplanting link, in an optional embodiment, after the operation vehicle performs step 1012, it recognizes the target land, and at this time, it performs a soil preparation link, and then the target land exhibits a situation that the ground soil is ploughed, and then it proceeds to step 1013, it proceeds to a ridging link, after the ridging link is performed, the ground of the current operation scene exhibits a ridged situation, and at this time, it recognizes the target land again, and then it determines that the target operation link is a transplanting link, and thus it implements unmanned automated production operation.

In step 1015, when it is identified that the crop maturity in the current operation scene is greater than the preset maturity, the target operation link is determined as a harvesting link, the present invention can first determine an interested area, extract features according to a semantic segmentation model, obtain all crops in the current operation scene, determine the maturity of the crops according to the color, size, shape, etc. of the crops, compare with the preset maturity, and finally determine whether to harvest.

Fig. 3 is a second schematic flow chart of the method for automatically producing outdoor vegetables according to the present invention, which further includes, before identifying the current operation scene of the target plot:

acquiring positioning information of an operation vehicle;

In step 201, the present invention obtains the location information of the place where the working vehicle is located according to the location device arranged on the working vehicle, and the present invention can realize the obtaining of the location information of the working vehicle by collecting the longitude and latitude information of the working vehicle through the global positioning system GPS or the beidou satellite navigation system BDS.

In step 202, in a preset map, a land parcel where the current position of the operation vehicle is located is determined according to the positioning information of the operation vehicle, and the land parcel where the current position of the operation vehicle is located is determined as the target land parcel.

The invention can realize the full automation of the unmanned vehicle in the production operation, not only can realize the continuous operation of each operation link in a target land, but also can continue the continuous operation of each operation link when the unmanned vehicle arrives at another land after the operation of the target land is finished, thereby improving the production efficiency and reducing the manual management cost.

Fig. 4 is a third schematic flow chart of the automatic open field vegetable production method provided by the present invention, before obtaining the positioning information of the working vehicle, the method includes:

In step 301, the edge track graph of each land parcel is converted into a polygon, and longitude and latitude information of all vertexes corresponding to each polygon is acquired.

After determining the edge track graph of each land, converting the edge track graph of each land into a regular or irregular polygon, determining the vertex of the polygon of each land through a Global Positioning System (GPS) or a Beidou satellite navigation system (BDS), and acquiring the longitude and latitude of each vertex.

In step 302, mapping all vertices corresponding to each polygon to an initial map according to the longitude and latitude information of each vertex, in an optional embodiment, determining geometric coordinates of a parcel boundary by using a gaussian projection algorithm, performing geometric modeling in an unmanned tractor path planning system, taking the first vertex coordinate as an origin, and displaying the other vertices in a two-dimensional plane rectangular coordinate system according to the position relationship between the vertices and the origin.

In step 303, after the mapping of each vertex in all the plots in the initial map is completed, reconstructing each plot according to all the vertices corresponding to each polygon in the initial map, that is, connecting all the vertices of each polygon, determining the polygons formed after the connection is completed as the plots, and determining the preset map after determining the construction of all the plots in the initial map.

The method and the device can realize the construction of the preset map according to the positioning of the operation vehicle so as to determine the land parcel where the operation vehicle is located in real time, and can correct the preset map according to the movement track of the operation vehicle in the subsequent operation process, thereby realizing the production operation of the operation vehicle in the process of continuously updating the preset map.

Fig. 5 is a signal processing schematic diagram of an automatic open field vegetable production operation method provided by the invention, and the automatic open field vegetable production operation method based on unmanned crops further provides a production operation system for realizing signal processing, and the production operation system comprises an operation scene acquisition and identification module, an operation strategy formulation module and an information display module, wherein the information module is used for acquiring and displaying operation real-time data so as to display operation state information of agricultural machinery and a real-time operation track of the agricultural machinery.

The operation scene acquisition and identification module can acquire operation data and analyze the operation data aiming at a real-time operation scene of the operation vehicle, wherein the operation data acquisition comprises the acquisition of operation land block parameters, crop data and agricultural implement parameters; the operation land parameter comprises a land obstacle distribution position, a land size and a land boundary coordinate; the crop data comprises the type of the crops planted in the land, the quantity of the crops, the planting density of the crops, the height of the seedlings, the planting distance of the seedlings, the height of the mature crops and the planting distance of the mature crops; the farm implement data comprises the speed gear of the unmanned tractor, the operation width of the soil preparation machine, the ridge forming machine, the transplanter and the harvester and the transplanting spacing gear of the transplanter; the job scene data analysis comprises identifying based on job links; and storing the operating land parameter, the crop data and the farm implement parameter into a memory.

Optionally, the operation policy making module may match an operation policy corresponding to an operation link from a preset policy library according to different operation links, which may refer to step 102, and is not described herein again.

Optionally, the information display module can acquire real-time working state information of the agricultural machine for the operation of the unmanned agricultural machine, wherein the real-time working state information comprises attitude (turning and straight walking), operation links (plowing and soil preparation, ridging, transplanting and harvesting) and operation track data information of the agricultural machine.

Optionally, the agricultural machinery real-time working state information acquisition module is further included and is used for acquiring the agricultural machinery real-time working state information in the operation process of the unmanned operation vehicle, wherein the agricultural machinery real-time working state information comprises agricultural machinery posture information, operation link information and running track data information, the agricultural machinery posture information comprises turning or straight going, and the operation link information comprises a soil preparation link, a ridging link, a transplanting link and a harvesting link.

Fig. 6 is a schematic structural diagram of an automatic production device for outdoor vegetables according to the present invention, which discloses an automatic production device for outdoor vegetables, comprising an identification unit 1: the method comprises a step 101 for identifying a current operation scene of a target land parcel and determining a target operation link matched with the current operation scene, wherein the target operation link is a land preparation link, a ridging link, a transplanting link or a harvesting link, and the working principle of the identification unit 1 can refer to the step, and is not described herein again.

The automatic production operation device for the open field vegetables further comprises a matching unit 2: the target operation strategy is used for matching the target operation strategy corresponding to the target operation link from a preset strategy library, where the target operation strategy includes an instruction to install a target agricultural implement, an instruction to set target operation parameters, an instruction to execute a target planning path, and a target operation action, and the working principle of the matching unit 2 may refer to the foregoing step 102, which is not described herein again.

The automatic production operation device for the open field vegetables further comprises a control unit 3: and when the target agricultural implement is installed on the working vehicle, setting target working parameters according to the target working strategy, and controlling the working vehicle to execute a target working action in a target land according to a target planned path, where the working principle of the control unit 3 may refer to step 103, which is not described herein again.

Fig. 7 is a schematic structural diagram of an electronic device provided in the present invention. As shown in fig. 7, the electronic device may include: a processor (processor) 710, a communication Interface (Communications Interface) 720, a memory (memory) 730, and a communication bus 740, wherein the processor 710, the communication Interface 720, and the memory 730 communicate with each other via the communication bus 740. Processor 710 may call logic instructions in memory 730 to perform a method of automated production of open field vegetables, the method comprising: identifying a current operation scene of a target plot, and determining a target operation link matched with the current operation scene, wherein the target operation link is a soil preparation link, a ridging link, a transplanting link or a harvesting link; matching a target operation strategy corresponding to the target operation link from a preset strategy library, wherein the target operation strategy comprises instructions for installing a target agricultural implement, instructions for setting target operation parameters, instructions for executing a target planning path and target operation actions; and under the condition that the target agricultural implement is installed on the working vehicle, setting target working parameters according to the target working strategy, and controlling the working vehicle to execute target working actions in a target plot according to a target planned path.

In addition, the logic instructions in the memory 730 can be implemented in the form of software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

In another aspect, the present invention also provides a computer program product, the computer program product includes a computer program, the computer program can be stored on a non-transitory computer readable storage medium, when the computer program is executed by a processor, the computer can execute a method for automatically producing outdoor vegetables, the method includes: identifying a current operation scene of a target plot, and determining a target operation link matched with the current operation scene, wherein the target operation link is a soil preparation link, a ridging link, a transplanting link or a harvesting link; matching a target operation strategy corresponding to the target operation link from a preset strategy library, wherein the target operation strategy comprises instructions for installing a target agricultural implement, instructions for setting target operation parameters, instructions for executing a target planning path and target operation actions; and under the condition that the target agricultural implement is installed on the working vehicle, setting target working parameters according to the target working strategy, and controlling the working vehicle to execute target working actions in a target plot according to a target planned path.

In still another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, the computer program being implemented by a processor to perform the method for automatically producing outdoor vegetables provided by the above methods, the method comprising: identifying a current operation scene of a target plot, and determining a target operation link matched with the current operation scene, wherein the target operation link is a soil preparation link, a ridging link, a transplanting link or a harvesting link; matching a target operation strategy corresponding to the target operation link from a preset strategy library, wherein the target operation strategy comprises instructions for installing a target agricultural implement, instructions for setting target operation parameters, instructions for executing a target planning path and target operation actions; and under the condition that the target agricultural implement is installed on the working vehicle, setting target working parameters according to the target working strategy, and controlling the working vehicle to execute target working actions in a target plot according to a target planned path.

The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.

Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment may be implemented by software plus a necessary general hardware platform, and may also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.

Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims

1. An automatic production operation method for open field vegetables is characterized by comprising the following steps:

2. The automatic production operation method of outdoor vegetables according to claim 1, wherein said identifying a current operation scene of a target plot and determining a target operation link matching the current operation scene comprises:

determining the target operation link as a soil preparation link under the conditions that soil is air-dried, soil moisture is lost, the ground weed rate is larger than a preset value, the land is uneven or the current ground has no ridges or crops in the current operation scene; or

Determining the target operation link as a ridging link under the condition that the ground soil in the current operation scene is identified to be ploughed; or

Determining the target operation link as a transplanting link under the condition that the ridging of the ground of the current operation scene is recognized; or

3. The automatic production operation method of outdoor vegetables according to claim 1, wherein the step of matching out a target operation strategy corresponding to the target operation link from a preset strategy library comprises: matching a soil preparation operation strategy from a preset strategy library under the condition that the target operation link is a soil preparation link;

the land preparation control system is also used for indicating and setting land preparation operation parameters, wherein the land preparation operation parameters comprise that the moving speed of the operation vehicle is a first speed;

4. The method of claim 1, wherein the matching of the target operation strategy corresponding to the target operation link from the predetermined strategy library comprises: matching a ridging operation strategy from a preset strategy library under the condition that the target operation link is a ridging link;

5. The method of claim 1, wherein the matching of the target operation strategy corresponding to the target operation link from the predetermined strategy library comprises: matching a transplanting operation strategy from a preset strategy library under the condition that the target operation link is a transplanting link;

the transplanting operation strategy is used for indicating that the transplanting machine is installed on the operation vehicle;

6. The method of claim 1, wherein the matching of the target operation strategy corresponding to the target operation link from the predetermined strategy library comprises: matching a harvesting operation strategy from a preset strategy library under the condition that the target operation link is a harvesting link;

7. The automated open field vegetable production method according to claim 1, further comprising, before identifying the current operation scene of the target plot:

acquiring positioning information of the operation vehicle;

8. The automatic production operation method of outdoor vegetables according to claim 7, before obtaining the positioning information of the operation vehicle, comprising:

converting the edge track graph of each land parcel into a polygon, and collecting longitude and latitude information of all vertexes corresponding to each polygon;

9. An open field vegetables automated production operation device which characterized in that includes:

an identification unit: the system comprises a land preparation link, a ridging link, a transplanting link or a harvesting link, wherein the land preparation link, the ridging link, the transplanting link or the harvesting link is used for identifying a current operation scene of a target land parcel and determining a target operation link matched with the current operation scene;

a control unit: and the target operation control system is used for setting target operation parameters according to the target operation strategy and controlling the operation vehicle to execute target operation actions in a target plot according to a target planned path under the condition that the target agricultural implement is installed on the operation vehicle.

10. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the method of automated production of outdoor vegetables according to any one of claims 1-8.

11. A non-transitory computer readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method of automatically producing outdoor vegetables according to any one of claims 1 to 8.