CN114240921A

Movatterモバイル変換

Info

Publication number: CN114240921A
Application number: CN202111599488.0A
Authority: CN
Inventors: 罗新勇
Original assignee: Guangzhou Xaircraft Technology Co Ltd
Current assignee: Guangzhou Xaircraft Technology Co Ltd
Priority date: 2021-12-24
Filing date: 2021-12-24
Publication date: 2022-03-25

Abstract

The application provides a region inspection method, a region inspection device, electronic equipment, a region inspection system and a readable storage medium, wherein the method comprises the following steps: determining boundary information of an area to be inspected according to image information of the area to be inspected, wherein the image information comprises: the high-precision map or the picture containing the region to be inspected; generating a target inspection route which travels by taking the boundary of the area to be inspected as a reference according to the boundary information of the area to be inspected; obtaining a routing inspection result obtained by performing routing inspection on the target routing inspection route, wherein the routing inspection result comprises: and the picture comprises the crop root and/or the water quantity of the area to be inspected. The method can acquire a large number of uniform images which are along the boundary of the area to be inspected and contain the crop roots and/or the water quantity, and further the accuracy of the state information of the area obtained based on the image analysis is greatly improved.

Description

Area inspection method, device, electronic equipment, system and readable storage medium

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to a method, an apparatus, an electronic device, a system, and a readable storage medium for area inspection.

Background

Along with the continuous development of unmanned aerial vehicle technology, unmanned aerial vehicle is more and more extensive in the application in various fields. For example, scientific management of the farmland can be performed by means of unmanned aerial vehicles. Taking rice planting as an example, in the planting process of rice, the inspection of a rice field can be completed by means of an unmanned aerial vehicle. Specifically, can be patrolled and examined in the flight of paddy field top by unmanned aerial vehicle, at the image of patrolling and examining the in-process and shooting the paddy field, and then can be through carrying out the analysis with the water yield, plant diseases and insect pests, weeds and the state information such as stem tiller number that determine the paddy field to the image. However, when the rice grows to a leaf age and tillers are luxuriant, the roots of the rice can be shielded, the unmanned aerial vehicle cannot shoot images of the root areas of the rice, and the state information related to the roots of the rice, such as the water amount of the rice field, plant diseases and insect pests, cannot be analyzed through the images.

In the prior art, in order to solve the above problems, a robot arm camera may be fixedly installed at the edge of the rice field to shoot the root of the rice in a short distance, so as to obtain an image of the root region containing the rice.

However, the uniformity of data acquisition cannot be guaranteed by using the prior art, and the accuracy of the state information of the rice field analyzed by using the image may be affected.

Disclosure of Invention

An object of the application is to provide a method, a device, an electronic device, a system and a readable storage medium for region inspection aiming at the defects in the prior art, so as to solve the problem that the uniformity of data acquisition cannot be guaranteed in the prior art, and then the accuracy of the state information of the rice field analyzed by using an image is possibly influenced.

In order to achieve the above purpose, the technical solutions adopted in the embodiments of the present application are as follows:

in a first aspect, an embodiment of the present application provides a method for area inspection, including:

determining boundary information of an area to be inspected according to image information of the area to be inspected, wherein the image information comprises: the high-precision map or the picture containing the region to be inspected;

generating a target inspection route which travels by taking the boundary of the area to be inspected as a reference according to the boundary information of the area to be inspected;

obtaining a routing inspection result obtained by performing routing inspection on the target routing inspection route, wherein the routing inspection result comprises: and the picture comprises the crop root and/or the water quantity of the area to be inspected.

As a possible implementation manner, the number of the areas to be inspected is multiple;

the generating of the target inspection route which travels by taking the boundary of the area to be inspected as a reference according to the boundary information of the area to be inspected includes:

determining a combined routing inspection route of a plurality of areas to be inspected according to boundary information of the plurality of areas to be inspected with incidence relation, and taking the combined routing inspection route as the target routing inspection route;

the combined inspection route is a route which is used for uniformly inspecting the plurality of areas to be inspected through one-time inspection task.

As a possible implementation manner, the plurality of areas to be inspected having an association relationship includes: a plurality of areas to be inspected having a common boundary;

the method for determining the combined routing inspection route of the plurality of areas to be inspected according to the boundary information of the plurality of areas to be inspected with the incidence relation comprises the following steps:

determining a common boundary among the plurality of areas to be inspected;

and determining the joint routing inspection routes of the plurality of areas to be inspected based on the common boundary and the unique boundary except the common boundary in the boundary information of each area to be inspected.

As a possible implementation manner, the plurality of areas to be inspected having an association relationship includes: a first area and at least one second area within a home range of the first area;

determining a routing inspection route of the first area based on the boundary information of the first area;

and taking the routing inspection route of the first area as a combined routing inspection route of the first area and each second area.

As a possible implementation manner, the determining a joint routing inspection route of a plurality of areas to be inspected according to boundary information of the plurality of areas to be inspected having an association relationship includes:

responding to the operation that a user selects a plurality of areas to be inspected, and determining whether the areas to be inspected have an association relation;

if so, determining a joint routing inspection route of the multiple regions to be inspected according to the boundary information of the multiple regions to be inspected with the incidence relation.

As a possible implementation manner, the generating a target inspection route traveling with reference to the boundary of the area to be inspected according to the boundary information of the area to be inspected includes:

acquiring a plurality of sampling points positioned on the boundary of the area to be inspected according to the boundary information of the area to be inspected;

and generating a target routing inspection route which is routed to the plurality of sampling points according to the position information of the plurality of sampling points.

As a possible implementation manner, the obtaining of the inspection result obtained by performing the inspection with the target inspection route includes:

and acquiring a routing inspection result of the area to be inspected, which is obtained by performing routing inspection by using the target routing inspection route and routing inspection parameters corresponding to the target routing inspection route.

As a possible implementation manner, before obtaining the inspection result of the area to be inspected, which is obtained by performing inspection with the target inspection route and the inspection parameter corresponding to the target inspection route, the method further includes:

and determining the inspection parameters corresponding to the target inspection route according to the types of the crops planted in the area to be inspected.

and determining routing inspection parameters corresponding to the target routing inspection route according to the track shape of the target routing inspection route.

As a possible implementation manner, the determining, according to the image information of the area to be inspected, the boundary information of the area to be inspected includes:

acquiring a high-precision map of the area to be inspected;

and determining the boundary information of the area to be inspected according to the high-precision map of the area to be inspected.

As a possible implementation manner, the acquiring a high-precision map of the area to be inspected includes:

if the high-precision map of the area to be inspected does not exist, determining an aerial route of the area in which the area to be inspected is located according to a satellite map;

carrying out aerial photography according to the aerial photography route to obtain an aerial photography picture of the area where the area to be inspected is located;

and splicing the aerial pictures to obtain the high-precision map of the area to be patrolled and examined.

and inputting the picture containing the area to be inspected into a boundary identification model obtained by pre-training to obtain the boundary information of the area to be inspected.

As a possible implementation manner, the area to be inspected includes: a farmland to be patrolled;

after obtaining the inspection result obtained by performing inspection with the target inspection route, the method further comprises the following steps:

and carrying out image recognition on the picture containing the crop root and the water quantity of the farmland to be patrolled and examined, and determining the water quantity distribution information and the pest and disease damage information of the farmland to be patrolled and examined.

As a possible implementation manner, the image recognition is performed on the picture containing the root and the water amount of the farmland to be patrolled and examined, and the water amount distribution information and the pest and disease information of the farmland to be patrolled and examined are determined, including:

performing image recognition on the picture containing the crop roots and the water quantity of the farmland to be inspected to obtain reference water quantity distribution information and reference pest and disease damage information;

according to the reference water distribution information and the reference pest information, and the attribute information of the to-be-patrolled farmland, the pre-trained region assessment model is used to obtain the water distribution information and the pest information of the to-be-patrolled farmland, wherein the attribute information of the to-be-patrolled farmland comprises: area and/or shape.

In a second aspect, an embodiment of the present application provides an area inspection device, including:

the determining module is used for determining the boundary information of the area to be patrolled and examined according to the image information of the area to be patrolled and examined, wherein the image information comprises: the high-precision map or the picture containing the region to be inspected;

the generating module is used for generating a target inspection route which travels by taking the boundary of the area to be inspected as a reference according to the boundary information of the area to be inspected;

the acquisition module is used for acquiring an inspection result obtained by performing inspection on the target inspection route, and the inspection result comprises: and the picture comprises the crop root and/or the water quantity of the area to be inspected.

the generation module is specifically configured to:

determining a common boundary among the plurality of areas to be inspected;

the generation module is specifically configured to:

As a possible implementation manner, the generating module is specifically configured to:

As a possible implementation manner, the obtaining module is specifically configured to:

As a possible implementation manner, the determining module is further configured to:

As a possible implementation manner, the determining module is specifically configured to:

acquiring a high-precision map of the area to be inspected;

the determination module is further to:

In a third aspect, an embodiment of the present application provides an electronic device, including: a processor and a memory, the memory storing machine readable instructions executable by the processor, the processor executing the machine readable instructions when the electronic device is running to perform the steps of the area inspection method according to the first aspect.

In a fourth aspect, an embodiment of the present application provides an inspection system, including: the electronic device and the unmanned aerial vehicle in the third aspect are in communication connection with the unmanned aerial vehicle, the electronic device sends the generated target inspection route to the unmanned aerial vehicle, and the unmanned aerial vehicle is used for executing inspection according to the target inspection route and sending an inspection result to the electronic device.

In a fifth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the steps of the area inspection method according to the first aspect.

The area inspection method, the area inspection device, the electronic equipment, the area inspection system and the readable storage medium can determine the boundary information of the area to be inspected based on the image information of the area to be inspected, and further can generate a target inspection route which advances by taking the boundary of the area to be inspected as a reference according to the boundary information. Because the target routing inspection route advances by taking the boundary of the area to be inspected as a reference, pictures on the boundary of the area to be inspected can be uniformly collected. Because the condition that the root of the crop or the bottom of the area is not shielded on the boundary exists, the picture acquired by performing the inspection according to the target inspection route can contain the information of the root of the crop and/or the water quantity of the area to be inspected. Consequently, can gather along waiting to patrol and examine regional border a large amount of, even and contain the image of crop root and/or water yield through this embodiment, and then make the accuracy that obtains regional status information based on these image analysis obtain greatly promoting, simultaneously, need not to increase extra inspection device, can also greatly reduce the cost that the region was patrolled and examined.

In addition, to a plurality of regions of patrolling and examining of treating that have the incidence relation, can be unified by unmanned aerial vehicle in a task of patrolling and examining according to jointly patrolling and examining the route and marcing to can reduce or avoid the repetition of route when guaranteeing the coverage of patrolling and examining of the regional border of each treating, reduce redundant information, promoted and patrolled and examined efficiency.

In addition, in the scene that the border of waiting to patrol and examine the regional border is comparatively complicated irregular border, through acquireing above-mentioned a plurality of sampling points to connect above-mentioned a plurality of sampling points, can generate the orbit of patrolling and examining that the orbit is comparatively simple simultaneously to the coverage that waits to patrol and examine the regional border and satisfy the requirement, thereby can guarantee not to influence and patrol and examine the result accuracy, simultaneously, can reduce the complexity of patrolling and examining again, promote and patrol and examine efficiency.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.

FIG. 1 is a schematic diagram of an exemplary scenario according to an embodiment of the present application;

fig. 2 is a schematic flow chart of a region inspection method provided in the embodiment of the present application;

FIG. 3 is an exemplary diagram of generating a joint inspection route for a plurality of areas to be inspected having a common boundary;

FIG. 4 is an exemplary diagram of generating a joint inspection route for a plurality of areas to be inspected having an affiliation;

fig. 5 is another schematic flow chart of the area inspection method according to the embodiment of the present application;

FIG. 6 is an exemplary diagram of generating a target routing inspection path by obtaining sampling points;

fig. 7 is another schematic flow chart of the area inspection method according to the embodiment of the present application;

fig. 8 is a block diagram of an area inspection device according to an embodiment of the present disclosure;

fig. 9 is a schematic structural diagram of anelectronic device 90 according to an embodiment of the present application.

Detailed Description

In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it should be understood that the drawings in the present application are for illustrative and descriptive purposes only and are not used to limit the scope of protection of the present application. Additionally, it should be understood that the schematic drawings are not necessarily drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow diagrams may be performed out of order, and steps without logical context may be performed in reverse order or simultaneously. One skilled in the art, under the guidance of this application, may add one or more other operations to, or remove one or more operations from, the flowchart.

In addition, the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.

In order to enable those skilled in the art to use the present disclosure, the following embodiments are given in conjunction with a specific application scenario "unmanned aerial vehicle performs farm inspection". It will be apparent to those skilled in the art that the general principles defined herein may be applied to other embodiments and applications without departing from the spirit and scope of the application. Although the present application is described primarily in the context of field inspection by drones, it should be understood that this is merely one exemplary embodiment.

It should be noted that in the embodiments of the present application, the term "comprising" is used to indicate the presence of the features stated hereinafter, but does not exclude the addition of further features.

In the prior art, a robot arm camera is fixedly erected at the edge of a rice field to shoot the roots of rice in a short distance, so that the problem that the roots of rice cannot be shot because the roots of rice are shielded when the rice grows to have luxuriant leaf age tillers is solved. However, for cost reasons, it is necessary to mount the robot arm cameras at long distance intervals. Each robot arm camera can only capture images within a certain range around itself. Therefore, in the existing method, only the image of the rice root of a small part of the rice field can be shot. Because the rice occupies a small proportion in the whole rice field, the uniformity of data acquisition cannot be guaranteed by the mode of the prior art, and further, the actual state of the rice field may not be reflected by the state information of the rice field analyzed by the acquired images, and the accuracy of the state information of the rice field analyzed by the images may be influenced.

This application embodiment is based on above-mentioned problem, treat the regional border of patrolling and examining through the discernment, and the planning is with the route of patrolling and examining of treating the regional border of patrolling and examining as the benchmark, when making to patrol and examine according to this route execution of patrolling and examining, can gather along the image of farmland border in a large number, evenly just containing the crop root and/or the farmland water yield, and then make the accuracy that obtains regional status information based on these image analysis obtain greatly promoting, simultaneously, need not to increase extra inspection device, can also greatly reduce the cost that the region was patrolled and examined.

The method of the embodiment of the application can be applied to a scene of regional inspection, and the region can be a farmland, such as a rice field, or the region can also be a forest region. The embodiment of the application does not limit the specific form of the area, and the problem that the root of the crop is shielded due to flourishing growth of the crop in the area can be solved by adopting the method of the embodiment of the application.

Fig. 1 is an exemplary scenario diagram of an embodiment of the present application, and as shown in fig. 1, the method may relate to a drone and an electronic device. This unmanned aerial vehicle and electronic equipment can constitute the system of patrolling and examining. In this system of patrolling and examining, unmanned aerial vehicle and electronic equipment can establish communication connection. The electronic device may be a terminal, a server, or other devices with computing processing capability. The electronic equipment can obtain a target inspection route of an area to be inspected through executing the steps of the method, the electronic equipment can send the target inspection route to the unmanned aerial vehicle, and then the unmanned aerial vehicle performs inspection according to the target inspection route. In the process of patrolling and examining, unmanned aerial vehicle can control built-in shooting part, and the picture that contains crop root and/or water yield in waiting to patrol and examine the region is gathered as the result of patrolling and examining to camera for example. The unmanned aerial vehicle can further send the inspection result to the electronic equipment or other equipment responsible for analysis and processing to perform analysis and processing. Taking the electronic device as an example for analysis, after the electronic device analyzes and processes the inspection result, information such as pest and disease distribution and/or water distribution of the area to be inspected can be obtained.

It should be noted that, for practical purposes, other devices with an aerial photography function besides the unmanned aerial vehicle may be used to perform the above-mentioned inspection. This is not a particular limitation of the present application.

As another exemplary scenario, the processing chip in the unmanned aerial vehicle may execute the method steps of the present application to obtain an inspection route of the area to be inspected, and control the unmanned aerial vehicle to perform inspection according to the inspection route. The unmanned aerial vehicle can send the picture of patrolling and examining the in-process and gathering for the equipment that is responsible for carrying out analysis processes carries out analysis processes to information such as the plant diseases and insect pests distribution and/or the water distribution that obtain waiting to patrol and examine the region.

Fig. 2 is a schematic flow diagram of the area inspection method provided in the embodiment of the present application, and an execution main body of the method may be the electronic device or the unmanned aerial vehicle. For convenience of description, the following embodiments are described taking an execution subject as an example of an electronic device. As shown in fig. 2, the method includes:

s201, determining the boundary information of the area to be inspected according to the image information of the area to be inspected, wherein the image information comprises: and (4) high-precision maps or pictures containing the to-be-patrolled areas.

Optionally, the electronic device may obtain and store the image information of the to-be-inspected area in advance, and the image information may be generated by an image of the to-be-inspected area shot by the electronic device using the unmanned aerial vehicle, or may be generated by other processing devices from which the electronic device directly obtains the image information.

In one case, the image information may be a high-precision map including the area to be inspected. The high-precision Map may be, for example, a Digital Ortho Map (DOM).

Under another kind of circumstances, above-mentioned image information can be for unmanned aerial vehicle to the above-mentioned picture that contains the above-mentioned region of patrolling and examining of waiting to patrol and examine the region and obtaining. The picture contains the boundary of the area to be inspected and the crops located within the boundary.

Optionally, the electronic device may identify the image information, so as to determine the boundary information of the area to be inspected. For example, the boundary information of the area to be inspected may be represented by coordinate positions of all coordinate points constituting the boundary.

As another mode, the electronic device may further determine the boundary information of the area to be inspected by Real Time Kinematic (RTK) measurement.

Alternatively, this step may be performed based on a user's trigger instruction. Illustratively, the electronic equipment displays images of one or more farmlands on an interface of the electronic equipment, a user frames the farmlands to be inspected in a mouse frame selection mode or a touch sliding frame selection mode, and the like, correspondingly, the electronic equipment can determine boundary information of the farmlands to be inspected by using the method of the step, and the boundary information of the farmlands to be inspected is displayed on the interface. The user can finely adjust the boundary of the farmland identified by the electronic equipment on the basis, and the electronic equipment can further take the boundary after the fine adjustment by the user as the boundary of the area to be patrolled and examined and record the boundary information of the boundary.

And S202, generating a target routing inspection route which travels by taking the boundary of the area to be inspected as a reference according to the boundary information of the area to be inspected.

Optionally, the target routing inspection route is advanced based on a boundary of an area to be inspected, and specifically may include: the target inspection route is a route formed according to the track of the boundary of the area to be inspected, or the target inspection route is a route formed by simplifying or adjusting the track of the boundary of the area to be inspected on the basis of the boundary of the area to be inspected, and the overlapping degree of the formed target inspection route and the track of the boundary of the area to be inspected meets the preset requirement.

After determining the boundary information of the area to be inspected, the electronic device may obtain the target inspection route based on the boundary information, where the target inspection route travels based on the boundary of the area to be inspected. A method of specifically generating the target patrol route will be described in detail in the following embodiments.

Optionally, the user may perform fine adjustment on the target inspection route generated by the electronic device, and the fine-adjusted target inspection route is used as the inspection route when performing inspection in the following steps.

S203, obtaining a routing inspection result obtained by performing routing inspection on the target routing inspection route, wherein the routing inspection result comprises: the picture containing the root and/or the water quantity of the crops in the area to be inspected.

Optionally, electronic equipment can patrol and examine the route with the above-mentioned target that generates and send for unmanned aerial vehicle, patrol and examine according to the route execution of patrolling and examining of above-mentioned target by unmanned aerial vehicle to evenly gather and wait to patrol and examine the picture on the regional boundary, unmanned aerial vehicle can send the picture to electronic equipment in real time or in batches. Because the condition that the root of the crop or the bottom of the area is not shielded on the boundary exists, the picture acquired by performing the inspection according to the target inspection route can contain the information of the root of the crop and/or the water quantity of the area to be inspected. And then can utilize these pictures accurate analysis to go out the region of waiting to patrol and examine, for example wait to patrol and examine disease and pest information, water distribution information etc. in farmland.

Optionally, before the unmanned aerial vehicle performs the routing inspection according to the target routing inspection route, routing inspection parameters suitable for flying at a lower height on the boundary may be predetermined and configured, and may include: fly height, fly speed, etc. And the routing inspection parameter is used as a routing inspection parameter corresponding to the target routing inspection route. When the inspection is executed, the unmanned aerial vehicle inspects the route according to the target and uses the inspection parameters to travel. The manner of determining the patrol parameter will be described in detail in the following embodiments. In addition, unmanned aerial vehicle can also open accurate imitative ground function, for example open millimeter wave radar, binocular vision sensor, vision sensor etc.. In addition, the whole scene obstacle avoidance function can be started.

In this embodiment, based on the image information of the area to be inspected, the boundary information of the area to be inspected can be determined, and then, according to the boundary information, a target inspection route that travels with the boundary of the area to be inspected as a reference can be generated. Because the target routing inspection route advances by taking the boundary of the area to be inspected as a reference, pictures on the boundary of the area to be inspected can be uniformly collected. Because the condition that the root of the crop or the bottom of the area is not shielded on the boundary exists, the picture acquired by performing the inspection according to the target inspection route can contain the information of the root of the crop and/or the water quantity of the area to be inspected. Consequently, can gather along waiting to patrol and examine regional border a large amount of, even and contain the image of crop root and/or water yield through this embodiment, and then make the accuracy that obtains regional status information based on these image analysis obtain greatly promoting, simultaneously, need not to increase extra inspection device, can also greatly reduce the cost that the region was patrolled and examined.

Taking the above-mentioned area to be patrolled as the farmland to be patrolled as an example, after the patrolling result of the farmland to be patrolled is obtained through the above-mentioned embodiment, the state information of the farmland to be patrolled can be obtained through the following analysis.

Optionally, image recognition is performed on the picture containing the crop roots and the water amount of the farmland to be inspected, and water amount distribution information and pest and disease information of the region to be inspected are determined.

Above-mentioned image recognition can refer to through single image recognition in order to analyze out the water distribution and the pest and disease damage information etc. of waiting to patrol and examine the farmland, perhaps, can also refer to through multi-level image recognition in order to obtain the higher recognition result of accuracy.

Aiming at the multi-level image recognition, the image recognition can be firstly carried out on the picture containing the crop root and the water quantity of the farmland to be patrolled and examined, and the reference water quantity distribution information and the reference pest information are obtained. On this basis, can again according to this reference water distribution information and reference plant diseases and insect pests information to and the above-mentioned attribute information of waiting to patrol and examine the farmland, use the regional aassessment model of training in advance, obtain the water distribution information and the plant diseases and insect pests information of waiting to patrol and examine the farmland, wherein, the attribute information of waiting to patrol and examine the farmland includes: area and/or shape.

Optionally, the region evaluation model may include, for example: a farmland water quantity evaluation model, a pest and disease data evaluation model and the like.

After water distribution information and pest and disease information of a farmland to be patrolled and examined are obtained, the water distribution information and the pest and disease information can be displayed on a high-precision map so that a user can conveniently check the water distribution information and the pest and disease information.

The display mode may include, for example, one or more of the following three:

the first method comprises the following steps: and displaying the distribution and the severity of the water quantity and the pest and disease information through a prescription chart and preset colors.

And the second method comprises the following steps: the original picture that the boundary of the farmland was patrolled and examined can be shown, and this original picture can refer to the original picture that unmanned aerial vehicle gathered.

And the third is that: and counting the pest category, the severity ratio, the water quantity degree, the water addition quantity required, the historical data comparison result and the like by using the water quantity and the distribution information of the pest information, and displaying the counted information.

In addition to the display described above, the electronic device may also present a task report. For example, the water distribution information and the pest information of the farmland to be patrolled and examined are stored into a file with a preset format for a user to download, print and the like.

As described above, the target inspection route traveling with reference to the boundary of the area to be inspected may include two cases, one in which the target inspection route travels along the trajectory of the boundary of the area to be inspected, and the other in which the trajectory of the boundary of the area to be inspected is simplified or adjusted on the basis of the boundary of the area to be inspected to form the target inspection route. Hereinafter, the method of generating the target patrol route in each of these two cases will be described in detail.

First, a route generation process in a manner that the target patrol route travels along the trajectory of the boundary of the area to be patrolled will be described below.

Optionally, the number of the areas to be inspected may be one or multiple. When the number of the target routing inspection routes is one, the target routing inspection routes which travel along the boundary track of the area to be inspected can be generated directly on the basis of the boundary information of the area to be inspected. For example, if the boundary of the area to be inspected is a rectangular track, a position point on the rectangular track may be selected as a starting point of inspection, and a target inspection route that starts from the starting point, travels in a clockwise direction, and passes through the position points on the rectangular track may be generated.

When the number of the areas to be inspected is multiple, it may be determined whether there is an association relationship between the multiple areas to be inspected, where the association relationship may be, for example, that a common boundary exists between the areas to be inspected or that a certain area to be inspected is included in the range of another area to be inspected. If the plurality of areas to be inspected have no relation, the target inspection route which travels along the boundary track of each area to be inspected can be generated according to the method for each area to be inspected.

If the incidence relation exists among the multiple regions to be inspected, the combined inspection route of the multiple regions to be inspected can be determined according to the boundary information of the multiple regions to be inspected with the incidence relation, and the combined inspection route is used as the target inspection route.

The combined inspection route is a route which is used for uniformly inspecting the plurality of areas to be inspected through one inspection task.

And determining the joint routing inspection route by using the boundary information of the plurality of areas to be inspected with the incidence relation. The joint inspection route can cover the boundaries of the plurality of areas to be inspected, or the coverage rate of the boundaries of the plurality of areas to be inspected can be greater than or equal to a preset coverage rate threshold value. Simultaneously, more repeated routes can also be avoided appearing in this joint route of patrolling and examining. Furthermore, to these a plurality of regions of patrolling and examining, can be unified by unmanned aerial vehicle in a task of patrolling and examining according to this joint route and marching to can guarantee when the coverage of patrolling and examining of each border of waiting to patrol and examine the region, can reduce or avoid the repetition of route, reduce redundant information, promoted and patrolled and examined efficiency. Illustratively, if four farmlands are adjacent to each other to form a field shape, the control route passes through the middle adjacent boundary only once when the combined inspection route is generated for the four farmlands, so as to avoid repeated flight and complete the unified inspection of the four farmlands through one flight.

As an alternative embodiment, the above-described joint patrol route may be determined based on an instruction of the user. Specifically, the electronic device may determine whether the plurality of areas to be inspected have an association relationship in response to an operation of selecting the plurality of areas to be inspected by the user. If so, determining a joint routing inspection route of the multiple regions to be inspected according to the boundary information of the multiple regions to be inspected with the incidence relation.

Illustratively, the electronic device displays images of one or more farmlands on an interface thereof, a user frames the farmlands to be inspected through mouse frame selection or touch sliding frame selection, and the like, and accordingly, the electronic device can be triggered to determine the boundaries of the farmlands to be inspected, and whether the farmlands to be inspected have an incidence relation or not is judged based on the method of the embodiment, and a combined inspection route is generated when the farmlands to be inspected have the incidence relation.

Optionally, the electronic device may determine whether an association relationship exists between the multiple regions to be inspected according to coordinates of each position point in the boundary of the multiple regions to be inspected.

Two alternatives for determining the above-described joint inspection route are described below.

In a first optional manner, the plurality of areas to be inspected having an association relationship includes: a plurality of areas to be inspected having a common boundary.

In this case, in determining the above-described joint patrol route, a common boundary between the plurality of areas to be patrolled may be determined first. And then, determining the joint routing inspection routes of the plurality of areas to be inspected based on the common boundary and the unique boundary except the common boundary in the boundary information of the areas to be inspected.

Optionally, the common boundary between the areas to be inspected may be determined according to the coordinates of each position point in the boundaries of the areas to be inspected. When the joint inspection route is generated, the common boundary can be subjected to duplicate removal processing and the like based on a preset route planning algorithm, and the joint inspection route is generated according to the connection relation among routes for the unique boundary.

Fig. 3 is an exemplary diagram for generating a joint inspection route of a plurality of areas to be inspected having a common boundary, and as shown in fig. 3, a field a, a field B, a field C, and a field D are adjacent to each other to form a field shape, and for the four fields, the joint inspection route as shown in fig. 3 may be generated. Where D1 denotes a route start point, D2 denotes a route end point, and an arrow denotes a traveling direction of the route.

By the mode, the inspection coverage rate of the boundary of each inspection area can be guaranteed, meanwhile, the repetition of the route can be reduced or avoided, redundant information is reduced, and the inspection efficiency is improved.

In a second optional manner, the multiple regions to be inspected having the association relationship include: a first area and at least one second area within a home range of the first area.

In this case, when the joint patrol route is determined, the patrol route of the first area may be determined based on the boundary information of the first area. Furthermore, the routing inspection route of the first area is used as a joint routing inspection route of the first area and each second area.

This approach may be applicable to scenarios in which the area of the first region is large, while one or more second regions of smaller area are present within the home range of the first region. The second region is located within the home range of the first region, which may mean that the second region is entirely located within the boundary of the first region, or that the ratio of the area of the second region located within the boundary of the first region to the total area of the second region is greater than a specific threshold.

When one or more second areas with smaller areas are in the home range of the first area with larger areas, the routing inspection route of the first area can be used as a joint routing inspection route of the first area and each second area. Because the boundary track of the second region with the smaller area is shorter and is in the first region, therefore, the inspection result of the first region is simultaneously used as the inspection result of each second region, the inspection complexity can be reduced while the inspection result accuracy is not influenced, and the inspection efficiency is improved.

The determination method of the routing inspection route of the first area may use the determination method of the target routing inspection route of the area to be inspected, and specifically refer to the foregoing embodiment, which is not described herein again.

Fig. 4 is an exemplary diagram of a combined routing inspection route for generating a plurality of regions to be inspected having an attribution relationship, and as shown in fig. 3, a farmland E is a farmland with a large area, and a farmland F, a farmland G, and a farmland H are farmlands with a small area within the attribution range of the farmland E, respectively, and then for these four farmlands, the combined routing inspection route as shown in fig. 4 can be generated. Where N1 is both a route start point and a route end point, and the arrow is used to indicate the traveling direction of the route.

Through the mode, the accuracy of the inspection result can be guaranteed not to be influenced, meanwhile, the inspection complexity can be reduced, and the inspection efficiency is improved.

Hereinafter, a process of forming a target patrol route by simplifying or adjusting a trajectory of a boundary of an area to be patrolled on the basis of the boundary of the area to be patrolled will be described.

Fig. 5 is another schematic flow chart of the area inspection method according to the embodiment of the present application, and as shown in fig. 6, an optional manner of generating the target inspection route traveling with the boundary of the area to be inspected as the reference according to the boundary information of the area to be inspected in step S202 includes:

s501, acquiring a plurality of sampling points positioned on the boundary of the area to be inspected according to the boundary information of the area to be inspected.

Optionally, the boundary of the to-be-inspected area may be sampled at preset distance intervals to obtain a plurality of sampling points. Alternatively, the sampling points may be set according to the inflection point positions of the boundary trajectories. Each sampling point represents a respective position point, which can be represented by position point coordinates.

And S502, generating a target routing inspection route which passes through the plurality of sampling points according to the position information of the plurality of sampling points.

Optionally, the plurality of sampling points may be sequentially connected according to the position coordinates of the plurality of sampling points, and c, the target routing inspection route is formed.

The method of the embodiment can be applied to the scene that the boundary of the region to be inspected is a complex irregular boundary. Under this condition, through acquireing above-mentioned a plurality of sampling points to connect above-mentioned a plurality of sampling points, can generate the orbit and comparatively simply satisfy the orbit of patrolling and examining of requirement to the coverage on the border of waiting to patrol and examine the region simultaneously, thereby can guarantee not to influence and patrol and examine the result accuracy, simultaneously, can reduce the complexity of patrolling and examining again, promote and patrol and examine efficiency.

Fig. 6 is an exemplary diagram of generating a target patrol route by acquiring sampling points, and as shown in fig. 6, the boundary of the field M is an irregular boundary and the track is complex. For the farmland M, 12 sampling points from the sampling point 1 to thesampling point 12 can be obtained on the boundary of the farmland M, and the 12 sampling points are connected to form a target routing inspection route. The starting point and the end point of the target routing inspection route are sampling points 1, and arrows are used for indicating the traveling direction of the route.

It should be noted that the above manner of generating the target inspection route by obtaining the sampling points may be applied to one area to be inspected, or may be applied to a plurality of areas to be inspected. Specifically, when there is one area to be inspected, the target inspection route of the area to be inspected may be generated by directly using the steps of the above steps S501 to S502. When the number of the areas to be inspected is multiple, the boundary information of each area to be inspected can be fused to obtain a fused boundary. And then, the steps of the steps S501-S502 are used again, a plurality of sampling points are obtained from the fused boundary, and a target routing inspection route is generated, wherein the target routing inspection route is a route which is used for uniformly routing inspection to a plurality of areas to be inspected through one-time routing inspection task. The target inspection route is advanced, and unified inspection of a plurality of areas to be inspected can be completed at one time.

As described above, before the unmanned aerial vehicle performs inspection according to the target inspection route, the inspection parameters suitable for flying at a lower height on the boundary may be predetermined and configured, and the inspection parameters may be used as the inspection parameters corresponding to the target inspection route. A method of determining the patrol parameter corresponding to the target patrol route will be described below.

Alternatively, the inspection parameter may be determined by any one of the following methods.

In a first optional mode, the inspection parameters corresponding to the target inspection route can be determined according to the types of crops planted in the area to be inspected.

Optionally, for different crop types, the inspection parameters that most closely match the crop type may be selected. The inspection parameters matched with each crop type can be determined in advance through historical data, simulation tests and the like, and the corresponding relation between the crop type and the inspection parameters is stored in the electronic equipment. Furthermore, in this embodiment, the crop type of the area to be inspected may be first obtained, and then the inspection parameter corresponding to the target inspection route of the area to be inspected may be found according to the corresponding relationship between the crop type and the inspection parameter.

Through this kind of mode, can be so that unmanned aerial vehicle patrols and examines with the parameter of patrolling and examining that the crop type that waits to patrol and examine the region is the most matched, and then make the result of patrolling and examining that obtains more accurate.

In a second optional mode, the routing inspection parameter corresponding to the target routing inspection route can be determined according to the track shape of the target routing inspection route.

Optionally, for different track shapes, the tour inspection parameter most matched with the track shape may be selected. For example, for regular shapes, such as rectangles, etc., faster flight speeds may be used. For irregular shapes with complex trajectories, slower flight speeds can be used to take a clearer picture of the roots of the crops.

Through this kind of mode, can be so that unmanned aerial vehicle patrols and examines with the orbit shape that patrols and examines the route with the target and patrol and examine the parameter and patrol and examine most closely, and then make the result of patrolling and examining that obtains more accurate.

Optionally, the routing inspection parameters determined by the two optional modes may include, for example: flying height, flying speed, course photographing overlapping degree, camera angle and the like.

Based on the above embodiment, the unmanned aerial vehicle may perform the inspection according to the target inspection route and the inspection parameter corresponding to the target inspection route, and accordingly, in step S203, the inspection result of the area to be inspected, which is obtained by performing the inspection according to the target inspection route and the inspection parameter corresponding to the target inspection route, may be obtained.

An alternative manner of determining the boundary information of the area to be inspected in the above step S201 will be described below.

In the first optional mode, a high-precision map of the area to be inspected can be obtained, and the boundary information of the area to be inspected is determined according to the high-precision map of the area to be inspected.

As previously described, the image information of the area to be inspected may include the above-described high-precision map, such as a DOM. The electronic equipment can determine the boundary information of the area to be inspected by carrying out image recognition on the high-precision map.

In one case, if a high-precision map containing an area to be inspected has been stored in advance on the electronic device, the electronic device may directly acquire the high-precision map containing the area to be inspected.

In another case, if the high-precision map including the area to be inspected is not stored on the electronic device, the high-precision map may be acquired in the following manner.

Fig. 7 is another schematic flow chart of the area inspection method provided in the embodiment of the present application, and as shown in fig. 7, an optional manner of obtaining the high-precision map includes:

s701, determining an aerial route of the area where the area to be patrolled and examined is located according to the satellite map.

Optionally, the aerial route of the area where the area to be inspected is located may be determined on the satellite map by a manual indication or automatic identification. It should be understood that the region to be inspected is a region of a relatively large range including the region to be inspected.

And S702, carrying out aerial photography according to the aerial photography route to obtain the aerial photography picture of the area where the area to be inspected is located.

The unmanned aerial vehicle can be controlled to take photo by plane according to the aerial photographing route, and after the aerial photographing is carried out, aerial photographing pictures of the area where the to-be-patrolled and examined area is located can be obtained. The aerial photo can be a photo containing the precision of the region to be patrolled and examined and meeting the preset requirement.

And S703, splicing the aerial pictures to obtain the high-precision map of the area to be patrolled.

And after the high-precision map of the area to be patrolled is obtained, the high-precision map can be used for determining the target patrolling route. Meanwhile, the electronic equipment can store the high-precision map and use the high-precision map for subsequent routing inspection.

In a second mode, the picture including the area to be inspected may be input into a boundary recognition model obtained by pre-training, so as to obtain the boundary information of the area to be inspected.

As previously described, the image information of the area to be inspected may include a picture of the area to be inspected, which may be, for example, a picture acquired by the drone flying in advance over the area to be inspected. The electronic device can input the picture into the boundary identification model to obtain the boundary information of the region to be inspected. The boundary recognition model may be a model obtained by training a large number of training samples in advance, and the model may automatically and accurately recognize the boundary information in the picture.

Based on the same inventive concept, the embodiment of the present application further provides an area inspection device corresponding to the area inspection method, and as the principle of solving the problem of the device in the embodiment of the present application is similar to the area inspection method in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and repeated details are not repeated.

Fig. 8 is a block diagram of an area inspection device according to an embodiment of the present application, and as shown in fig. 8, the device includes:

a determiningmodule 801, configured to determine boundary information of an area to be inspected according to image information of the area to be inspected, where the image information includes: and the high-precision map or the picture containing the area to be patrolled and examined.

Agenerating module 802, configured to generate a target inspection route that travels with the boundary of the area to be inspected as a reference according to the boundary information of the area to be inspected.

An obtainingmodule 803, configured to obtain a routing inspection result obtained by performing routing inspection on the target routing inspection route, where the routing inspection result includes: and the picture comprises the crop root and/or the water quantity of the area to be inspected.

As an optional implementation manner, the area to be inspected is multiple.

Thegenerating module 802 is specifically configured to:

As an optional implementation manner, the multiple areas to be inspected having an association relationship includes: a plurality of areas to be inspected having a common boundary.

Thegenerating module 802 is specifically configured to:

determining a common boundary among the plurality of areas to be inspected;

As an optional implementation manner, the multiple areas to be inspected having an association relationship includes: a first area and at least one second area within a home range of the first area.

Thegenerating module 802 is specifically configured to:

As an optional implementation manner, thegenerating module 802 is specifically configured to:

As an optional implementation manner, the obtainingmodule 803 is specifically configured to:

As an alternative implementation, the determiningmodule 801 is further configured to:

As an optional implementation manner, the determiningmodule 801 is specifically configured to:

acquiring a high-precision map of the area to be inspected;

As an optional implementation manner, the area to be inspected includes: a farmland to be patrolled;

thedetermination module 801 is further configured to:

The description of the processing flow of each module in the device and the interaction flow between the modules may refer to the related description in the above method embodiments, and will not be described in detail here.

An embodiment of the present application further provides anelectronic device 90, as shown in fig. 9, which is a schematic structural diagram of theelectronic device 90 provided in the embodiment of the present application, and includes: aprocessor 91, amemory 92, and optionally abus 93. Thememory 92 stores machine-readable instructions (e.g., execution instructions corresponding to the determining module, the generating module, the obtaining module, etc. in the apparatus in fig. 8) executable by theprocessor 91, when theelectronic device 90 runs, theprocessor 91 communicates with thememory 92 through thebus 93, and the machine-readable instructions when executed by theprocessor 91 perform the method steps in the above method embodiments.

An embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the area inspection method are performed.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to corresponding processes in the method embodiments, and are not described in detail in this application. In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical division, and there may be other divisions in actual implementation, and for example, a plurality of modules or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or modules through some communication interfaces, and may be in an electrical, mechanical or other form.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. 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.

The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application.

Claims

Translated fromChinese

1.一种区域巡检方法，其特征在于，包括：1. a regional inspection method, is characterized in that, comprises:

根据待巡检区域的图像信息，确定所述待巡检区域的边界信息，其中，所述图像信息包括：高精地图，或者，包含所述待巡检区域的图片；According to the image information of the area to be inspected, the boundary information of the area to be inspected is determined, wherein the image information includes: a high-precision map, or a picture including the area to be inspected;

根据所述待巡检区域的边界信息，生成以所述待巡检区域的边界为基准而行进的目标巡检路线；According to the boundary information of the area to be inspected, a target inspection route based on the boundary of the area to be inspected is generated;

获取以所述目标巡检路线执行巡检所得到的巡检结果，所述巡检结果包括：包含所述待巡检区域的作物根部和/或水量的图片。The inspection result obtained by performing the inspection on the target inspection route is acquired, and the inspection result includes: a picture including the crop root and/or the amount of water in the area to be inspected.

2.根据权利要求1所述的方法，其特征在于，所述待巡检区域为多个；2. The method according to claim 1, wherein the to-be-inspected areas are multiple;

所述根据所述待巡检区域的边界信息，生成以所述待巡检区域的边界为基准而行进的目标巡检路线，包括：The generating a target inspection route based on the boundary of the to-be-inspected area according to the boundary information of the to-be-inspected area includes:

根据具有关联关系的多个待巡检区域的边界信息，确定所述多个待巡检区域的联合巡检路线，并将所述联合巡检路线作为所述目标巡检路线；According to the boundary information of the multiple areas to be inspected with the associated relationship, determine the joint inspection route of the multiple areas to be inspected, and use the joint inspection route as the target inspection route;

其中，所述联合巡检路线为通过一次巡检任务对所述多个待巡检区域统一巡检的路线。Wherein, the joint inspection route is a route for unified inspection of the multiple to-be-inspected areas through one inspection task.

3.根据权利要求2所述的方法，其特征在于，所述具有关联关系的多个待巡检区域包括：具有公共边界的多个待巡检区域；3 . The method according to claim 2 , wherein the multiple areas to be inspected with an associated relationship include: multiple areas to be inspected with a common boundary; 3 .

所述根据具有关联关系的多个待巡检区域的边界信息，确定所述多个待巡检区域的联合巡检路线，包括：The determining the joint inspection route of the plurality of to-be-inspected areas according to the boundary information of the plurality of to-be-inspected areas with associated relationships includes:

确定所述多个待巡检区域之间的公共边界；determining a common boundary between the multiple areas to be inspected;

基于所述公共边界以及各所述待巡检区域的边界信息中除所述公共边界外的独有边界，确定所述多个待巡检区域的联合巡检路线。A joint inspection route of the multiple to-be-inspected areas is determined based on the common boundary and the unique boundary other than the common boundary in the boundary information of each of the to-be-inspected areas.

4.根据权利要求2所述的方法，其特征在于，所述具有关联关系的多个待巡检区域包括：第一区域以及处于所述第一区域的归属范围内的至少一个第二区域；4. The method according to claim 2, wherein the multiple to-be-inspected areas with an associated relationship include: a first area and at least one second area within the scope of the first area;

基于所述第一区域的边界信息，确定所述第一区域的巡检路线；determining the inspection route of the first area based on the boundary information of the first area;

将所述第一区域的巡检路线作为所述第一区域以及各所述第二区域的联合巡检路线。The inspection route of the first area is used as the joint inspection route of the first area and each of the second areas.

5.根据权利要求2-4任一项所述的方法，其特征在于，所述根据具有关联关系的多个待巡检区域的边界信息，确定所述多个待巡检区域的联合巡检路线，包括：5. The method according to any one of claims 2-4, wherein the joint inspection of the plurality of to-be-inspected areas is determined according to the boundary information of the plurality of to-be-inspected areas with an associated relationship routes, including:

响应用户选择多个待巡检区域的操作，确定所述多个待巡检区域是否具有关联关系；In response to the user's operation of selecting multiple areas to be inspected, determining whether the multiple areas to be inspected have an associated relationship;

若是，则根据具有关联关系的多个待巡检区域的边界信息，确定所述多个待巡检区域的联合巡检路线。If so, the joint inspection route of the plurality of to-be-inspected areas is determined according to the boundary information of the plurality of to-be-inspected areas with the associated relationship.

6.根据权利要求1所述的方法，其特征在于，所述根据所述待巡检区域的边界信息，生成以所述待巡检区域的边界为基准而行进的目标巡检路线，包括：6. The method according to claim 1, wherein generating a target inspection route based on the boundary of the to-be-inspected area according to the boundary information of the to-be-inspected area, comprising:

根据所述待巡检区域的边界信息，获取位于所述待巡检区域的边界上的多个采样点；According to the boundary information of the to-be-inspected area, acquire a plurality of sampling points located on the boundary of the to-be-inspected area;

根据所述多个采样点的位置信息，生成途径所述多个采样点的目标巡检路线。According to the location information of the plurality of sampling points, a target inspection route passing through the plurality of sampling points is generated.

7.根据权利要求1所述的方法，其特征在于，所述获取以所述目标巡检路线执行巡检所得到的巡检结果，包括：7. The method according to claim 1, wherein the acquiring the inspection result obtained by performing the inspection on the target inspection route comprises:

获取以所述目标巡检路线以及所述目标巡检路线对应的巡检参数执行巡检所得到的所述待巡检区域的巡检结果。Obtain the inspection result of the to-be-inspected area obtained by performing the inspection with the target inspection route and the inspection parameters corresponding to the target inspection route.

8.根据权利要求7所述的方法，其特征在于，所述获取以所述目标巡检路线以及所述目标巡检路线对应的巡检参数执行巡检所得到的所述待巡检区域的巡检结果之前，还包括：8 . The method according to claim 7 , wherein the acquiring the target inspection route and the inspection parameters corresponding to the target inspection route and performing the inspection of the area to be inspected obtained. 9 . Before the inspection results, it also includes:

根据所述待巡检区域所种植的作物类型，确定所述目标巡检路线对应的巡检参数。According to the type of crops planted in the area to be inspected, the inspection parameters corresponding to the target inspection route are determined.

9.根据权利要求7所述的方法，其特征在于，所述获取以所述目标巡检路线以及所述目标巡检路线对应的巡检参数执行巡检所得到的所述待巡检区域的巡检结果之前，还包括：9 . The method according to claim 7 , wherein the acquiring the target inspection route and the inspection parameters corresponding to the target inspection route and performing the inspection of the to-be-inspected area obtained by the inspection. 10 . Before the inspection results, it also includes:

根据所述目标巡检路线的轨迹形状，确定所述目标巡检路线对应的巡检参数。According to the trajectory shape of the target patrol route, the patrol parameter corresponding to the target patrol route is determined.

10.根据权利要求1所述的方法，其特征在于，所述根据待巡检区域的图像信息，确定所述待巡检区域的边界信息，包括：10. The method according to claim 1, wherein the determining the boundary information of the to-be-inspected area according to the image information of the to-be-inspected area comprises:

获取所述待巡检区域的高精地图；Obtain a high-precision map of the area to be inspected;

根据所述待巡检区域的高精地图，确定所述待巡检区域的边界信息。The boundary information of the to-be-inspected area is determined according to the high-precision map of the to-be-inspected area.

11.根据权利要求10所述的方法，其特征在于，所述获取所述待巡检区域的高精地图，包括：11. The method according to claim 10, wherein the acquiring a high-precision map of the area to be inspected comprises:

若不存在所述待巡检区域的高精地图，则根据卫星地图确定所述待巡检区域所在区域的航拍路线；If there is no high-precision map of the to-be-inspected area, determine the aerial photography route of the area where the to-be-inspected area is located according to the satellite map;

根据所述航拍路线进行航拍，得到所述待巡检区域所在区域的航拍图片；Aerial photography is performed according to the aerial photography route to obtain an aerial photography picture of the area where the area to be inspected is located;

对所述航拍图片进行拼接处理，得到所述待巡检区域的高精地图。The aerial pictures are spliced to obtain a high-precision map of the area to be inspected.

12.根据权利要求1所述的方法，其特征在于，所述根据待巡检区域的图像信息，确定所述待巡检区域的边界信息，包括：12. The method according to claim 1, wherein the determining the boundary information of the to-be-inspected area according to the image information of the to-be-inspected area comprises:

将包含所述待巡检区域的图片输入预先训练得到的边界识别模型中，得到所述待巡检区域的边界信息。Input the picture including the area to be inspected into the boundary recognition model obtained by pre-training to obtain the boundary information of the area to be inspected.

13.根据权利要求1所述的方法，其特征在于，所述待巡检区域包括：待巡检农田；13. The method according to claim 1, wherein the area to be inspected comprises: farmland to be inspected;

所述获取以所述目标巡检路线执行巡检所得到的巡检结果之后，还包括：After the acquiring the inspection result obtained by performing the inspection on the target inspection route, the method further includes:

对包含所述待巡检农田的作物根部以及水量的图片进行图像识别，确定所述待巡检农田的水量分布信息以及病虫害信息。Image recognition is performed on the picture containing the crop roots and water quantity of the farmland to be inspected, and the water quantity distribution information and disease and insect pest information of the farmland to be inspected are determined.

14.根据权利要求13所述的方法，其特征在于，所述对包含所述待巡检农田的根部以及水量的图片进行图像识别，确定所述待巡检农田的水量分布信息以及病虫害信息，包括：14. The method according to claim 13, wherein the image recognition is performed on a picture containing the roots and water volume of the farmland to be inspected, and the water volume distribution information and disease and insect pest information of the farmland to be inspected are determined, include:

对包含所述待巡检农田的作物根部以及水量的图片进行图像识别，得到参考水量分布信息以及参考病虫害信息；Perform image recognition on the picture containing the crop roots and water quantity of the farmland to be inspected, and obtain reference water quantity distribution information and reference disease and insect pest information;

根据所述参考水量分布信息以及参考病虫害信息，以及所述待巡检农田的属性信息，使用预先训练的区域评估模型，得到所述待巡检农田的水量分布信息以及病虫害信息，其中，所述待巡检农田的属性信息包括：面积和/或形状。According to the reference water distribution information and reference disease and insect pest information, and the attribute information of the farmland to be inspected, the pre-trained regional evaluation model is used to obtain the water distribution information and disease and insect pest information of the farmland to be inspected, wherein the The attribute information of the farmland to be inspected includes: area and/or shape.

15.一种区域巡检装置，其特征在于，包括：15. An area inspection device, characterized in that it comprises:

确定模块，用于根据待巡检区域的图像信息，确定所述待巡检区域的边界信息，其中，所述图像信息包括：高精地图，或者，包含所述待巡检区域的图片；a determination module, configured to determine the boundary information of the to-be-inspected area according to the image information of the to-be-inspected area, wherein the image information includes: a high-precision map, or a picture including the to-be-inspected area;

生成模块，用于根据所述待巡检区域的边界信息，生成以所述待巡检区域的边界为基准而行进的目标巡检路线；a generating module, configured to generate a target inspection route based on the boundary of the to-be-inspected area according to the boundary information of the to-be-inspected area;

获取模块，用于获取以所述目标巡检路线执行巡检所得到的巡检结果，所述巡检结果包括：包含所述待巡检区域的作物根部和/或水量的图片。An acquisition module, configured to acquire inspection results obtained by performing inspection on the target inspection route, where the inspection results include: pictures including crop roots and/or water volume in the area to be inspected.

16.一种电子设备，其特征在于，包括：处理器和存储器，所述存储器存储有所述处理器可执行的机器可读指令，当电子设备运行时，所述处理器执行所述机器可读指令，以执行时执行如权利要求1至14任一所述的区域巡检方法的步骤。16. An electronic device, comprising: a processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor executes the machine-readable instructions. Read the instruction to execute the steps of the area inspection method according to any one of claims 1 to 14 when executed.

17.一种巡检系统，其特征在于，包括：权利要求16所述的电子设备以及无人机，所述电子设备与所述无人机通信连接，所述电子设备将生成的目标巡检路线发送给无人机，所述无人机用于按照所述目标巡检路线执行巡检，并将巡检结果发送给所述电子设备。17. An inspection system, comprising: the electronic device of claim 16 and an unmanned aerial vehicle, wherein the electronic device is connected in communication with the unmanned aerial vehicle, and the electronic device inspects the generated target. The route is sent to the drone, and the drone is used to perform inspection according to the target inspection route, and send the inspection result to the electronic device.

18.一种计算机可读存储介质，其特征在于，该计算机可读存储介质上存储有计算机程序，该计算机程序被处理器运行时执行如权利要求1至14任一所述的区域巡检方法的步骤。18. A computer-readable storage medium, characterized in that, a computer program is stored on the computer-readable storage medium, and the computer program executes the regional inspection method according to any one of claims 1 to 14 when the computer program is run by the processor A step of.