WO2019227948A1 - 目标区域作业的规划方法、装置、存储介质及处理器 - Google Patents

目标区域作业的规划方法、装置、存储介质及处理器 Download PDF

Info

Publication number
WO2019227948A1
WO2019227948A1 PCT/CN2019/071998 CN2019071998W WO2019227948A1 WO 2019227948 A1 WO2019227948 A1 WO 2019227948A1 CN 2019071998 W CN2019071998 W CN 2019071998W WO 2019227948 A1 WO2019227948 A1 WO 2019227948A1
Authority
WO
WIPO (PCT)
Prior art keywords
sub
area
path
operated
center position
Prior art date
Application number
PCT/CN2019/071998
Other languages
English (en)
French (fr)
Inventor
代双亮
Original Assignee
广州极飞科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 广州极飞科技有限公司 filed Critical 广州极飞科技有限公司
Priority to AU2019276115A priority Critical patent/AU2019276115B2/en
Priority to EP19812180.8A priority patent/EP3805981A4/en
Priority to JP2020566656A priority patent/JP2021525426A/ja
Priority to US17/044,105 priority patent/US20210150184A1/en
Publication of WO2019227948A1 publication Critical patent/WO2019227948A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/13—Satellite images
    • A—HUMAN NECESSITIES
    • A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01B—SOIL WORKING IN AGRICULTURE OR FORESTRY; PARTS, DETAILS, OR ACCESSORIES OF AGRICULTURAL MACHINES OR IMPLEMENTS, IN GENERAL
    • A01B79/00—Methods for working soil
    • A01B79/005—Precision agriculture
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3407—Route searching; Route guidance specially adapted for specific applications
    • G01C21/343—Calculating itineraries, i.e. routes leading from a starting point to a series of categorical destinations using a global route restraint, round trips, touristic trips
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • G06F18/24133—Distances to prototypes
    • G06F18/24137—Distances to cluster centroïds
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/02—Agriculture; Fishing; Forestry; Mining
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G06V10/457—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by analysing connectivity, e.g. edge linking, connected component analysis or slices
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/188—Vegetation
    • A—HUMAN NECESSITIES
    • A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01B—SOIL WORKING IN AGRICULTURE OR FORESTRY; PARTS, DETAILS, OR ACCESSORIES OF AGRICULTURAL MACHINES OR IMPLEMENTS, IN GENERAL
    • A01B69/00—Steering of agricultural machines or implements; Guiding agricultural machines or implements on a desired track
    • A01B69/007—Steering or guiding of agricultural vehicles, e.g. steering of the tractor to keep the plough in the furrow
    • A01B69/008—Steering or guiding of agricultural vehicles, e.g. steering of the tractor to keep the plough in the furrow automatic

Definitions

  • the present invention relates to the field of computers, and in particular, to a method, a device, a storage medium, and a processor for planning a target area operation.
  • Orchard plant protection is mainly concerned with the control of disease and insect pests of fruit trees. Only proper management of fruit trees can produce high-quality fruits. Compared to farmland plant protection, the density of orchard plants is low. If the field operation method is adopted, it is easy to cause waste of pesticides and water resources. However, if manual precision positioning is used, additional procedures will be added for plant protection, which will waste more human, material and financial resources.
  • At least some embodiments of the present invention provide a method, a device, a storage medium, and a processor for planning a target area operation to solve at least the technical problems that the orchard plant protection method used in the related technology is likely to cause waste of resources and higher costs .
  • a method for planning a target area operation including:
  • map image information of the target area to be operated identify multiple sub-areas contained in the target area of the work from the map image information, wherein the multiple sub-areas correspond to multiple objects to be operated; plan the operation of the equipment in the standby area according to the multiple sub-areas.
  • the action path within the work target area to control the work equipment to traverse multiple sub-areas when working along the action path.
  • identifying the multiple sub-regions contained in the target area to be operated from the map image information includes: identifying the geometric center position of each sub-region in the multiple sub-regions and the outer contour of each sub-region from the map image information.
  • the geometric center position is the center position of the circle; when the outer contour is rectangular, the geometric center position is the center position of the rectangle; when the outer contour is oval, the geometric center position is The center position of the ellipse; when the outer contour is an irregular shape, the geometric center position is the centroid position of the irregular shape.
  • planning the action path of the work equipment in the target area according to multiple sub-regions includes: generating a transition path that traverses multiple target objects in the target region based on the geometric center position of each of the multiple sub-regions; Based on the outer contours of each of the multiple sub-areas, plan the work path of multiple to-be-worked objects; add the work path to the transition path to generate the action path of the work equipment in the to-be-targeted area.
  • generating a transition path for traversing a plurality of to-be-operated objects in a to-be-operated target area based on the geometric center position of each of the plurality of sub-areas includes: a selection step of selecting, from the plurality of sub-areas, the closest distance to the take-off position of the work equipment The sub-region is the starting sub-region; the establishment step starts from the geometric center position of the starting sub-region, searches for the geometric center position of the adjacent sub-region nearest to the current sub-region in order, and establishes between the adjacent geometric center positions Transition path; a determination step, which determines whether there are sub-areas that are not yet connected, and if so, returns to the establishment step, until a transition path is generated that traverses multiple objects to be operated.
  • planning the work path of multiple to-be-operated objects based on the outer contours of each of the multiple sub-regions includes: a determining step of determining the actual area of the current sub-region based on the outer contours of the current sub-region selected from the multiple sub-regions ; The first judgment step, when the actual area is less than the preset area, the fixed-point rotation operation path is used; when the actual area is greater than or equal to the preset area, the spiral operation path and / or the round-trip operation path are used; the second judgment step, the judgment is more Whether all the sub-areas are planned, and if not, return to the determination step, so as to plan the work path for the to-be-operated objects in the next sub-area adjacent to the current sub-area, until the work paths of multiple to-be-operated objects are all planned.
  • the first determining step includes: determining a preset area according to the working width of the work equipment, and when the maximum diameter of the current sub-area is smaller than the working width, a fixed-point rotation work path is adopted; when the maximum diameter of the current sub-area is greater than or When the working width is equal to the working width, a spiral working path and / or a round-trip working path are used.
  • the adjacent Two or more sub-regions are identified as one sub-region.
  • the method before controlling the work equipment to traverse multiple sub-areas while working along the action path, the method further includes: obtaining a first height, a second height, a third height, and a fourth height, where the first height is each to-be-worked
  • the surveying and mapping altitude of the object the second altitude is the altitude of the take-off point of the working equipment, the third altitude is the height of each to-be-operated object, and the fourth altitude is a preset height added to the height of each to-be-operated object;
  • the first altitude, the second altitude, the third altitude, and the fourth altitude are used to calculate the actual flying altitude of the operation equipment.
  • a device for planning a target area operation including:
  • the first acquisition module is configured to acquire map image information of the target region to be operated; the identification module is configured to identify a plurality of sub-regions included in the target region from the map image information, where the multiple sub-regions are related to multiple objects to be operated Corresponding; the planning module is configured to plan the action path of the work equipment in the target area to be operated according to multiple sub-areas, so as to control the work equipment to traverse multiple sub-areas when working along the action path.
  • the identification module is configured to identify a geometric center position of each of the plurality of subregions and an outer contour of each subregion from the map image information.
  • the geometric center position is the center position of the circle; when the outer contour is rectangular, the geometric center position is the center position of the rectangle; when the outer contour is oval, the geometric center position is The center position of the ellipse; when the outer contour is an irregular shape, the geometric center position is the centroid position of the irregular shape.
  • the planning module includes: a generating unit configured to generate a transition path traversing a plurality of to-be-operated objects in a target region based on a geometric center position of each of the multiple sub-regions; a planning unit configured to be based on a plurality of sub-regions The outer contour of each sub-area in the planning of the work path of multiple to-be-worked objects; the processing unit is configured to add the work path to the transition path to generate an action path of the work equipment in the to-be-worked target area.
  • the generating unit includes: selecting a sub-unit configured to select a sub-region closest to the take-off position of the operating equipment from a plurality of sub-regions as a starting sub-region; establishing a sub-unit configured to set the geometry from the starting sub-region Starting from the center position, sequentially find the geometric center position of the adjacent sub-region closest to the current sub-region, and establish a transition path between the adjacent geometric center positions; determine the sub-units, set to determine whether there are sub-regions that are not yet connected, If so, return to establishing a subunit until a transition path is generated that traverses multiple objects to be operated.
  • the planning unit includes: a determination subunit configured to determine an actual area of the current subarea according to an outer contour of the current subarea selected from the plurality of subareas; and a first determination subunit configured to be set when the actual area is less than a preset When the area is fixed, a fixed-point rotation work path is used; when the actual area is greater than or equal to the preset area, a spiral work path and / or a round-trip work path are used; the second judgment subunit is set to determine whether multiple sub-areas are all planned, if not , Then return to the determination subunit, so as to plan the work path for the to-be-operated objects in the next sub-area adjacent to the current sub-area, until the work paths of multiple to-be-operated objects are all planned.
  • the first judging sub-unit is configured to determine a preset area according to the working width of the working equipment.
  • a fixed-point rotation work path is adopted; when the maximum diameter of the current sub-area
  • a spiral working path and / or a round-trip working path are used.
  • the adjacent Two or more sub-regions are identified as one sub-region.
  • the above device further includes: a second acquisition module configured to acquire a first height, a second height, a third height, and a fourth height, wherein the first height is a surveying altitude of each object to be operated, and the first The second height is the altitude of the take-off point of the work equipment, the third height is the height of each to-be-worked object, and the fourth height is a preset height added to the height of each to-be-worked object; the calculation module is set to use the first The first altitude, the second altitude, the third altitude, and the fourth altitude calculate the actual flying altitude of the operation equipment.
  • a second acquisition module configured to acquire a first height, a second height, a third height, and a fourth height, wherein the first height is a surveying altitude of each object to be operated, and the first The second height is the altitude of the take-off point of the work equipment, the third height is the height of each to-be-worked object, and the fourth height is a preset
  • a storage medium is also provided.
  • the storage medium includes a stored program, and during the program running, a device in which the storage medium is located is controlled to execute the above-mentioned target area job planning method.
  • a processor is further provided.
  • the processor is configured to run a program, and the program executes the foregoing target area job planning method when the program is run.
  • a method of acquiring map image information of a target area to be operated and identifying multiple sub-areas corresponding to a plurality of target objects included in the target area from the map image information according to Multiple sub-areas plan the action path of the work equipment in the target area to be operated and control the work equipment to traverse multiple sub-areas while working along the action path, so that in actual application, only the target area to be operated is selected, and then the system will directly
  • the orchard plant protection method used in the technology is easy to cause waste of resources and higher cost technical problems.
  • FIG. 1 is a flowchart of a method for planning a target area operation according to an embodiment of the present invention
  • FIG. 2 is a schematic diagram of extracting part of data from a high-definition map image for labeling according to a preferred embodiment of the present invention
  • FIG. 3 is a schematic diagram of identifying a geometric center position of each sub-region from map image information according to a preferred embodiment of the present invention
  • FIG. 4 is a schematic diagram of a transition path planning process according to a preferred embodiment of the present invention.
  • FIG. 5 is a structural block diagram of a device for planning a target area operation according to one embodiment of the present invention.
  • FIG. 6 is a structural block diagram of a device for planning a target area operation according to a preferred embodiment of the present invention.
  • an embodiment of a method for planning a target area operation is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings may be in a computer system such as a set of computer-executable instructions. Perform, and although the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than here.
  • FIG. 1 is a flowchart of a method for planning a target area operation according to an embodiment of the present invention. As shown in FIG. 1, the method includes the following steps:
  • Step S12 obtaining map image information of the target area to be operated
  • Step S14 identifying a plurality of sub-areas included in the target area to be operated from the map image information, where the plurality of sub-areas correspond to a plurality of objects to be operated;
  • step S16 the action path of the work equipment in the target area to be operated is planned according to the multiple sub-areas, so as to control the work equipment to traverse the multiple sub-areas when working along the action path.
  • a method of acquiring map image information of a target area to be operated and identifying multiple sub-areas corresponding to multiple objects to be operated included in the target area to be operated from the map image information may be planned according to the multiple sub-areas.
  • the location of the area and the obtained high-definition image generate the action path of the entire target area to be operated, thereby achieving the technical effect of not only achieving accurate plant protection but also reducing a large amount of labor costs, thereby solving the problems in the related technology.
  • the orchard plant protection method is easy to cause waste of resources and higher cost technical problems.
  • the above method is generally applied to a control terminal for remotely operating a drone.
  • the above-mentioned map images include two-dimensional maps, three-dimensional maps, DSM maps, pictures, videos, pictures, and the like.
  • the target area to be operated may include, but is not limited to, an orchard plant protection area (for example, an apple orchard plant protection area), a fruit picking area (for example, an apple picking area), a fruit pruning area (for example, a grape pruning area, a cotton pruning area) ),
  • a field area (a wheat field harvesting area), which includes a plurality of objects to be operated in the target area to be operated, for example, when the area to be operated is an orchard, the object to be operated is a fruit tree; when the target area to be operated is When it is a field, the object to be operated is a piece of crop such as wheat.
  • the above-mentioned work equipment may be a drone with a plant protection work function, or it may be a ground work equipment, such as a
  • identifying a plurality of sub-areas included in the target area to be operated from the map image information may include the following execution steps:
  • step S141 the geometric center position of each sub-region in the multiple sub-regions and the outer contour of each sub-region are identified from the map image information.
  • the geometric center position when the outer contour is circular, the geometric center position may be a circle center position; when the outer contour is rectangular, the geometric center position may be a rectangular center position; when the outer contour is elliptical, the geometric center position may be It can be the center position of the ellipse; when the outer contour is an irregular shape, the geometric center position can be the centroid position of the irregular shape.
  • it is usually necessary to further label it in the map image.
  • the present invention is not limited to the labeling form, as long as it can identify the outer contour and the center position. For example, three points are used to label a circle. The skilled person can understand that when three points are marked, the outer contour and center of the circle can be obtained according to the usual algorithm.
  • Another example is to use a rectangular frame to mark a rectangular area, another example is to use four points to mark a rectangular area, another example is to use a circle center to mark the center position of a circular area, and use a circular frame to mark the outer contour of the center area.
  • a mapping drone or an aerial drone is used to obtain a high-definition map image. Then, in view of the large amount of data contained in the acquired map image, for this reason, it is necessary to extract part of the data from the acquired map image (for example, a partial image with high visibility) for labeling as a training set.
  • the labeling method is based on the high-definition map image collected by the drone.
  • the edges of each fruit tree are manually labeled with a preset shape (for example, a circle), and then the corresponding round frame data is automatically generated by the terminal.
  • the round frame data may include, but is not limited to, true circle center position and radius data of each fruit tree in the high-definition map image.
  • FIG. 2 is a schematic diagram of extracting part of data from a high-definition map image for labeling according to a preferred embodiment of the present invention.
  • the left side is the input original image
  • the right side is the visibility extracted from the original image.
  • the higher part of the data is annotated image.
  • the circular lines that appear in the image on the right are the data for the labeled boundaries.
  • the deep network model is mainly obtained through repeated training based on the above-mentioned circularly labeled target detection.
  • the specific process is as follows: First, the original image (usually an RGB image with a resolution of 256 ⁇ 256) is taken as an input item and a feature map (usually a small-sized and layered abstraction) is obtained through a convolutional neural network (CNN) Image, its resolution can be 16 ⁇ 16).
  • CNN convolutional neural network
  • the convolutional neural network is a pre-trained classification network.
  • the bottom layer i.e.
  • the feature map is subjected to a convolution process with a kernel of 1 to output position information (loc) and the probability of all target classifications (logits (c 1 , c 2 , ... c p )).
  • loc can be expressed as ⁇ (cx, cy, radius), where cx, cy represents the center point of the target circle, and radius represents the offset value of the radius. Logits are mainly used to distinguish fruit trees from other objects and backgrounds.
  • P is the positive target (the target is the fruit tree)
  • Neg is the negative target (the target is the background)
  • l is the true parameter of the labeled circle
  • g is the predicted parameter of the labeled circle
  • d is the default circle parameter
  • smooth L1 is the loss function.
  • FIG. 3 is a schematic diagram of identifying a geometric center position of each sub-region from map image information according to a preferred embodiment of the present invention.
  • the system can The orchard high-resolution map image can accurately identify and label the geometric center position of each of the multiple sub-regions from the map image information by using AI image recognition technology.
  • the action path planning can be completed by using the geometric center position of each fruit tree.
  • two or more adjacent sub-regions may be determined as one sub-region.
  • planning the action path of the work equipment in the target area to be operated according to multiple sub-areas may include the following execution steps:
  • Step S161 Generate a transition path that traverses a plurality of objects to be operated in a target area to be operated based on the geometric center position of each of the plurality of sub-areas;
  • Step S162 Plan the work paths of multiple objects to be worked based on the outer contour of each of the multiple sub-areas
  • Step S163 Add a work path to the transition path to generate an action path of the work equipment in the target area to be worked.
  • the geometric center position of each fruit tree is accurately identified from the high-definition image of the orchard to be operated through the above-mentioned deep learning and computer vision.
  • a transition path for traversing each fruit tree in the orchard to be operated is generated according to the pixel coordinates of the geometric center position of each of the multiple sub-regions. This transition path is used to determine the sequential spraying order of each fruit tree in the entire orchard.
  • the working path of each fruit tree is planned according to the outer contour of each sub-region.
  • the work path is used to determine the spraying method of each fruit tree in the entire orchard.
  • a complete set of action paths capable of spraying all fruit trees in the entire orchard is formed.
  • step S161 generating a transition path for traversing a plurality of objects to be operated in the target region based on the geometric center position of each of the plurality of sub-regions may include the following execution steps:
  • Step S1611 the sub-area closest to the take-off position of the operating equipment is selected as the starting sub-area from the multiple sub-areas;
  • Step S1612 starting from the geometric center position of the starting sub-region, sequentially searching for the geometric center position of the adjacent sub-region closest to the current sub-region, and establishing a transition path between the adjacent geometric center positions;
  • step S1613 it is determined whether there are sub-areas that are not yet connected, and if so, return to step S1612 until a transition path is generated that traverses multiple objects to be operated.
  • the drone In the process of generating the transition path, first, the drone needs to select a sub-area from a plurality of sub-areas that is closest to the geometric center position of the drone's take-off position as the starting sub-area; second, from the geometric center of the starting sub-area At the beginning of the position, according to the shortest path algorithm, the sub-area nearest to the current geometric center position is selected from the adjacent one or more geometric center positions; then, a line is used between the current sub-region and the selected adjacent sub-region.
  • a transition path is established between two geometric center positions. In the end, all the geometric center positions marked in the high-definition image are connected to each other without repeating one another to obtain the transition path that the drone travels between the fruit trees in the entire orchard.
  • Fig. 4 is a schematic diagram of a transition path planning process according to one of the preferred embodiments of the present invention.
  • the geometric center positions of each fruit tree in the orchard are obtained by inputting the original image (A1, A2, ... A35). Afterwards, the fruit tree closest to the drone's takeoff position can be used as the starting point of departure. Assuming that the fruit tree closest to the drone's take-off position is the fruit tree where A1 is located, the sub-region where A1 is located is the starting sub-region.
  • planning the work paths of multiple to-be-operated objects based on the outer contour of each of the multiple sub-regions may include the following execution steps:
  • Step S1621 Determine the actual area of the current sub-region according to the outer contour of the current sub-region selected from the multiple sub-regions;
  • Step S1622 when the actual area is smaller than the preset area, a fixed-point rotation work path is used; when the actual area is greater than or equal to the preset area, a spiral work path and / or a round-trip work path is used;
  • Step S1623 it is determined whether all the sub-areas have been planned. If not, the process returns to step S1621, so as to plan the work path for the to-be-operated objects in the next sub-area adjacent to the current sub-area until the work paths of the multiple to-be-operated objects All planning is completed.
  • the preset area may be determined according to the working width of the working equipment (usually 1.5 m-3 m).
  • a fixed-point rotation working path can be adopted. For example: control the drone to hover above the corresponding geometric center position of the current sub-area, and spray pesticides to the current fruit tree through the rotation operation method.
  • the spiral work path is particularly suitable for fruit tree plant protection services in hilly areas, and can automatically plan spraying paths based on surveying and mapping information and the growth of fruit trees. If the diameter of the crown of the fruit tree is small, no one will spin on the fruit tree for a week to spray. If the diameter of the crown of the fruit tree is large, the drone will fly above the fruit tree with the crown as the center and fly from the center to the surrounding area.
  • the drone will only turn on the sprayer when it is flying over the fruit tree to perform the route, and the sprayer is turned off at other times to ensure that the pesticide is effectively sprayed on the leaves.
  • the drone can be controlled to spray pesticides on the current fruit tree using a round-wave or round-wave operation over the current sub-area.
  • step S16 before the control work equipment traverses a plurality of sub-areas while working along the action path, it may further include the following execution steps:
  • Step S17 Obtain a first altitude, a second altitude, a third altitude, and a fourth altitude, where the first altitude is the surveying altitude of each object to be operated, the second altitude is the altitude of the take-off point of the operating equipment, and the third The height is the height of each to-be-worked object, and the fourth height is a preset height added to the height of each to-be-worked object;
  • step S18 the actual flying height of the work equipment is calculated using the first altitude, the second altitude, the third altitude, and the fourth altitude.
  • the actual altitude of the fruit tree can be determined either by a three-dimensional digital surface model (DSM) map or by mapping data.
  • DSM digital surface model
  • the height of the fruit tree can be measured manually, but it can also be determined by the distance sensor of the working machine. It can be seen that the planning of the action path is actually three-dimensional.
  • the drone can use the global navigation satellite system (GNSS) real-time differential positioning (RTK) navigation component to provide altitude data for the drone to perform fixed altitude flight.
  • GNSS global navigation satellite system
  • RTK real-time differential positioning
  • the flying height is affected by the height of the crop and the surrounding environment. Generally, the flying height is 1.5-2.5 meters from the plant canopy. If you use RTK to determine the height, you need to refer to the terrain difference and choose an appropriate height.
  • the surveying and mapping equipment can record not only latitude and longitude information, but also elevation information. Therefore, during the surveying and mapping process, the surveyor needs to maintain a vertical touch to the ground to ensure the collected elevation data. Accurate.
  • the flying height of the drone for each fruit tree is based on the altitude of the water level at the takeoff point, and is calculated by combining the altitude of the fruit tree mapping, the height of the fruit tree itself and the height from the treetop. The specific calculation formula is as follows:
  • UAV flight altitude (altitude of fruit tree mapping-altitude of takeoff point horizontal plane) + (altitude of fruit tree + height from treetop).
  • FIG. 5 is a structural block diagram of a device for planning a target area operation according to an embodiment of the present invention.
  • the device includes: a first obtaining module 10 configured to obtain map image information of a target area to be operated; Module 20 is configured to identify multiple sub-areas included in the target area to be operated from the map image information, where multiple sub-areas correspond to multiple objects to be operated; planning module 30 is set to plan the operation equipment to The action path within the work target area to control the work equipment to traverse multiple sub-areas when working along the action path.
  • the identification module 20 is configured to identify, from the map image information, the geometric center position of each sub-region in the multiple sub-regions and the outer contour of each sub-region.
  • the geometric center position is the center position of the circle; when the outer contour is rectangular, the geometric center position is the center position of the rectangle; when the outer contour is oval, the geometric center position is The center position of the ellipse; when the outer contour is an irregular shape, the geometric center position is the centroid position of the irregular shape.
  • FIG. 6 is a structural block diagram of a planning device for a target area operation according to one of the preferred embodiments of the present invention.
  • the planning module 30 includes a generating unit 300 configured to be based on each of a plurality of sub-areas. The geometric center position of the area generates a transition path that traverses multiple to-be-operated objects in the to-be-targeted area; the planning unit 302 is configured to plan the work paths of multiple to-be-operated objects based on the outer contours of each of the multiple sub-areas; the processing unit 304. Add a work path to the transition path to generate an action path of the work equipment in the target area to be worked.
  • the generating unit 300 includes: selecting a sub-unit (not shown in the figure), configured to select a sub-region closest to the take-off position of the operating equipment from a plurality of sub-regions as a starting sub-region; Not shown in the figure), set to start from the geometric center position of the starting sub-region, find the geometric center position of the adjacent sub-region nearest to the current sub-region in turn, and establish a transition path between adjacent geometric center positions;
  • the judging subunit (not shown in the figure) is set to judge whether there is a sub-area that is not yet connected, and if so, return to establishing a subunit until a transition path that traverses multiple objects to be operated is generated.
  • the planning unit 302 includes: a determination subunit (not shown in the figure), configured to determine the actual area of the current subregion according to the outer contour of the current subregion selected from the plurality of subregions; a first judgment subunit ( (Not shown in the figure), set to use a fixed-point rotation work path when the actual area is less than the preset area; when the actual area is greater than or equal to the preset area, a spiral work path and / or a round-trip work path are used; the second judge A unit (not shown in the figure), which is set to judge whether multiple sub-areas are all planned, and if not, return to determine a sub-unit in order to plan a work path for a to-be-targeted object in the next sub-area adjacent to the current sub-area, Until the operation paths of multiple objects to be operated are all planned.
  • a determination subunit configured to determine the actual area of the current subregion according to the outer contour of the current subregion selected from the plurality of subregions
  • a first judgment subunit
  • the first judging sub-unit (not shown in the figure) is configured to determine a preset area according to the working width of the working equipment, and when the maximum diameter of the current sub-area is smaller than the working width, a fixed-point rotation working path is adopted; When the maximum diameter of the current sub-area is greater than or equal to the working width, a spiral working path and / or a round-trip working path is used.
  • the adjacent Two or more sub-regions are identified as one sub-region.
  • the above device further includes: a second obtaining module 40 configured to obtain the first height, the second height, the third height, and the fourth height, where the first height is each job to be performed
  • the surveying and mapping altitude of the object the second altitude is the altitude of the take-off point of the working equipment, the third altitude is the height of each to-be-operated object, and the fourth altitude is a preset height added to the height of each to-be-operated object;
  • the calculation module 50 is configured to calculate the actual flying height of the operation equipment using the first altitude, the second altitude, the third altitude, and the fourth altitude.
  • One embodiment of the present invention may also provide a computer terminal.
  • the computer terminal may include: one or more processors and a memory.
  • the memory may be configured to store software programs and modules, such as program instructions / modules corresponding to the security vulnerability detection method and device in the embodiments of the present invention.
  • the processor executes various software programs and modules stored in the memory to execute various programs. Functional application and data processing, that is, the planning method for achieving the above-mentioned target area operations.
  • the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, a flash memory, or other non-volatile solid-state memory.
  • the memory may further include a memory remotely set with respect to the processor, and these remote memories may be connected to the terminal through a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
  • the processor may call the information stored in the memory and the application program through the transmission device to perform the following steps: obtaining map image information of the target area to be operated; and identifying multiple sub-areas included in the target area to be operated from the map image information, wherein, The multiple sub-areas correspond to multiple to-be-operated objects; according to the multiple sub-areas, the action path of the work equipment in the to-be-targeted area is planned to control the work equipment to traverse multiple sub-areas when working along the action path.
  • the processor may further execute the program code of the following steps: identifying the geometric center position of each sub-region in the multiple sub-regions and the outer contour of each sub-region from the map image information.
  • the processor may further execute the program code of the following steps: generating a transition path traversing a plurality of objects to be operated in a target area to be operated based on a geometric center position of each of the plurality of sub areas; The outline of each sub-area is used to plan the work path of multiple to-be-worked objects; the work path is added to the transition path to generate the action path of the work equipment in the to-be-targeted area.
  • the processor may further execute the program code of the following steps: a selection step, selecting a sub-area closest to the take-off position of the operating equipment from a plurality of sub-areas as a starting sub-area; and a establishing step from the starting sub-area.
  • a selection step selecting a sub-area closest to the take-off position of the operating equipment from a plurality of sub-areas as a starting sub-area; and a establishing step from the starting sub-area.
  • the geometric center position the geometric center position of the adjacent sub-region nearest to the current sub-region is searched in turn, and a transition path is established between the adjacent geometric center positions; the judgment step is to determine whether there are sub-regions that are not yet connected. , Return to the establishment step until a transition path is generated that traverses multiple objects to be operated.
  • the processor may further execute the program code of the following steps: a determining step of determining an actual area of the current sub-area according to an outer contour of the current sub-area selected from a plurality of sub-areas; a first determining step, when the actual area is less than When the area is preset, a fixed-point rotation work path is used; when the actual area is greater than or equal to the preset area, a spiral work path and / or a round-trip work path are used; the second determination step is to determine whether all the sub-regions are all planned, if not, Then return to the determination step, so as to plan the work path for the to-be-operated objects in the next sub-area adjacent to the current sub-area, until the work paths of multiple to-be-operated objects are all planned.
  • the processor may further execute the program code of the following steps: determining a preset area according to the working width of the work equipment, and when the maximum diameter of the current sub-area is less than the working width, a fixed-point rotation work path is adopted; when the current sub-area When the maximum diameter of the area is greater than or equal to the working width, a spiral working path and / or a round-trip working path is used.
  • the processor may further execute the program code of the following steps: obtaining a first height, a second height, a third height, and a fourth height, where the first height is a surveying altitude of each object to be operated, and the first The second height is the altitude of the take-off point of the work equipment, the third height is the height of each to-be-worked object, and the fourth height is a preset height added to the height of each to-be-worked object; the first height and the second The altitude, third altitude, and fourth altitude calculate the actual flight altitude of the work equipment.
  • the computer terminal may be any computer terminal device in a computer terminal group.
  • the computer terminal may also be a terminal device such as a smart phone (such as an Android mobile phone, an iOS mobile phone, etc.), a tablet computer, an applause computer, and mobile Internet devices (Mobile Internet Devices (MID), PAD).
  • the computer terminal may be located in at least one network device among multiple network devices in a computer network.
  • One embodiment of the present invention also provides a storage medium.
  • the storage medium may be configured to store program code executed by the method for planning a target area operation provided in the first embodiment.
  • the foregoing storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.
  • the storage medium is configured to store program code for performing the following steps: obtaining map image information of the target area to be operated; and identifying multiple sub-objects included in the target area to be operated from the map image information. Area, where multiple sub-areas correspond to multiple to-be-worked objects; plan the action path of the work equipment in the to-be-worked target area according to the multiple sub-areas to control the work equipment to traverse multiple sub-areas when working along the action path.
  • the storage medium is further configured to store program code for performing the following steps: identifying the geometric center position of each sub-region in the multiple sub-regions from the map image information and the outer position of each sub-region profile.
  • the storage medium is further configured to store program code for performing the following steps: based on the geometric center position of each of the multiple subareas, generating and traversing multiple to-be-worked objects in the to-be-worked target area
  • the transition path is planned based on the outer contour of each sub-region in the multiple sub-regions.
  • the work path of multiple to-be-operated objects is planned; the work path is added to the transition path to generate the action path of the work equipment in the target region to be operated.
  • the storage medium is further configured to store program code for performing the following steps: a selection step, and selecting a sub-region closest to the take-off position of the operating equipment from a plurality of sub-regions as a starting sub-region ;
  • the establishing step starting from the geometric center position of the starting sub-region, sequentially searching for the geometric center position of the adjacent sub-region closest to the current sub-region, and establishing a transition path between adjacent geometric center positions;
  • the judging step judging Whether there are sub-areas that are not yet connected, and if so, return to the establishment step until a transition path is generated that traverses multiple objects to be operated.
  • the storage medium is further configured to store program code for performing the following steps: a determining step of determining an actual area of the current sub-region according to an outer contour of the current sub-region selected from a plurality of sub-regions ; The first judgment step, when the actual area is less than the preset area, the fixed-point rotation operation path is used; when the actual area is greater than or equal to the preset area, the spiral operation path and / or the round-trip operation path are used; the second judgment step, the judgment is more Whether all the sub-areas are planned, and if not, return to the determination step, so as to plan the work path for the to-be-operated objects in the next sub-area adjacent to the current sub-area, until the work paths of multiple to-be-operated objects are all planned.
  • the storage medium is further configured to store program code for performing the following steps: determining a preset area according to the working width of the work equipment, and when the maximum diameter of the current sub-area is less than the working width , Using fixed-point rotation work path; when the maximum diameter of the current sub-area is greater than or equal to the width of the work, a spiral work path and / or round-trip work path.
  • the storage medium is further configured to store program code for performing the following steps: obtaining a first height, a second height, a third height, and a fourth height, where the first height is every Surveying and mapping altitude of each to-be-worked object, the second height is the altitude of the take-off point of the work equipment, the third height is the height of each to-be-work object, and the fourth height is an increase based on the height of each to-be-work object Set the altitude; use the first altitude, the second altitude, the third altitude, and the fourth altitude to calculate the actual flight altitude of the operating equipment.
  • sequence numbers of the foregoing embodiments of the present invention are merely for description, and do not represent the superiority or inferiority of the embodiments.
  • the disclosed technical content can be implemented in other ways.
  • the device embodiments described above are only schematic.
  • the division of the unit may be a logical function division.
  • multiple units or components may be combined or may be combined. Integration into another system, or some features can be ignored or not implemented.
  • the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, units or modules, and may be electrical or other forms.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the objective of the solution of this embodiment.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist separately physically, or two or more units may be integrated into one unit.
  • the above integrated unit may be implemented in the form of hardware or in the form of software functional unit.
  • the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium.
  • the technical solution of the present invention essentially or part that contributes to the existing technology or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium , Including a number of instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in various embodiments of the present invention.
  • the foregoing storage media include: U disks, Read-Only Memory (ROM), Random Access Memory (RAM), mobile hard disks, magnetic disks, or optical disks, and other media that can store program codes .

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Strategic Management (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Economics (AREA)
  • Software Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Computing Systems (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Remote Sensing (AREA)
  • General Engineering & Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Databases & Information Systems (AREA)
  • Medical Informatics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Operations Research (AREA)
  • Development Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Quality & Reliability (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Biophysics (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Molecular Biology (AREA)
  • Biomedical Technology (AREA)
  • Agronomy & Crop Science (AREA)

Abstract

本发明公开了一种目标区域作业的规划方法、装置、存储介质及处理器。该方法包括：获取待作业目标区域的地图影像信息；从地图影像信息中识别出待作业目标区域包含的多个子区域，其中，多个子区域与多个待作业对象相对应；根据多个子区域规划作业设备在待作业目标区域内的行动路径，以控制作业设备在沿行动路径作业时遍历多个子区域。本发明解决了相关技术中所采用的果园植保方式易造成资源的浪费、且成本较高的技术问题。

Description

目标区域作业的规划方法、装置、存储介质及处理器 技术领域
本发明涉及计算机领域，具体而言，涉及一种目标区域作业的规划方法、装置、存储介质及处理器。
背景技术
中国是果业大国，近些年来的水果种植面积和产量一直稳居世界第一，同时也是世界上最大的水果消费国。为了确保果业健康有序地发展，机械化果园植保将会是促进果业发展的重要研究课题。果园植保主要关注于果树的病虫害的防治，只有果树管理适当才能产出优质的果实。相对于农田植保来讲，果园植株的密集度较低。如果采用大田作业方式，则易造成农药和水资源的浪费。而如果采用人工精密定位方式，则又会为植保添加额外程序，需要浪费更多的人力、物力和财力。
针对上述的问题，目前尚未提出有效的解决方案。
发明内容
本发明至少部分实施例提供了一种目标区域作业的规划方法、装置、存储介质及处理器，以至少解决相关技术中所采用的果园植保方式易造成资源的浪费、且成本较高的技术问题。
根据本发明其中一实施例，提供了一种目标区域作业的规划方法，包括：
获取待作业目标区域的地图影像信息；从地图影像信息中识别出待作业目标区域包含的多个子区域，其中，多个子区域与多个待作业对象相对应；根据多个子区域规划作业设备在待作业目标区域内的行动路径，以控制作业设备在沿行动路径作业时遍历多个子区域。
可选地，从地图影像信息中识别出待作业目标区域包含的多个子区域包括：从地图影像信息中识别出多个子区域中每个子区域的几何中心位置以及每个子区域的外轮廓。
可选地，当外轮廓为圆形时，几何中心位置为圆形的圆心位置；当外轮廓为矩形时，几何中心位置为矩形的中心位置；当外轮廓为椭圆形时，几何中心位置为椭圆的 圆心位置；当外轮廓为不规则形状时，几何中心位置为不规则形状的形心位置。
可选地，根据多个子区域规划作业设备在待作业目标区域内的行动路径包括：基于多个子区域中每个子区域的几何中心位置生成遍历待作业目标区域内多个待作业对象的过渡路径；基于多个子区域中每个子区域的外轮廓规划多个待作业对象的作业路径；在过渡路径添加作业路径，以生成作业设备在待作业目标区域内的行动路径。
可选地，基于多个子区域中每个子区域的几何中心位置生成遍历待作业目标区域内多个待作业对象的过渡路径包括：选取步骤，多个子区域中选取与作业设备的起飞位置距离最近的子区域为起始子区域；建立步骤，从起始子区域的几何中心位置开始，依次查找与当前子区域距离最近的相邻子区域的几何中心位置，并在相邻几何中心位置之间建立过渡路径；判断步骤，判断是否存在尚未连通的子区域，如果是，则返回建立步骤，直至生成遍历多个待作业对象的过渡路径。
可选地，基于多个子区域中每个子区域的外轮廓规划多个待作业对象的作业路径包括：确定步骤，根据从多个子区域中选取的当前子区域的外轮廓确定当前子区域的实际面积；第一判断步骤，当实际面积小于预设面积时，采用定点自转作业路径；当实际面积大于或等于预设面积时，采用螺旋作业路径和/或往返作业路径；第二判断步骤，判断多个子区域是否全部规划完毕，如果否，则返回确定步骤，以便为当前子区域相邻的下一个子区域内的待作业对象规划作业路径，直至多个待作业对象的作业路径全部规划完毕。
可选地，第一判断步骤包括：根据作业设备的作业幅宽确定预设面积，当当前子区域的最大直径小于作业幅宽时，采用定点自转作业路径；当当前子区域的最大直径大于或等于作业幅宽时，采用螺旋作业路径和/或往返作业路径。
可选地，当相邻的两个或多个子区域的重合面积大于或等于预设阈值，或，当相邻的两个或多个子区域重合面积大于或等于预设占比时，将相邻的两个或多个子区域确定为一个子区域。
可选地，在控制作业设备在沿行动路径作业时遍历多个子区域之前，还包括：获取第一高度、第二高度、第三高度和第四高度，其中，第一高度为每个待作业对象的测绘海拔高度，第二高度为作业设备的起飞点海拔高度，第三高度为每个待作业对象自身高度，第四高度为每个待作业对象自身高度的基础上增加的预设高度；采用第一高度、第二高度、第三高度和第四高度计算作业设备的实际飞行高度。
根据本发明其中一实施例，还提供了一种目标区域作业的规划装置，包括：
第一获取模块，设置为获取待作业目标区域的地图影像信息；识别模块，设置为 从地图影像信息中识别出待作业目标区域包含的多个子区域，其中多个子区域与多个待作业对象相对应；规划模块，设置为根据多个子区域规划作业设备在待作业目标区域内的行动路径，以控制作业设备在沿行动路径作业时遍历多个子区域。
可选地，识别模块，设置为从地图影像信息中识别出多个子区域中每个子区域的几何中心位置以及每个子区域的外轮廓。
可选地，当外轮廓为圆形时，几何中心位置为圆形的圆心位置；当外轮廓为矩形时，几何中心位置为矩形的中心位置；当外轮廓为椭圆形时，几何中心位置为椭圆的圆心位置；当外轮廓为不规则形状时，几何中心位置为不规则形状的形心位置。
可选地，规划模块包括：生成单元，设置为基于多个子区域中每个子区域的几何中心位置生成遍历待作业目标区域内多个待作业对象的过渡路径；规划单元，设置为基于多个子区域中每个子区域的外轮廓规划多个待作业对象的作业路径；处理单元，设置为在过渡路径添加作业路径，以生成作业设备在待作业目标区域内的行动路径。
可选地，生成单元包括：选取子单元，设置为从多个子区域中选取与作业设备的起飞位置距离最近的子区域为起始子区域；建立子单元，设置为从起始子区域的几何中心位置开始，依次查找与当前子区域距离最近的相邻子区域的几何中心位置，并在相邻几何中心位置之间建立过渡路径；判断子单元，设置为判断是否存在尚未连通的子区域，如果是，则返回建立子单元，直至生成遍历多个待作业对象的过渡路径。
可选地，规划单元包括：确定子单元，设置为根据从多个子区域中选取的当前子区域的外轮廓确定当前子区域的实际面积；第一判断子单元，设置为当实际面积小于预设面积时，采用定点自转作业路径；当实际面积大于或等于预设面积时，采用螺旋作业路径和/或往返作业路径；第二判断子单元，设置为判断多个子区域是否全部规划完毕，如果否，则返回确定子单元，以便为当前子区域相邻的下一个子区域内的待作业对象规划作业路径，直至多个待作业对象的作业路径全部规划完毕。
可选地，第一判断子单元，设置为根据作业设备的作业幅宽确定预设面积，当当前子区域的最大直径小于作业幅宽时，采用定点自转作业路径；当当前子区域的最大直径大于或等于作业幅宽时，采用螺旋作业路径和/或往返作业路径。
可选地，当相邻的两个或多个子区域的重合面积大于或等于预设阈值，或，当相邻的两个或多个子区域重合面积大于或等于预设占比时，将相邻的两个或多个子区域确定为一个子区域。
可选地，上述装置还包括：第二获取模块，设置为获取第一高度、第二高度、第三高度和第四高度，其中，第一高度为每个待作业对象的测绘海拔高度，第二高度为 作业设备的起飞点海拔高度，第三高度为每个待作业对象自身高度，第四高度为每个待作业对象自身高度的基础上增加的预设高度；计算模块，设置为采用第一高度、第二高度、第三高度和第四高度计算作业设备的实际飞行高度。
根据本发明其中一实施例，还提供了一种存储介质，存储介质包括存储的程序，其中，在程序运行时控制存储介质所在设备执行上述目标区域作业的规划方法。
根据本发明其中一实施例，还提供了一种处理器，处理器设置为运行程序，其中，程序运行时执行上述目标区域作业的规划方法。
在本发明至少部分实施例中，采用获取待作业目标区域的地图影像信息，以及从地图影像信息中识别出待作业目标区域包含的与多个待作业对象相对应的多个子区域的方式，根据多个子区域规划作业设备在待作业目标区域内的行动路径并控制作业设备在沿行动路径作业时遍历多个子区域，达到了在实际应用时只需要选择待作业目标区域，然后***会直接根据所选择待作业目标区域的位置以及获取到的高清影像生成整个待作业目标区域的行动路径的目的，从而实现了既可以做到精准植保，又可以减少大量的人工成本的技术效果，进而解决了相关技术中所采用的果园植保方式易造成资源的浪费、且成本较高的技术问题。
附图说明
此处所说明的附图用来提供对本发明的进一步理解，构成本申请的一部分，本发明的示意性实施例及其说明用于解释本发明，并不构成对本发明的不当限定。在附图中：
图1是根据本发明其中一实施例的目标区域作业的规划方法的流程图；
图2是根据本发明其中一优选实施例的从高清地图影像中提取部分数据进行标注过程的示意图；
图3是根据本发明其中一优选实施例的从地图影像信息中识别出每个子区域的几何中心位置的示意图；
图4是根据本发明其中一优选实施例的过渡路径规划过程的示意图；
图5是根据本发明其中一实施例的目标区域作业的规划装置的结构框图；
图6是根据本发明其中一优选实施例的目标区域作业的规划装置的结构框图。
具体实施方式
为了使本技术领域的人员更好地理解本发明方案，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分的实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都应当属于本发明保护的范围。
需要说明的是，本发明的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本发明的实施例能够以除了在这里图示或描述的那些以外的顺序实施。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程、方法、***、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
根据本发明其中一实施例，提供了一种目标区域作业的规划方法的实施例，需要说明的是，在附图的流程图示出的步骤可以在诸如一组计算机可执行指令的计算机***中执行，并且，虽然在流程图中示出了逻辑顺序，但是在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤。
图1是根据本发明其中一实施例的目标区域作业的规划方法的流程图，如图1所示，该方法包括如下步骤：
步骤S12，获取待作业目标区域的地图影像信息；
步骤S14，从地图影像信息中识别出待作业目标区域包含的多个子区域，其中，多个子区域与多个待作业对象相对应；
步骤S16，根据多个子区域规划作业设备在待作业目标区域内的行动路径，以控制作业设备在沿行动路径作业时遍历多个子区域。
通过上述步骤，可以采用获取待作业目标区域的地图影像信息，以及从地图影像信息中识别出待作业目标区域包含的与多个待作业对象相对应的多个子区域的方式，根据多个子区域规划作业设备在待作业目标区域内的行动路径并控制作业设备在沿行动路径作业时遍历多个子区域，达到了在实际应用时只需要选择待作业目标区域，然后***会直接根据所选择待作业目标区域的位置以及获取到的高清影像生成整个待作业目标区域的行动路径的目的，从而实现了既可以做到精准植保，又可以减少大量的 人工成本的技术效果，进而解决了相关技术中所采用的果园植保方式易造成资源的浪费、且成本较高的技术问题。
上述方法通常应用于遥控无人机作业的控制终端上。上述地图影像包括二维地图、三维地图、DSM地图、图画、影片、图片等。上述待作业目标区域可以包括但不限于：果园植保区域(例如：苹果园植保区域)、果实采摘区域(例如：苹果采摘区域)、果实剪枝区域(例如：葡萄剪枝区域、棉花剪枝区域)、田地区域(麦田收割区域)，在所述待作业目标区域中含有多个待作业对象，例如所述待作业区域为果园时，所述待作业对象为果树；当所述待作业目标区域为田地时，所述待作业对象为成片的小麦等作物。上述作业设备可以是具有植保作业功能的无人机，也可以为地面作业设备，如拖拉机。以下可选实施例将主要以果园植保区域为例进行解释说明。
可选地，在步骤S14中，从地图影像信息中识别出待作业目标区域包含的多个子区域可以包括以下执行步骤：
步骤S141，从地图影像信息中识别出多个子区域中每个子区域的几何中心位置以及每个子区域的外轮廓。
具体地，当外轮廓为圆形时，几何中心位置可以为圆形的圆心位置；当外轮廓为矩形时，几何中心位置可以为矩形的中心位置；当外轮廓为椭圆形时，几何中心位置可以为椭圆的圆心位置；当外轮廓为不规则形状时，几何中心位置可以为不规则形状的形心位置。识别上述几何中心位置，通常需要在地图影像中对其进行进一步的标注，本发明不限定标注形式，只要其能标识出外轮廓和中心位置即可，例如采用三个点标注一个圆，本领域内技术人员可以理解，当标注三个点时就可以按照惯常算法得到圆的外轮廓和圆心。又如采用矩形框标注矩形区域，又如采用四个点标注矩形区域，又如采用圆心标注圆形区域的中心位置，用圆形框标注圆心区域的外轮廓等。
在一个可选实施例中，首先，利用测绘无人机或者航拍无人机获取高清的地图影像。然后，鉴于获取到的地图影像所包含的数据量较大，为此，需要从获取到的地图影像中提取部分数据(例如：可见度较高的部分图像)进行标注作为训练集。标注方式是基于无人机采集的高清的地图影像，首先通过人工方式将每株果树的边缘采用预设形状(例如：圆形)加以标注，然后由终端自动生成对应的圆框数据。该圆框数据可以包括但不限于：高清地图影像中每株果树的真实圆心位置以及半径数据。
图2是根据本发明其中一优选实施例的从高清地图影像中提取部分数据进行标注过程的示意图，如图2所示，左侧为输入的原始图像，右侧则为从原始图像中提取可见度较高的部分数据进行标注的图像。右侧图像中出现的圆形线条即为标注的边界的数据。
在此基础上，深度网络模型主要是基于上述圆形标注的目标检测进行反复训练得到。具体过程如下：首先，将原始图像(通常为RGB图，其分辨率可以为256×256)作为输入项，通过卷积神经网络(CNN)得到特征图(通常为尺寸较小且分层的抽象图，其分辨率可以为16×16)。该卷积神经网络为预训练的分类网络。另外，考虑到特征图的层级越高，提取到的特征越抽象，而在果园中果树的分布相对密集，为此，在本发明提供的一个可选实施例中，将选用底层(即层级较低)的特征图，以便能够更加容易检测到目标物体(即每株果树)。其次，对特征图进行核为1的卷积处理以分别输出位置信息(loc)和所有目标分类的概率(logits(c 1，c 2，…c p))。loc可以表示为Δ(cx，cy，radius)，其中，cx，cy表示目标圆的中心点，radius表示半径的偏置值。logits则主要用于区分果树与其他物体以及背景。
在得到上述计算结果之后，还可以根据上述圆框数据分别计算分类损失值和圆的回归损失值，进而执行梯度反向传递处理，以优化模型参数，其具体计算过程如以下公式所示：
Figure PCTCN2019071998-appb-000001
Figure PCTCN2019071998-appb-000002
Figure PCTCN2019071998-appb-000003
Figure PCTCN2019071998-appb-000004
Figure PCTCN2019071998-appb-000005
其中，P为正例目标(目标为果树)，Neg为反例目标(目标为背景)，l为标注圆的真实参数，g为标注圆的预测参数，d为默认值圆参数，smooth L1为损失函数。
图3是根据本发明其中一优选实施例的从地图影像信息中识别出每个子区域的几何中心位置的示意图，如图3所示，通过反复训练并修正上述深度网络模型，***可以根据输入的果园高清地图影像，能够通过使用AI图像识别技术准确地从地图影像信息中识别出多个子区域中每个子区域的几何中心位置并且加以标注。而在后续规划过程中，通过使用每株果树的几何中心位置即可完成行动路径规划。
需要说明的是，在上述可选实施例中，当相邻的两个或多个子区域的重合面积大于或等于预设阈值，或，当相邻的两个或多个子区域重合面积大于或等于预设占比时，相邻的两个或多个子区域可被确定为一个子区域。
可选地，在步骤S16中，根据多个子区域规划作业设备在待作业目标区域内的行动路径可以包括以下执行步骤：
步骤S161，基于多个子区域中每个子区域的几何中心位置生成遍历待作业目标区域内多个待作业对象的过渡路径；
步骤S162，基于多个子区域中每个子区域的外轮廓规划多个待作业对象的作业路径；
步骤S163，在过渡路径添加作业路径，以生成作业设备在待作业目标区域内的行动路径。
在本发明的一个可选实施例中，首先，通过上述深度学习和计算机视觉从待作业果园的高清影像中准确识别出每株果树的几何中心位置。其次，根据多个子区域中每个子区域的几何中心位置的像素坐标生成遍历待作业果园内各株果树的过渡路径。该过渡路径用于确定整个果园中每株果树的依次喷洒顺序。然后，再根据每个子区域的外轮廓规划每株果树的作业路径。作业路径用于确定整个果园中每株果树的药物喷洒方式。最终，通过将过渡路径与作业路径相结合，从而形成一整套能够喷洒整个果园内所有果树的完整行动路径。
可选地，在步骤S161中，基于多个子区域中每个子区域的几何中心位置生成遍历待作业目标区域内多个待作业对象的过渡路径可以包括以下执行步骤：
步骤S1611，多个子区域中选取与作业设备的起飞位置距离最近的子区域为起始子区域；
步骤S1612，从起始子区域的几何中心位置开始，依次查找与当前子区域距离最近的相邻子区域的几何中心位置，并在相邻几何中心位置之间建立过渡路径；
步骤S1613，判断是否存在尚未连通的子区域，如果是，则返回步骤S1612，直至生成遍历多个待作业对象的过渡路径。
在过渡路径生成过程中，首先，无人机需要从多个子区域中选取与无人机起飞位置最近的几何中心位置所在的子区域作为起始子区域；其次，从起始子区域的几何中心位置开始，根据最短路径算法从相邻的一个或多个几何中心位置中选取距离当前几何中心位置最近的子区域；然后，在当前子区域与选取的相邻子区域之间采用连线在 这两个几何中心位置之间建立过渡路径。最终，通过将高清图像中标注的全部几何中心位置不重复地两两相连，得到无人机在整个果园的各株果树之间行进的过渡路径。
图4是根据本发明其中一优选实施例的过渡路径规划过程的示意图，如图4所示，通过输入原始图像，在获取到果园内各株果树的几何中心位置(A1，A2，…A35)之后，可以将距离无人机起飞位置最近的果树作为起始出发地。假设当前距离无人机起飞位置最近的果树为A1所在位置的果树，则A1所在的子区域即为起始子区域。从该从起始子区域的几何中心位置A1开始，查找与A1所在子区域距离最近的相邻子区域的几何中心位置A2，并在A1与A2之间建立过渡路径(其实质上为分段路径)。其次，判断是否存在尚未连通的子区域(即查找尚未连通的几何中心位置)，通过查找发现与A2所在子区域距离最近的相邻子区域的几何中心位置A3尚未连通，因此，需要在A1与A2之间建立过渡路径。然后，再判断是否存在尚未连通的子区域，通过查找发现与A3所在子区域距离最近的相邻子区域的几何中心位置A4尚未连通，因此，需要在A3与A4之间建立过渡路径。以此类推，直至A1至A35全部连通完毕，最终得到上述遍历果园内全部果树的过渡路径。
可选地，在步骤S162中，基于多个子区域中每个子区域的外轮廓规划多个待作业对象的作业路径可以包括以下执行步骤：
步骤S1621，根据从多个子区域中选取的当前子区域的外轮廓确定当前子区域的实际面积；
步骤S1622，当实际面积小于预设面积时，采用定点自转作业路径；当实际面积大于或等于预设面积时，采用螺旋作业路径和/或往返作业路径；
步骤S1623，判断多个子区域是否全部规划完毕，如果否，则返回步骤S1621，以便为当前子区域相邻的下一个子区域内的待作业对象规划作业路径，直至多个待作业对象的作业路径全部规划完毕。
在优选实施过程中，可以根据作业设备的作业幅宽(通常为1.5米-3米)确定预设面积。在当前子区域的最大直径小于作业幅宽时，可以采用定点自转作业路径。例如：控制无人机悬停在当前子区域的几何中心位置对应的上空，通过自转作业方式向当前果树喷洒农药。
在当前子区域的最大直径大于或等于作业幅宽时，采用螺旋作业路径和/或往返作业路径。具体地，螺旋作业路径特别适用于丘陵地区的果树植保服务，能够根据测绘信息和果树的生长情况自动规划喷洒路径。若果树的树冠直径较小，无人机会在果树上方，自旋一周进行喷洒。若果树的树冠直径较大，则无人机在果树上方，以树冠为 中心，从中心到周边进行“蚊香状航线”飞行。另外，无人机只有在飞行到果树上方执行航线时，才会打开喷头喷洒，在其他时间段喷头均处于关闭状态，从而确保农药被有效地喷洒在树叶上。此外，通过采用往返作业路径，可以控制无人机在当前子区域上方采用往返方波形或往返波浪形的作业方式向当前果树喷洒农药。
可选地，在步骤S16，控制作业设备在沿行动路径作业时遍历多个子区域之前，还可以包括以下执行步骤：
步骤S17，获取第一高度、第二高度、第三高度和第四高度，其中，第一高度为每个待作业对象的测绘海拔高度，第二高度为作业设备的起飞点海拔高度，第三高度为每个待作业对象自身高度，第四高度为每个待作业对象自身高度的基础上增加的预设高度；
步骤S18，采用第一高度、第二高度、第三高度和第四高度计算作业设备的实际飞行高度。
当果树处于山地时，不但需要考虑果树的自身高度，还需要考虑果树的实际海拔高度。果树的实际海拔高度既可以通过三维的数字表面模型(DSM)地图来确定，也可以根据测绘数据来确定。而果树的自身高度可以通过人工方式测量得到，当然也可以通过作业机的距离传感器来确定。由此可见，行动路径的规划实际上是三维的。
在果树植保导航过程中，无人机可以使用全球导航卫星***(GNSS)实时差分定位(RTK)导航组件为无人机提供的高度数据进行定高飞行。飞行高度受作物高度及周围环境的影响，一般飞行高度距离植物冠层1.5-2.5米，如果是使用RTK定高，还需要参考地势差，选择合适的高度。
当测绘人员使用测绘设备对果树进行定点航线测绘时，测绘设备不仅能够记录经纬度信息，还会记录高程信息，因此在测绘过程中需要测绘器保持竖直触地状态，以确保采集到的高程数据准确无误。在此过程中，无人机针对每株果树的飞行高度是以起飞点水平面的海拔高度为基准，再综合果树测绘海拔高度、果树自身高度和离树梢高度计算得到的，具体计算公式如下：
无人机的飞行高度＝(果树测绘海拔高度-起飞点水平面的海拔高度)+(果树自身高度+离树梢高度)。
根据本发明其中一实施例，提供了一种目标区域作业的规划装置的实施例。图5是根据本发明其中一实施例的目标区域作业的规划装置的结构框图，如图5所示，该 装置包括：第一获取模块10，设置为获取待作业目标区域的地图影像信息；识别模块20，设置为从地图影像信息中识别出待作业目标区域包含的多个子区域，其中多个子区域与多个待作业对象相对应；规划模块30，设置为根据多个子区域规划作业设备在待作业目标区域内的行动路径，以控制作业设备在沿行动路径作业时遍历多个子区域。
可选地，识别模块20，设置为从地图影像信息中识别出多个子区域中每个子区域的几何中心位置以及每个子区域的外轮廓。
可选地，当外轮廓为圆形时，几何中心位置为圆形的圆心位置；当外轮廓为矩形时，几何中心位置为矩形的中心位置；当外轮廓为椭圆形时，几何中心位置为椭圆的圆心位置；当外轮廓为不规则形状时，几何中心位置为不规则形状的形心位置。
可选地，图6是根据本发明其中一优选实施例的目标区域作业的规划装置的结构框图，如图6所示，规划模块30包括：生成单元300，设置为基于多个子区域中每个子区域的几何中心位置生成遍历待作业目标区域内多个待作业对象的过渡路径；规划单元302，设置为基于多个子区域中每个子区域的外轮廓规划多个待作业对象的作业路径；处理单元304，设置为在过渡路径添加作业路径，以生成作业设备在待作业目标区域内的行动路径。
可选地，生成单元300包括：选取子单元(图中未示出)，设置为从多个子区域中选取与作业设备的起飞位置距离最近的子区域为起始子区域；建立子单元(图中未示出)，设置为从起始子区域的几何中心位置开始，依次查找与当前子区域距离最近的相邻子区域的几何中心位置，并在相邻几何中心位置之间建立过渡路径；判断子单元(图中未示出)，设置为判断是否存在尚未连通的子区域，如果是，则返回建立子单元，直至生成遍历多个待作业对象的过渡路径。
可选地，规划单元302包括：确定子单元(图中未示出)，设置为根据从多个子区域中选取的当前子区域的外轮廓确定当前子区域的实际面积；第一判断子单元(图中未示出)，设置为当实际面积小于预设面积时，采用定点自转作业路径；当实际面积大于或等于预设面积时，采用螺旋作业路径和/或往返作业路径；第二判断子单元(图中未示出)，设置为判断多个子区域是否全部规划完毕，如果否，则返回确定子单元，以便为当前子区域相邻的下一个子区域内的待作业对象规划作业路径，直至多个待作业对象的作业路径全部规划完毕。
可选地，第一判断子单元(图中未示出)，设置为根据作业设备的作业幅宽确定预设面积，当当前子区域的最大直径小于作业幅宽时，采用定点自转作业路径；当当前子区域的最大直径大于或等于作业幅宽时，采用螺旋作业路径和/或往返作业路径。
可选地，当相邻的两个或多个子区域的重合面积大于或等于预设阈值，或，当相邻的两个或多个子区域重合面积大于或等于预设占比时，将相邻的两个或多个子区域确定为一个子区域。
可选地，如图6所示，上述装置还包括：第二获取模块40，设置为获取第一高度、第二高度、第三高度和第四高度，其中，第一高度为每个待作业对象的测绘海拔高度，第二高度为作业设备的起飞点海拔高度，第三高度为每个待作业对象自身高度，第四高度为每个待作业对象自身高度的基础上增加的预设高度；计算模块50，设置为采用第一高度、第二高度、第三高度和第四高度计算作业设备的实际飞行高度。
本发明其中一实施例还可以提供一种计算机终端。在本实施例中，该计算机终端可以包括：一个或多个处理器以及存储器。
其中，存储器可设置为存储软件程序以及模块，如本发明实施例中的安全漏洞检测方法和装置对应的程序指令/模块，处理器通过运行存储在存储器内的软件程序以及模块，从而执行各种功能应用以及数据处理，即实现上述的目标区域作业的规划方法。存储器可包括高速随机存储器，还可以包括非易失性存储器，如一个或者多个磁性存储装置、闪存、或者其他非易失性固态存储器。在一些实例中，存储器可进一步包括相对于处理器远程设置的存储器，这些远程存储器可以通过网络连接至终端。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
处理器可以通过传输装置调用存储器存储的信息及应用程序，以执行下述步骤：获取待作业目标区域的地图影像信息；从地图影像信息中识别出待作业目标区域包含的多个子区域，其中，多个子区域与多个待作业对象相对应；根据多个子区域规划作业设备在待作业目标区域内的行动路径，以控制作业设备在沿行动路径作业时遍历多个子区域。
可选的，上述处理器还可以执行如下步骤的程序代码：从地图影像信息中识别出多个子区域中每个子区域的几何中心位置以及每个子区域的外轮廓。
可选的，上述处理器还可以执行如下步骤的程序代码：基于多个子区域中每个子区域的几何中心位置生成遍历待作业目标区域内多个待作业对象的过渡路径；基于多个子区域中每个子区域的外轮廓规划多个待作业对象的作业路径；在过渡路径添加作业路径，以生成作业设备在待作业目标区域内的行动路径。
可选的，上述处理器还可以执行如下步骤的程序代码：选取步骤，多个子区域中选取与作业设备的起飞位置距离最近的子区域为起始子区域；建立步骤，从起始子区 域的几何中心位置开始，依次查找与当前子区域距离最近的相邻子区域的几何中心位置，并在相邻几何中心位置之间建立过渡路径；判断步骤，判断是否存在尚未连通的子区域，如果是，则返回建立步骤，直至生成遍历多个待作业对象的过渡路径。
可选的，上述处理器还可以执行如下步骤的程序代码：确定步骤，根据从多个子区域中选取的当前子区域的外轮廓确定当前子区域的实际面积；第一判断步骤，当实际面积小于预设面积时，采用定点自转作业路径；当实际面积大于或等于预设面积时，采用螺旋作业路径和/或往返作业路径；第二判断步骤，判断多个子区域是否全部规划完毕，如果否，则返回确定步骤，以便为当前子区域相邻的下一个子区域内的待作业对象规划作业路径，直至多个待作业对象的作业路径全部规划完毕。
可选的，上述处理器还可以执行如下步骤的程序代码：根据作业设备的作业幅宽确定预设面积，当当前子区域的最大直径小于作业幅宽时，采用定点自转作业路径；当当前子区域的最大直径大于或等于作业幅宽时，采用螺旋作业路径和/或往返作业路径。
可选的，上述处理器还可以执行如下步骤的程序代码：获取第一高度、第二高度、第三高度和第四高度，其中，第一高度为每个待作业对象的测绘海拔高度，第二高度为作业设备的起飞点海拔高度，第三高度为每个待作业对象自身高度，第四高度为每个待作业对象自身高度的基础上增加的预设高度；采用第一高度、第二高度、第三高度和第四高度计算作业设备的实际飞行高度。
本领域普通技术人员可以理解，该计算机终端可以是计算机终端群中的任意一个计算机终端设备。当然，计算机终端也可以是智能手机(如Android手机、iOS手机等)、平板电脑、掌声电脑以及移动互联网设备(Mobile Internet Devices，MID)、PAD等终端设备。可选地，在本实施例中，上述计算机终端可以位于计算机网络的多个网络设备中的至少一个网络设备。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令终端设备相关的硬件来完成，该程序可以存储于一计算机可读存储介质中，存储介质可以包括：闪存盘、只读存储器(Read-Only Memory，ROM)、随机存取器(Random Access Memory，RAM)、磁盘或光盘等。
本发明其中一实施例还提供了一种存储介质。可选地，在本实施例中，上述存储介质可以设置为保存上述实施例一所提供的目标区域作业的规划方法所执行的程序代码。
可选地，在本实施例中，上述存储介质可以位于计算机网络中计算机终端群中的任意一个计算机终端中，或者位于移动终端群中的任意一个移动终端中。
可选地，在本实施例中，存储介质被设置为存储用于执行以下步骤的程序代码：获取待作业目标区域的地图影像信息；从地图影像信息中识别出待作业目标区域包含的多个子区域，其中，多个子区域与多个待作业对象相对应；根据多个子区域规划作业设备在待作业目标区域内的行动路径，以控制作业设备在沿行动路径作业时遍历多个子区域。
可选地，在本实施例中，存储介质还被设置为存储用于执行以下步骤的程序代码：从地图影像信息中识别出多个子区域中每个子区域的几何中心位置以及每个子区域的外轮廓。
可选的，在本实施例中，存储介质还被设置为存储用于执行以下步骤的程序代码：基于多个子区域中每个子区域的几何中心位置生成遍历待作业目标区域内多个待作业对象的过渡路径；基于多个子区域中每个子区域的外轮廓规划多个待作业对象的作业路径；在过渡路径添加作业路径，以生成作业设备在待作业目标区域内的行动路径。
可选的，在本实施例中，存储介质还被设置为存储用于执行以下步骤的程序代码：选取步骤，多个子区域中选取与作业设备的起飞位置距离最近的子区域为起始子区域；建立步骤，从起始子区域的几何中心位置开始，依次查找与当前子区域距离最近的相邻子区域的几何中心位置，并在相邻几何中心位置之间建立过渡路径；判断步骤，判断是否存在尚未连通的子区域，如果是，则返回建立步骤，直至生成遍历多个待作业对象的过渡路径。
可选的，在本实施例中，存储介质还被设置为存储用于执行以下步骤的程序代码：确定步骤，根据从多个子区域中选取的当前子区域的外轮廓确定当前子区域的实际面积；第一判断步骤，当实际面积小于预设面积时，采用定点自转作业路径；当实际面积大于或等于预设面积时，采用螺旋作业路径和/或往返作业路径；第二判断步骤，判断多个子区域是否全部规划完毕，如果否，则返回确定步骤，以便为当前子区域相邻的下一个子区域内的待作业对象规划作业路径，直至多个待作业对象的作业路径全部规划完毕。
可选的，在本实施例中，存储介质还被设置为存储用于执行以下步骤的程序代码：根据作业设备的作业幅宽确定预设面积，当当前子区域的最大直径小于作业幅宽时，采用定点自转作业路径；当当前子区域的最大直径大于或等于作业幅宽时，采用螺旋作业路径和/或往返作业路径。
可选的，在本实施例中，存储介质还被设置为存储用于执行以下步骤的程序代码：获取第一高度、第二高度、第三高度和第四高度，其中，第一高度为每个待作业对象的测绘海拔高度，第二高度为作业设备的起飞点海拔高度，第三高度为每个待作业对象自身高度，第四高度为每个待作业对象自身高度的基础上增加的预设高度；采用第一高度、第二高度、第三高度和第四高度计算作业设备的实际飞行高度。
上述本发明实施例序号仅仅为了描述，不代表实施例的优劣。
在本发明的上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见其他实施例的相关描述。
在本申请所提供的几个实施例中，应该理解到，所揭露的技术内容，可通过其它的方式实现。其中，以上所描述的装置实施例仅仅是示意性的，例如所述单元的划分，可以为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个***，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，单元或模块的间接耦合或通信连接，可以是电性或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本发明各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可为个人计算机、服务器或者网络设备等)执行本发明各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述仅是本发明的优选实施方式，应当指出，对于本技术领域的普通技术人 员来说，在不脱离本发明原理的前提下，还可以做出若干改进和润饰，这些改进和润饰也应视为本发明的保护范围。

Claims (20)

  1. 一种目标区域作业的规划方法，包括：
    获取待作业目标区域的地图影像信息；
    从所述地图影像信息中识别出所述待作业目标区域包含的多个子区域，其中，所述多个子区域与多个待作业对象相对应；
    根据所述多个子区域规划作业设备在所述待作业目标区域内的行动路径，以控制所述作业设备在沿所述行动路径作业时遍历所述多个子区域。
  2. 根据权利要求1所述的方法，其中，从所述地图影像信息中识别出所述待作业目标区域包含的所述多个子区域包括：
    从所述地图影像信息中识别出所述多个子区域中每个子区域的几何中心位置以及每个子区域的外轮廓。
  3. 根据权利要求2所述的方法，其中，当所述外轮廓为圆形时，所述几何中心位置为所述圆形的圆心位置；当所述外轮廓为矩形时，所述几何中心位置为所述矩形的中心位置；当所述外轮廓为椭圆形时，所述几何中心位置为所述椭圆的圆心位置；当所述外轮廓为不规则形状时，所述几何中心位置为所述不规则形状的形心位置。
  4. 根据权利要求2或3所述的方法，其中，根据所述多个子区域规划所述作业设备在所述待作业目标区域内的行动路径包括：
    基于所述多个子区域中每个子区域的几何中心位置生成遍历所述待作业目标区域内所述多个待作业对象的过渡路径；
    基于所述多个子区域中每个子区域的外轮廓规划所述多个待作业对象的作业路径；
    在所述过渡路径添加所述作业路径，以生成所述作业设备在所述待作业目标区域内的行动路径。
  5. 根据权利要求4所述的方法，其中，基于所述多个子区域中每个子区域的几何中心位置生成遍历所述待作业目标区域内所述多个待作业对象的过渡路径包括：
    选取步骤，所述多个子区域中选取与所述作业设备的起飞位置距离最近的子区域为起始子区域；
    建立步骤，从所述起始子区域的几何中心位置开始，依次查找与当前子区域距离最近的相邻子区域的几何中心位置，并在相邻几何中心位置之间建立过渡路径；
    判断步骤，判断是否存在尚未连通的子区域，如果是，则返回所述建立步骤，直至生成遍历所述多个待作业对象的过渡路径。
  6. 根据权利要求4所述的方法，其中，基于所述多个子区域中每个子区域的外轮廓规划所述多个待作业对象的作业路径包括：
    确定步骤，根据从所述多个子区域中选取的当前子区域的外轮廓确定所述当前子区域的实际面积；
    第一判断步骤，当所述实际面积小于预设面积时，采用定点自转作业路径；当所述实际面积大于或等于所述预设面积时，采用螺旋作业路径和/或往返作业路径；
    第二判断步骤，判断所述多个子区域是否全部规划完毕，如果否，则返回所述确定步骤，以便为所述当前子区域相邻的下一个子区域内的待作业对象规划作业路径，直至所述多个待作业对象的作业路径全部规划完毕。
  7. 根据权利要求6所述的方法，其中，所述第一判断步骤包括：
    根据所述作业设备的作业幅宽确定所述预设面积，当所述当前子区域的最大直径小于所述作业幅宽时，采用定点自转作业路径；当所述当前子区域的最大直径大于或等于所述作业幅宽时，采用螺旋作业路径和/或往返作业路径。
  8. 根据权利要求1所述的方法，其中，当相邻的两个或多个子区域的重合面积大于或等于预设阈值，或，当相邻的两个或多个子区域重合面积大于或等于预设占比时，将所述相邻的两个或多个子区域确定为一个子区域。
  9. 根据权利要求1所述的方法，其中，在控制所述作业设备在沿所述行动路径作业时遍历所述多个子区域之前，还包括：
    获取第一高度、第二高度、第三高度和第四高度，其中，所述第一高度为每个待作业对象的测绘海拔高度，所述第二高度为所述作业设备的起飞点海拔高度，所述第三高度为每个待作业对象自身高度，所述第四高度为所述每个待作业对象自身高度的基础上增加的预设高度；
    采用所述第一高度、所述第二高度、所述第三高度和所述第四高度计算所述作业设备的实际飞行高度。
  10. 一种目标区域作业的规划装置，包括：
    第一获取模块，设置为获取待作业目标区域的地图影像信息；
    识别模块，设置为从所述地图影像信息中识别出所述待作业目标区域包含的多个子区域，其中，所述多个子区域与多个待作业对象相对应；
    规划模块，设置为根据所述多个子区域规划作业设备在所述待作业目标区域内的行动路径，以控制所述作业设备在沿所述行动路径作业时遍历所述多个子区域。
  11. 根据权利要求10所述的装置，其中，所述识别模块，设置为从所述地图影像信息中识别出所述多个子区域中每个子区域的几何中心位置以及每个子区域的外轮廓。
  12. 根据权利要求11所述的装置，其中，当所述外轮廓为圆形时，所述几何中心位置为所述圆形的圆心位置；当所述外轮廓为矩形时，所述几何中心位置为所述矩形的中心位置；当所述外轮廓为椭圆形时，所述几何中心位置为所述椭圆的圆心位置；当所述外轮廓为不规则形状时，所述几何中心位置为所述不规则形状的形心位置。
  13. 根据权利要求11或12所述的装置，其中，所述规划模块包括：
    生成单元，设置为基于所述多个子区域中每个子区域的几何中心位置生成遍历所述待作业目标区域内所述多个待作业对象的过渡路径；
    规划单元，设置为基于所述多个子区域中每个子区域的外轮廓规划所述多个待作业对象的作业路径；
    处理单元，设置为在所述过渡路径添加所述作业路径，以生成所述作业设备在所述待作业目标区域内的行动路径。
  14. 根据权利要求13所述的装置，其中，所述生成单元包括：
    选取子单元，设置为从所述多个子区域中选取与所述作业设备的起飞位置距离最近的子区域为起始子区域；
    建立子单元，设置为从所述起始子区域的几何中心位置开始，依次查找与当前子区域距离最近的相邻子区域的几何中心位置，并在相邻几何中心位置之间建立过渡路径；
    判断子单元，设置为判断是否存在尚未连通的子区域，如果是，则返回所述建立子单元，直至生成遍历所述多个待作业对象的过渡路径。
  15. 根据权利要求13所述的装置，其中，所述规划单元包括：
    确定子单元，设置为根据从所述多个子区域中选取的当前子区域的外轮廓确定所述当前子区域的实际面积；
    第一判断子单元，设置为当所述实际面积小于预设面积时，采用定点自转作业路径；当所述实际面积大于或等于所述预设面积时，采用螺旋作业路径和/或往返作业路径；
    第二判断子单元，设置为判断所述多个子区域是否全部规划完毕，如果否，则返回所述确定子单元，以便为所述当前子区域相邻的下一个子区域内的待作业对象规划作业路径，直至所述多个待作业对象的作业路径全部规划完毕。
  16. 根据权利要求15所述的装置，其中，所述第一判断子单元，设置为根据所述作业设备的作业幅宽确定所述预设面积，当所述当前子区域的最大直径小于所述作业幅宽时，采用定点自转作业路径；当所述当前子区域的最大直径大于或等于所述作业幅宽时，采用螺旋作业路径和/或往返作业路径。
  17. 根据权利要求10所述的装置，其中，当相邻的两个或多个子区域的重合面积大于或等于预设阈值，或，当相邻的两个或多个子区域重合面积大于或等于预设占比时，将所述相邻的两个或多个子区域确定为一个子区域。
  18. 根据权利要求10所述的装置，其中，所述装置还包括：
    第二获取模块，设置为获取第一高度、第二高度、第三高度和第四高度，其中，所述第一高度为每个待作业对象的测绘海拔高度，所述第二高度为所述作业设备的起飞点海拔高度，所述第三高度为每个待作业对象自身高度，所述第四高度为所述每个待作业对象自身高度的基础上增加的预设高度；
    计算模块，设置为采用所述第一高度、所述第二高度、所述第三高度和所述第四高度计算所述作业设备的实际飞行高度。
  19. 一种存储介质，所述存储介质包括存储的程序，其中，在所述程序运行时控制所述存储介质所在设备执行权利要求1至9中任意一项所述的目标区域作业的规划方法。
  20. 一种处理器，所述处理器设置为运行程序，其中，所述程序运行时执行权利要求1至9中任意一项所述的目标区域作业的规划方法。
PCT/CN2019/071998 2018-05-28 2019-01-16 目标区域作业的规划方法、装置、存储介质及处理器 WO2019227948A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
AU2019276115A AU2019276115B2 (en) 2018-05-28 2019-01-16 Target Region Operation Planning Method and Apparatus, Storage Medium, and Processor
EP19812180.8A EP3805981A4 (en) 2018-05-28 2019-01-16 METHOD AND DEVICE FOR PLANNING OPERATION IN A TARGET REGION, STORAGE MEDIUM AND PROCESSOR
JP2020566656A JP2021525426A (ja) 2018-05-28 2019-01-16 ターゲット領域作業の計画方法、装置、記憶媒体及びプロセッサ
US17/044,105 US20210150184A1 (en) 2018-05-28 2019-01-16 Target region operation planning method and apparatus, storage medium, and processor

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810525552.2A CN108846325A (zh) 2018-05-28 2018-05-28 目标区域作业的规划方法、装置、存储介质及处理器
CN201810525552.2 2018-05-28

Publications (1)

Publication Number Publication Date
WO2019227948A1 true WO2019227948A1 (zh) 2019-12-05

Family

ID=64209893

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/071998 WO2019227948A1 (zh) 2018-05-28 2019-01-16 目标区域作业的规划方法、装置、存储介质及处理器

Country Status (6)

Country Link
US (1) US20210150184A1 (zh)
EP (1) EP3805981A4 (zh)
JP (1) JP2021525426A (zh)
CN (1) CN108846325A (zh)
AU (1) AU2019276115B2 (zh)
WO (1) WO2019227948A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111242554A (zh) * 2020-01-17 2020-06-05 秒针信息技术有限公司 拣货方式类型确定方法和装置
US11455794B2 (en) * 2019-07-08 2022-09-27 National Taiwan University System and method for orchard recognition on geographic area

Families Citing this family (39)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108846325A (zh) * 2018-05-28 2018-11-20 广州极飞科技有限公司 目标区域作业的规划方法、装置、存储介质及处理器
US11074447B1 (en) * 2018-07-13 2021-07-27 Hana Resources, Inc. Land analysis system using drone-captured data
WO2020107354A1 (zh) * 2018-11-29 2020-06-04 深圳市大疆创新科技有限公司 控制方法和设备
CN110069073A (zh) * 2018-11-30 2019-07-30 广州极飞科技有限公司 作业控制方法、装置及植保***
CN109683627A (zh) * 2018-12-10 2019-04-26 杭州瓦屋科技有限公司 一种植保无人机作业自动识别地块的方法及***
CN109341702B (zh) * 2018-12-13 2021-07-20 广州极飞科技股份有限公司 作业区域内的路线规划方法、装置、设备及存储介质
CN109358650B (zh) * 2018-12-14 2022-11-18 国网冀北电力有限公司检修分公司 巡检路径规划方法、装置、无人机和计算机可读存储介质
CN109766049A (zh) * 2018-12-14 2019-05-17 广州极飞科技有限公司 为作业设备分配目标地块的方法和控制设备
CN111442773A (zh) * 2019-01-16 2020-07-24 无锡先导智能装备股份有限公司 运动路径的生成方法
CN109885060B (zh) * 2019-01-18 2020-06-26 丰疆智能科技研究院(常州)有限公司 路径管理***及其管理方法
CN111982096B (zh) * 2019-05-23 2022-09-13 广州极飞科技股份有限公司 一种作业路径生成方法、装置及无人飞行器
CN111504297B (zh) * 2019-06-03 2023-08-11 极目(海南)智能育种装备有限公司 无路网导航作业方法、装置及导航设备
CN110345959B (zh) * 2019-06-10 2023-11-03 同济人工智能研究院(苏州)有限公司 一种基于“门”点的路径规划方法
CN110162099B (zh) * 2019-07-18 2019-10-29 南京嘉谷初成通信科技有限公司 一种无人机的植保喷洒方法、无人机及存储介质
CN111752298A (zh) * 2019-09-30 2020-10-09 广州极飞科技有限公司 无人机作业航线生成方法及相关装置
CN110926472A (zh) * 2019-10-29 2020-03-27 东北大学 一种智能果园路径规划方法
CN110825091A (zh) * 2019-11-29 2020-02-21 洛阳中科龙网创新科技有限公司 一种基于无人机的智能拖拉机智能选路方法及装置
CN112948371A (zh) * 2019-12-10 2021-06-11 广州极飞科技股份有限公司 数据处理方法、装置、存储介质、处理器
CN113009884B (zh) * 2019-12-19 2022-06-21 广州极飞科技股份有限公司 无人设备的作业控制方法、装置、设备及存储介质
CN111766864B (zh) * 2019-12-30 2022-09-13 广州极飞科技股份有限公司 路径生成方法、装置、电子设备和计算机可读存储介质
CN111561934A (zh) * 2020-06-24 2020-08-21 平湖市中地测绘规划有限公司 基于无人机的地质勘探规划方法
CN112189398B (zh) * 2020-09-28 2023-03-07 广州极飞科技股份有限公司 土地平整方法、***、装置、设备及存储介质
JP2022063484A (ja) * 2020-10-12 2022-04-22 カワサキモータース株式会社 道路推定プログラム、道路推定方法及び道路推定装置
CN112668793B (zh) * 2020-12-31 2022-09-13 广州极飞科技股份有限公司 补给点位确定方法、作业规划方法及相关装置
CN112859920B (zh) * 2021-01-19 2022-04-15 济南市政公用资产管理运营有限公司 基于大数据的智慧城市管理方法
CN113074740B (zh) * 2021-04-29 2023-11-17 广州极飞科技股份有限公司 一种作业区域内的航线规划方法、装置、设备及介质
CN114115327A (zh) * 2021-09-28 2022-03-01 佛山中科云图智能科技有限公司 一种基于dsm模型的航线规划方法和规划装置
CN113985882B (zh) * 2021-10-29 2024-02-27 珠海格力电器股份有限公司 作业路径规划方法、装置、电子设备和存储介质
CN117693721A (zh) * 2021-11-09 2024-03-12 深圳市大疆创新科技有限公司 作业规划方法、控制装置、控制终端及存储介质
CN114355877B (zh) * 2021-11-25 2023-11-03 烟台杰瑞石油服务集团股份有限公司 一种多机器人作业区域的分配方法和装置
CN114137974A (zh) * 2021-11-26 2022-03-04 广州极飞科技股份有限公司 中耕控制方法、装置、***和电子设备
CN114283067B (zh) * 2021-12-30 2023-09-01 广州极飞科技股份有限公司 一种处方图获取方法、装置、存储介质及终端设备
CN115482269B (zh) * 2022-09-22 2023-05-09 佳都科技集团股份有限公司 一种土方量计算方法、装置、终端设备以及存储介质
CN115545352B (zh) * 2022-11-29 2023-04-18 水利部珠江水利委员会珠江水利综合技术中心 基于水资源分区管理的数据处理方法及***
CN116485063B (zh) * 2023-06-20 2023-08-18 成都工业职业技术学院 一种基于大数据的无人驾驶碾压机群控制方法及装置
CN117315170B (zh) * 2023-09-12 2024-04-05 华大天元(北京)科技股份有限公司 电网作业环境地图的构建方法、装置、设备及介质
CN117146831B (zh) * 2023-10-31 2024-01-02 北京佳格天地科技有限公司 基于机器学习和无人机的果树生长状态评估方法及***
CN117436675B (zh) * 2023-12-20 2024-03-08 国网浙江省电力有限公司金华供电公司 用于绿色仓储园区的人车物出入智能策略生成方法及***
CN117934485B (zh) * 2024-03-25 2024-05-31 天津市肿瘤医院（天津医科大学肿瘤医院） 基于ct图像的肺部气管路径特征提取方法、***及介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105116911A (zh) * 2015-07-20 2015-12-02 广州极飞电子科技有限公司 无人机喷药方法
CN107390715A (zh) * 2017-07-07 2017-11-24 深圳市华琥技术有限公司 一种基于无人机的喷药控制方法
CN107450576A (zh) * 2017-07-24 2017-12-08 哈尔滨工程大学 一种桥梁检测无人机路径规划的方法
CN108846325A (zh) * 2018-05-28 2018-11-20 广州极飞科技有限公司 目标区域作业的规划方法、装置、存储介质及处理器

Family Cites Families (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5461494B2 (ja) * 2011-09-14 2014-04-02 ヤマハ発動機株式会社 自動走行車両及び自動走行車両の制御方法
CN106062510B (zh) * 2014-04-25 2021-08-03 索尼公司 信息处理装置、信息处理方法和计算机程序
JP2016225863A (ja) * 2015-06-01 2016-12-28 株式会社Ｎｔｔファシリティーズ 撮影システム、撮影方法及びプログラム
JP6375503B2 (ja) * 2015-10-15 2018-08-22 株式会社プロドローン 飛行型検査装置および検査方法
JP6691721B2 (ja) * 2016-02-15 2020-05-13 株式会社トプコン 飛行計画作成方法及び飛行体誘導システム
US11029352B2 (en) * 2016-05-18 2021-06-08 Skydio, Inc. Unmanned aerial vehicle electromagnetic avoidance and utilization system
IL264830B (en) * 2016-08-18 2022-07-01 Tevel Aerobotics Tech Ltd A system and method for managing a fleet of drones/unmanned aerial vehicles for picking and thinning
CN106504233B (zh) * 2016-10-18 2019-04-09 国网山东省电力公司电力科学研究院 基于Faster R-CNN的无人机巡检图像电力小部件识别方法及***
JP6833452B2 (ja) * 2016-10-28 2021-02-24 株式会社東芝 巡視点検システム、情報処理装置、巡視点検制御プログラム
CA3200552A1 (en) * 2016-11-16 2018-05-16 Floratine Products Group, Inc. Method to use a colored photoluminescent composition in agricultural applications
CN106873631B (zh) * 2017-04-21 2020-07-28 广州极飞科技有限公司 无人机控制方法、植保作业方法、无人机及地面站
CN107264806B (zh) * 2017-06-28 2020-05-12 苏州极目机器人科技有限公司 一种无人机的植保喷洒方法
JP6555786B2 (ja) * 2017-07-10 2019-08-07 株式会社プロドローン 無人航空機の飛行高度設定方法および無人航空機システム

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105116911A (zh) * 2015-07-20 2015-12-02 广州极飞电子科技有限公司 无人机喷药方法
CN107390715A (zh) * 2017-07-07 2017-11-24 深圳市华琥技术有限公司 一种基于无人机的喷药控制方法
CN107450576A (zh) * 2017-07-24 2017-12-08 哈尔滨工程大学 一种桥梁检测无人机路径规划的方法
CN108846325A (zh) * 2018-05-28 2018-11-20 广州极飞科技有限公司 目标区域作业的规划方法、装置、存储介质及处理器

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3805981A4 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11455794B2 (en) * 2019-07-08 2022-09-27 National Taiwan University System and method for orchard recognition on geographic area
CN111242554A (zh) * 2020-01-17 2020-06-05 秒针信息技术有限公司 拣货方式类型确定方法和装置
CN111242554B (zh) * 2020-01-17 2023-10-17 秒针信息技术有限公司 拣货方式类型确定方法和装置

Also Published As

Publication number Publication date
EP3805981A4 (en) 2021-07-28
JP2021525426A (ja) 2021-09-24
EP3805981A1 (en) 2021-04-14
CN108846325A (zh) 2018-11-20
US20210150184A1 (en) 2021-05-20
AU2019276115A1 (en) 2020-12-24
AU2019276115B2 (en) 2021-12-16

Similar Documents

Publication Publication Date Title
WO2019227948A1 (zh) 目标区域作业的规划方法、装置、存储介质及处理器
CN110297483B (zh) 待作业区域边界获取方法、装置，作业航线规划方法
WO2020103110A1 (zh) 一种基于点云地图的图像边界获取方法、设备及飞行器
US20190188847A1 (en) Utilizing artificial intelligence with captured images to detect agricultural failure
US9928659B2 (en) Method and system for generating augmented reality agricultural presentations
US11116145B2 (en) Automated optimization of agricultural treatments based on raster image data system
US11690368B2 (en) Agricultural plant detection and control system
CN109197278B (zh) 作业策略的确定方法及装置、药物喷洒策略的确定方法
US11285612B2 (en) Coordinating agricultural robots
WO2021051278A1 (zh) 地表特征识别方法、设备、无人机及计算机可读存储介质
WO2020103109A1 (zh) 一种地图生成方法、设备、飞行器及存储介质
CN110832494A (zh) 一种语义生成方法、设备、飞行器及存储介质
CN113597874B (zh) 一种除草机器人及其除草路径的规划方法、装置和介质
CN114206110A (zh) 用于生成用于利用农业设备来处理田地的应用地图的方法
JP2020129363A (ja) 表現を生成するための方法およびそのような表現に基づいて自律デバイスに動作を学習させるためのシステム
Delmerico et al. “on-the-spot training” for terrain classification in autonomous air-ground collaborative teams
WO2019104678A1 (zh) 一种控制方法、终端、管理平台、***及存储介质
WO2020208641A1 (en) Recurrent pattern image classification and registration
Moazzam et al. Crop and weeds classification in aerial imagery of sesame crop fields using a patch-based deep learning model-ensembling method
CN109814551A (zh) 谷物处理自动驾驶***、自动驾驶方法以及自动识别方法
WO2021081896A1 (zh) 喷洒无人机的作业规划方法、***和设备
US12001512B2 (en) Generating labeled synthetic training data
WO2022061496A1 (zh) 对象边界提取方法、装置、可移动平台及存储介质
Satoto et al. Rice disease classification based on leaf damage using deep learning
Hamzah et al. Visualization of Tree Species Identification Using Mask RCNNs for Tropical Forests in Malaysia

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19812180

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2020566656

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2019276115

Country of ref document: AU

Date of ref document: 20190116

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2019812180

Country of ref document: EP

Effective date: 20210111