CN113808155B - Air route planning and crop operation method, device, equipment and storage medium - Google Patents
Air route planning and crop operation method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113808155B CN113808155B CN202010537072.5A CN202010537072A CN113808155B CN 113808155 B CN113808155 B CN 113808155B CN 202010537072 A CN202010537072 A CN 202010537072A CN 113808155 B CN113808155 B CN 113808155B
- Authority
- CN
- China
- Prior art keywords
- crop
- determining
- image
- main direction
- planting
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 103
- 238000009825 accumulation Methods 0.000 claims abstract description 84
- 238000010586 diagram Methods 0.000 claims description 24
- 238000002372 labelling Methods 0.000 claims description 21
- 238000009499 grossing Methods 0.000 claims description 20
- 238000001514 detection method Methods 0.000 claims description 14
- 238000013136 deep learning model Methods 0.000 claims description 12
- 238000012216 screening Methods 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 6
- 241000196324 Embryophyta Species 0.000 description 8
- 230000000694 effects Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 239000000575 pesticide Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000007921 spray Substances 0.000 description 2
- 238000005507 spraying Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 235000018481 Hylocereus undatus Nutrition 0.000 description 1
- 244000157072 Hylocereus undatus Species 0.000 description 1
- 241000508269 Psidium Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000004720 fertilization Effects 0.000 description 1
- 239000003337 fertilizer Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- 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
- G01C21/20—Instruments for performing navigational calculations
- G01C21/22—Plotting boards
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20061—Hough transform
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30188—Vegetation; Agriculture
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Marine Sciences & Fisheries (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- Mining & Mineral Resources (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Animal Husbandry (AREA)
- Agronomy & Crop Science (AREA)
- Automation & Control Theory (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention provides a route planning method, a crop operation method, a device, equipment and a storage medium, wherein the route planning method comprises the following steps: determining a crop image and determining the main direction of planting rows in the crop image; determining an accumulation curve based on the principal direction and the crop distribution in the crop image; determining a planting row area in the crop image based on the accumulation curve and the straight line set determined by the main direction; an air route planning map is determined based on the connected areas of the crops in each planting row area. The technical scheme provided by the embodiment of the invention can enable the air route planning to be more matched with the actual planting rows, meet the requirement of operation according to the rows and improve the operation efficiency and the accuracy.
Description
Technical Field
The embodiment of the invention relates to the technical field of agriculture, in particular to a method, a device, equipment and a storage medium for route planning and crop operation.
Background
Along with the development of unmanned aerial vehicle technique, more and more users begin to adopt unmanned aerial vehicle to carry out the plant protection operation, especially utilize unmanned aerial vehicle to carry out pesticide and spray and chemical fertilizer and spray etc. have little, the pesticide high-usage of harm, reduce advantages such as intensity of labour to crops.
When the unmanned aerial vehicle performs plant protection operation, the unmanned aerial vehicle generally performs operation according to a planning chart. The prior method for determining the air route planning map is to approximately generate the air route planning map which operates according to rows by a method of equidistant parallel line planning based on a target operation farmland satellite map or a mapping. However, when the air route planning diagram is determined based on the existing method to carry out operation, the situation that the planned air route is not matched with the actual planting row easily occurs, and therefore the requirement of the crops according to the row cannot be met.
Disclosure of Invention
The embodiment of the invention provides a method, a device, equipment and a storage medium for route planning and crop operation, which can enable the route planning to be more matched with an actual planting row, meet the requirement of operation according to the row and improve the operation efficiency and the accuracy.
In a first aspect, an embodiment of the present invention provides a route planning method, including:
determining a crop image and determining the main direction of planting rows in the crop image;
determining an accumulation curve based on the principal direction and the crop distribution in the crop image;
determining a planting row area in the crop image based on the accumulation curve and the straight line set determined by the main direction;
an air route planning map is determined based on the connected areas of the crops in each planting row area.
In a second aspect, embodiments of the present invention provide a method of crop operations, comprising:
determining a course planning diagram by adopting the method provided by the embodiment of the invention;
and operating the crops based on the air route planning diagram.
In a third aspect, an embodiment of the present invention further provides an airline planning apparatus, including:
the first determining module is used for determining a crop image and determining the main direction of a planting row in the crop image;
a second determining module for determining an accumulation curve based on the principal direction and the crop distribution in the crop image;
a third determining module, configured to determine a planting row area in the crop image based on the accumulation curve and the set of straight lines determined by the main direction;
and the fourth determination module is used for determining the air route planning map based on the connected domain of the crops in each planting row area.
In a fourth aspect, an embodiment of the present invention provides an apparatus, including:
one or more processors;
a storage device to store one or more programs,
when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the methods provided by the embodiments of the present invention.
In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program is used to implement a method provided by an embodiment of the present invention when executed by a processor.
According to the technical scheme provided by the embodiment of the invention, the accumulation curve is determined according to the main direction of the planting rows in the crop image and the crop distribution in the crop image, the planting row area in the crop image is determined based on the accumulation curve and the straight line set determined by the main direction, the air route planning map is determined according to the connected domain of the crops in each planting row area, namely, the planting row area is determined according to the accumulation curve and the main direction of the planting rows, and the air route planning map is determined according to the connected domain of the crops in each planting row area, so that the air route planning can be more matched with the actual planting rows, the row-by-row operation requirement is met, and the operation efficiency and the accuracy are improved.
Drawings
FIG. 1 is a flow chart of a route planning method provided by an embodiment of the present invention;
FIG. 2a is a flow chart of a method for planning routes according to an embodiment of the present invention;
FIG. 2b is a crop image;
FIG. 2c is an image of a crop and a circumscribed rectangle;
FIG. 2d is a schematic image of the determination of the plant row area;
FIG. 3a is a flow chart of a route planning method according to an embodiment of the present invention;
FIG. 3b is an image of the area where vegetation is located;
FIG. 3c is an image of the crop obtained by screening of FIG. 3 b;
FIG. 3d is a diagram illustrating the effect of marking connected components in the crop image;
FIG. 3e is an image of a field to be performed;
FIG. 3f is a schematic illustration of a single row line connecting connected domain keypoints of a crop;
FIG. 3g is a schematic illustration of an airline planning map;
FIG. 4a is a flow chart of a route planning method according to an embodiment of the present invention;
FIG. 4b is a flowchart of a route planning method according to an embodiment of the present invention;
FIG. 4c is a flow chart of a method of operating a crop according to an embodiment of the present invention;
FIG. 5a is a block diagram of a route planning device according to an embodiment of the present invention;
FIG. 5b is a block diagram of a crop work apparatus according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an apparatus according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not to be construed as limiting the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Fig. 1 is a flowchart of an airline planning method according to an embodiment of the present invention, where the method may be performed by an airline planning apparatus, the apparatus may be implemented by software and/or hardware, and the apparatus may be configured in a device such as an unmanned aerial vehicle, a computer, a server, or a cloud. The method provided by the embodiment of the invention is suitable for the situation of air route planning when crops are operated according to rows, and as shown in figure 1, the technical scheme provided by the embodiment of the invention comprises the following steps:
s110: and determining a crop image and determining the main direction of the planting rows in the crop image.
In an implementation manner of the embodiment of the present invention, optionally, the crop image may be determined by shooting a farmland image, inputting the farmland image into the crop recognition model to obtain a crop image, and recognizing the crop image quickly and accurately by recognizing the mapping image through the crop recognition model. Or in another implementation manner of the embodiment of the present invention, the image of the farmland may be processed by an image algorithm, so as to identify the crops, and obtain the image of the crops. The crop image may be a gray scale image of the crop, or may be a binary image of the crop, or may also be an image in another format.
It should be noted that the method for determining the crop image is not limited to the above method, and other methods capable of extracting the crop image from the farmland image may be adopted.
In an implementation manner of the embodiment of the present invention, optionally, the determining the main direction of the planting rows in the crop image includes: and performing straight line detection on the crop image based on the Hough straight line detection method, and determining the main direction of planting rows in the crop image based on detected straight line data. Specifically, the crop image can be converted into a polar hough space, and an angle and radius list of the straight lines in the front sequence is returned through a hough space accumulator. And determining the direction of the planting row by performing statistical analysis on the result returned by the Hough space accumulator. The angle with the largest occurrence frequency can be selected as the direction of the planting rows, or when the returned result is less than the set number, the first sorted angle is selected as the main direction of the planting rows, or other methods for selecting the main direction are also possible. For example, the partial results returned by the hough space accumulator may refer to the contents shown in table 1.
TABLE 1
In the results of the above-mentioned serial numbers 1 to 7, the angle is 0.85, or 0.83, rho values are different, so that it can be obtained that a plurality of straight lines (there are more planting rows in the image, and one straight line represents one planting row) exist in the same direction (possibly the main direction), and the above-mentioned returned result is statistically analyzed, and the main direction is 0.8336628550028777.
In the embodiment of the present invention, the detection of the straight line in the crop image is not limited to the hough straight line detection method described above, and may be other straight line detection methods.
S120: determining an accumulation curve based on the principal direction and a crop distribution in the crop image.
In an implementation manner of the embodiment of the present invention, optionally, the determining an accumulation curve based on the main direction and a crop distribution in the crop image includes: and determining an accumulation curve based on the number of the crop pixels or the number of the non-crop pixels in the crop image and the main direction. Specifically, the external rectangle of the crop image can be determined, the length direction and the width direction of the external rectangle are respectively used as two coordinate axes, and the number of crop pixel points or the number of non-crop pixel points is accumulated in the width direction to obtain an accumulation curve. Details can be found in the following description of the embodiments. Or determining an external rectangle of the crop image by taking the main direction as the height direction, and accumulating the number of crop pixels or the number of non-crop pixels in the height direction by taking the length direction and the height direction of the external rectangle as two coordinate axes respectively to obtain an accumulation curve. Details can be found in the following description of the embodiments.
In a specific embodiment, optionally, the circumscribed rectangle of the crop image may not be determined, and the main direction may be taken as one coordinate axis, and the direction perpendicular to the main direction may be taken as another coordinate axis. And accumulating the number of the crop pixel points or the number of the non-crop pixel points in the main direction to obtain an accumulation curve. Or the external rectangle of the crop image can be uncertain, the main direction can be taken as a vertical axis, the direction vertical to the main direction is taken as an abscissa axis, and the number of the crop pixel points or the number of the non-crop pixel points is accumulated in the main direction to obtain an accumulation curve.
Therefore, the accumulation curve is determined through the main direction and the crop distribution in the crop image, a basis can be provided for determining the crop image planting row area, and the planting row area can be accurately determined.
S130: and determining a planting row area in the crop image based on the accumulation curve and the straight line set determined by the main direction.
In the embodiment of the present invention, specifically, a peak top point (or a valley point) of the accumulation curve may be determined, and the planting row area in the crop image is cut out based on a straight line set determined by the peak top point (or the valley point) and the main direction. The straight line set determined by the main direction is a set formed by straight lines parallel to the main direction. Or specifically, the accumulated curve may be smoothed, and a peak top (or a valley point) of the smoothed accumulated curve is determined, so that the planting line region in the crop image is cut out based on a straight line set determined by the peak top (the valley point) and the principal direction. As a method of smoothing, a method in the related art can be referred to. The specific method for determining the planting row area can be referred to the following description of the embodiment.
S140: an air route planning map is determined based on the connected areas of the crops in each planting row area.
In the embodiment of the present invention, the connected domain of the crop may be an area formed by each crop pixel point, or may also be understood as an area where the crop is located.
In one implementation of this embodiment of the present invention, the determining an airline planning map based on connected areas of crops in each planting row area includes: determining connected domain key points of crops based on the connected domain of the crops in each planting row area; and determining a routing graph based on the connected domain key points. The determination method of the key points of the connected domain may be the middle point of the cutting line in the horizontal direction of the connected domain, may also be the geometric centroid of the connected domain, and may also have other similar methods capable of achieving the same purpose. The connected domain key point is characterized by aiming at a single connected domain, and is convenient for the planting line curve to be fitted with a coordinate point of the connected domain. The method of plant row curve fitting includes, but is not limited to, generating a set of corresponding centerline points corresponding to the set of keypoints by local weighted regression (LOWESS), wherein the centerline may be generated by interpolation methods including, but not limited to, inter 1d interpolation (where the code may refer to scipy. Interplate. Interp1d).
In an implementation manner of the embodiment of the present invention, optionally, the determining a routing graph based on the connected domain key points includes: connecting connected region key points of crops in each planting row region into a single row; and connecting the head and the tail of the single lines of the adjacent planting rows to obtain a course planning map. Specifically, the key points of the connected regions of the crops in each planting row region are connected into a single row, the single rows of the adjacent planting rows are connected in a zigzag manner to obtain an air route planning diagram, and the air route planning diagram can be added with coordinate information of each position, so that the related operation can be performed on a single crop.
According to the technical scheme provided by the embodiment of the invention, the accumulation curve is determined according to the main direction of the planting rows in the crop image and the crop distribution in the crop image, the planting row area in the crop image is determined based on the accumulation curve and the straight line set determined by the main direction, the air route planning map is determined according to the connected area of the crops in each planting row area, namely, the planting row area is determined according to the accumulation curve and the main direction of the planting rows, and the air route planning map is determined according to the communication of the crops in each planting row area with the determined air route planning map, so that the air route planning can be more matched with the actual planting rows, the requirement of the row-by-row operation is met, and the operation efficiency and the accuracy are improved.
Fig. 2a is a flowchart of an airline planning method according to an embodiment of the present invention, which may be combined with various alternatives in one or more of the above embodiments, where, optionally,
the determining an accumulation curve based on the number of non-crop pixel points in the crop image and the principal direction includes:
determining a circumscribed rectangle of the crop image by taking the main direction as a height direction;
and accumulating the number of non-crop pixel points in the height direction of the external rectangle by taking the length direction of the external rectangle as an abscissa axis and the height direction of the external rectangle as an ordinate axis to obtain an accumulation curve.
Optionally, the determining a plant row area in the crop image based on the accumulation curve and the set of straight lines determined by the main direction includes:
smoothing the accumulated curve, and determining the peak vertex of the smoothed accumulated curve;
cutting out a planting row area in the crop image based on the peak of the peak and the straight line set determined by the main direction; and the straight line set determined by the main direction is a set formed by straight lines parallel to the main direction.
As shown in fig. 2a, the technical solution provided by the embodiment of the present invention includes:
s210: determining a crop image and determining a main direction of a planting row in the crop image.
The description of S210 may refer to the description of S110 in the above embodiment.
S220: and determining a circumscribed rectangle of the crop image by taking the main direction as a height direction.
In the embodiment of the present invention, specifically, the circumscribed rectangle of the crop image is determined by taking the main direction as the height direction of the circumscribed rectangle. For example, as shown in fig. 2b as a crop image, a circumscribed rectangle obtained by taking the main direction of the planting row in the crop image as the height direction of the circumscribed rectangle may refer to fig. 2c, and a specific method may be to rotate the crop image so that the main direction of the planting row is the height direction of the rectangle, and then make the circumscribed rectangle of the crop image based on all the vertices of the crop image.
S230: and accumulating the number of non-crop pixel points in the height direction of the external rectangle by taking the length direction of the external rectangle as an abscissa axis and the height direction of the external rectangle as an ordinate axis to obtain an accumulation curve.
In the embodiment of the present invention, the image is scanned, and the number of non-crop pixels accumulated in the height direction (main direction) of the circumscribed rectangle for each abscissa position in the image is taken as the ordinate, thereby obtaining an accumulation curve. The accumulation curve can be referred to the curve in fig. 2 d.
S240: and smoothing the accumulation curve, and determining the peak top of the accumulation curve after smoothing.
In the embodiment of the present invention, the smoothing process includes, but is not limited to, moving average filtering denoising, denoising after LOWESS smoothing, denoising after fitting of a Univariate Spline (Univariate Spline), and denoising after smoothing of a Savitzky _ Golay filter. The denoising case includes, but is not limited to, modifying the value of the smoothed negative number of the Savitzky _ Golay filter, and the like. The peak vertex and width of the accumulation curve after the smoothing process are calculated, and a SciPy peak finding algorithm (wherein, code content can refer to SciPy.
S250: cutting out a planting row area in the crop image based on the peak of the peak and the straight line set determined by the main direction; the straight line set determined by the main direction is a set formed by straight lines parallel to the main direction.
In an implementation manner of the embodiment of the present invention, optionally, for any two adjacent peak vertices, a planting area between two target straight lines respectively passing through the two peak vertices is a planting row area, where the two target straight lines are respectively straight lines parallel to the main direction. For example, as shown in fig. 2d, the straight line passing through the peak of the peak is the target straight line, and the planting area between two adjacent target straight lines is the planting row area. Wherein the width of the planting row area is larger than the transverse width of the crops, and the target straight line can be the middle boundary line of two rows of crops.
In the embodiment of the invention, the straight line set determined by the main direction can be deviated left and right in a certain neighborhood range, under the condition that the length direction of the external rectangle is an abscissa axis, the height direction of the external rectangle is an ordinate axis, and the number of non-crop pixel points is accumulated in the height direction of the external rectangle to obtain an accumulation curve, the triggering condition of deviation can be that the accumulated value of an original accumulation curve in the neighborhood is equal to the abscissa axis point of the height of the external rectangle. The reason for the shift is that there is a possibility that a peak top is shifted from a horizontal axis point where the original true accumulated value is zero after being smoothed, and the shift is limited. Therefore, after the accumulated curve is subjected to smoothing processing, if a target position with the accumulated value as the height of the circumscribed rectangle on the accumulated curve before the smoothing processing is searched in the range of the set distance threshold value from the peak top point, the target straight line passing through the peak top point is translated to the target position. Specifically, a distance threshold (neighborhood) is set, a point with the accumulated value of the accumulated curve before smoothing processing as the height of the circumscribed rectangle is searched in the neighborhood of the peak of the wave, and the straight line passing through the peak of the wave is translated to the point with the accumulated value of the accumulated curve before smoothing processing as the height of the circumscribed rectangle, so that the position of the straight line parallel to the main direction can be accurately determined, and the planting row area can be accurately determined. In determining the planting row area, if the left and right boundary lines are absent, the boundary lines may be supplemented.
Therefore, by determining the external rectangle of the crop image, taking the length direction of the external rectangle as an abscissa axis and the height direction of the external rectangle as an ordinate axis, accumulating the number of non-crop pixel points in the height direction of the external rectangle to obtain an accumulation curve, and cutting out the planting line area in the crop image through the peak of the wave crest and a straight line set determined in the main direction, the planting line area can be accurately determined according to actual conditions, and a basis is provided for route planning.
S260: an air route planning map is determined based on the connected areas of the crops in each planting row area.
In another implementation manner of the embodiment of the present invention, the method for determining the accumulation curve may further include: and determining an accumulation curve based on the number of the crop pixel points in the crop image and the main direction. The method comprises the following steps: determining a circumscribed rectangle of the crop image by taking the main direction as a height direction; and accumulating the number of crop pixel points in the height direction of the external rectangle by taking the length direction of the external rectangle as an abscissa axis and the height direction of the external rectangle as an ordinate axis to obtain an accumulation curve. Correspondingly, the determining the planting row area in the crop image based on the accumulation curve and the straight line set determined by the main direction comprises: smoothing the accumulation curve, and determining a valley point of the smoothed accumulation curve; cutting out a planting row area in the crop image based on the valley point and the straight line set determined by the main direction; the straight line set determined by the main direction is a set formed by straight lines parallel to the main direction. The accumulation method of the crop pixel points in the accumulation curve can refer to the accumulation method of the non-crop pixel points in the above embodiment, and the two methods are similar.
Cutting out a planting row area in the crop image based on the straight line set determined by the trough position and the main direction, wherein the cutting out of the planting row area in the crop image may include: aiming at any two adjacent valley points, a planting area between two target straight lines respectively passing through the two valley points is a planting row area, wherein the two target straight lines are respectively straight lines parallel to the main direction. Among them, the method of determining the valley point may be a method in the related art. It should be noted that, in other implementation manners of the embodiment of the present invention, determining an accumulation curve based on the number of crop pixels or the number of non-crop pixels in the crop image and the principal direction may include: determining a circumscribed rectangle of the crop image; the main direction is parallel to the width direction of the circumscribed rectangle; and accumulating the number of the crop pixels or the number of the non-crop pixels in the width direction of the external rectangle by taking the length direction of the external rectangle as a first coordinate axis and the width direction of the external rectangle as a second coordinate axis to obtain an accumulation curve. Wherein the first coordinate axis and the second coordinate axis are perpendicular to each other. The method for obtaining the accumulation curve has the same principle as the method for obtaining the accumulation curve in the embodiment, except that the height direction of the external rectangle is the vertical direction, and the width direction of the external rectangle is not necessarily the vertical direction.
Fig. 3a is a flowchart of an airline planning method according to an embodiment of the present invention, which may be combined with various optional solutions in one or more embodiments of the present invention, in the embodiment, a crop image is a binary image of a crop, and optionally, the determining the crop image includes:
and inputting the farmland image to be executed into the crop recognition model to obtain a crop image.
Optionally, the method provided in the embodiment of the present invention further includes:
extracting an image of a region where vegetation is located from a farmland image;
screening vegetation connected domains in the image of the area where the vegetation is located, reserving the connected domains of the crops, generating a crop image serving as a crop marking image, or marking the area to obtain a crop marking image;
and inputting the crop labeling image and the farmland image into a deep learning model for pre-training to obtain a crop recognition model.
As shown in fig. 3a, the technical solution provided by the embodiment of the present invention includes:
s310: and extracting an image of the area where the vegetation is located from each farmland image.
In the embodiment of the invention, a plurality of farmland images can be shot to form a farmland image set, and the region image of the vegetation is extracted from each farmland image.
The method for extracting the image of the area where the vegetation is located includes, but is not limited to, color space, such as red, green and blue (RGB) hue, saturation and brightness (HSV), color index, vegetation index and other distinguishing methods. For example, exG =2 × Green-Red-Blue, using the ultragreen index (process Green). The right side of the formula is a certain pixel value of an RGB three channel, and the practical use of the formula needs mathematical processing such as normalization. And after calculating the ultragreen index, separating a vegetation area through a threshold value, wherein the vegetation area is larger than the threshold value and is a non-zero value, and the vegetation area is set to zero when the vegetation area is smaller than the threshold value, so that a binary image is generated. The threshold value may be set manually as needed, or may be obtained by binary Otsu method (Ostu).
S320: and screening vegetation connected domains in the area images of the vegetation, reserving the connected domains of the crops, generating the crop images as the crop labeling images, or labeling the crop connected domains in the area images to obtain the crop labeling images.
In the embodiment of the present invention, the screening method of the vegetation connected domain includes, but is not limited to, a thresholding method, a statistical screening method, a shape screening method, a texture screening method, and the like. The statistical screening method determines the area range of crops by counting the areas of all connected domains and determining the area range of the crops by means of modes, dense intervals and the like, and vegetation connected domains in the area range are reserved and used as the connected domains of the crops. Fig. 3b is an image of an area where the vegetation is located, and as shown in fig. 3b, one blob may be regarded as one connected domain, and the area of each connected domain may be calculated. The total area of the vegetation area is more than or equal to the total area of the crop area. Reference may be made to fig. 3c for a crop image generated after screening, wherein the crop image may be a binarized image. The crop image may also be referred to as a label image, and all connected domains in 3c may be replaced with corresponding gaussian circles by using a gaussian circle method.
In the embodiment of the present invention, the method for obtaining the crop labeling image may also be to label a crop connected domain in the area image where the plant is located, for example, an artificial labeling method may be adopted, or the crop connected domain may also be generated by an algorithm, where the specific method for labeling the connected domain is to label the crop action in the crop image by using a closed area, for example, a quadrangle, a polygon, or the like. Referring to fig. 3d, an effect diagram of labeling connected components in a crop image can be obtained. Therefore, the method can avoid the phenomenon of error occurrence of the crop connected domain and can ensure that the determination of the crop connected domain is more accurate.
S330: and inputting the crop labeling image and the farmland image into a deep learning model for pre-training to obtain a crop identification model.
In the embodiment of the present invention, the deep learning model may be a target detection model, for example, a YOLO (young Only Look one) model, and the deep learning model may be a convolutional neural network model. The marked crop images and the corresponding farmland images can be input into the deep learning model for pre-training to obtain a crop recognition model.
The crop recognition model training process may be: the multiple crop annotation images and the corresponding farmland images can be divided into a training data set, a testing data set and a verification data set. And training the deep learning model through the training data set, and testing the trained deep learning model through the testing data set, so as to update the network parameters in the deep learning model. And finally, verifying the trained deep learning model through a verification data set, evaluating the effect, and judging that the model can be used for crop identification when the effect evaluation reaches a preset condition.
S340: and inputting the farmland image to be executed into the crop recognition model to obtain a crop image.
Therefore, the crop is identified through the crop identification model, the crop image is obtained, the processing efficiency can be improved, and the crop image can be accurately obtained.
S350: the main direction of the planting rows in the image of the crop is determined.
S360: determining an accumulation curve based on the principal direction and a crop distribution in the crop image.
S370: and determining a planting row area in the crop image based on the accumulation curve and the straight line set determined by the main direction.
S380: an air route planning map is determined based on the connected areas of the crops in each planting row area.
The introduction of S340-S380 can refer to the above embodiments. Wherein, the image of the farmland to be executed can refer to fig. 3e, the one-way line connecting the key points of the connected domain of the crop can refer to fig. 3f, and the air route planning map can refer to fig. 3g.
Fig. 4a is a flowchart of an airline planning method according to an embodiment of the present invention, and in the embodiment of the present invention, as shown in fig. 4a, a technical solution according to the embodiment of the present invention includes:
s410: and extracting an image of the area where the vegetation is located from the farmland image.
S420: and screening vegetation connected domains in the area images of the vegetation, reserving the connected domains of the crops, generating the crop images as the crop labeling images, or labeling the crop connected domains in the area images to obtain the crop labeling images.
S430: and inputting the crop labeling image and the farmland image into a deep learning model for pre-training to obtain a crop identification model.
S440: and inputting the farmland image to be executed into the crop recognition model to obtain a crop image.
S450: and performing straight line detection on the crops based on the Hough straight line detection method, and determining the main direction of planting rows in the crop image based on the detected straight line data.
S460: and determining a circumscribed rectangle of the crop image by taking the main direction as a height direction.
S470: and accumulating the number of the non-crop pixel points in the height direction of the external rectangle by taking the length direction of the external rectangle as an abscissa axis and the height direction of the external rectangle as an ordinate axis to obtain an accumulation curve.
S480: and smoothing the accumulated curve, and determining the peak vertex of the smoothed accumulated curve.
S490: cutting out a planting row area in the crop image based on the peak of the peak and the straight line set determined by the main direction; the straight line set determined by the main direction is a set formed by straight lines parallel to the main direction.
S491: and determining the key points of the connected domains of the crops based on the connected domains of the crops in each planting row area.
S492: and determining a routing graph based on the connected domain key points.
The steps in this embodiment may be described with reference to the above embodiments. The method provided by the present application may also refer to the method shown in fig. 4 b.
On the basis of any of the foregoing embodiments, the method provided in the embodiment of the present invention may further include: and adding coordinate information to each position in the route locus diagram to generate the route locus diagram. In the related technology, the situation that a planned route is not matched with an actual planting row easily occurs in a route planning map, the stay operation aiming at a single crop in a single row crop is difficult to realize, the requirement of the unmanned aerial vehicle for the line-by-line operation exists for the crops planted in rows with gaps (gaps between the plants or the rows) among the plants, such as guava, dragon fruits, oranges and the like, but the requirement of fine refinement cannot be met by the current simple parallel line planning.
Fig. 4c is a flowchart of a crop operation method, where the method may be executed by a crop operation apparatus, the apparatus may be implemented by software and/or hardware, and the apparatus may be configured in a device such as an unmanned aerial vehicle, a computer, a server, or a cloud, as shown in fig. 4c, and a technical solution provided in an embodiment of the present invention includes:
s41: and determining an air route planning diagram.
The method provided by the above embodiment of the present invention is used to determine the routing chart, and please refer to the above embodiment, which will not be described repeatedly.
S42: and operating the crops based on the air route planning diagram.
In the embodiment of the invention, the operations of spraying medicine, fertilizing and the like can be carried out on crops based on the routing chart. Specifically, can control unmanned aerial vehicle flight based on the air route planning picture, when unmanned aerial vehicle reachd the crop position, perhaps reachd the settlement position of crop, carry out operations such as spraying medicine, fertilization to the crop. For example, the operation can be performed on a fruit tree area.
According to the technical scheme provided by the embodiment of the invention, the air route planning map is determined by the method provided by the embodiment, and the crops are operated based on the air route planning map, so that the requirement of operation according to rows can be met, and the operation efficiency and the accuracy are improved.
Fig. 5a is a structural block diagram of an airline planning apparatus according to an embodiment of the present invention, and as shown in fig. 5a, the apparatus includes: a first determination module 510, a second determination module 520, a third determination module 530, and a fourth determination module 540.
A first determining module 510, configured to determine a crop image and determine a main direction of a planting row in the crop image;
a second determining module 520, configured to determine an accumulation curve based on the main direction and a crop distribution in the crop image;
a third determining module 530, configured to determine a planting row area in the crop image based on the cumulative curve and the set of straight lines determined by the main direction;
a fourth determining module 540, configured to determine an air route planning map based on the connected areas of the crops in each planting row area.
Optionally, the second determining module 520 is configured to determine an accumulation curve based on the number of crop pixels or the number of non-crop pixels in the crop image and the principal direction.
Optionally, the second determining module 520 is configured to determine a circumscribed rectangle of the crop image with the main direction as a height direction;
and accumulating the number of crop pixel points or the number of non-crop pixel points in the height direction of the external rectangle by taking the length direction of the external rectangle as an abscissa axis and the height direction of the external rectangle as an ordinate axis to obtain an accumulation curve.
Optionally, the second determining module 520 is configured to determine an accumulation curve based on the number of crop pixels or the number of non-crop pixels in the crop image and the principal direction, and includes:
determining a circumscribed rectangle of the crop image; the main direction is parallel to the width direction of the circumscribed rectangle;
and accumulating the number of the crop pixels or the number of the non-crop pixels in the width direction of the external rectangle by taking the length direction of the external rectangle as a first coordinate axis and the width direction of the external rectangle as a second coordinate axis to obtain an accumulation curve.
Optionally, if the length direction of the external rectangle is taken as an abscissa axis and the height direction of the external rectangle is taken as an ordinate axis, accumulating the number of non-crop pixel points in the height direction of the external rectangle to obtain an accumulation curve; a third determining module 530, configured to perform smoothing on the accumulated curve and determine a peak top of the smoothed accumulated curve;
cutting out a planting row area in the crop image based on the peak of the peak and the straight line set determined by the main direction; the straight line set determined by the main direction is a set formed by straight lines parallel to the main direction.
Optionally, the cutting out a planting row area in the crop image based on the set of straight lines determined by the peak and the main direction includes:
aiming at any two adjacent peak vertexes, a planting area between two target straight lines respectively passing through the two peak vertexes is a planting row area, wherein the two target straight lines are respectively straight lines parallel to the main direction.
Optionally, after the accumulated curve is smoothed, if a target position where an accumulated value on the accumulated curve before smoothing is the height of the circumscribed rectangle is searched within a range of a set distance threshold from the peak vertex, translating the target straight line passing through the peak vertex to the target position.
Optionally, if the length direction of the external rectangle is taken as an abscissa axis and the height direction of the external rectangle is taken as an ordinate axis, accumulating the number of crop pixel points in the height direction of the external rectangle to obtain an accumulation curve; a third determining module 530, configured to smooth the accumulation curve and determine a valley point of the smoothed accumulation curve;
cutting out a planting row area in the crop image based on the valley point and the straight line set determined by the main direction; and the straight line set determined by the main direction is a set formed by straight lines parallel to the main direction.
Optionally, cutting out a planting row area in the crop image based on the straight line set determined by the valley position and the main direction, including:
aiming at any two adjacent valley points, a planting area between two target straight lines respectively passing through the two valley points is a planting row area, wherein the two target straight lines are respectively straight lines parallel to the main direction.
Optionally, the fourth determining module 540 is configured to determine an air route planning map based on the connected area of the crop in each planting row area, and includes:
determining connected domain key points of crops based on the connected domain of the crops in each planting row area;
determining a routing graph based on the connected domain key points.
Optionally, the determining the routing plan based on the connected domain key points includes:
connecting connected region key points of crops in each planting row region into a single row;
and connecting the head and the tail of the single lines of the adjacent planting rows to obtain a course planning diagram.
Optionally, the determining the main direction of the planting row in the crop image includes:
and performing straight line detection on the crop image based on the Hough straight line detection method, and determining the main direction of planting rows in the crop image based on the detected straight line data.
Optionally, the determining the crop image includes:
and inputting the farmland image to be executed into the crop recognition model to obtain a crop image.
Optionally, the apparatus further comprises a training module, configured to:
extracting an image of a region where the vegetation is located from each farmland image;
screening vegetation connected domains in the area images of the vegetation, reserving the connected domains of the crops, generating crop images serving as crop labeling images, or labeling the connected domains of the crops in the area images to obtain the crop labeling images;
and inputting the crop labeling image and the farmland image into a deep learning model for pre-training to obtain a crop identification model.
Optionally, the connected domain of the crop adopts a gaussian circle; and marking the connected domain of the crops by adopting polygons.
Optionally, the apparatus further includes a generating module, configured to add coordinate information to each position in the route trajectory graph, and generate the route trajectory graph.
Optionally, the crop image includes a binary image of the crop, or a grayscale image of the crop.
The device can execute the method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
Fig. 5b is a block diagram of a crop operation device according to an embodiment of the present invention, and as shown in fig. 5b, the device includes an air route planning device 51 and an operation module 52 according to an embodiment of the present invention.
The route planning device 51 is used for determining a route planning diagram.
The specific structure of the route planning device may refer to the above embodiments.
An operation module 52 for operating on the crop based on the airline planning map.
The device can execute the method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Fig. 6 is a schematic structural diagram of an apparatus according to an embodiment of the present invention, where the apparatus may be a computer, a server, an unmanned aerial vehicle, a cloud end device, or the like. As shown in fig. 6, the apparatus includes:
one or more processors 610, one processor 610 being exemplified in fig. 6;
a memory 620;
the apparatus may further include: an input device 630 and an output device 640.
The processor 610, the memory 620, the input device 630 and the output device 640 in the apparatus may be connected by a bus or other means, and fig. 6 illustrates the connection by a bus as an example.
The memory 620, as a non-transitory computer readable storage medium, may be used to store software programs, computer executable programs, and modules, such as program instructions/modules corresponding to a method of route planning in an embodiment of the present invention (e.g., the first determining module 510, the second determining module 520, the third determining module 530, and the fourth determining module 540 shown in FIG. 5 a) or program instructions/modules corresponding to a method of crop operation in an embodiment of the present invention (e.g., the route planning apparatus 51 and the operations module 52 shown in FIG. 5 b). The processor 610 executes various functional applications of the computer device and data processing by running software programs, instructions and modules stored in the memory 620, namely, a route planning method for implementing the above method embodiments, namely:
determining a crop image and determining the main direction of planting rows in the crop image;
determining an accumulation curve based on the principal direction and a crop distribution in the crop image;
determining a planting row area in the crop image based on the accumulation curve and the straight line set determined by the main direction;
an air route planning map is determined based on the connected areas of the crops in each planting row area.
Alternatively, the first and second electrodes may be,
the crop operation method provided by the embodiment of the invention is realized, namely:
determining a crop image and determining the main direction of planting rows in the crop image;
determining an accumulation curve based on the principal direction and a crop distribution in the crop image;
determining a planting row area in the crop image based on the accumulation curve and the straight line set determined by the main direction;
determining a course planning map based on the connected areas of the crops in each planting row area;
and operating the crops based on the air route planning diagram.
The memory 620 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of the computer device, and the like. Further, the memory 620 may include high speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, memory 620 optionally includes memory located remotely from processor 610, which may be connected to the terminal device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input means 630 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function controls of the computer device. The output device 640 may include a display device such as a display screen.
An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a route planning method according to an embodiment of the present invention:
determining a crop image and determining the main direction of planting rows in the crop image;
determining an accumulation curve based on the principal direction and a crop distribution in the crop image;
determining a planting row area in the crop image based on the accumulation curve and the straight line set determined by the main direction;
an air route planning map is determined based on the connected areas of the crops in each planting row area.
Alternatively, the first and second electrodes may be,
the crop operation method provided by the embodiment of the invention is realized, namely:
determining a crop image and determining the main direction of planting rows in the crop image;
determining an accumulation curve based on the principal direction and a crop distribution in the crop image;
determining a planting row area in the crop image based on the accumulation curve and the straight line set determined by the main direction;
determining a course planning map based on the connected areas of the crops in each planting row area;
and operating the crops based on the air route planning diagram. Any combination of one or more computer-readable media may be employed. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be noted that the foregoing description is only exemplary of the invention and that the principles of the technology may be employed. Those skilled in the art will appreciate that the present invention is not limited to the particular embodiments described herein, and that various obvious changes, rearrangements and substitutions will now be apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (18)
1. A method of route planning, comprising:
determining a crop image and determining the main direction of planting rows in the crop image;
determining an accumulation curve based on the principal direction and the crop distribution in the crop image;
determining a planting row area in the crop image based on the accumulation curve and the straight line set determined by the main direction;
determining a course planning map based on the connected areas of the crops in each planting row area;
the determining of the main direction of the planting row in the crop image comprises:
performing linear detection on the crop image based on a linear detection method, and determining the main direction of planting rows in the crop image based on detected linear data;
the determining an accumulation curve based on the principal direction and a crop distribution in the crop image comprises:
determining an accumulation curve based on the number of the crop pixels or the number of the non-crop pixels in the crop image and the main direction;
wherein the planting row area determination mode comprises at least one of the following modes: determining the planting row area of the non-crop pixel points according to the peak of the wave crest; and determining the planting row area of the crop pixel points according to the valley points.
2. The method of claim 1, wherein determining an accumulation curve based on the number of crop pixels or the number of non-crop pixels in the crop image and the principal direction comprises:
determining a circumscribed rectangle of the crop image by taking the main direction as a height direction;
and accumulating the number of crop pixel points or the number of non-crop pixel points in the height direction of the external rectangle by taking the length direction of the external rectangle as an abscissa axis and the height direction of the external rectangle as an ordinate axis to obtain an accumulation curve.
3. The method of claim 1, wherein determining an accumulation curve based on the number of crop pixels or the number of non-crop pixels in the crop image and the principal direction comprises:
determining a circumscribed rectangle of the crop image; the main direction is parallel to the width direction of the circumscribed rectangle;
and accumulating the number of the crop pixel points or the number of the non-crop pixel points in the width direction of the external rectangle by taking the length direction of the external rectangle as a first coordinate axis and the width direction of the external rectangle as a second coordinate axis to obtain an accumulation curve.
4. The method according to claim 2, wherein if the length direction of the circumscribed rectangle is taken as an abscissa axis and the height direction of the circumscribed rectangle is taken as an ordinate axis, the number of non-crop pixels is accumulated in the height direction of the circumscribed rectangle to obtain an accumulation curve;
determining a plant row area in the crop image based on the accumulation curve and the set of straight lines determined by the main direction, including:
smoothing the accumulated curve, and determining the peak vertex of the smoothed accumulated curve;
cutting out a planting row area in the crop image based on the peak of the peak and the straight line set determined by the main direction; the straight line set determined by the main direction is a set formed by straight lines parallel to the main direction.
5. The method of claim 4, wherein the cutting out the row area in the crop image based on the set of straight lines determined by the peak vertices and the principal direction comprises:
aiming at any two adjacent peak vertexes, a planting area between two target straight lines respectively passing through the two peak vertexes is a planting row area, wherein the two target straight lines are respectively straight lines parallel to the main direction.
6. The method of claim 5,
and after the accumulated curve is subjected to smoothing processing, if a target position with the accumulated value as the height of the circumscribed rectangle on the accumulated curve before the smoothing processing is searched within the range of the set distance threshold value from the peak top point, translating the target straight line passing through the peak top point to the target position.
7. The method according to claim 2, wherein if the length direction of the circumscribed rectangle is taken as an abscissa axis and the height direction of the circumscribed rectangle is taken as an ordinate axis, accumulating the number of the crop pixel points in the height direction of the circumscribed rectangle to obtain an accumulation curve;
determining a plant row area in the crop image based on the accumulation curve and the set of straight lines determined by the main direction, including:
smoothing the accumulation curve, and determining a valley point of the smoothed accumulation curve;
cutting out a planting row area in the crop image based on the valley point and the straight line set determined by the main direction; the straight line set determined by the main direction is a set formed by straight lines parallel to the main direction.
8. The method of claim 7, wherein cutting out a row area in the crop image based on the valley point and the set of straight lines determined by the principal direction comprises:
aiming at any two adjacent valley points, a planting area between two target straight lines respectively passing through the two valley points is a planting row area, wherein the two target straight lines are respectively straight lines parallel to the main direction.
9. The method of claim 1, wherein determining an airline planning map based on connected areas of crops in each planted row area comprises:
determining connected domain key points of crops based on the connected domain of the crops in each planting row area;
and determining a routing graph based on the connected domain key points.
10. The method of claim 9, wherein determining the routing graph based on the connected domain keypoints comprises:
connecting connected region key points of crops in each planting row region into a single row;
and connecting the head and the tail of the single lines of the adjacent planting rows to obtain a course planning map.
11. The method of claim 1, wherein determining the crop image comprises:
and inputting the farmland image to be executed into the crop recognition model to obtain a crop image.
12. The method of claim 11, further comprising:
extracting an image of a region where the vegetation is located from each farmland image;
screening vegetation connected domains in the area images where the vegetation is located, reserving the connected domains of the crops, generating the crop images as the crop labeling images, or labeling the connected domains of the crops in the area images to obtain the crop labeling images;
and inputting the crop labeling image and the farmland image into a deep learning model for pre-training to obtain a crop recognition model.
13. The method of any one of claims 1-12, further comprising:
and adding coordinate information to each position in the air route planning diagram to generate an air route locus diagram.
14. The method according to any one of claims 1 to 12, wherein the crop image comprises a binary image of the crop or a grayscale image of the crop.
15. A method of operating a crop, comprising:
determining an airline planning map using the method of any one of claims 1-14;
and operating the crops based on the routing diagram.
16. An airline planning apparatus, comprising:
the first determining module is used for determining a crop image and determining the main direction of a planting row in the crop image;
a second determining module for determining an accumulation curve based on the principal direction and the crop distribution in the crop image;
a third determining module, configured to determine a planting row area in the crop image based on the accumulation curve and the set of straight lines determined by the main direction;
the fourth determination module is used for determining a route planning map based on the connected domain of the crops in each planting row area;
the determining the main direction of the planting rows in the crop image comprises:
performing linear detection on the crop image based on a linear detection method, and determining the main direction of planting rows in the crop image based on detected linear data;
the second determining module is used for determining an accumulation curve based on the number of the crop pixel points or the number of the non-crop pixel points in the crop image and the main direction;
wherein the planting row area determination mode comprises at least one of the following modes: determining a non-crop pixel point planting row area according to the peak of the wave; and determining the planting row area of the crop pixel points according to the valley points.
17. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-15.
18. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-15.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010537072.5A CN113808155B (en) | 2020-06-12 | 2020-06-12 | Air route planning and crop operation method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010537072.5A CN113808155B (en) | 2020-06-12 | 2020-06-12 | Air route planning and crop operation method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113808155A CN113808155A (en) | 2021-12-17 |
| CN113808155B true CN113808155B (en) | 2023-04-11 |
Family
ID=78892193
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010537072.5A Active CN113808155B (en) | 2020-06-12 | 2020-06-12 | Air route planning and crop operation method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113808155B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107958226A (en) * | 2017-12-15 | 2018-04-24 | 海信集团有限公司 | A kind of road curve detection method, device and terminal |
| CN109308465A (en) * | 2018-09-14 | 2019-02-05 | 百度在线网络技术（北京）有限公司 | Table line detecting method, apparatus, equipment and computer-readable medium |
| CN109933091A (en) * | 2019-04-19 | 2019-06-25 | 北方天途航空技术发展（北京）有限公司 | Paths planning method, storage medium and the electronic equipment of unmanned machine operation |
| CN110297483A (en) * | 2018-03-21 | 2019-10-01 | 广州极飞科技有限公司 | To operating area boundary acquisition methods, device, operation flight course planning method |
-
2020
- 2020-06-12 CN CN202010537072.5A patent/CN113808155B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107958226A (en) * | 2017-12-15 | 2018-04-24 | 海信集团有限公司 | A kind of road curve detection method, device and terminal |
| CN110297483A (en) * | 2018-03-21 | 2019-10-01 | 广州极飞科技有限公司 | To operating area boundary acquisition methods, device, operation flight course planning method |
| CN109308465A (en) * | 2018-09-14 | 2019-02-05 | 百度在线网络技术（北京）有限公司 | Table line detecting method, apparatus, equipment and computer-readable medium |
| CN109933091A (en) * | 2019-04-19 | 2019-06-25 | 北方天途航空技术发展（北京）有限公司 | Paths planning method, storage medium and the electronic equipment of unmanned machine operation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113808155A (en) | 2021-12-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210342585A1 (en) | Systems and methods for extracting and vectorizing features of satellite imagery | |
| CN110148196B (en) | Image processing method and device and related equipment | |
| Costea et al. | Creating roadmaps in aerial images with generative adversarial networks and smoothing-based optimization | |
| US20180182122A1 (en) | Remote determination of quantity stored in containers in geographical region | |
| Bargoti et al. | A pipeline for trunk detection in trellis structured apple orchards | |
| CN109886155B (en) | Single-plant rice detection and positioning method, system, equipment and medium based on deep learning | |
| CN111126287A (en) | Remote sensing image dense target deep learning detection method | |
| US11145089B2 (en) | Method for measuring antenna downtilt based on multi-scale detection algorithm | |
| de Silva et al. | Towards agricultural autonomy: crop row detection under varying field conditions using deep learning | |
| CN109949229A (en) | A kind of target cooperative detection method under multi-platform multi-angle of view | |
| Zhang et al. | AgriPest-YOLO: A rapid light-trap agricultural pest detection method based on deep learning | |
| CN115115954A (en) | Intelligent identification method for pine nematode disease area color-changing standing trees based on unmanned aerial vehicle remote sensing | |
| Biglia et al. | 3D point cloud density-based segmentation for vine rows detection and localisation | |
| CN113470017B (en) | Power transmission line safety early warning detection method, device and equipment based on artificial intelligence | |
| Borrenpohl et al. | Automated pruning decisions in dormant sweet cherry canopies using instance segmentation | |
| CN110188661A (en) | Boundary Recognition method and device | |
| CN113808155B (en) | Air route planning and crop operation method, device, equipment and storage medium | |
| Jia et al. | YOLOF-Snake: An efficient segmentation model for green object fruit | |
| CN113033386A (en) | High-resolution remote sensing image-based transmission line channel hidden danger identification method and system | |
| Mejia et al. | Strawberry localization in a ridge planting with an autonomous rover | |
| Shahid et al. | Aerial imagery-based tobacco plant counting framework for efficient crop emergence estimation | |
| CN116612386A (en) | Pepper disease and pest identification method and system based on hierarchical detection double-task model | |
| Treboux et al. | Towards retraining of machine learning algorithms: an efficiency analysis applied to smart agriculture | |
| Marreiros et al. | Progress in Artificial Intelligence: 20th EPIA Conference on Artificial Intelligence, EPIA 2021, Virtual Event, September 7–9, 2021, Proceedings | |
| Nyarko et al. | Tomato fruit disease detection based on improved single shot detection algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |