CN108596937A - field boundary detection method and device - Google Patents
field boundary detection method and device Download PDFInfo
- Publication number
- CN108596937A CN108596937A CN201810404978.2A CN201810404978A CN108596937A CN 108596937 A CN108596937 A CN 108596937A CN 201810404978 A CN201810404978 A CN 201810404978A CN 108596937 A CN108596937 A CN 108596937A
- Authority
- CN
- China
- Prior art keywords
- image
- grid
- pixel
- value
- gray value
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 39
- 238000012545 processing Methods 0.000 claims abstract description 55
- 238000000034 method Methods 0.000 claims description 20
- 238000004422 calculation algorithm Methods 0.000 claims description 16
- 230000009467 reduction Effects 0.000 claims description 11
- 230000002776 aggregation Effects 0.000 claims description 7
- 238000004220 aggregation Methods 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 6
- 239000002699 waste material Substances 0.000 abstract description 4
- 230000015654 memory Effects 0.000 description 20
- 238000010586 diagram Methods 0.000 description 16
- 238000011017 operating method Methods 0.000 description 16
- 230000006870 function Effects 0.000 description 9
- 230000008569 process Effects 0.000 description 5
- 238000009435 building construction Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000009313 farming Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
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
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
-
- G06T5/70—
-
- 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
Abstract
The present invention relates to technical field of image processing, more particularly to a kind of field boundary detection method and device, processing is reduced to obtain the first image by obtaining image to be detected and carrying out the first interference, wherein, described image to be detected is the image for including farmland, BORDER PROCESSING is carried out to obtain the second image to described first image, carrying out the second interference to second image reduces processing to obtain field boundary figure, reliably, efficiently to complete the detection to field boundary, and then effectively avoid the problem that using excessive time and waste of manpower resource.
Description
Technical field
The present invention relates to technical field of image processing, in particular to a kind of field boundary detection method and device.
Background technology
Currently, since rural area has, soil is with a varied topography, border detection error is big, coordinate geometry and keyboard input
The mainstream digital map graphic data acquisition mode for being combined into farmland and really weighing work.
Through inventor the study found that currently, the side for the combination that average each administrative village is inputted using coordinate geometry and keyboard
Formula completes a whole set of really power requirements of process half a year even longer duration, and is singly that digitlization is drawn the flow of field boundary and just needed
Nearly two months, and depend merely on be accomplished manually field boundary and digitize process when, influence very much the progress efficiency of whole item work.
Therefore a set of reliable, efficient field boundary automatic detection is provided know method for distinguishing, with effectively save human resources and saving
Time is a technical problem to be solved urgently.
Invention content
In view of this, the purpose of the present invention is to provide a kind of field boundary detection method and device, to solve above-mentioned skill
Art problem.
In order to achieve the above object, the embodiment of the present invention provides a kind of field boundary detection method, including：
Obtaining image to be detected and carrying out the first interference reduces processing to obtain the first image, wherein the mapping to be checked
As being the image for including farmland；
BORDER PROCESSING is carried out to obtain the second image to described first image；
Carrying out the second interference to second image reduces processing to obtain field boundary figure.
Optionally, in above-mentioned field boundary detection method, described acquisition image to be detected simultaneously carries out the first interference reduction
Processing to obtain the first image the step of include：
Each pixel of described image to be detected and the gray value of each pixel are obtained, and each pixel is divided to obtain
To multiple grids, wherein each grid includes multiple pixels；
The intermediate value of the corresponding gray value of each pixel in each grid is obtained, and using the intermediate value as the grid central point pair
The gray value for the pixel answered；
Maximum value and the minimum value of the corresponding grey scale value of each pixel in each grid are obtained to obtain the gray value of each grid
Range；
It is clustered using iso according to the intensity value ranges of the gray value of the central point pixel of each grid and each grid
Algorithm carries out tagsort to obtain two classification grids, and uses the mode of output with conditions to two classification grids to obtain
To the first image.
Optionally, in above-mentioned field boundary detection method, BORDER PROCESSING is carried out to obtain second to described first image
The step of image includes：
Wave band analysis is carried out to obtain a variety of single band images to described first image, side is carried out to each single band image
Boundary is identified to obtain single band Boundary Recognition result；
Each single band Boundary Recognition result is subjected to aggregation of data to obtain the second image.
Optionally, described that second image is carried out at the second interference reduction in above-mentioned field boundary detection method
Reason to include the step of obtaining field boundary figure：
The gray value of each pixel in the second image is obtained, and according to the gray value of a preset value and each pixel to each second figure
Each pixel as in carries out assignment, and is refined the boundary in second image to obtain third figure according to assigned result
Picture；
The maximum value of the corresponding gray value of each pixel in each grid in third image is obtained as in each grid
The gray value of the corresponding pixel of heart point；
It is worth to multiple regions according to the gray scale of each grid, and is obtained respectively according to the position of the corresponding grid in each region
The perimeter in the region；
The focus maximum value of the perimeter in each region grid corresponding with the region is subjected to product to obtain the 4th image；
Iso clustering algorithms are used to classify the 4th image of the result of product to obtain classification results, and according to institute
It states classification results and obtains field boundary image.
Optionally, in above-mentioned field boundary detection method, the classification results are that there are boundary and boundary, root is not present
The step of obtaining field boundary image according to the classification results include：
It is that there are each pixels in the grid of boundary farmland image according to each grid classification result in the three or four image
Gray value carries out assignment to each pixel, and is refined the boundary in the 4th third image to obtain according to assigned result
To the 5th the 4th image：
The maximum value in the gray value of each pixel in the 5th the 4th image in each grid is obtained as the grid
The gray value of the corresponding pixel in center, and assignment is carried out according to the gray value of the pixel, and carried out carefully according to the assignment
Change output to obtain field boundary.
The present invention also provides a kind of field boundary detection devices, including：
First interference reduces module, and processing is reduced to obtain the first figure for obtaining image to be detected and carrying out the first interference
Picture, wherein described image to be detected is the image for including farmland；
Margin processing module, for carrying out BORDER PROCESSING to described first image to obtain the second image；
Second interference reduces module, and processing is reduced to obtain field boundary for carrying out the second interference to second image
Figure.
Optionally, in above-mentioned field boundary detection device, first interference reduces module and includes：
Division submodule, the gray value of each pixel and each pixel for obtaining described image to be detected, and to each described
Pixel is divided to obtain multiple grids, wherein each grid includes multiple pixels；
First assignment submodule, the intermediate value for obtaining the corresponding gray value of each pixel in each grid, and by the intermediate value
Gray value as the corresponding pixel of the grid central point；
Range acquisition submodule, the maximum value and minimum value of the corresponding grey scale value for obtaining each pixel in each grid with
Obtain the intensity value ranges of each grid；
First image obtains submodule, is used for the gray value of the central point pixel according to each grid and each grid
Intensity value ranges use iso clustering algorithms to carry out tagsort to obtain two classification grids, and to two classification grid
Lattice use the mode of output with conditions to obtain the first image.
Optionally, in above-mentioned field boundary detection device, margin processing module includes：
Submodule is identified, for carrying out wave band analysis to obtain a variety of single band images, to each to described first image
Single band image carries out Boundary Recognition to obtain single band Boundary Recognition result；
Second image obtains submodule, for each single band Boundary Recognition result to be carried out aggregation of data to obtain the
Two images.
Optionally, in above-mentioned field boundary detection device, second interference reduces module and includes：
Third image obtains submodule, for obtaining the gray value of each pixel in the second image, and according to a preset value and
The gray value of each pixel carries out assignment to each pixel in each second image, and according to assigned result in second image
Boundary is refined to obtain third image；
Second assignment submodule, the maximum for obtaining the corresponding gray value of each pixel in each grid in third image
It is worth the gray value of the corresponding pixel of central point as each grid；
Perimeter obtains submodule, for being worth to multiple regions according to the gray scale of each grid, and according to each region pair
The position for the grid answered obtains the perimeter in each region；
Computational submodule, for by the focus maximum value of the perimeter in each region grid corresponding with region progress product with
Obtain the 4th image；
Boundary image obtains submodule, for being classified using iso clustering algorithms to the 4th image of the result of product
To obtain classification results, and field boundary image is obtained according to the classification results.
Optionally, in above-mentioned field boundary detection device, the boundary image obtains submodule and includes：
Image acquiring unit, for being that there are boundary farmland images according to each grid classification result in the three or four image
Grid in the gray value of each pixel assignment is carried out to each pixel, and according to assigned result in the 4th third image
Boundary is refined to obtain the 5th the 4th image：
Boundary obtaining unit, in the gray value for obtaining each pixel in the 5th the 4th image in each grid
Gray value of the maximum value as the corresponding pixel in grid center, and assignment is carried out according to the gray value of the pixel, and
Refinement output is carried out to obtain field boundary according to the assignment.
A kind of field boundary detection method and device provided in an embodiment of the present invention, method include：Obtain image to be detected
And the first interference reduction processing is carried out to obtain the first image, wherein described image to be detected is the image for including farmland, to institute
It states the first image and carries out BORDER PROCESSING to obtain the second image, carrying out the second interference to second image reduces processing to obtain
Field boundary figure.By the above method reliably, efficiently to complete the detection to field boundary, and then effectively avoid using
The problem of more times and waste of manpower resource.
Description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 is a kind of connection block diagram of terminal device provided in an embodiment of the present invention.
Fig. 2 is a kind of flow diagram of field boundary detection method provided in an embodiment of the present invention.
Fig. 3 is the flow diagram of step S110 in Fig. 2.
Fig. 4 is the flow diagram of step S120 in Fig. 2.
Fig. 5 is the flow diagram of step S130 in Fig. 2.
Fig. 6 is the flow diagram of step S135 in Fig. 5.
Fig. 7 is a kind of module frame chart of field boundary detection device provided in an embodiment of the present invention.
Fig. 8 is the connection block diagram that a kind of first interference provided in an embodiment of the present invention reduces module.
Fig. 9 is a kind of connection block diagram of margin processing module provided in an embodiment of the present invention.
Figure 10 is the connection block diagram that a kind of second interference provided in an embodiment of the present invention reduces module.
Figure 11 is the connection block diagram that a kind of boundary image provided in an embodiment of the present invention obtains submodule.
Icon：10- terminal devices；12- memories；14- processors；100- field boundary detection devices；110- first is dry
Disturb reduction module；112- divides submodule；114- the first assignment submodules；116- range acquisition submodules；The first images of 118-
Obtain submodule；120- margin processing modules；122- identifies submodule；The second images of 124- obtain submodule；130- second is dry
Disturb reduction module；131- third images obtain submodule；132- the second assignment submodules；133- perimeters obtain submodule；134-
Computational submodule；135- boundary images obtain submodule；135a- image acquiring units；The boundaries 135b- obtaining unit.
Specific implementation mode
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.The present invention being usually described and illustrated herein in the accompanying drawings is implemented
The component of example can be arranged and be designed with a variety of different configurations.
Therefore, below the detailed description of the embodiment of the present invention to providing in the accompanying drawings be not intended to limit it is claimed
The scope of the present invention, but be merely representative of the present invention selected embodiment.Based on the embodiments of the present invention, this field is common
The every other embodiment that technical staff is obtained without creative efforts belongs to the model that the present invention protects
It encloses.
It should be noted that：Similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined, then it further need not be defined and explained in subsequent attached drawing in a attached drawing.
As shown in Figure 1, being the block diagram of terminal device 10 provided in an embodiment of the present invention.In the embodiment of the present invention
Terminal device 10 can be the equipment for having data-handling capacity.As shown in Figure 1, terminal device 10 includes：Memory 12 and place
Manage device 14.
The memory 12 is directly or indirectly electrically connected between each other with processor 14, with realize data transmission or
Interaction.It is electrically connected for example, these elements can be realized between each other by one or more communication bus or signal wire.Memory
The software function module being stored in the form of software or firmware (Firmware) in the memory 12 is stored in 12, it is described
Processor 14 is stored in software program and module in memory 12 by operation, such as the field boundary in the embodiment of the present invention
Detection device 100 realizes the field boundary inspection in the embodiment of the present invention to perform various functions application and data processing
Survey method.
Wherein, the terminal device 10 may be, but not limited to, smart mobile phone, computer (personal computer,
PC), tablet computer, digital assistants (personal digital assistant, PDA), mobile internet surfing equipment (mobile
Internet device, MID), it is not specifically limited herein.
The memory 12 may be, but not limited to, random access memory (Random Access Memory, RAM),
Read-only memory (Read Only Memory, ROM), programmable read only memory (Programmable Read-Only
Memory, PROM), erasable read-only memory (Erasable Programmable Read-Only Memory, EPROM),
Electricallyerasable ROM (EEROM) (Electrically Erasable Programmable Read-Only Memory,
EEPROM) etc..Wherein, memory 12 is for storing program, and the processor 14 executes the journey after receiving and executing instruction
Sequence.
The processor 14 may be a kind of IC chip, the processing capacity with signal.Above-mentioned processor 14
Can be general processor, including central processing unit (Central Processing Unit, CPU), network processing unit
(Network Processor, NP) etc..It can also be digital signal processor (DSP), application-specific integrated circuit (ASIC), scene
Programmable gate array (FPGA) either other programmable logic device, discrete gate or transistor logic, discrete hardware group
Part.It may be implemented or execute disclosed each method, step and the logic diagram in the embodiment of the present invention.General processor can be with
It is microprocessor or the processor can also be any conventional processor etc..
It is appreciated that structure shown in FIG. 1 is only to illustrate, terminal device 10 may also include it is more than shown in Fig. 1 or
Less component, or with the configuration different from shown in Fig. 1.Each component shown in Fig. 1 may be used hardware, software or its
Combination is realized.
Referring to Fig. 2, a kind of field boundary detection method provided by the invention, the method includes the steps S110~S130
Three steps.
Step S110：Obtaining image to be detected and carrying out the first interference reduces processing to obtain the first image, wherein described
Image to be detected is the image for including farmland.
Image to be detected is the image that image acquisition device arrives, and generally includes farming in described image to be detected
Object, building construction and farmland reduce processing to remove building construction and agriculture by carrying out the first interference to described image to be detected
Field etc., so that the first obtained image is the image for only including farmland.
Step S120：BORDER PROCESSING is carried out to obtain the second image to described first image.
Wherein, to described first image carry out BORDER PROCESSING mode be, to described first image carry out Boundary Recognition with
The second image is obtained, and second image includes the boundary in each farmland, the side of Boundary Recognition is carried out to described first image
The mode of linear identification may be used in formula, can also be worth to the second image according to the gray scale of each pixel in the first image, herein
It is not especially limited.
Step S130：Carrying out the second interference to second image reduces processing to obtain field boundary figure.
Since the boundary in farmland is usually wider, processing is reduced so that the agriculture obtained by carrying out interference to second image
Field boundary image is more clear accurately.
Through the above steps, to carry out the first interference reduction processing to described image to be detected, to effectively remove image
In interference information, and Boundary Recognition is carried out to obtain the boundary in farmland to image after removal is interfered, and known into row bound
Do not further decrease interference afterwards so that obtained field boundary figure, and then the field boundary figure that obtains of effective guarantee can
By property, and effectively prevent measuring the case where drawing the overspending time and causing waste of human resource using artificial.
Incorporated by reference to Fig. 3, described acquisition image to be detected simultaneously carries out the first interference reduction processing to obtain the step of the first image
Suddenly include：
Step S112：Obtain each pixel of described image to be detected and the gray value of each pixel, and to each pixel into
Row is divided to obtain multiple grids, wherein each grid includes multiple pixels.
Wherein, the quantity of the corresponding pixel of each grid can be but not limited to 9 or 25.In the present embodiment, often
The quantity for the pixel that a grid includes is 9, and is arranged in a manner of nine grids.
Step S114：The intermediate value of the corresponding gray value of each pixel in each grid is obtained, and using the intermediate value as the grid
The gray value of the corresponding pixel of lattice central point.
Step S116：Maximum value and the minimum value of the corresponding grey scale value of each pixel in each grid are obtained to obtain each grid
Intensity value ranges.
Step S118：It is adopted according to the intensity value ranges of the gray value of the central point pixel of each grid and each grid
Tagsort is carried out with iso clustering algorithms to obtain two classification grids, and output with conditions is used to two classification grids
Mode to obtain the first image.
Specifically, according to iso clustering algorithms progress tagsort to obtain two classification grids, it is corresponding effectively to distinguish
Whether grid is the corresponding grid of farmland image, and the mode of output with conditions is used to obtain described first image to realize to not being
The grid of the farmland image is rejected, and then effectively reduces interference.For example, prestoring default gray value in the memory
Range and setting gray value, the default intensity value ranges may include the corresponding pixel of field boundary intensity value ranges and
Build corresponding intensity value ranges in house etc..The gray value and each grid of the central point pixel according to each grid
Intensity value ranges use iso clustering algorithms carry out tagsort by obtain two classification grids in a manner of can be：According to
The gray value of the central point pixel of each grid, the intensity value ranges of each grid, the default intensity value ranges and
Setting gray value uses iso clustering algorithms to carry out tagsort to obtain two classification grids.
Incorporated by reference to Fig. 4, carrying out the step of BORDER PROCESSING is to obtain the second image to described first image includes：
Step S122：Wave band analysis is carried out to obtain a variety of single band images, to each single band to described first image
Image carries out Boundary Recognition to obtain single band Boundary Recognition result.
Step S124：Each single band Boundary Recognition result is subjected to aggregation of data to obtain the second image.
Specifically, carrying out wave band analysis to obtain tri- single band images of R, G and B, and for every to described first image
The image of a wave band exports after carrying out Boundary Recognition respectively, and the image after exporting carries out aggregation of data so as to be examined into row bound
The result of survey is more accurate.
Since there may be the boundaries in the farmland obtained after wave band synthesis after carrying out wave band integrated treatment to figure
It is wider, it is more accurate for the image that further detects carry out field boundary, incorporated by reference to Fig. 5, optionally, in the present embodiment
In, it is described that second interference reduction processing is carried out to include the step of obtaining field boundary figure to second image：
Step S131：The gray value of each pixel in the second image is obtained, and according to a preset value and the gray value of each pixel
To in each second image each pixel carry out assignment, and according to assigned result to the boundary in second image refined with
Obtain third image.
Specifically, the pixel is then assigned a value of 1 when the gray value of pixel is more than the preset value, when the ash of the pixel
The pixel is then assigned a value of 0 by angle value when being less than the preset value, and is refined to second image according to assigned result, example
Such as, the pixel for being assigned a value of 0 is rejected, to obtain the third image.
Step S132：The maximum value of the corresponding gray value of each pixel in each grid in third image is obtained as each
The gray value of the corresponding pixel of central point of grid.
Step S133：It is worth to multiple regions according to the gray scale of each grid, and according to the corresponding grid in each region
Position obtains the perimeter in each region.
Step S134：The focus maximum value of the perimeter in each region grid corresponding with the region is subjected to product to be multiplied
Product result.
Step S135：Iso clustering algorithms are used to classify the result of product to obtain classification results, and according to institute
It states classification results and obtains field boundary image.
By above-mentioned setting, with the further accuracy for ensureing the field boundary image boundary recognized.
Specifically, the perimeter in farmland is typically larger than the perimeter in house, by by the perimeter and the focus maximum value into
Row product is to expand the corresponding perimeter value in each region, for the perimeter in each region after expansion, simultaneously using iso clustering algorithms
Classified based on a setting perimeter value, for example, when the perimeter in each region after expansion is less than the setting perimeter value, is then divided
It is not farmland that result after class, which is the corresponding region of the perimeter, and the perimeter in each region after expansion is more than the setting perimeter value
When, then it is farmland that sorted result, which is the corresponding region of the perimeter, and it is that the region in farmland obtains to be according to the classification results
Field boundary, with the further accuracy for ensureing the field boundary obtained.
To further decrease interference, and then ensure the accuracy of field boundary identification, optionally, in the present embodiment, institute
Classification results are stated to be farmland image and wrap the step of not being farmland image, field boundary image is obtained according to the classification results
It includes：
Step S135a：It is each pixel in the grid there are boundary according to each grid classification result in the third image
Gray value carries out assignment to each pixel, and is refined to the boundary in the third image according to assigned result to obtain the
Four images.
Step S135b：Obtain the maximum value conduct in the gray value of each pixel in the 4th image in each grid
The gray value of the corresponding pixel in grid center, and assignment is carried out according to the gray value of the pixel, and according to the assignment
Refinement output is carried out to obtain field boundary.
Incorporated by reference to Fig. 7, on the basis of the above, the present invention also provides a kind of field boundary detection device 100, the farmland side
Boundary's detection device 100 includes：First interference reduces module 110, the interference of margin processing module 120 and second reduces module 130.
First interference reduces module 110 reduces processing to obtain for obtaining image to be detected and carrying out the first interference
First image, wherein described image to be detected is the image for including farmland.Specifically, the first interference reduction module 110 can
For executing step S110 shown in Fig. 2, specific operating method can refer to the detailed description of step S110.
Incorporated by reference to Fig. 8, optionally, in the present embodiment, the editor module 110 includes：Divide submodule 112, first
Assignment submodule 114, range acquisition submodule 116 and the first image obtain submodule 118.
The gray value for dividing submodule 112 and being used to obtain each pixel and each pixel of described image to be detected, and it is right
Each pixel is divided to obtain multiple grids, wherein each grid includes multiple pixels.Specifically, the division
Submodule 112 can be used for executing step S112 shown in Fig. 3, and specific operating method can refer to retouching in detail for step S112
It states.
The first assignment submodule 114 is used to obtain the intermediate value of the corresponding gray value of each pixel in each grid, and will
Gray value of the intermediate value as the corresponding pixel of the grid central point.Specifically, the first assignment submodule 114 can be used for
Step S114 shown in Fig. 3 is executed, specific operating method can refer to the detailed description of step S114.
The range acquisition submodule 116 is used to obtain the maximum value and most of the corresponding grey scale value of each pixel in each grid
Small value is to obtain the intensity value ranges of each grid.Specifically, the range acquisition submodule 116 can be used for executing shown in Fig. 3
Step S116, specific operating method can refer to the detailed description of step S116.
Described first image acquisition submodule 118 is used for the gray value of the central point pixel according to each grid and each institute
The intensity value ranges for stating grid use iso clustering algorithms to carry out tagsort to obtain two classification grids, and to described in two
Classification grid uses the mode of output with conditions to obtain the first image.Specifically, described first image obtains submodule 118 and can use
In executing step S118 shown in Fig. 3, specific operating method can refer to the detailed description of step S118.
The margin processing module 120 is used to carry out BORDER PROCESSING to described first image to obtain the second image.Specifically
Ground, the margin processing module 120 can be used for executing step S120 shown in Fig. 2, and specific operating method can refer to step
The detailed description of S120.
Incorporated by reference to Fig. 9, optionally, in the present embodiment, the margin processing module 120 includes identification submodule and second
Image obtains submodule 124.
The identification submodule 122 is used to carry out wave band to described first image to analyze to obtain a variety of single band images,
Boundary Recognition is carried out to obtain single band Boundary Recognition result to each single band image.Specifically, the identification submodule 122
It can be used for executing step S122 shown in Fig. 4, specific operating method can refer to the detailed description of step S122.
Second image obtain submodule 124 be used for will each single band Boundary Recognition result progress aggregation of data with
Obtain the second image.Specifically, second image obtains submodule 124 and can be used for executing step S124 shown in Fig. 4, has
The operating method of body can refer to the detailed description of step S124.
Second interference reduces module 130 and is used to carry out the second interference to second image to reduce processing to obtain agriculture
Field boundary figure.Specifically, the second interference reduction module 130 can be used for executing step S130 shown in Fig. 2, specifically
Operating method can refer to the detailed description of step S130.
Optional incorporated by reference to Figure 10, in the present embodiment, second interference reduces module 130 and includes：Third image obtains
Submodule 131, the second assignment submodule 132, perimeter is obtained to obtain submodule 133, computational submodule 134 and boundary image and obtain
Submodule 135.
The third image obtains the gray value that submodule 131 is used to obtain each pixel in the second image, and pre- according to one
If the gray value of value and each pixel carries out assignment to each pixel in each second image, and according to assigned result to second figure
Boundary as in is refined to obtain third image.Specifically, the third image acquisition submodule 131 can be used for execution figure
Step S131 shown in 5, specific operating method can refer to the detailed description of step S131.
The second assignment submodule 132 is used to obtain the corresponding gray value of each pixel in each grid in third image
Maximum value as each grid the corresponding pixel of central point gray value.Specifically, the second assignment submodule 132 can
For executing step S132 shown in Fig. 5, specific operating method can refer to the detailed description of step S132.
The perimeter obtains submodule 133 and is used to be worth to multiple regions according to the gray scale of each grid, and according to each described
The position of the corresponding grid in region obtains the perimeter in each region.Specifically, the perimeter obtains submodule 133 and can be used for holding
Step S133 shown in row Fig. 5, specific operating method can refer to the detailed description of step S133.
The computational submodule 134 is used to carry out the focus maximum value of the perimeter in each region grid corresponding with the region
Product is to obtain result of product.Specifically, the computational submodule 134 can be used for executing step S134 shown in Fig. 5, specifically
Operating method can refer to the detailed description of step S134.
The boundary image obtain submodule 135 be used for the result of product use iso clustering algorithms to classify with
Classification results are obtained, and field boundary image is obtained according to the classification results.Specifically, the boundary image obtains submodule
135 can be used for executing step S135 shown in Fig. 5, and specific operating method can refer to the detailed description of step S135.
Incorporated by reference to Figure 11, optionally, in the present embodiment, the boundary image obtains submodule 135 and includes：Image obtains
Unit 135a and boundary obtaining unit 135b.
Described image obtaining unit 135a is used to according to each grid classification result in the third image be that there are boundaries
In grid the gray value of each pixel to each pixel carry out assignment, and according to assigned result to the boundary in the third image into
Row refinement is to obtain the 4th image.Specifically, described image obtaining unit 135a can be used for executing step shown in Fig. 6
S135a, specific operating method can refer to the detailed description of step S135a.
The boundary obtaining unit 135b is used to obtain the gray value of each pixel in the 4th image in each grid
In gray value of the maximum value as the corresponding pixel in grid center, and assignment is carried out according to the gray value of the pixel,
And refinement output is carried out to obtain field boundary according to the assignment.Specifically, the boundary obtaining unit 135b can be used for holding
Step S135b shown in row Fig. 6, specific operating method can refer to the detailed description of step S135b.
To sum up, a kind of field boundary detection method and device provided by the invention, by obtaining image to be detected and carrying out
First interference reduces processing to obtain the first image, wherein described image to be detected is the image for including farmland, to described first
Image carries out BORDER PROCESSING to obtain the second image, and carrying out the second interference to second image reduces processing to obtain farmland side
Boundary's figure reliably, efficiently to complete the detection to field boundary, and then effectively avoids using excessive time and waste of manpower
The problem of resource.
In several embodiments that the embodiment of the present invention is provided, it should be understood that disclosed device and method also may be used
To realize by another way.Device and method embodiment described above is only schematical, for example, in attached drawing
Flow chart and block diagram show the device of multiple embodiments according to the present invention, the possibility of method and computer program product is realized
Architecture, function and operation.In this regard, each box in flowchart or block diagram can represent module, a program
A part for a part for section or code, the module, section or code includes that one or more is patrolled for realizing defined
Collect the executable instruction of function.It should also be noted that at some as the function of in the realization method replaced, being marked in box
It can occur in a different order than that indicated in the drawings.It is also noted that each box in block diagram and or flow chart,
And the combination of the box in block diagram and or flow chart, function or the dedicated of action as defined in executing can be used to be based on hardware
Device realize, or can realize using a combination of dedicated hardware and computer instructions.In addition, in each implementation of the present invention
Each function module in example can integrate to form an independent part, can also be modules individualism,
An independent part can be integrated to form with two or more modules.
It, can be with if the function is realized and when sold or used as an independent product in the form of software function module
It is stored in a computer read/write memory medium.Based on this understanding, technical scheme of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be expressed in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be
People's computer, electronic equipment or network equipment etc.) execute all or part of step of each embodiment the method for the present invention
Suddenly.And storage medium above-mentioned includes：USB flash disk, read-only memory (ROM, Read-Only Memory), is deposited mobile hard disk at random
The various media that can store program code such as access to memory (RAM, Random Access Memory), magnetic disc or CD.
It should be noted that herein, the terms "include", "comprise" or its any other variant are intended to the packet of nonexcludability
Contain, so that the process, method, article or equipment including a series of elements includes not only those elements, but also includes
Other elements that are not explicitly listed, or further include for elements inherent to such a process, method, article, or device.
In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including the element
Process, method, article or equipment in there is also other identical elements.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, any made by repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of field boundary detection method, which is characterized in that the method includes：
Obtaining image to be detected and simultaneously carrying out the first interference reduces processing to obtain the first image, wherein described image to be detected is
Image including farmland；
BORDER PROCESSING is carried out to obtain the second image to described first image；
Carrying out the second interference to second image reduces processing to obtain field boundary figure.
2. field boundary detection method according to claim 1, which is characterized in that described acquisition image to be detected simultaneously carries out
First interference reduces the step of processing is to obtain the first image：
Each pixel of described image to be detected and the gray value of each pixel are obtained, and each pixel is divided more to obtain
A grid, wherein each grid includes multiple pixels；
The intermediate value of the corresponding gray value of each pixel in each grid is obtained, and the intermediate value is corresponding as the grid central point
The gray value of pixel；
Maximum value and the minimum value of the corresponding grey scale value of each pixel in each grid are obtained to obtain the intensity value ranges of each grid；
Iso clustering algorithms are used according to the intensity value ranges of the gray value of the central point pixel of each grid and each grid
Tagsort is carried out to obtain two classification grids, and the mode of output with conditions is used to two classification grids to obtain the
One image.
3. field boundary detection method according to claim 2, which is characterized in that carry out boundary to described first image
Reason to obtain the second image the step of include：
Wave band analysis is carried out to obtain a variety of single band images to described first image, each single band image is known into row bound
Not to obtain single band Boundary Recognition result；
Each single band Boundary Recognition result is subjected to aggregation of data to obtain the second image.
4. field boundary detection method according to claim 2, which is characterized in that described to carry out the to second image
Two interference reduce processing to include the step of obtaining field boundary figure：
The gray value of each pixel in the second image is obtained, and according to the gray value of a preset value and each pixel in each second image
Each pixel carry out assignment, and the boundary in second image is refined to obtain third image according to assigned result；
Obtain central point of the maximum value of the corresponding gray value of each pixel in each grid in third image as each grid
The gray value of corresponding pixel；
It is worth to multiple regions according to the gray scale of each grid, and is obtained according to the position of the corresponding grid in each region each described
The perimeter in region；
The focus maximum value of the perimeter in each region grid corresponding with the region is subjected to product to obtain result of product；
It uses iso clustering algorithms to classify to obtain classification results the result of product, and is obtained according to the classification results
To field boundary image.
5. field boundary detection method according to claim 4, which is characterized in that the classification results be farmland image and
The step of not being farmland image, field boundary image is obtained according to the classification results includes：
According to each grid classification result in the third image be farmland image grid in each pixel gray value to each picture
Member carries out assignment, and is refined the boundary in the third image to obtain the 4th image according to assigned result：
The maximum value in the gray value of each pixel in the 4th image in each grid is obtained as the grid center
The gray value of corresponding pixel, and according to the gray value of the pixel carry out assignment, and according to the assignment carry out refinement output with
Obtain field boundary.
6. a kind of field boundary detection device, which is characterized in that including：
First interference reduces module, interferes reduction processing to obtain the first image for obtaining image to be detected and carrying out first,
Wherein, described image to be detected is the image for including farmland；
Margin processing module, for carrying out BORDER PROCESSING to described first image to obtain the second image；
Second interference reduces module, and processing is reduced to obtain field boundary figure for carrying out the second interference to second image
Shape.
7. field boundary detection device according to claim 6, which is characterized in that first interference reduces module packet
It includes：
Division submodule, the gray value of each pixel and each pixel for obtaining described image to be detected, and to each pixel
It is divided to obtain multiple grids, wherein each grid includes multiple pixels；
First assignment submodule, the intermediate value for obtaining the corresponding gray value of each pixel in each grid, and using the intermediate value as
The gray value of the corresponding pixel of the grid central point；
Range acquisition submodule, the maximum value and minimum value of the corresponding grey scale value for obtaining each pixel in each grid are to obtain
The intensity value ranges of each grid；
First image obtains submodule, is used for the ash of the gray value and each grid of the central point pixel according to each grid
Angle value range uses iso clustering algorithms to carry out tagsort to obtain two classification grids, and is adopted to two classification grids
With the mode of output with conditions to obtain the first image.
8. field boundary detection device according to claim 7, which is characterized in that margin processing module includes：
Submodule is identified, for carrying out wave band analysis to obtain a variety of single band images, to each unicast to described first image
Section image carries out Boundary Recognition to obtain single band Boundary Recognition result；
Second image obtains submodule, for each single band Boundary Recognition result to be carried out aggregation of data to obtain the second figure
Picture.
9. field boundary detection device according to claim 7, which is characterized in that second interference reduces module packet
It includes：
Third image obtains submodule, the gray value for obtaining each pixel in the second image, and according to a preset value and each picture
The gray value of member carries out assignment to each pixel in each second image, and according to assigned result to the boundary in second image
It is refined to obtain third image；
Second assignment submodule, the maximum value for obtaining the corresponding gray value of each pixel in each grid in third image are made
For the gray value of the corresponding pixel of central point of each grid；
Perimeter obtains submodule, for being worth to multiple regions according to the gray scale of each grid, and it is corresponding according to each region
The position of grid obtains the perimeter in each region；
Computational submodule, for the focus maximum value of the perimeter in each region grid corresponding with the region to be carried out product to obtain
Result of product；
Boundary image obtains submodule, for using iso clustering algorithms to classify to obtain the 4th image of the result of product
Field boundary image is obtained to classification results, and according to the classification results.
10. field boundary detection device according to claim 9, which is characterized in that the classification results are farmland image
It is not farmland image, the boundary image obtains submodule and includes：
Image acquiring unit, for being that there are the grid of boundary farmland image according to each grid classification result in the three or four image
The gray value of each pixel to each pixel carries out assignment in lattice, and according to assigned result to the boundary in the 4th third image
It is refined to obtain the 5th the 4th image：
Boundary obtaining unit, the maximum in gray value for obtaining each pixel in the 5th the 4th image in each grid
It is worth the gray value as the corresponding pixel in grid center, and according to the gray value of pixel progress assignment, and according to
The assignment carries out refinement output to obtain field boundary.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810404978.2A CN108596937A (en) | 2018-04-28 | 2018-04-28 | field boundary detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810404978.2A CN108596937A (en) | 2018-04-28 | 2018-04-28 | field boundary detection method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108596937A true CN108596937A (en) | 2018-09-28 |
Family
ID=63620339
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810404978.2A Pending CN108596937A (en) | 2018-04-28 | 2018-04-28 | field boundary detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108596937A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116243353A (en) * | 2023-03-14 | 2023-06-09 | 广西壮族自治区自然资源遥感院 | Forest right investigation and measurement method and system based on Beidou positioning |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101308544A (en) * | 2008-07-11 | 2008-11-19 | 中国科学院地理科学与资源研究所 | Spatial heterogeneity mode recognition method and layering method based on grids |
| US20110074783A1 (en) * | 2003-12-18 | 2011-03-31 | 1626628 Ontario Limited | System, Apparatus and Method for Mapping |
| CN102867115A (en) * | 2012-08-29 | 2013-01-09 | 南京农业大学 | Farmland division method based on fuzzy c-means clustering |
| CN104751477A (en) * | 2015-04-17 | 2015-07-01 | 薛笑荣 | Space domain and frequency domain characteristic based parallel SAR (synthetic aperture radar) image classification method |
| CN205103412U (en) * | 2015-11-19 | 2016-03-23 | 四川大学 | Make up foldable sample thief that fetches earth |
| US9430499B2 (en) * | 2014-02-18 | 2016-08-30 | Environmental Systems Research Institute, Inc. | Automated feature extraction from imagery |
-
2018
- 2018-04-28 CN CN201810404978.2A patent/CN108596937A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110074783A1 (en) * | 2003-12-18 | 2011-03-31 | 1626628 Ontario Limited | System, Apparatus and Method for Mapping |
| CN101308544A (en) * | 2008-07-11 | 2008-11-19 | 中国科学院地理科学与资源研究所 | Spatial heterogeneity mode recognition method and layering method based on grids |
| CN102867115A (en) * | 2012-08-29 | 2013-01-09 | 南京农业大学 | Farmland division method based on fuzzy c-means clustering |
| US9430499B2 (en) * | 2014-02-18 | 2016-08-30 | Environmental Systems Research Institute, Inc. | Automated feature extraction from imagery |
| CN104751477A (en) * | 2015-04-17 | 2015-07-01 | 薛笑荣 | Space domain and frequency domain characteristic based parallel SAR (synthetic aperture radar) image classification method |
| CN205103412U (en) * | 2015-11-19 | 2016-03-23 | 四川大学 | Make up foldable sample thief that fetches earth |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116243353A (en) * | 2023-03-14 | 2023-06-09 | 广西壮族自治区自然资源遥感院 | Forest right investigation and measurement method and system based on Beidou positioning |
| CN116243353B (en) * | 2023-03-14 | 2024-02-27 | 广西壮族自治区自然资源遥感院 | Forest right investigation and measurement method and system based on Beidou positioning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104169945B (en) | To the two-stage classification of the object in image | |
| Sadeghi-Tehran et al. | Multi-feature machine learning model for automatic segmentation of green fractional vegetation cover for high-throughput field phenotyping | |
| US9251420B2 (en) | System for mapping and identification of plants using digital image processing and route generation | |
| CN103164692B (en) | A kind of special vehicle instrument automatic identification system based on computer vision and method | |
| CN111553240B (en) | Corn disease condition grading method and system and computer equipment | |
| CN109416313A (en) | Image map collecting system and method | |
| CN113269257A (en) | Image classification method and device, terminal equipment and storage medium | |
| CN109165666A (en) | Multi-tag image classification method, device, equipment and storage medium | |
| CN106462401A (en) | Program generation device, program generation method, and program | |
| CN113536958B (en) | Navigation path extraction method, device, agricultural robot and storage medium | |
| CN109416749A (en) | A kind of the gradient category method, apparatus and readable storage medium storing program for executing of image | |
| CN111429448A (en) | Bioluminescence target counting method based on weak segmentation information | |
| Shaharum et al. | Mapping the spatial distribution and changes of oil palm land cover using an open source cloud-based mapping platform | |
| JP2018005467A (en) | Farmwork plan support device and farmwork plan support method | |
| CN111860537A (en) | Deep learning-based green citrus identification method, equipment and device | |
| CN114638294A (en) | Data enhancement method and device, terminal equipment and storage medium | |
| Nandhini et al. | Machine learning technique for crop disease prediction through crop leaf image | |
| CN108596937A (en) | field boundary detection method and device | |
| Kini et al. | Techniques of deep learning and image processing in plant leaf disease detection: A review | |
| CN109656928A (en) | Relationship preparation method and device between table | |
| JP2017162098A (en) | Learning method, information processing device and learning program | |
| CN110688934B (en) | Space sampling active learning classification method, electronic equipment and storage medium | |
| CN105069480A (en) | Polarized SAR terrain classification method based on Gauss filtering and PSO | |
| Krupiński et al. | One class SVM for building detection on Sentinel-2 images | |
| CN108764183A (en) | A kind of plant disease diagnostic method, device and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180928 |