CN107220647A - Crop location of the core method and system under a kind of blade crossing condition - Google Patents
Crop location of the core method and system under a kind of blade crossing condition Download PDFInfo
- Publication number
- CN107220647A CN107220647A CN201710415434.1A CN201710415434A CN107220647A CN 107220647 A CN107220647 A CN 107220647A CN 201710415434 A CN201710415434 A CN 201710415434A CN 107220647 A CN107220647 A CN 107220647A
- Authority
- CN
- China
- Prior art keywords
- image
- target crop
- crop
- gray
- pixel
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides crop location of the core method and system under a kind of blade crossing condition, and methods described includes：Original-gray image based on target crop, obtains the gray level image and bianry image of target crop；Gray level image and bianry image based on the target crop, obtain the center point coordinate of target crop.Scheme of the present invention has the advantages that：The interference of crop cross vanes can be effectively excluded, the accuracy and speed of crop location of the core is improved.
Description
Technical field
The present invention relates to crop automatic identification field of locating technology, make more particularly, under a kind of blade crossing condition
Thing location of the core method and system.
Background technology
Crop automatic identification and location technology based on machine vision can be crop with the distribution situation of quick obtaining crop
Field machineryization management reference is provided, help to reduce the working strength of labourer, improve operating efficiency and precision.Crop
Automatic identification and positioning can generally be realized by gathering the Two-dimensional Color Image or three dimensional local information of crop.Two-dimensional color figure
As being obtained using color camera, the colouring information comprising crop, using flexible, use cost is relatively low；Three-dimensional location data needs
Obtained by depth camera, stereoscopic camera or laser sensor, the cloud data of crop can be generated, cost is higher, calculate data
Amount is big.Thus crop identification and positioning based on coloured image are always the focus of scientific research.
Crop identification and localization method based on coloured image are the image informations that crop is obtained using color camera, are passed through
Image is analyzed and processed, crop is extracted and positions its central point.The green information of crop is normally applied by crop from complexity
Background in split, extract profile and the UNICOM region of crop, the barycenter for then calculating UNICOM region obtains crop
Central point.But this method is when detecting crop in irregular shape, easily there is deviation in the positioning of crop central point.
Prior art determines crop row to be measured by the statistics with histogram of pixel column first to the target crop extracted,
Then the statistics with histogram of pixel column is carried out to crop row to be measured, the central point of crop is determined, this method can overcome crop
The influence in irregular shape caused to positioning, but when crop leaf intersects, the failure of crop location of the core can be caused.
When crossing instances occurs in blade, skeletonizing processing generally is carried out to crop map picture.In the skeleton of image, the terminal position of blade
Distal point occurs, the intersection and crop center position of blade can have distal point and intersection in crosspoint, retrieval skeleton
Point, is classified and logic judgment to crosspoint, so as to realize the positioning to crop central point, but this method amount of calculation compared with
Greatly, and accuracy rate is relatively low.
The content of the invention
The present invention is overcomes above mentioned problem or solves the above problems that there is provided under a kind of blade crossing condition at least in part
Crop location of the core method and system.
According to an aspect of the present invention, a kind of crop location of the core method under blade crossing condition is proposed, including：
Step 1, the original-gray image based on target crop, obtains the gray level image and bianry image of target crop；
Step 2, gray level image and bianry image based on the target crop, obtain the center point coordinate of target crop.
Further, the step 1 further comprises：
S11, the original-gray image based on target crop obtains the binary map of the target crop original-gray image
Picture；
S12, carries out morphology denoising to the bianry image of the target crop original-gray image, determines the mesh
It is denoted as the image region of interest of thing；
S13, the image region of interest based on the target crop obtains the binary map of the target crop image region of interest
Picture.
Further, the step 2 further comprises：
S21, by the original-gray image of the target crop and the bianry image of the image region of interest of the target crop
Fusion, obtains the gray level image of the image region of interest of target crop；
S22, obtains the minimum point of the gray level image of the image region of interest of the target crop；Obtain the target crop
Image region of interest gray level image in surrounding pixel point drop be more than threshold value minimum point；
The minimum point that S23, the gray level image of the image region of interest based on the target crop and the S22 are obtained, profit
With watershed algorithm, the center point coordinate of target crop is obtained.
Further, also include before the step 1：
The initial pictures of target crop are subjected to gray processing processing, the gray processing processing comprises the following steps,
Igray(i, j)=G (i, j) * 1.262-R (i, j) * 0.884-B (i, j) * 0.311,
Wherein i, j be pixel ranks coordinate, G (i, j), R (i, j) and B (i, j) be respectively image (i, j) place pixel G,
The gray value of R, B color component, Igray (i, j) is the gray value of converted images (i, j) place pixel.
Further, the S12 further comprises：
Original-gray image based on target crop, obtains turn of the bianry image of the target crop original-gray image
Threshold value is changed to try to achieve using maximum variance between clusters.
Further, the S12 further comprises：
Operation is opened using morphology to remove to weeds noise in the bianry image of the target crop original-gray image
Interference；
To after denoising the bianry image of the target crop original-gray image pixel value carry out floor projection, obtain with
Pixel column coordinate is the drop shadow curve of abscissa；Demarcated with intermediate pixel behavior, drop shadow curve is divided into two parts, find every
Region is the image region of interest of the target crop between the corresponding pixel column coordinate in curve minimum position, two pixel columns.
Further, the S22 further comprises：
Minimum point and maximum point in the gray level image for the image region of interest for calculating the target crop in eight neighborhood,
And the average value of minimum point and maximum point is calculated respectively, the difference of the two, as threshold value, retains and surrounding pixel point drop
More than the minimum point of threshold value, final local minimum is obtained.
Further, the S23 further comprises：
The minimum point obtained using the S22 carries out prospect to the gray level image of the image region of interest of the target crop
Mark；It is input picture to the gray level image after mark using watershed algorithm, obtains the central area of target crop；
Central area based on target crop, is added to the x coordinate of pixel, y-coordinate in central area sums respectively, and
Count the number of pixel in central area, x coordinate and, y-coordinate and with the ratio of pixel number be final crop
Heart point coordinates.
According to a further aspect of the invention there is provided crop location of the core system under a kind of blade crossing condition, including：
Acquisition module, for the original-gray image based on target crop, obtains the gray level image and two-value of target crop
Image；
Locating module, for gray level image and bianry image based on the target crop, obtains the center of target crop
Point coordinates.
According to another aspect of the invention, there is provided a kind of non-transient computer readable storage medium storing program for executing, it is characterised in that described non-
Transitory computer readable storage medium stores computer instruction, and it is any as described above that the computer instruction performs the computer
Described method.
The application proposes crop location of the core method and system under a kind of blade crossing condition, scheme tool of the present invention
Have the advantages that：The interference of crop cross vanes can be effectively excluded, the accuracy and speed of crop location of the core is improved.
Brief description of the drawings
Fig. 1 is to be shown according to the overall flow of crop location of the core method under a kind of blade crossing condition of the embodiment of the present invention
It is intended to；
Fig. 2 is to be illustrated according to the flow of crop location of the core method under a kind of blade crossing condition of the embodiment of the present invention
Figure；
Fig. 3 is according to the target crop of crop location of the core method under a kind of blade crossing condition of the embodiment of the present invention
Original-gray image schematic diagram；
Fig. 4 is according to the target crop of crop location of the core method under a kind of blade crossing condition of the embodiment of the present invention
Original bianry image schematic diagram；
Fig. 5 is that the target according to crop location of the core method under a kind of blade crossing condition of the embodiment of the present invention is made
The bianry image floor projection schematic diagram of thing original-gray image；
Fig. 6 is that the target according to corn location of the core method under a kind of blade crossing condition of the embodiment of the present invention is beautiful
Rice image region of interest schematic diagram；
Fig. 7 is that the target according to corn location of the core method under a kind of blade crossing condition of the embodiment of the present invention is beautiful
The original-gray image schematic diagram of rice；
Fig. 8 is that the target according to corn location of the core method under a kind of blade crossing condition of the embodiment of the present invention is beautiful
The bianry image schematic diagram of rice.
Fig. 9 is that the target according to corn location of the core method under a kind of blade crossing condition of the embodiment of the present invention is beautiful
The minimum area schematic of the original-gray image of rice；
Figure 10 is according to utilizing a point water in corn location of the core method under a kind of blade crossing condition of the embodiment of the present invention
The crop central area schematic diagram that ridge algorithm dividing processing is obtained；
Figure 11 is according to utilizing a point water in corn location of the core method under a kind of blade crossing condition of the embodiment of the present invention
The corn center point coordinate schematic diagram that ridge algorithm dividing processing is obtained；
Figure 12 is the general frame according to corn location of the core system under a kind of blade crossing condition of the embodiment of the present invention
Schematic diagram；
Figure 13 is the knot according to the equipment of corn location of the core method under a kind of blade crossing condition of the embodiment of the present invention
Structure block schematic illustration.
Embodiment
With reference to the accompanying drawings and examples, the embodiment to the present invention is described in further detail.Implement below
Example is used to illustrate the present invention, but is not limited to the scope of the present invention.
In such as Fig. 1, a specific embodiment of the invention, a kind of crop location of the core method under blade crossing condition is shown
Overall flow schematic diagram.Generally, including：Step 1, the original-gray image based on target crop, obtains the ash of target crop
Spend image and bianry image；Step 2, gray level image and bianry image based on the target crop, are obtained in target crop
Heart point coordinates.
In another specific embodiment of the invention, crop location of the core method, described under a kind of blade crossing condition
Step 1 further comprises：S11, the original-gray image based on target crop obtains the target crop original-gray image
Bianry image；S12, carries out morphology denoising, it is determined that described to the bianry image of the target crop original-gray image
The image region of interest of target crop；S13, the image region of interest based on the target crop obtains the target crop image emerging
The bianry image in interesting area.
In another specific embodiment of the invention, crop location of the core method, described under a kind of blade crossing condition
Step 2 further comprises：
S21, by the original-gray image of the target crop and the bianry image of the image region of interest of the target crop
Fusion, obtains the gray level image of the image region of interest of target crop；
S22, obtains the minimum point of the gray level image of the image region of interest of the target crop；Obtain the target crop
Image region of interest gray level image in surrounding pixel point drop be more than threshold value minimum point；
The minimum point that S23, the gray level image of the image region of interest based on the target crop and the S22 are obtained, profit
With watershed algorithm, the center point coordinate of target crop is obtained.
In another specific embodiment of the invention, crop location of the core method, described under a kind of blade crossing condition
Also include before step 1：
The initial pictures of target crop are subjected to gray processing processing, the gray processing processing comprises the following steps,
Igray(i, j)=G (i, j) * 1.262-R (i, j) * 0.884-B (i, j) * 0.311,
Wherein i, j be pixel ranks coordinate, G (i, j), R (i, j) and B (i, j) be respectively image (i, j) place pixel G,
The gray value of R, B color component, Igray (i, j) is the gray value of converted images (i, j) place pixel.
In another specific embodiment of the invention, crop location of the core method, described under a kind of blade crossing condition
S12 further comprises：
Operation is opened using morphology to remove to weeds noise in the bianry image of the target crop original-gray image
Interference；
To after denoising the bianry image of the target crop original-gray image pixel value carry out floor projection, obtain with
Pixel column coordinate is the drop shadow curve of abscissa；Demarcated with intermediate pixel behavior, drop shadow curve is divided into two parts, find every
Region is the image region of interest of the target crop between the corresponding pixel column coordinate in curve minimum position, two pixel columns.
In another specific embodiment of the invention, crop location of the core method, described under a kind of blade crossing condition
S22 further comprises：
Minimum point and maximum point in the gray level image for the image region of interest for calculating the target crop in eight neighborhood,
And the average value of minimum point and maximum point is calculated respectively, the difference of the two, as threshold value, retains and surrounding pixel point drop
More than the minimum point of threshold value, final local minimum is obtained.
In another specific embodiment of the invention, crop location of the core method, described under a kind of blade crossing condition
S23 further comprises：
The minimum point obtained using the S22 carries out prospect to the gray level image of the image region of interest of the target crop
Mark；It is input picture to the gray level image after mark using watershed algorithm, obtains the central area of target crop；
Central area based on target crop, is added to the x coordinate of pixel, y-coordinate in central area sums respectively, and
Count the number of pixel in central area, x coordinate and, y-coordinate and with the ratio of pixel number be final crop
Heart point coordinates.
The schematic flow sheet of crop location of the core method under such as Fig. 2, a kind of blade crossing condition of the embodiment of the present invention.This
Specific embodiment provides a kind of crop location of the core method under blade crossing instances.This method takes into full account weeds, blade
The influences of the factor to crop location of the core such as intersection, improve speed and the degree of accuracy of crop location of the core.Methods described
Specifically include following steps.
The height and angle of camera are installed in adjustment, camera is vertically shot crop row, it is ensured that made in the image of collection
Thing row is approximately parallel to horizontal direction, and crop to be measured is located at the centre position of image, and crop row where it is referred to as specific crop
OK.
Image is being changed as follows：
Igray(i, j)=G (i, j) * 1.262-R (i, j) * 0.884-B (i, j) * 0.311,
Wherein i, j be pixel ranks coordinate, G (i, j), R (i, j) and B (i, j) be respectively image (i, j) place pixel G,
The gray value of R, B color component, Igray (i, j) is the gray value of converted images (i, j) place pixel.
Described bianry image, white pixel point (gray value is 1) is crop, and black pixel point (gray value is 0) is the back of the body
Scape.Morphology opening operation is carried out to bianry image with square structure element, the small white area of area in bianry image is removed
Domain noise.
The bianry image obtained according to denoising determines region of interest as follows：To the pixel grey scale of bianry image
Value carries out floor projection, obtains the drop shadow curve using pixel column coordinate as abscissa, will by boundary of intermediate pixel rows Midrow
Drop shadow curve is divided into two parts, and every curve has minimum value min1, min2, and each minimum value may correspond to one or many
Individual pixel column coordinate, nearest recording distance intermediate pixel rows Midrow pixel column coordinate is Rowmin1, Rowmin2, it is determined that
Region between Rowmin1 and Rowmin2 is region of interest.
The area of each connected region in bianry image region of interest is calculated, the maximum region of Retention area is obtained comprising to be measured
The bianry image of crop.
Bianry image and gray level image comprising crop to be measured are merged as follows, new gray-scale map is extracted
As Inew：It is ash that detection, which includes the gray value at the white pixel point coordinates (i, j) of crop bianry image to be measured, white pixel point,
The gray value spent at corresponding gray value Igray (i, j) in image, black pixel point is set to 0.
Crop central area is newborn blade, in gray level image Inew, and the gray value in the region is higher than maturation around
Blade, the drop of grey scale pixel value is larger, can be determined by detecting the minimum of gray scale in pixel eight neighborhood in gray level image
The central area of crop.But generally there is substantial amounts of local minizing point in gray level image, easily cause error detection.Using such as
Lower formula is extended minimum computing to it, and the minimum for being less than threshold value h in image with neighborhood territory pixel gray value drop is clicked through
Horizontal blanking is handled, and obtains local minimum：
BW1=EM (Inew, h),
Wherein, BW1 represents to extend the gray level image that minimum computing is obtained, and its minimum to image is marked；EM
Represent the minimum computing of extension；H represents drop threshold value.Drop threshold value is flat by calculating image maximum point average value and minimum point
The difference of average is obtained.
Morphology is carried out to image using equation below and forces minimum computing, to mark image minimum, eliminates and specifies area
Overseas every other minimum：
BW2=Imposemin (Inew, BW1),
Wherein, BW2 represents the gray level image after mark, and Imposemin represents that morphology forces minimum computing.
Image BW2 using mark carries out the center that segmentation obtains crop to image as input picture using watershed algorithm
Region.
The center-of-mass coordinate of crop central area is calculated as follows, positions crop central point.Work first to obtaining
Thing central area is extracted, and obtains region centered on the bianry image of central area, white pixel point (gray value is 1), black
Colour vegetarian refreshments (gray value is 0) is background.Scan statistics are carried out to the white pixel point of central area bianry image, center is obtained
The number N of area pixel point, and the pixel column coordinate x addition summations of all white pixel points are obtained into X, pixel column coordinate y phases
Plus summation obtains Y, the center-of-mass coordinate (Xcenter, Ycenter) for obtaining crop central area is calculated according to following equation,
Wherein, ceil represents floor operation, then in original image crop center point coordinate for (Xcenter+Rowmin1,
Ycenter)。
There is provided a kind of crop location of the core method under blade crossing condition for still another embodiment of the present invention.With corn
Exemplified by image, under field conditions (factors), the quick positioning to corn central point is realized.
The present embodiment acquired original to image in middle row crop be approximately horizontal direction, the row crop for it is specific make
Thing row, corn to be measured is located in the middle part of specific crop row.
Fig. 3 is the original-gray image schematic diagram of the target corn of the embodiment of the present invention.Gray scale is carried out to the image of collection
Conversion, it is 138 to calculate gray threshold using maximum variance between clusters, is bianry image by greyscale image transitions, as shown in figure 4,
White pixel point (gray value is 1) is plant (corn or weeds), and black pixel point (gray value is 0) is background.
Fig. 5 target corns described in corn location of the core method under a kind of blade crossing condition of the embodiment of the present invention are former
The bianry image floor projection schematic diagram of beginning gray level image.Fig. 6 is according to beautiful under a kind of blade crossing condition of the embodiment of the present invention
Target corn map is as region of interest schematic diagram described in rice location of the core method.First, it is 4 that pixel size is selected in the present embodiment
The square structure element of pixel carries out opening operation to the bianry image, eliminates the small white portion of bianry image area；
Then, floor projection is carried out to the bianry image after denoising, obtains drop shadow curve；It will be thrown by boundary of intermediate pixel rows Midrow
Shadow curve is divided into Midrow=360 in two parts, the present embodiment；Determine minimum value min1, min2 and its correspondingly of every curve
Pixel column coordinate, nearest selected distance intermediate pixel rows Midrow pixel column coordinate is Rowmin1, Rowmin2, this implementation
Example in min1=0, min2=0, corresponding pixel column coordinate be Rowmin1=299, Rowmin2=631, then Rowmin1 and
Region between Rowmin2 is defined as the region of interest of image.
Fig. 7 is that the target according to corn location of the core method under a kind of blade crossing condition of the embodiment of the present invention is beautiful
The original-gray image schematic diagram of rice.Fig. 8 is according to corn location of the core under a kind of blade crossing condition of the embodiment of the present invention
The bianry image schematic diagram of target corn described in method.The area in each region in region of interest is counted, corn to be measured is located at interest
In area, due to intersecting with other blades, so its region area is maximum.The maximum region of Retention area, removes zero
Dissipate the interference of blade.Corn region to be measured area is 23048 in the present embodiment.Detection includes corn bianry image to be measured
White pixel point, its coordinate is (i, j), and the gray value of the white pixel point in new gray level image Inew is the grey chromatic graphs of Fig. 3
As the value at (i, j) place.Gray value of the black pixel point of Maize Regional to be measured in new gray level image Inew is 0.
Fig. 9 is that the target according to corn location of the core method under a kind of blade crossing condition of the embodiment of the present invention is beautiful
The minimum area schematic of the original-gray image of rice；Minimum computing is extended for the gray level image Inew to embodiment to obtain
Gray value near the BW1 obtained, BW1 corn central point is higher than peripheral image vegetarian refreshments.Minimum point is averaged in the present embodiment
It is worth for 147.09, the average value of maximum point is 150.47, and it is 3.38 to set drop threshold value h, eliminates the minimum of tiny area.
Figure 10 is according to utilizing a point water in corn location of the core method under a kind of blade crossing condition of the embodiment of the present invention
The crop central area schematic diagram that ridge algorithm dividing processing is obtained.Applied morphology forces the gray scale of minimum computing mark embodiment
Image Inew, to mark image as input picture, carries out dividing processing to image using watershed algorithm, obtains in embodiment
Heart district domain, as shown in Figure 10.
Figure 11 is according to utilizing a point water in corn location of the core method under a kind of blade crossing condition of the embodiment of the present invention
The corn center point coordinate schematic diagram that ridge algorithm dividing processing is obtained.
The corn central area shape of Figure 10 acquisitions is simultaneously irregular, and the barycenter for calculating the region is used as the central point of corn.
Statistics is scanned to the pixel of central area, center-of-mass coordinate is calculated according to formula (4).In the present embodiment, central area
Pixel N=557, the x coordinate sum X=89017 of pixel, y-coordinate sum Y=152204, acquisition center-of-mass coordinate (160,
270), then the center point coordinate of corn is (459,270), as a result as shown in Figure 11 cross.
Such as Figure 12, in another specific embodiment of the invention, show that crop central point is determined under a kind of blade crossing condition
Position system overall framework schematic diagram.On the whole, including：Acquisition module A1, for the original-gray image based on target crop, is obtained
Take the gray level image and bianry image of target crop；Locating module A2, for the gray level image based on the target crop and two
It is worth image, obtains the center point coordinate of target crop.
In another specific embodiment of the invention, crop location of the core system, described under a kind of blade crossing condition
Acquisition module is additionally operable to：Original-gray image based on target crop, obtains the two-value of the target crop original-gray image
Image；Morphology denoising is carried out to the bianry image of the target crop original-gray image, the target crop is determined
Image region of interest；Image region of interest based on the target crop, obtains the binary map of the target crop image region of interest
Picture.
In another specific embodiment of the invention, crop location of the core system, described under a kind of blade crossing condition
Locating module is additionally operable to：
S21, by the original-gray image of the target crop and the bianry image of the image region of interest of the target crop
Fusion, obtains the gray level image of the image region of interest of target crop；
S22, obtains the minimum point of the gray level image of the image region of interest of the target crop；Obtain the target crop
Image region of interest gray level image in surrounding pixel point drop be more than threshold value minimum point；
The minimum point that S23, the gray level image of the image region of interest based on the target crop and the S22 are obtained, profit
With watershed algorithm, the center point coordinate of target crop is obtained.
In another specific embodiment of the invention, crop location of the core system, described under a kind of blade crossing condition
Acquisition module, is additionally operable to the initial pictures of target crop carrying out gray processing processing, the gray processing processing comprises the following steps,
Igray(i, j)=G (i, j) * 1.262-R (i, j) * 0.884-B (i, j) * 0.311,
Wherein i, j be pixel ranks coordinate, G (i, j), R (i, j) and B (i, j) be respectively image (i, j) place pixel G,
The gray value of R, B color component, Igray (i, j) is the gray value of converted images (i, j) place pixel.
In another specific embodiment of the invention, crop location of the core system, described under a kind of blade crossing condition
Acquisition module, is additionally operable to the original-gray image based on target crop, obtains the two-value of the target crop original-gray image
The switching threshold of image is tried to achieve using maximum variance between clusters.
In another specific embodiment of the invention, crop location of the core system, described under a kind of blade crossing condition
Acquisition module, is additionally operable to：
Operation is opened using morphology to remove to weeds noise in the bianry image of the target crop original-gray image
Interference；
To after denoising the bianry image of the target crop original-gray image pixel value carry out floor projection, obtain with
Pixel column coordinate is the drop shadow curve of abscissa；Demarcated with intermediate pixel behavior, drop shadow curve is divided into two parts, find every
Region is the image region of interest of the target crop between the corresponding pixel column coordinate in curve minimum position, two pixel columns.
In another specific embodiment of the invention, crop location of the core system, described under a kind of blade crossing condition
Locating module, is additionally operable to：
Minimum point and maximum point in the gray level image for the image region of interest for calculating the target crop in eight neighborhood,
And the average value of minimum point and maximum point is calculated respectively, the difference of the two, as threshold value, retains and surrounding pixel point drop
More than the minimum point of threshold value, final local minimum is obtained.
In another specific embodiment of the invention, crop location of the core system, described under a kind of blade crossing condition
Locating module, is additionally operable to：
The minimum point obtained using the S22 carries out prospect to the gray level image of the image region of interest of the target crop
Mark；It is input picture to the gray level image after mark using watershed algorithm, obtains the central area of target crop；
Central area based on target crop, is added to the x coordinate of pixel, y-coordinate in central area sums respectively, and
Count the number of pixel in central area, x coordinate and, y-coordinate and with the ratio of pixel number be final crop
Heart point coordinates.
Figure 13 shows the structural frames of the equipment of crop location of the core method under the blade crossing condition of the embodiment of the present application
Figure.
The equipment of crop location of the core method under reference picture 13, the blade crossing condition, including：Processor
(processor) 1301, memory (memory) 1302 and bus 1303；
Wherein,
The processor 1301 and memory 1302 complete mutual communication by the bus 1303；
The processor 1301 is used to call the programmed instruction in the memory 1302, is implemented with performing above-mentioned each method
The method that is there is provided of example, for example including：Step 1, the original-gray image based on target crop, obtains the gray-scale map of target crop
Picture and bianry image；Step 2, gray level image and bianry image based on the target crop, obtain the central point of target crop
Coordinate.
The present embodiment discloses a kind of computer program product, and the computer program product includes being stored in non-transient calculating
Computer program on machine readable storage medium storing program for executing, the computer program includes programmed instruction, when described program instruction is calculated
Machine perform when, computer is able to carry out the method that above-mentioned each method embodiment is provided, for example including：Step 1, made based on target
The original-gray image of thing, obtains the gray level image and bianry image of target crop；Step 2, the ash based on the target crop
Image and bianry image are spent, the center point coordinate of target crop is obtained.
The present embodiment provides a kind of non-transient computer readable storage medium storing program for executing, the non-transient computer readable storage medium storing program for executing
Computer instruction is stored, the computer instruction makes the computer perform the method that above-mentioned each method embodiment is provided, example
Such as include：Step 1, the original-gray image based on target crop, obtains the gray level image and bianry image of target crop；Step
2, gray level image and bianry image based on the target crop obtain the center point coordinate of target crop.
One of ordinary skill in the art will appreciate that：Realizing all or part of step of above method embodiment can pass through
Programmed instruction related hardware is completed, and foregoing program can be stored in a computer read/write memory medium, the program
Upon execution, the step of including above method embodiment is performed；And foregoing storage medium includes：ROM, RAM, magnetic disc or light
Disk etc. is various can be with the medium of store program codes.
The embodiment such as equipment of crop location of the core method is only signal under blade crossing condition described above
Property, wherein the unit illustrated as separating component can be or may not be physically separate, it is used as unit
The part of display can be or may not be physical location, you can with positioned at a place, or can also be distributed to many
On individual NE.Some or all of module therein can be selected to realize this embodiment scheme according to the actual needs
Purpose.Those of ordinary skill in the art are not in the case where paying performing creative labour, you can to understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
Realized by the mode of software plus required general hardware platform, naturally it is also possible to pass through hardware.Understood based on such, on
The part that technical scheme substantially in other words contributes to prior art is stated to embody in the form of software product, should
Computer software product can be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disc, CD, including some fingers
Order is to cause a computer equipment (can be personal computer, server, or network equipment etc.) to perform each implementation
Method described in some parts of example or embodiment.
Finally, the present processes are only preferably embodiment, are not intended to limit the scope of the present invention.It is all
Within the spirit and principles in the present invention, any modification, equivalent substitution and improvements made etc. should be included in the protection of the present invention
Within the scope of.
Claims (10)
1. a kind of crop location of the core method under blade crossing condition, it is characterised in that including：
Step 1, the original-gray image based on target crop, obtains the gray level image and bianry image of target crop；
Step 2, gray level image and bianry image based on the target crop, obtain the center point coordinate of target crop.
2. the method as described in claim 1, it is characterised in that the step 1 further comprises：
S11, the original-gray image based on target crop obtains the bianry image of the target crop original-gray image；
S12, morphology denoising is carried out to the bianry image of the target crop original-gray image, determines that the target is made
The image region of interest of thing；
S13, the image region of interest based on the target crop obtains the bianry image of the target crop image region of interest.
3. method as claimed in claim 2, it is characterised in that the step 2 further comprises：
S21, the original-gray image of the target crop is merged with the bianry image of the image region of interest of the target crop,
Obtain the gray level image of the image region of interest of target crop；
S22, obtains the minimum point of the gray level image of the image region of interest of the target crop；Obtain the figure of the target crop
It is more than the minimum point of threshold value in the gray level image of picture region of interest with surrounding pixel point drop；
S23, the minimum point that the gray level image of the image region of interest based on the target crop and the S22 are obtained, using point
Water ridge algorithm, obtains the center point coordinate of target crop.
4. the method as described in claim 1, it is characterised in that also include before the step 1：
The initial pictures of target crop are subjected to gray processing processing, the gray processing processing comprises the following steps,
Igray(i, j)=G (i, j) * 1.262-R (i, j) * 0.884-B (i, j) * 0.311,
Wherein i, j are the ranks coordinate of pixel, and G (i, j), R (i, j) and B (i, j) are respectively image (i, j) place pixel G, R, B face
The gray value of colouring component, Igray (i, j) is the gray value of converted images (i, j) place pixel.
5. method as claimed in claim 2, it is characterised in that the S12 further comprises：
Original-gray image based on target crop, obtains the conversion threshold of the bianry image of the target crop original-gray image
Value is tried to achieve using maximum variance between clusters.
6. method as claimed in claim 2, it is characterised in that the S12 further comprises：
Interference of the operation removal to weeds noise in the bianry image of the target crop original-gray image is opened using morphology；
Floor projection is carried out to the pixel value of the bianry image of the target crop original-gray image after denoising, obtained with pixel
Row coordinate is the drop shadow curve of abscissa；Demarcated with intermediate pixel behavior, drop shadow curve is divided into two parts, find every curve
Region is the image region of interest of the target crop between the corresponding pixel column coordinate in minimum value position, two pixel columns.
7. method as claimed in claim 4, it is characterised in that the S22 further comprises：
Minimum point and maximum point in the gray level image for the image region of interest for calculating the target crop in eight neighborhood, and point
Not Ji Suan minimum point and maximum point average value, the difference of the two, as threshold value, reservation is more than with surrounding pixel point drop
The minimum point of threshold value, obtains final local minimum.
8. method as claimed in claim 7, it is characterised in that the S23 further comprises：
The minimum point obtained using the S22 carries out prospect mark to the gray level image of the image region of interest of the target crop
Note；It is input picture to the gray level image after mark using watershed algorithm, obtains the central area of target crop；
Central area based on target crop, is added to the x coordinate of pixel, y-coordinate in central area sums respectively, and count
The number of pixel in central area, x coordinate and, y-coordinate and be final crop central point with the ratio of pixel number
Coordinate.
9. crop location of the core system under a kind of blade crossing condition, it is characterised in that including：
Acquisition module, for the original-gray image based on target crop, obtains the gray level image and bianry image of target crop；
Locating module, for gray level image and bianry image based on the target crop, the central point for obtaining target crop is sat
Mark.
10. a kind of non-transient computer readable storage medium storing program for executing, it is characterised in that the non-transient computer readable storage medium storing program for executing is deposited
Computer instruction is stored up, the computer instruction makes the computer perform the method as described in claim 1 to 8 is any.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710415434.1A CN107220647B (en) | 2017-06-05 | 2017-06-05 | Crop center point positioning method and system under blade crossing condition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710415434.1A CN107220647B (en) | 2017-06-05 | 2017-06-05 | Crop center point positioning method and system under blade crossing condition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107220647A true CN107220647A (en) | 2017-09-29 |
| CN107220647B CN107220647B (en) | 2020-03-31 |
Family
ID=59947183
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710415434.1A Active CN107220647B (en) | 2017-06-05 | 2017-06-05 | Crop center point positioning method and system under blade crossing condition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107220647B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111627059A (en) * | 2020-05-28 | 2020-09-04 | 桂林市思奇通信设备有限公司 | Method for positioning center point position of cotton blade |
| CN111738159A (en) * | 2020-06-23 | 2020-10-02 | 桂林市思奇通信设备有限公司 | Cotton terminal bud positioning method based on vector calibration |
| CN111753688A (en) * | 2020-06-12 | 2020-10-09 | 广州极飞科技有限公司 | Planting line center line determining method and device, electronic equipment and storage medium |
| CN112541383A (en) * | 2020-06-12 | 2021-03-23 | 广州极飞科技有限公司 | Method and device for identifying weed area |
| CN113298768A (en) * | 2021-05-20 | 2021-08-24 | 山东大学 | Cotton detection, segmentation and counting method and system |
| CN113421301A (en) * | 2021-07-08 | 2021-09-21 | 浙江大学 | Method and system for positioning central area of field crop |
| CN113469112A (en) * | 2021-07-19 | 2021-10-01 | 三门峡市扶贫开发办公室 | Crop growth condition image identification method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103488991A (en) * | 2013-09-30 | 2014-01-01 | 中国农业大学 | Method for extracting leading line of farmland weeding machine |
| CN104392460A (en) * | 2014-12-12 | 2015-03-04 | 山东大学 | Adherent white blood cell segmentation method based on nucleus-marked watershed transformation |
| CN104484877A (en) * | 2014-12-12 | 2015-04-01 | 山东大学 | AML cell segmentation method based on Meanshift cluster and morphological operations |
-
2017
- 2017-06-05 CN CN201710415434.1A patent/CN107220647B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103488991A (en) * | 2013-09-30 | 2014-01-01 | 中国农业大学 | Method for extracting leading line of farmland weeding machine |
| CN104392460A (en) * | 2014-12-12 | 2015-03-04 | 山东大学 | Adherent white blood cell segmentation method based on nucleus-marked watershed transformation |
| CN104484877A (en) * | 2014-12-12 | 2015-04-01 | 山东大学 | AML cell segmentation method based on Meanshift cluster and morphological operations |
Non-Patent Citations (2)
| Title |
|---|
| 张春龙: "自然环境下农业机器人作业目标信息获取与视觉伺服策略研究", 《中国博士学位论文全文数据库-信息科技辑》 * |
| 高静: "基于形态学分水岭算法的细胞图像分割", 《中国优秀硕士学位论文全文数据库-信息科技辑》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111627059A (en) * | 2020-05-28 | 2020-09-04 | 桂林市思奇通信设备有限公司 | Method for positioning center point position of cotton blade |
| CN111627059B (en) * | 2020-05-28 | 2023-05-30 | 桂林市思奇通信设备有限公司 | Cotton leaf center point positioning method |
| CN111753688A (en) * | 2020-06-12 | 2020-10-09 | 广州极飞科技有限公司 | Planting line center line determining method and device, electronic equipment and storage medium |
| CN112541383A (en) * | 2020-06-12 | 2021-03-23 | 广州极飞科技有限公司 | Method and device for identifying weed area |
| CN112541383B (en) * | 2020-06-12 | 2021-12-28 | 广州极飞科技股份有限公司 | Method and device for identifying weed area |
| CN111753688B (en) * | 2020-06-12 | 2022-03-18 | 广州极飞科技股份有限公司 | Planting line center line determining method and device, electronic equipment and storage medium |
| CN111738159A (en) * | 2020-06-23 | 2020-10-02 | 桂林市思奇通信设备有限公司 | Cotton terminal bud positioning method based on vector calibration |
| CN113298768A (en) * | 2021-05-20 | 2021-08-24 | 山东大学 | Cotton detection, segmentation and counting method and system |
| CN113298768B (en) * | 2021-05-20 | 2022-11-08 | 山东大学 | Cotton detection, segmentation and counting method and system |
| CN113421301A (en) * | 2021-07-08 | 2021-09-21 | 浙江大学 | Method and system for positioning central area of field crop |
| CN113469112A (en) * | 2021-07-19 | 2021-10-01 | 三门峡市扶贫开发办公室 | Crop growth condition image identification method and system |
| CN113469112B (en) * | 2021-07-19 | 2022-06-21 | 三门峡市乡村振兴局 | Crop growth condition image identification method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107220647B (en) | 2020-03-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107220647A (en) | Crop location of the core method and system under a kind of blade crossing condition | |
| CN112581629B (en) | Augmented reality display method, device, electronic equipment and storage medium | |
| CN109165538B (en) | Bar code detection method and device based on deep neural network | |
| CN109146948B (en) | Crop growth phenotype parameter quantification and yield correlation analysis method based on vision | |
| CN109325504A (en) | A kind of underwater sea cucumber recognition methods and system | |
| Li et al. | An overlapping-free leaf segmentation method for plant point clouds | |
| CN107633516A (en) | A kind of method and apparatus for identifying surface deformation class disease | |
| CN109711268B (en) | Face image screening method and device | |
| CN110400322A (en) | Fruit point cloud segmentation method based on color and three-dimensional geometric information | |
| CN110263794B (en) | Training method of target recognition model based on data enhancement | |
| CN108961316B (en) | Image processing method and device and server | |
| CN109685806A (en) | Image significance detection method and device | |
| CN116523898A (en) | Tobacco phenotype character extraction method based on three-dimensional point cloud | |
| CN109657540A (en) | Withered tree localization method and system | |
| CN116704333B (en) | Single tree detection method based on laser point cloud data | |
| CN111738310B (en) | Material classification method, device, electronic equipment and storage medium | |
| CN117079125A (en) | Kiwi fruit pollination flower identification method based on improved YOLOv5 | |
| CN111783648A (en) | Method and device for extracting guardrail in road point cloud | |
| CN114743008B (en) | Single plant vegetation point cloud data segmentation method and device and computer equipment | |
| JP6546385B2 (en) | IMAGE PROCESSING APPARATUS, CONTROL METHOD THEREOF, AND PROGRAM | |
| CN115937466A (en) | Three-dimensional model generation method, system and storage medium integrating GIS | |
| CN115587943A (en) | Method and device for denoising point cloud data, electronic device and storage medium | |
| CN115294322A (en) | Underwater ship bottom suspicious target detection method and device, electronic equipment and readable medium | |
| CN110276260B (en) | Commodity detection method based on depth camera | |
| CN113435358A (en) | Sample generation method, device, equipment and program product for training model |
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 |