CN104794712B - Individual plant pear tree yield detecting system based on electronic recognition - Google Patents
Individual plant pear tree yield detecting system based on electronic recognition Download PDFInfo
- Publication number
- CN104794712B CN104794712B CN201510178864.7A CN201510178864A CN104794712B CN 104794712 B CN104794712 B CN 104794712B CN 201510178864 A CN201510178864 A CN 201510178864A CN 104794712 B CN104794712 B CN 104794712B
- Authority
- CN
- China
- Prior art keywords
- value
- pear tree
- image
- pixel
- unilateral
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 240000001987 Pyrus communis Species 0.000 title claims abstract description 138
- 235000014443 Pyrus communis Nutrition 0.000 claims abstract description 118
- 238000012545 processing Methods 0.000 claims abstract description 65
- 235000013399 edible fruits Nutrition 0.000 claims abstract description 48
- 241000220324 Pyrus Species 0.000 claims description 36
- 238000012546 transfer Methods 0.000 claims description 17
- 238000001914 filtration Methods 0.000 claims description 16
- 238000012360 testing method Methods 0.000 claims description 8
- 239000003623 enhancer Substances 0.000 claims description 6
- 230000002708 enhancing effect Effects 0.000 claims description 5
- 238000004519 manufacturing process Methods 0.000 claims description 4
- 239000000203 mixture Substances 0.000 claims description 4
- 238000003860 storage Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 239000003595 mist Substances 0.000 claims 1
- 238000000926 separation method Methods 0.000 claims 1
- 238000001514 detection method Methods 0.000 description 7
- 235000021017 pears Nutrition 0.000 description 7
- 238000005259 measurement Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000012010 growth Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000000034 method Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- FFRBMBIXVSCUFS-UHFFFAOYSA-N 2,4-dinitro-1-naphthol Chemical compound C1=CC=C2C(O)=C([N+]([O-])=O)C=C([N+]([O-])=O)C2=C1 FFRBMBIXVSCUFS-UHFFFAOYSA-N 0.000 description 1
- 206010011224 Cough Diseases 0.000 description 1
- 241000196324 Embryophyta Species 0.000 description 1
- 206010021703 Indifference Diseases 0.000 description 1
- 239000003513 alkali Substances 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000006408 female gonad development Effects 0.000 description 1
- 230000004720 fertilization Effects 0.000 description 1
- 230000005078 fruit development Effects 0.000 description 1
- 230000004345 fruit ripening Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000003306 harvesting Methods 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000002420 orchard Substances 0.000 description 1
- 230000008122 ovule development Effects 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 230000002786 root growth Effects 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 241000894007 species Species 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to a kind of individual plant pear tree yield detecting system based on electronic recognition, including CCD vision sensors, sharpening processor, unilateral yield identifier and embeded processor, the CCD vision sensors are used to carry out IMAQ to the side of individual plant pear tree to obtain unilateral pear tree image, the sharpening processor is used to carry out the unilateral pear tree image hazeization processing, haze one side pear tree image is removed to obtain, the unilateral yield identifier is used to go haze one side pear tree image to carry out image recognition to described, to obtain pear tree one side fruit number, the embeded processor is connected with the unilateral yield identifier, for determining whole yield of the individual plant pear tree based on pear tree one side fruit number.By the present invention, whole yield of individual plant pear tree can be also predicted exactly under haze weather.
Description
Technical field
The present invention relates to detection of electrons field, more particularly to a kind of individual plant pear tree production quantity detecting system based on electronic recognition
System.
Background technology
Pears (Pear), fruit title, rose family Pyrus L, perennial deciduous tree fruit tree, leaf is avette, Hua Duobai
Color, the colors of general pears show golden yellow or warm yellow for crust, and the inside pulp is then well-illuminated white, fresh and tender succulence, taste
Sweetness, core taste is slightly sour, cool sexuality.Pear tree harvests between 7~September during fruit maturation, can using fresh herb or section dry.With rock sugar together
Water is stewed, cough can be treated.Its species and kind are extremely more, and cultivated area is also more broad.
But if pear tree is excessively planted, it will cause the unbalanced supply-demand in region, the downward price adjustment amplitude of pears is excessive,
The income of peasant is have impact on the contrary.Therefore need to carry out pear tree yield estimation, in terms of the pear tree yield progress pear tree plantation of estimation
The modulation drawn, stablize the price of pears while ensureing that pear tree is supplied, safeguard the interests of peasant.
Pear tree yield detecting system of the prior art either by way of manual measurement or passes through image recognition
Mode is carried out, but the former excessively relies on manually, expends a large amount of human costs and time cost, and the latter uses single image, list
Individual estimation parameter is detected, and the yield detection technique indifference of all kinds pear tree, the degree of accuracy is not high, and can not be various
Effective detection is realized to pear tree under haze weather.
Therefore, it is necessary to which a kind of new pear tree yield detecting system, can substitute original manual measurement mode, detection is improved
Efficiency, meanwhile, influence of the haze weather to detection is overcome, so as to can accurately obtain every plant of pear tree in all weather
True production, important reference data is provided for the production schedule of orchard worker.
The content of the invention
In order to solve the above problems, the invention provides a kind of individual plant pear tree yield detecting system based on electronic recognition,
Direct picture collection is carried out to individual plant pear tree by high-definition camera, whole fruit numbers are estimated based on front fruit number, more
It is essential that determine influence factor of the haze to image always according to atmospheric attenuation model, and to being gathered under various haze weathers
Image carries out hazeization processing, has widened the application of detecting system.
According to an aspect of the present invention, there is provided a kind of individual plant pear tree yield detecting system based on electronic recognition, it is described
Before detecting system is arranged at individual plant pear tree, including CCD vision sensors, sharpening processor, unilateral yield identifier and insertion
Formula processor, the CCD vision sensors are used to carry out IMAQ to the side of individual plant pear tree to obtain unilateral pear tree image,
The sharpening processor is used to carry out the unilateral pear tree image hazeization processing, and haze one side pear tree figure is removed to obtain
Picture, the unilateral yield identifier are used to go haze one side pear tree image to carry out image recognition to described, to obtain pear tree one side
Fruit number, the embeded processor are connected with the unilateral yield identifier, for based on the pear tree one side fruit number
Amount determines whole yield of the individual plant pear tree.
More specifically, in the individual plant pear tree yield detecting system based on electronic recognition, in addition to：Power supply,
Including solar powered device, battery, switching switch and electric pressure converter, the switching switch and the solar energy electric supplier
Part and the battery connect respectively, according to battery dump energy decide whether to be switched to the solar powered device with by
The solar powered device power supply, the electric pressure converter and the switching switch connection, will be by switching switch input
5V voltage conversions be 3.3V voltages；Mobile hard disk, for prestoring Pear Fruit upper limit gray threshold, Pear Fruit lower limit
Gray threshold and estimation multiplying power, the Pear Fruit upper limit gray threshold and the Pear Fruit lower limit gray threshold are used for will figure
Pear Fruit as in separates with image background, and the estimation multiplying power is used to all produce based on pear tree one side yield estimation pear tree
Amount；Display device, it is connected with the embeded processor, for showing word corresponding with whole yield of the individual plant pear tree
Information；The CCD vision sensors are used to shoot the front of the individual plant pear tree, are schemed with obtaining the unilateral pear tree
Picture；The sharpening processor includes：Sub- device is stored, for prestoring sky upper limit gray threshold and sky lower limit gray scale
Threshold value, the sky upper limit gray threshold and the sky lower limit gray threshold are used to isolate the sky areas in image, also
For prestoring presetted pixel value threshold value, the presetted pixel value threshold value value is between 0 to 255；Haze Concentration Testing
Device, in air, for detecting the haze concentration of individual plant pear tree position in real time, and haze is determined according to haze concentration
Intensity is removed, the haze removes intensity value between 0 to 1；The sub- device of region division, connect the CCD vision sensors
To receive the unilateral pear tree image, gray processing processing is carried out to the unilateral pear tree image to obtain gray processing area image,
Also it is connected with storing sub- equipment, by gray value in the gray processing area image in the sky upper limit gray threshold and the day
Pixel between empty lower limit gray threshold identifies and forms gray processing sky sub-pattern, is partitioned into from the gray processing area image
The gray processing sky sub-pattern is being gone on patrol with obtaining the non-sky subgraph of gray processing based on the non-sky subgraph of the gray processing
Correspondence position in area image obtains the non-sky subgraph of colour corresponding with the non-sky subgraph of the gray processing；Black leads to
Road obtains sub- equipment, is connected with the sub- equipment of the region division to obtain the non-sky subgraph of the colour, for the colour
Each pixel in non-sky subgraph, calculate its R, the Color Channel pixel value of G, B tri-, in the non-sky subgraph of the colour
The R of all pixels, G, the color in the Color Channel pixel values of B tri- where the minimum Color Channel pixel value of one numerical value of extraction are led to
Road is as black channel；Overall air light value obtains sub- equipment, is connected with the sub- equipment of storage to obtain presetted pixel value threshold
Value, equipment sub- with the region division and the black channel obtain sub- equipment and are connected respectively to obtain the unilateral pear tree image
With the black channel, black channel pixel value in the unilateral pear tree image is more than or equal to the multiple of presetted pixel value threshold value
Pixel forms set of pixels to be tested, using the gray value of the pixel in the set of pixels to be tested with maximum gradation value as overall
Air light value；Atmospheric scattering light value obtains sub- equipment, equipment sub- with the region division and the sub- equipment of haze Concentration Testing
Connect respectively, to each pixel of the unilateral pear tree image, extract its R, minimum value is made in the Color Channel pixel value of G, B tri-
For target pixel value, Gaussian filter EPGF (the edge-preserving gaussian for keeping edge are used
Filter processing) is filtered to the target pixel value to obtain filtered target pixel value, target pixel value is subtracted into filtering
Target pixel value is filtered processing to obtain object pixel difference, using EPGF to obtain filtered target to object pixel difference
Pixel value difference, filtered target pixel value is subtracted into filtered target pixel value difference to obtain haze and removes a reference value, haze is removed
Intensity is multiplied by haze and removes a reference value to obtain haze removal threshold value, takes haze to remove the minimum value in threshold value and target pixel value
As comparison reference, atmospheric scattering light value of the maximum in comparison reference and 0 as each pixel is taken；Medium transmits
Rate obtains sub- equipment, obtains sub- equipment with the overall air light value and the atmospheric scattering light value obtains sub- equipment and connected respectively
Connect, the atmospheric scattering light value of each pixel divided by overall air light value removed into value to obtain, by 1 subtract it is described except value to obtain
The medium transfer rate of each pixel；Sharpening image obtains sub- equipment, equipment sub- with the region division, the overall air
Light value obtains sub- equipment and the medium transfer rate obtains sub- equipment and connected respectively, and the medium for 1 being subtracted each pixel transmits
Rate is multiplied by overall air light value to obtain product value to obtain the first difference, by first difference, and the unilateral pear tree is schemed
The pixel value of each pixel subtracts the product value to obtain the second difference as in, by second difference divided by each picture
The medium transfer rate of element is to obtain the sharpening pixel value of each pixel, the picture of each pixel in the unilateral pear tree image
Element value includes the R of each pixel in the unilateral pear tree image, the Color Channel pixel value of G, B tri-, correspondingly, acquisition it is each
The sharpening pixel value of individual pixel includes the R of each pixel, the Color Channel sharpening pixel value of G, B tri-, all pixels it is clear
Clearization pixel value composition removes haze one side pear tree image；The unilateral yield identifier respectively with the sharpening processor and institute
Mobile hard disk connection is stated, the unilateral yield identifier includes：Contrast enhancer device, it is connected with the sharpening processor
Haze one side pear tree image is removed to obtain, goes haze one side pear tree image to perform contrast enhancement processing to described, to be increased
Strong image；The sub- device of wavelet filtering, it is connected with the contrast enhancer device, the enhancing image is performed at wavelet filtering
Reason, to obtain filtering image；The sub- device of gray processing processing, is connected with the sub- device of the wavelet filtering, the filtering image is held
Row gray processing processing, to obtain gray level image；The sub- device of image recognition, sub- device and the movement are handled with the gray processing
Hard disk connects respectively, by gray value in the gray level image in the Pear Fruit upper limit gray threshold and the Pear Fruit
Pixel between lower limit gray threshold identifies and forms multiple Pear Fruit subgraphs, by the sum of multiple Pear Fruit subgraphs
As pear tree one side fruit number；The embeded processor connects respectively with the mobile hard disk, the unilateral yield identifier
Connect, calculate pear tree one side fruit number with estimating the product of multiplying power, whole yield using the product as the individual plant pear tree.
More specifically, in the individual plant pear tree yield detecting system based on electronic recognition：The embeded processor
The resources occupation rate of itself is calculated, when the resources occupation rate of itself is less than the first preset percentage, substitutes the unilateral yield
The operation of identifier.
More specifically, in the individual plant pear tree yield detecting system based on electronic recognition：The embeded processor
When the resources occupation rate of itself is more than the second preset percentage, terminate the replacement of the operation to the unilateral yield identifier.
More specifically, in the individual plant pear tree yield detecting system based on electronic recognition：Described first default percentage
Than being pre-stored in second preset percentage in the mobile hard disk, first preset percentage is less than described the
Two preset percentages.
More specifically, in the individual plant pear tree yield detecting system based on electronic recognition：By the embedded processing
Device and the unilateral yield identifier are integrated on one piece of surface-mounted integrated circuit.
Brief description of the drawings
Embodiment of the present invention is described below with reference to accompanying drawing, wherein：
Fig. 1 is the structure of the individual plant pear tree yield detecting system based on electronic recognition according to embodiment of the present invention
Block diagram.
Embodiment
Below with reference to accompanying drawings to the embodiment of the individual plant pear tree yield detecting system based on electronic recognition of the invention
It is described in detail.
Pear tree is stronger than apple to the adaptability of external environment.Cold-resistant, drought-enduring, waterlogging, Salt And Alkali Tolerance.Winter minimum temperature-
More than 25 degree of area, most kinds can safe overwinterings.Well developed root system, vertical root is deep up to more than 2-3m, horizontal branch distribution compared with
Extensively, about 2 times or so of hat width.Light happiness temperature, preferably selects that soil layer is deep, well-drained gentle slope mountain planting, especially with chiltern earth
Native mountain region is ideal.Dryness is strong, and layer is more apparent.As a result early, fruiting period length, some kinds 2-3 starts result, the best fruiting period
It can maintain more than 50 years.
Bloomed after a small number of kind floral leaves of pear tree while open or first lamina, after pollen fertilization, fruit germinates, holder
It is core to develop for pulp, ovary development, and Ovule Development is seed.During fruit development, early stage is mainly cell point
Split, tissue differentiation, stage is that cell expands and pulp maturation.Volume of fruits growth curve is into S types.Pears root growth has every year
Two summit of growths：When first time summit of growth appears in young sprout and stopped growing；Second of peak appears in the 9-10 months.Suitable
Under the conditions of, pears root system can grow in the anniversary, no rest period.
Identification of the prior art to pear tree yield is known using image mostly except the manual measurement mode of original backwardness
Other technology, but due to lacking haze eliminating equipment, cause under various haze weathers, detection image is smudgy, pear tree yield
Error is excessively bigger than normal, it could even be possible to leading to not carry out yield identification.
The present invention has built a kind of individual plant pear tree yield detecting system based on electronic recognition, instead of the side of manual measurement
Formula, introduces haze removal mechanisms at work, has effectively ensured the precision and reliability of the estimation of pear tree yield.
Fig. 1 is the structure of the individual plant pear tree yield detecting system based on electronic recognition according to embodiment of the present invention
Block diagram, before the detecting system is arranged at individual plant pear tree, including CCD vision sensors 1, sharpening processor 2, unilateral yield
Identifier 3 and embeded processor 4, embeded processor 4 are known with CCD vision sensors 1, sharpening processor 2, unilateral yield
Other device 3 is connected respectively, and sharpening processor 2 is connected respectively with CCD vision sensors 1, unilateral yield identifier 3.
Wherein, the CCD vision sensors 1 are used to carry out IMAQ to the side of individual plant pear tree to obtain unilateral pear tree
Image, the sharpening processor 2 are used to carry out the unilateral pear tree image hazeization processing, go haze unilateral to obtain
Pear tree image, the unilateral yield identifier 3 is used to go haze one side pear tree image to carry out image recognition to described, to obtain pears
Unilateral fruit number is set, the embeded processor 4 is connected with the unilateral yield identifier 3, for single based on the pear tree
Side fruit number determines whole yield of the individual plant pear tree.
Then, continue that the concrete structure of the individual plant pear tree yield detecting system based on electronic recognition of the present invention is entered to advance
The explanation of one step.
The detecting system also includes：Power supply, including solar powered device, battery, switching switch and voltage
Converter, the switching switch are connected respectively with the solar powered device and the battery, according to the remaining electricity of battery
Amount decides whether to be switched to the solar powered device to be powered by the solar powered device, the electric pressure converter with
The switching switch connection, so that the 5V voltage conversions of input will be switched by switching as 3.3V voltages.
The detecting system also includes：Mobile hard disk, for prestoring Pear Fruit upper limit gray threshold, Pear Fruit
Lower limit gray threshold and estimation multiplying power, the Pear Fruit upper limit gray threshold and the Pear Fruit lower limit gray threshold are used for
Pear Fruit in image is separated with image background, the estimation multiplying power is used for whole based on pear tree one side yield estimation pear tree
Yield.
The detecting system also includes：Display device, it is connected with the embeded processor 4, for showing and the list
Text information corresponding to whole yield of strain pear tree.
The CCD vision sensors 1 are used to shoot the front of the individual plant pear tree, to obtain the unilateral pear tree
Image.
The sharpening processor 2 includes：
Sub- device is stored, for prestoring sky upper limit gray threshold and sky lower limit gray threshold, on the sky
Limit gray threshold and the sky lower limit gray threshold are used to isolate sky areas in image, are additionally operable to prestore default
Pixel value threshold value, the presetted pixel value threshold value value is between 0 to 255；
The sub- device of haze Concentration Testing, in air, for detecting the haze concentration of individual plant pear tree position in real time,
And determining that haze removes intensity according to haze concentration, the haze removes intensity value between 0 to 1；
The sub- device of region division, the CCD vision sensors 1 are connected to receive the unilateral pear tree image, to the list
Side pear tree image carries out gray processing processing to obtain gray processing area image, is also connected with storing sub- equipment, by the gray processing
Pixel of the gray value between the sky upper limit gray threshold and the sky lower limit gray threshold identifies simultaneously in area image
Gray processing sky sub-pattern is formed, is partitioned into the gray processing sky sub-pattern from the gray processing area image to obtain gray scale
Change non-sky subgraph, based on correspondence position of the non-sky subgraph of the gray processing in beat image obtain with it is described
Colored non-sky subgraph corresponding to the non-sky subgraph of gray processing；
Black channel obtains sub- equipment, is connected with the sub- equipment of the region division to obtain the non-day null subgraph of the colour
Picture, for each pixel in the non-sky subgraph of the colour, calculate its R, the Color Channel pixel value of G, B tri-, in the coloured silk
The R of all pixels in the non-sky subgraph of color, the minimum Color Channel picture of one numerical value of extraction in the Color Channel pixel value of G, B tri-
Color Channel where element value is as black channel；
Overall air light value obtains sub- equipment, is connected with the sub- equipment of storage to obtain presetted pixel value threshold value, with institute
State the sub- equipment of region division and the black channel and obtain sub- equipment and connect respectively to obtain the unilateral pear tree image and described
Black channel, black channel pixel value in the unilateral pear tree image is more than or equal to multiple pixel groups of presetted pixel value threshold value
Into set of pixels to be tested, using the gray value of the pixel in the set of pixels to be tested with maximum gradation value as overall atmosphere light
Value；
Atmospheric scattering light value obtains sub- equipment, equipment sub- with the region division and the sub- equipment of haze Concentration Testing point
Do not connect, to each pixel of the unilateral pear tree image, extract its R, minimum value conduct in the Color Channel pixel value of G, B tri-
Target pixel value, use the Gaussian filter EPGF (edge-preserving gaussian filter) for keeping edge
Processing is filtered to the target pixel value to obtain filtered target pixel value, target pixel value is subtracted into filtered target pixel
Value is filtered processing to obtain object pixel difference, using EPGF to obtain filtered target pixel difference to object pixel difference
Value, filtered target pixel value is subtracted into filtered target pixel value difference to obtain haze and removes a reference value, haze removal intensity is multiplied
A reference value is removed with haze and removes threshold value to obtain haze, take haze remove the minimum value in threshold value and target pixel value be used as than
Compared with reference value, atmospheric scattering light value of the maximum in comparison reference and 0 as each pixel is taken；
Medium transfer rate obtains sub- equipment, obtains sub- equipment with the overall air light value and the atmospheric scattering light value obtains
Take sub- equipment to connect respectively, the atmospheric scattering light value of each pixel divided by overall air light value are removed into value to obtain, 1 is subtracted
It is described to remove value to obtain the medium transfer rate of each pixel；
Sharpening image obtains sub- equipment, and equipment sub- with the region division, the overall air light value obtain sub- equipment
Sub- equipment is obtained with the medium transfer rate to connect respectively, the medium transfer rate for 1 being subtracted each pixel is poor to obtain first
Value, is multiplied by overall air light value to obtain product value, by each pixel in the unilateral pear tree image by first difference
Pixel value subtract the product value to obtain the second difference, by second difference divided by the medium transfer rate of each pixel
To obtain the sharpening pixel value of each pixel, the pixel value of each pixel includes the list in the unilateral pear tree image
The R of each pixel in the pear tree image of side, the Color Channel pixel value of G, B tri-, correspondingly, the sharpening of each pixel of acquisition
Pixel value includes the R of each pixel, the Color Channel sharpening pixel value of G, B tri-, the sharpening pixel value composition of all pixels
Remove haze one side pear tree image.
The unilateral yield identifier 3 is connected with the sharpening processor 2 and the mobile hard disk respectively, the one side
Yield identifier 3 includes：
Contrast enhancer device, it is connected with the sharpening processor 2 and removes haze one side pear tree image to obtain, to institute
State haze one side pear tree image and perform contrast enhancement processing, to obtain enhancing image；
The sub- device of wavelet filtering, it is connected with the contrast enhancer device, wavelet filtering is performed to the enhancing image
Processing, to obtain filtering image；
The sub- device of gray processing processing, is connected with the sub- device of the wavelet filtering, and the filtering image is performed at gray processing
Reason, to obtain gray level image；
The sub- device of image recognition, handle sub- device with the gray processing and the mobile hard disk is connected respectively, by the ash
Picture of the gray value between the Pear Fruit upper limit gray threshold and the Pear Fruit lower limit gray threshold in degreeization image
Element identifies and forms multiple Pear Fruit subgraphs, using the sum of multiple Pear Fruit subgraphs as pear tree one side fruit number
Amount.
The embeded processor 4 is connected respectively with the mobile hard disk, the unilateral yield identifier 3, calculates pear tree
Unilateral fruit number and the product of estimation multiplying power, whole yield using the product as the individual plant pear tree.
Alternatively, in the individual plant pear tree yield detecting system based on electronic recognition：The embeded processor 4 is counted
The resources occupation rate of itself is calculated, when the resources occupation rate of itself is less than the first preset percentage, the unilateral yield is substituted and knows
The operation of other device 3；The embeded processor 4 terminates to institute when the resources occupation rate of itself is more than the second preset percentage
State the replacement of the operation of unilateral yield identifier 3；First preset percentage and second preset percentage are deposited in advance
In the mobile hard disk, first preset percentage is less than second preset percentage for storage；And can will be described embedding
Enter formula processor 4 and the unilateral yield identifier 3 is integrated on one piece of surface-mounted integrated circuit.
In addition, haze image can realize image by a series of images processing equipment remove haze, it is clear to obtain
The image of change, improve the visibility of image.These image processing equipments perform different image processing functions respectively, based on haze
The principle of formation, reach the effect for removing haze.The sharpening processing of haze image all has pole for dual-use field
Big application value, military domain include military and national defense, remote sensing navigate etc., civil area include road monitoring, target following and
Automatic Pilot etc..
The process that haze image is formed can be described with atmospheric attenuation process, be clear in haze image and real image
Changing the relation between image can be stated with the medium transfer rate of overall air light value and each pixel, i.e., in known haze figure
As in the case of, according to overall air light value and the medium transfer rate of each pixel, sharpening image can be solved.
Some be present effectively and by testing in the solution for overall air light value and the medium transfer rate of each pixel
The means of card, for example, medium transfer rate for each pixel is, it is necessary to obtain the big of overall air light value and each pixel
Gas scatters light value, and the atmospheric scattering light value of each pixel can be carried out to pixel value of each pixel in haze image
The Gaussian smoothing filter at edge is kept twice and is obtained, and therebetween, the intensity that haze removes is adjustable；And the acquisition of overall air light value
Mode has two kinds, and a kind of mode is, can be by obtaining black channel (i.e. in haze image some pixels of haze image
Black channel value it is very low, one kind in the Color Channel of black channel R, G, B tri-), it is black by finding in haze image
The maximum pixel of gray value is found in chrominance channel pixel value multiple pixels bigger than normal to obtain, will search out, gray value is most
The gray value of big pixel participates in the sharpening processing of each pixel in haze image as overall air light value；It is in addition, whole
Body atmosphere light value can also obtain in the following manner：The gray value of each pixel in haze image is calculated, gray value is maximum
The gray value of pixel is as overall air light value.
Specific haze image and real image are the relation between sharpening image, and the relation between parameters
Reference can be made to above content.
By the discussion to haze image formation basic theory, the relation between haze image and sharpening image has been built, has been used
Multiple parameters represent this relation, are then that reducible acquisition definition is higher by the multiple parameter values and haze image of acquisition
Image, because the acquisition of parameter has borrowed some statistical means and empirical means, therefore the higher image of the definition is not
Real image may be fully equivalent to, but there is the considerable degree of every field gone haze effect, be under haze weather
Operation provides effective guarantee.
Using the individual plant pear tree yield detecting system based on electronic recognition of the present invention, image recognition skill is based on for existing
The pear tree yield detecting system testing mechanism of art is unreasonable and yield accuracy of detection is brought due to not accounting for haze weather
The technical problem for causing system reliability difference is influenceed, estimates multiplying power by introducing so that calculate by pear tree one side fruit number
Whole yield of the individual plant pear tree are possibly realized, in addition, being carried out by introducing sharpening processor to image at haze
Reason, the normal work of detecting system of the invention is avoided by the unfavorable interference of various haze weathers.
It is understood that although the present invention is disclosed as above with preferred embodiment, but above-described embodiment and it is not used to
Limit the present invention.For any those skilled in the art, without departing from the scope of the technical proposal of the invention,
Many possible changes and modifications are all made to technical solution of the present invention using the technology contents of the disclosure above, or are revised as
With the equivalent embodiment of change.Therefore, every content without departing from technical solution of the present invention, the technical spirit pair according to the present invention
Any simple modifications, equivalents, and modifications made for any of the above embodiments, still fall within the scope of technical solution of the present invention protection
It is interior.
Claims (5)
1. a kind of individual plant pear tree yield detecting system based on electronic recognition, before being arranged at individual plant pear tree, the detecting system bag
CCD vision sensors, sharpening processor, unilateral yield identifier and embeded processor are included, the CCD vision sensors are used
IMAQ is carried out to obtain unilateral pear tree image in the side to individual plant pear tree, and the sharpening processor is used for the list
Side pear tree image carries out hazeization processing, and haze one side pear tree image is removed to obtain, and the unilateral yield identifier is used for pair
It is described to go haze one side pear tree image to carry out image recognition, to obtain pear tree one side fruit number, the embeded processor with
The unilateral yield identifier connection, for determining whole productions of the individual plant pear tree based on pear tree one side fruit number
Amount；
Characterized in that, the detecting system also includes：
Power supply, including solar powered device, battery, switching switch and electric pressure converter, the switching switch and institute
State solar powered device and the battery connects respectively, decided whether to be switched to the sun according to battery dump energy
To be powered by the solar powered device, the electric pressure converter connects energy power supply device with the switching switch, will be logical
The 5V voltage conversions for crossing switching switch input are 3.3V voltages；
Mobile hard disk, for prestoring Pear Fruit upper limit gray threshold, Pear Fruit lower limit gray threshold and estimation multiplying power,
The Pear Fruit upper limit gray threshold and the Pear Fruit lower limit gray threshold are used for the Pear Fruit and figure in image
As background separation, the estimation multiplying power is used for based on pear tree one side yield estimation pear tree whole yield；
Display device, it is connected with the embeded processor, for showing text corresponding with whole yield of the individual plant pear tree
Word information；
The CCD vision sensors are used to shoot the front of the individual plant pear tree, to obtain the unilateral pear tree image；
The sharpening processor includes：
Sub- device is stored, for prestoring sky upper limit gray threshold and sky lower limit gray threshold, the sky upper limit ash
Degree threshold value and the sky lower limit gray threshold are used to isolate the sky areas in image, are additionally operable to prestore presetted pixel
It is worth threshold value, the presetted pixel value threshold value value is between 0 to 255；
The sub- device of haze Concentration Testing, in air, for detecting the haze concentration of individual plant pear tree position, and root in real time
Determine that haze removes intensity according to haze concentration, the haze removes intensity value between 0 to 1；
The sub- device of region division, the CCD vision sensors are connected to receive the unilateral pear tree image, to the unilateral pear tree
Image carries out gray processing processing to obtain gray processing area image, is also connected with storing sub- equipment, by the gray processing administrative division map
Pixel of the gray value between the sky upper limit gray threshold and the sky lower limit gray threshold identifies and forms ash as in
Degreeization sky sub-pattern, the gray processing sky sub-pattern is partitioned into from the gray processing area image to obtain the non-day of gray processing
Null subgraph picture, the correspondence position based on the non-sky subgraph of the gray processing in beat image obtain and the gray processing
Colored non-sky subgraph corresponding to non-sky subgraph；
Black channel obtains sub- equipment, is connected with the sub- equipment of the region division to obtain the non-sky subgraph of the colour, pin
To each pixel in the non-sky subgraph of the colour, its R, the Color Channel pixel value of G, B tri-, in the non-day of colour are calculated
The minimum Color Channel pixel value institute of a numerical value is extracted in the R of all pixels in null subgraph picture, G, B tri- Color Channel pixel value
Color Channel as black channel；
Overall air light value obtains sub- equipment, is connected with the sub- equipment of storage to obtain presetted pixel value threshold value, with the area
Molecular Devices are drawn in domain and the black channel obtains sub- equipment and connected respectively to obtain the unilateral pear tree image and the black
Passage, multiple pixels composition that black channel pixel value in the unilateral pear tree image is more than or equal to presetted pixel value threshold value are treated
Set of pixels is examined, using the gray value of the pixel in the set of pixels to be tested with maximum gradation value as overall air light value；
Atmospheric scattering light value obtains sub- equipment, and equipment sub- with the region division and the sub- equipment of haze Concentration Testing connect respectively
Connect, to each pixel of the unilateral pear tree image, extract its R, minimum value is as target in the Color Channel pixel value of G, B tri-
Pixel value, processing is filtered to the target pixel value to be filtered using the Gaussian filter EPGF at edge is kept
Target pixel value, target pixel value is subtracted into filtered target pixel value to obtain object pixel difference, using EPGF to target picture
Plain difference is filtered processing to obtain filtered target pixel value difference, and filtered target pixel value is subtracted into filtered target pixel value difference
A reference value is removed to obtain haze, haze removal intensity is multiplied by into haze removes a reference value to obtain haze removal threshold value, takes mist
Minimum value in haze removal threshold value and target pixel value takes the maximum conduct in comparison reference and 0 as comparison reference
The atmospheric scattering light value of each pixel；
Medium transfer rate obtains sub- equipment, obtains sub- equipment with the overall air light value and the atmospheric scattering light value obtains son
Equipment is connected respectively, and the atmospheric scattering light value of each pixel divided by overall air light value are removed into value to obtain, and 1 is subtracted described
Except value to obtain the medium transfer rate of each pixel；
Sharpening image obtains sub- equipment, and equipment sub- with the region division, the overall air light value obtain sub- equipment and institute
Give an account of the sub- equipment of matter transfer rate acquisition to connect respectively, the medium transfer rate for subtracting each pixel by 1 is incited somebody to action to obtain the first difference
First difference is multiplied by overall air light value to obtain product value, by the pixel of each pixel in the unilateral pear tree image
Value subtracts the product value to obtain the second difference, by the medium transfer rate of second difference divided by each pixel to obtain
The sharpening pixel value of each pixel, the pixel value of each pixel includes the unilateral pear tree in the unilateral pear tree image
The R of each pixel in image, G, B tri- Color Channel pixel value, correspondingly, the sharpening pixel value of each pixel of acquisition
R including each pixel, G, the Color Channel sharpening pixel values of B tri-, the sharpening pixel value composition of all pixels remove haze
Unilateral pear tree image；
The unilateral yield identifier is connected with the sharpening processor and the mobile hard disk respectively, and the unilateral yield is known
Other device includes：
Contrast enhancer device, it is connected with the sharpening processor to obtain haze one side pear tree image, is gone to described
Haze one side pear tree image performs contrast enhancement processing, to obtain enhancing image；
The sub- device of wavelet filtering, it is connected with the contrast enhancer device, wavelet filtering processing is performed to the enhancing image,
To obtain filtering image；
The sub- device of gray processing processing, is connected with the sub- device of the wavelet filtering, and gray processing processing is performed to the filtering image, with
Obtain gray level image；
The sub- device of image recognition, handle sub- device with the gray processing and the mobile hard disk is connected respectively, by the gray processing
Pixel of the gray value between the Pear Fruit upper limit gray threshold and the Pear Fruit lower limit gray threshold is known in image
Not and multiple Pear Fruit subgraphs are formed, using the sum of multiple Pear Fruit subgraphs as pear tree one side fruit number；
The embeded processor is connected respectively with the mobile hard disk, the unilateral yield identifier, calculates pear tree one side fruit
The product of real number amount and estimation multiplying power, whole yield using the product as the individual plant pear tree.
2. the individual plant pear tree yield detecting system based on electronic recognition as claimed in claim 1, it is characterised in that：
The embeded processor calculates the resources occupation rate of itself, is less than the first preset percentage in the resources occupation rate of itself
When, substitute the operation of the unilateral yield identifier.
3. the individual plant pear tree yield detecting system based on electronic recognition as claimed in claim 2, it is characterised in that：
The embeded processor terminates to the unilateral yield when the resources occupation rate of itself is more than the second preset percentage
The replacement of the operation of identifier.
4. the individual plant pear tree yield detecting system based on electronic recognition as claimed in claim 3, it is characterised in that：
First preset percentage and second preset percentage are pre-stored in the mobile hard disk, and described first
Preset percentage is less than second preset percentage.
5. the individual plant pear tree yield detecting system based on electronic recognition as claimed in claim 1, it is characterised in that：
The embeded processor and the unilateral yield identifier are integrated on one piece of surface-mounted integrated circuit.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510178864.7A CN104794712B (en) | 2015-04-16 | 2015-04-16 | Individual plant pear tree yield detecting system based on electronic recognition |
| CN201710448181.8A CN107169940B (en) | 2015-04-16 | 2015-04-16 | Single pear tree yield obtaining method based on electronic identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510178864.7A CN104794712B (en) | 2015-04-16 | 2015-04-16 | Individual plant pear tree yield detecting system based on electronic recognition |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710448181.8A Division CN107169940B (en) | 2015-04-16 | 2015-04-16 | Single pear tree yield obtaining method based on electronic identification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104794712A CN104794712A (en) | 2015-07-22 |
| CN104794712B true CN104794712B (en) | 2017-12-01 |
Family
ID=53559492
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710448181.8A Active CN107169940B (en) | 2015-04-16 | 2015-04-16 | Single pear tree yield obtaining method based on electronic identification |
| CN201510178864.7A Active CN104794712B (en) | 2015-04-16 | 2015-04-16 | Individual plant pear tree yield detecting system based on electronic recognition |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710448181.8A Active CN107169940B (en) | 2015-04-16 | 2015-04-16 | Single pear tree yield obtaining method based on electronic identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN107169940B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104999200B (en) * | 2015-08-04 | 2016-08-24 | 青岛青知企业管理咨询有限公司 | Diver portable system |
| CN109447945B (en) * | 2018-09-21 | 2021-11-30 | 河南农业大学 | Quick counting method for basic wheat seedlings based on machine vision and graphic processing |
| CN110222677A (en) * | 2019-07-04 | 2019-09-10 | 苏州经贸职业技术学院 | A kind of loquat output statistics system based on raspberry pie |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201600330U (en) * | 2009-09-23 | 2010-10-06 | 中国农业大学 | System for recognizing and locating mature pineapples |
| US10499804B2 (en) * | 2011-02-24 | 2019-12-10 | DePuy Synthes Products, Inc. | Imaging sensor providing improved visualization for surgical scopes |
| CN103049888A (en) * | 2012-12-07 | 2013-04-17 | 西安电子科技大学 | Image/video demisting method based on combination of dark primary color of atmospheric scattered light |
| CN103065285A (en) * | 2012-12-30 | 2013-04-24 | 信帧电子技术（北京）有限公司 | Defogging method and device for image data |
| CN104182943B (en) * | 2014-08-27 | 2015-12-02 | 湖南大学 | A kind of single image defogging method capable merging human-eye visual characteristic |
| CN104360669B (en) * | 2014-11-27 | 2016-09-28 | 江苏华艺服饰有限公司 | A kind of spinning and weaving workshop environment control method |
| CN104474714B (en) * | 2014-11-27 | 2016-08-31 | 海安索菲亚生态环境新材料科技有限公司 | Roller-coaster passenger status real-time detecting system |
-
2015
- 2015-04-16 CN CN201710448181.8A patent/CN107169940B/en active Active
- 2015-04-16 CN CN201510178864.7A patent/CN104794712B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN104794712A (en) | 2015-07-22 |
| CN107169940A (en) | 2017-09-15 |
| CN107169940A8 (en) | 2019-04-05 |
| CN107169940B (en) | 2021-06-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Santesteban et al. | High-resolution UAV-based thermal imaging to estimate the instantaneous and seasonal variability of plant water status within a vineyard | |
| Fernández | Plant-based sensing to monitor water stress: Applicability to commercial orchards | |
| Stagakis et al. | Monitoring water stress and fruit quality in an orange orchard under regulated deficit irrigation using narrow-band structural and physiological remote sensing indices | |
| Lamb et al. | Using remote sensing to predict grape phenolics and colour at harvest in a Cabernet Sauvignon vineyard: Timing observations against vine phenology and optimising image resolution | |
| CN109948596A (en) | A method of rice identification and crop coverage measurement are carried out based on vegetation index model | |
| CN110472184A (en) | A kind of cloudy misty rain area rice recognition methods based on Landsat remotely-sensed data | |
| King et al. | Within‐vineyard variability in vine vegetative growth, yield, and fruit and wine composition of C abernet S auvignon in H awke's B ay, N ew Z ealand | |
| CN104704990B (en) | A kind of pomegranate tree electronization picking method automatically | |
| CN104794712B (en) | Individual plant pear tree yield detecting system based on electronic recognition | |
| CN106372592A (en) | Winter wheat plantation area calculation method based on winter wheat area index | |
| Marino et al. | Validation of an online system for the continuous monitoring of tree water status for sustainable irrigation managements in olive (Olea europaea L.) | |
| CN104949981A (en) | Automatic detection method and system for cotton five-euphylla period | |
| CN112836623A (en) | Facility tomato farming decision auxiliary method and device | |
| CN104732550B (en) | Pomegranate tree electronization plucks platform automatically | |
| Wang et al. | Automated mango flowering assessment via refinement segmentation | |
| CN102360428A (en) | Automatic detection methods for trefoil stage and seven-leaf stage of corn | |
| Saulino et al. | Wildfire promotes the invasion of Robinia pseudoacacia in the unmanaged Mediterranean Castanea sativa coppice forests | |
| CN104794442B (en) | Whole strain apple tree cooking level Identification platform | |
| JP6116012B2 (en) | How to harvest avocado | |
| CN105165773B (en) | Pesticide spraying speed control platform | |
| TEIMOURLOU et al. | A machine vision system for the real-time harvesting of ripe tomato | |
| Pasinetti et al. | How water affects growing plants: an experimental set-up based on 2D vision and on-the-edge sensing | |
| CN103125371A (en) | Method for carrying out field rapid assistant screening on crop drought-resisting mutants | |
| Valero et al. | Identification of agricultural crops in early stages using remote sensing images | |
| CN115249327A (en) | System and method for analyzing picking degree of individual tea tree |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Qian Fanglin Inventor before: Wang Aiyun |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20170614 Address after: 510665 room 501A, No. 59 Middle Road, Tianhe District, Guangdong, Guangzhou Applicant after: Qian Fanglin Address before: 224200 Dongtai, Jiangsu, East Road, North Road, No. Applicant before: Wang Aiyun |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20171010 Address after: 401346, Banan District of Chongqing City bounded Stone Street South 2-2-2 Applicant after: Chongqing Sheng Zan Technology Co.,Ltd. Address before: 510665 room 501A, No. 59 Middle Road, Tianhe District, Guangdong, Guangzhou Applicant before: Qian Fanglin |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20180112 Address after: Chongqing District of Banan city bridge 401344 Solitaire Town Street No. 11 6-8 Patentee after: Liu Mengxiang Address before: 401346, Banan District of Chongqing City bounded Stone Street South 2-2-2 Patentee before: Chongqing Sheng Zan Technology Co.,Ltd. |
|
| CP02 | Change in the address of a patent holder | ||
| CP02 | Change in the address of a patent holder |
Address after: 274300 Guocun Town Economic Development Zone, Shan county, Heze City, Shandong Province Patentee after: Liu Mengxiang Address before: Chongqing District of Banan city bridge 401344 Solitaire Town Street No. 11 6-8 Patentee before: Liu Mengxiang |
|
| CP02 | Change in the address of a patent holder | ||
| CP02 | Change in the address of a patent holder |
Address after: 401320 6-8, No.11, Jinqiao street, Jielong Town, Banan District, Chongqing Patentee after: Liu Mengxiang Address before: 274300 Guocun Town Economic Development Zone, Shan county, Heze City, Shandong Province Patentee before: Liu Mengxiang |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230918 Address after: Room 709, Unit 4, Building 1, Jufu Garden, No. 461 Huaixi Road, Hecheng District, Huaihua City, Hunan Province, 418000 Patentee after: Huaihua Chengzhe Information Technology Co.,Ltd. Address before: 401320 6-8, No. 11, Jinqiao street, Jielong Town, Banan District, Chongqing Patentee before: Liu Mengxiang |