CN105850376A - Electronic and automatic pomegranate picking method - Google Patents

Electronic and automatic pomegranate picking method Download PDF

Info

Publication number
CN105850376A
CN105850376A CN201610319750.4A CN201610319750A CN105850376A CN 105850376 A CN105850376 A CN 105850376A CN 201610319750 A CN201610319750 A CN 201610319750A CN 105850376 A CN105850376 A CN 105850376A
Authority
CN
China
Prior art keywords
fruit
value
image
pomegranate tree
sub
Prior art date
Application number
CN201610319750.4A
Other languages
Chinese (zh)
Inventor
孟庆峰
Original Assignee
孟庆峰
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 孟庆峰 filed Critical 孟庆峰
Priority to CN201510164663.1A priority Critical patent/CN104704990B/en
Priority to CN201610319750.4A priority patent/CN105850376A/en
Publication of CN105850376A publication Critical patent/CN105850376A/en

Links

Classifications

    • AHUMAN NECESSITIES
    • A01AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01DHARVESTING; MOWING
    • A01D46/00Picking of fruits, vegetables, hops, or the like; Devices for shaking trees or shrubs
    • A01D46/30Robotic devices for individually picking crops
    • AHUMAN NECESSITIES
    • A01AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01DHARVESTING; MOWING
    • A01D91/00Methods for harvesting agricultural products
    • A01D91/04Products growing above the soil

Abstract

The invention relates to an electronic and automatic pomegranate picking method. The method includes the following steps that firstly, an electronic and automatic pomegranate picking platform located in front of a pomegranate to be picked is provided, wherein the electronic and automatic pomegranate picking platform comprises a CMOS visual sensor, an image preprocessor, a fruit information detector and an AT89C51 single-chip microcomputer, the CMOS visual sensor is used for photographing the pomegranate to be picked to obtain a pomegranate image, the image preprocessor is used for removing haze components in the pomegranate image to obtain a preprocessed image, the fruit information detector is used for executing image processing on the preprocessed image to confirm whether each fruit on the pomegranate to be picked is ripe or not and confirm the actual position of each fruit, the AT89C51 single-chip microcomputer is connected with the fruit information detector, and picking strategies of corresponding fruits are determined on the basis of whether each fruit on the pomegranate to be picked is ripe or not and on the basis of the actual position of each fruit; secondly, the platform is operated.

Description

A kind of pomegranate tree electronization picking method automatically

The present invention is Application No. 201510164663.1, filing date April 8 in 2015 day, The divisional application of the patent of bright entitled " a kind of pomegranate tree electronization picking method automatically ".

Technical field

The present invention relates to electronics and pluck field, particularly relate to a kind of pomegranate tree electronization side of harvesting automatically Method.

Background technology

Pomegranate tree, originates in a planting fruit-trees in the Western Regions, is one of fruit of liking of citizen, is of high nutritive value, Pomegranate tree is also that people plant one of trees of viewing and admiring.The height of tree 2~4 meters, rugosity 10~30 centimeters.Stone Pomegranate tree performance is graceful, and the florescence is up to the several months, and between annual five, June, full-blown flowers are in full bloom, if bright rosy clouds, premium Like fire, the most bright-coloured, it is to integrate to eat and view and admire, Punica granatum L. wide adaptability in addition, premunition By force, cultivation is easy, thus, the cultivated area of pomegranate tree is more wide in range.

Along with raising and the expanding economy of agriculture and forestry plantation level, pomegranate tree is planted from original Dispersion plantation is to concentrating plantation development, and the most superhuge large-scale single-minded type pomegranate tree plantation is frequent Occurring in various places, this makes the operation to pomegranate tree be converted into that mechanically actuated becomes from manual operation can Energy.Mechanically actuated, in the application of pomegranate tree plant husbandry, can not only save a large amount of cost of labor, and The efficiency of pomegranate tree plantation can be improved, thus improve the economic well-being of workers and staff of plantation owner.

But, in prior art, the mechanically actuated to pomegranate tree plantation still mainly is limited to machinery concentration Spray medicine, machinery are concentrated and are irrigated and the aspect such as weeding concentrated by machinery, for needing most pomegranate tree in man-hour Pluck, the diversity that the professional and fruit owing to plucking is distributed on pomegranate tree, it is still necessary to arrange very Many harvestings personnel pluck in set time section, and this artificial Softening has harvesting and takes time and effort Drawback.Prior art there is also the means that some electronics are plucked, but due to based on image procossing skill Art, is easily affected by various haze weather.

Therefore, in order to overcome above-mentioned various drawback, need a kind of new pomegranate tree electronics to pluck scheme, On the one hand can substitute traditional artificial Softening, the professional and fruit adapting to pomegranate tree harvesting divides The feature of cloth diversity, it is right to realize according to the actual Maturity of fruit and position the most adaptively Effective harvesting of each fruit;On the other hand, it is possible to overcome the haze weather interference to detection image, Improve the reliability that electronics is plucked.

Summary of the invention

In order to solve the problems referred to above, the invention provides a kind of pomegranate tree electronization picking method automatically, The electromechanics of the motor-drive technique construction pomegranate tree electronization harvesting platform automatically quoting location technology sets Standby, quote image acquisition and treatment technology targetedly, obtain Maturity and the position of each fruit Put, so that it is determined that the harvesting drive scheme of each fruit, pluck flexibly on each strain pomegranate tree All mature fruits, while improving picking efficiency, determine haze pair always according to atmospheric attenuation model The influence factor of image, and go hazeization to process the image gathered under various haze weather, open up Wide pomegranate tree electronization plucks the range of application of platform automatically.

According to an aspect of the present invention, it is provided that a kind of pomegranate tree electronization picking method, the party automatically Method comprises the following steps: 1) provide a kind of front being positioned at pomegranate tree to be plucked pomegranate tree electronization Automatically pluck platform, described pomegranate tree electronization automatically pluck platform include CMOS vision sensor, Image pre-processor, fruit information detector and AT89C51 single-chip microcomputer, described CMOS vision passes Sensor is used for treating harvesting pomegranate tree and shoots to obtain pomegranate tree image, and described image pre-processor is used for Remove the haze composition in described pomegranate tree image to obtain pretreatment image, described fruit infomation detection Device for described pretreatment image is performed image procossing, every with on pomegranate tree to be plucked described in determining One fruit is the most ripe and physical location, described AT89C51 single-chip microcomputer and described fruit information are examined Survey device connects, the most ripe and physical location based on each fruit on described pomegranate tree to be plucked Determine the harvesting strategy of corresponding fruit;2) described platform is run.

More specifically, automatically pluck in platform in described pomegranate tree electronization, also include: power supply, Including solar powered device, accumulator, switching switch and electric pressure converter, described switching switch with Described solar powered device and described accumulator connect respectively, according to the decision of accumulator dump energy are No being switched to described solar powered device to be powered by described solar powered device, described voltage turns Parallel operation is connected with described switching switch, will be converted to 3.3V by the 5V voltage of switching switch input Voltage;Pluck execution equipment, the fruit on pomegranate tree to be plucked described in plucking;Harvesting driving sets Standby, it is used for driving described harvesting execution equipment;Real-time positioning equipment, is positioned at described harvesting execution equipment On, for plucking the current location of execution equipment described in real-time positioning;Transceiver, with far-end Agricultural management console sets up two-way wireless communication link, is used for receiving described agricultural management and controls The control instruction that platform sends, described control instruction includes the current location of each strain pomegranate tree, also with Described AT89C51 single-chip microcomputer connects plucks end signal with wireless transmission combination picture and pomegranate tree;North Bucket star localizer, the described pomegranate tree electronization sent for real-time reception the Big Dipper position location satellite is automatic Pluck current the Big Dipper data of platform;Pomegranate tree electronization is automatically plucked platform and is driven equipment, with institute State transceiver and described the Big Dipper localizer connects, respectively including dc motor, for basis The current location of each strain pomegranate tree and current the Big Dipper data, drive described pomegranate tree electronization automatically Pluck the front that platform arrives the current location of each strain pomegranate tree;Storage device, is used for prestoring Preset ripeness degree threshold value and default judgement amount threshold, described preset ripeness degree threshold value is a gray value, It is additionally operable to prestore pomegranate tree upper limit gray threshold, pomegranate tree lower limit gray threshold, fruit upper limit ash Degree threshold value and fruit lower limit gray threshold, described pomegranate tree upper limit gray threshold and described pomegranate tree lower limit Gray threshold is for by the pomegranate tree in image and background separation, described fruit upper limit gray threshold and institute State fruit lower limit gray threshold for by the fruit in image and background separation, be additionally operable to prestore mark Alignment upper limit gray threshold and calibration line lower limit gray threshold, described calibration line upper limit gray threshold and institute Stating calibration line lower limit gray threshold for by the calibration line in image and background separation, calibration line is being clapped Taking the photograph the position in target is given data;Described image pre-processor also includes: store sub-device, uses In prestoring sky upper limit gray threshold and sky lower limit gray threshold, described sky upper limit gray scale threshold Value and described sky lower limit gray threshold, for isolating the sky areas in image, are additionally operable to deposit in advance Storage presetted pixel value threshold value, described presetted pixel value threshold value value is between 0 to 255;Haze concentration Detect sub-device, be positioned in air, automatically pluck platform for detecting described pomegranate tree electronization in real time The haze concentration of position, and determine that intensity removed by haze according to haze concentration, described haze is removed Intensity value is between 0 to 1;Molecular device is drawn in region, connect described CMOS vision sensor with Receive described pomegranate tree image, described pomegranate tree image is carried out gray processing and processes to obtain gray processing district Area image, is also connected, by gray value in described gray processing area image in described sky with the sub-device of storage Pixel identification between empty upper limit gray threshold and described sky lower limit gray threshold also forms gray processing Sky sub pattern, is partitioned into described gray processing sky sub pattern to obtain from described gray processing area image Gray processing non-sky subimage, based on described gray processing non-sky subimage at described beat image In correspondence position obtain colour non-sky subimage corresponding to sky subimage non-with described gray processing; Black channel obtains sub-device, draws molecular device with described region and is connected to obtain the non-sky of described colour Subimage, for each pixel in described colour non-sky subimage, calculates its R, G, B tri- Color Channel pixel value, the R of all pixels in described colour non-sky subimage, G, B tri-face The Color Channel extracting the minimum Color Channel pixel value place of a numerical value in the pixel value of chrominance channel is made For black channel;Overall air light value obtains sub-device, and device with described storage is connected to obtain pre- If pixel value threshold value, draw molecular device with described region and described black channel obtains sub-device and connects respectively Connect to obtain described pomegranate tree image and described black channel, by black channel in described pomegranate tree image Pixel value forms set of pixels to be tested more than or equal to multiple pixels of presetted pixel value threshold value, treats described Inspection set of pixels has the gray value of pixel of maximum gradation value as overall air light value;Air dissipates Penetrate light value and obtain sub-device, draw molecular device with described region and the described sub-device of haze Concentration Testing divides Do not connect, each pixel to described pomegranate tree image, extract its R, G, B tri-Color Channel In pixel value, minima is as target pixel value, uses the Gaussian filter EPGF keeping edge Described target pixel value is filtered processing to obtain filter by (edge-preserving gaussian filter) Ripple target pixel value, deducts filtered target pixel value to obtain object pixel difference by target pixel value, EPGF is used to be filtered object pixel difference processing to obtain filtered target pixel value difference, will filter Ripple target pixel value deducts filtered target pixel value difference and removes reference value to obtain haze, is removed by haze Intensity is multiplied by haze removal reference value removes threshold value to obtain haze, takes haze and removes threshold value and target picture Minima in element value, as comparison reference, takes the maximum in comparison reference and 0 as each The atmospheric scattering light value of individual pixel;Medium transmission rate obtains sub-device, obtains with described overall air light value Frame finder part and described atmospheric scattering light value obtain sub-device and connect respectively, by the air of each pixel Scattering light value to obtain except value, deducts described except value is to obtain each divided by overall air light value by 1 The medium transmission rate of pixel;The sub-device of sharpening Image Acquisition, draws molecular device, institute with described region State the overall air light value device of acquisition and described medium transmission rate obtains sub-device and connects respectively, by 1 Deduct the medium transmission rate of each pixel to obtain the first difference, described first difference is multiplied by entirety The pixel value of each pixel in described pomegranate tree image, to obtain product value, is deducted institute by air light value State product value to obtain the second difference, by described second difference divided by the medium transmission rate of each pixel To obtain the sharpening pixel value of each pixel, the pixel of each pixel in described pomegranate tree image Value includes the R of each pixel in described pomegranate tree image, G, B tri-Color Channel pixel value, phase Ying Di, it is thus achieved that the sharpening pixel value of each pixel include the R, G, B tri-of each pixel Color Channel sharpening pixel value, the sharpening pixel value composition pretreatment image of all pixels;Described Fruit information detector is connected respectively with described image pre-processor and described storage device, described fruit Information detector includes: the sub-device of wavelet filtering, is connected with described image pre-processor, to described pre- Process image and perform wavelet filtering based on Harr Wavelets Filtering Algorithm, output filtering pomegranate tree image; Gray processing processes sub-device, and device with described wavelet filtering is connected, to described filtering pomegranate tree image Execution gray processing processes, it is thus achieved that gray processing pomegranate tree image;The sub-device of pomegranate tree identification, with described ash Degreeization processes sub-device and described storage device connects, respectively by mellow lime for described gray processing pomegranate tree image Angle value pixel between described pomegranate tree upper limit gray threshold and described pomegranate tree lower limit gray threshold Identify and form pomegranate tree pattern;The sub-device of calibration line identification, with described gray processing process sub-device and Described storage device connects respectively, by gray value in described gray processing pomegranate tree image at described calibration line Pixel identification between upper limit gray threshold and described calibration line lower limit gray threshold also forms calibration line Pattern;The sub-device of fruit identification, connects respectively with the described sub-device of pomegranate tree identification and described storage device Connect, by gray value in described pomegranate tree pattern at described fruit upper limit gray threshold and described fruit lower limit Pixel identification between gray threshold also forms multiple fruit pattern;The sub-device of fruit information gathering, with The described sub-device of calibration line identification, the described sub-device of fruit identification and described storage device connect respectively, Measure multiple fruit pattern respectively with the relative position of described calibration line pattern to determine each fruit Physical location, for each fruit pattern, statistical pixel gray value be less than or equal to described in be preset to The pixel quantity of ripe degree threshold value, when the pixel quantity of statistics is more than or equal to described default judgement amount threshold Time, determine that the fruit that described fruit pattern is corresponding is maturation, when described pixel quantity is preset less than described When judging amount threshold, determine that the fruit that described fruit pattern is corresponding is immaturity;Described AT89C51 Single-chip microcomputer drives equipment, described real-time positioning equipment, institute with described harvesting execution equipment, described harvesting State CMOS vision sensor, the described sub-device of pomegranate tree identification, the described sub-device of calibration line identification, The described sub-device of fruit identification and the described sub-device of fruit information gathering connect, respectively by described pomegranate tree Pattern, described calibration line pattern, the plurality of fruit pattern, the most ripe and reality of each fruit Position, border is compound in described pretreatment image form combination picture, and is determining corresponding fruit maturation Time provide the driving signal of corresponding fruit, perform equipment based on corresponding fruit physical location and described harvesting Current location determine the content driving signal of corresponding fruit, when determining corresponding fruit immaturity not Providing the driving signal of corresponding fruit, the driving signal of described corresponding fruit is used for controlling described harvesting and drives Pluck execution equipment described in dynamic device drives and arrive the physical location of corresponding fruit to realize correspondence fruit Real harvesting;Wherein, described AT89C51 single-chip microcomputer sends multiple fruit patterns respectively by preset order The driving signal of corresponding multiple corresponding fruit, and it is being sent the driving signal of all corresponding fruits After, send pomegranate tree and pluck end signal.

More specifically, automatically pluck in platform in described pomegranate tree electronization, the sub-device of described wavelet filtering Part, described gray processing process sub-device, the described sub-device of pomegranate tree identification, described calibration line identification Device, the described sub-device of fruit identification and the described sub-device of fruit information gathering are respectively adopted different Fpga chip realizes.

More specifically, automatically pluck in platform in described pomegranate tree electronization, the sub-device of described wavelet filtering Part, described gray processing process sub-device, the described sub-device of pomegranate tree identification, described calibration line identification Device, the described sub-device of fruit identification and the described sub-device of fruit information gathering be integrated into one piece integrated On circuit board.

More specifically, automatically pluck in platform in described pomegranate tree electronization, the sub-device of described wavelet filtering Part, described gray processing process sub-device, the described sub-device of pomegranate tree identification, described calibration line identification Device, the described sub-device of fruit identification and the described sub-device of fruit information gathering are integrated into one piece In fpga chip.

More specifically, automatically pluck in platform in described pomegranate tree electronization, described pomegranate tree image and The resolution of described pretreatment image is all 3840 × 2160.

Accompanying drawing explanation

Below with reference to accompanying drawing, embodiment of the present invention are described, wherein:

Fig. 1 is the structure automatically plucking platform according to the pomegranate tree electronization shown in embodiment of the present invention Block diagram.

Fig. 2 is the fruit automatically plucking platform according to the pomegranate tree electronization shown in embodiment of the present invention The block diagram of information detector.

Detailed description of the invention

Pomegranate tree electronization to the present invention plucks the embodiment of platform automatically below with reference to accompanying drawings It is described in detail.

Punica granatum L. originates in the little sub-West Asia country such as Iran, Afghanistan.Today Iran, Afghanistan and Ah Plug is visitd on the mountain of height above sea level 300-1000 rice of boundary and the Republic of Georgia, still has the wild stone of sheet Pomegranate woods.

Punica granatum L. be mankind's introducing and planting fruit tree the earliest and HUAMU it, in China, India and Asia, Africa, Europe are along various places, Mediterranean, all as cultivation of fruit tree, and the most with Africa.The U.S. mainly divides Cloth is in California.Spain on the west and south Iberia Peninsula of Europe using Punica granatum L. as state Flower, on 500,000 square kilometres of territories, whether before and after mountain region, plateau, rural room, town, Or the park of coastal city, garden, plantation spy is many for Flos Granati.Punica granatum L. Iranian in original producton location and near Area distribution is relatively wide, the many excellent kinds of selection-breeding.Punica granatum L. is beautiful because of its flowers and fruits, and cultivation is easy, deeply Liked by people.

The trend increasingly centralization that current pomegranate tree produces, each plantation only plant several even A type of pomegranate tree, the enormous amount of pomegranate tree.So planting patterns of feature, at the machine of use In the case of tool operation, efficiency and the benefit of plantation can be improved.But, due to the specialty of picking fruit Property and the dispersibility of fruit growth, substitute the artificial electronics plucked completely and pluck scheme and implement more tired Difficult.Even if there is some electronics to pluck scheme, also due to use means based on image procossing, Cannot avoid the interference to image of the various haze weather, the application conditions causing electronics to be plucked is more severe Carve.

The present invention has built a kind of pomegranate tree electronization and has automatically plucked platform, uses all-electronic side Formula realizes the harvesting of the pomegranate tree to fixed type, uses remote handle except plucking the replacing of pomegranate tree Beyond control, whole picking process need not other manual operations and participates in, and meanwhile, uses image to locate in advance Reason equipment eliminates the haze composition in detection image so that the pomegranate tree electronization of the present invention is adopted automatically Pluck platform and can be suitably used for various haze weather.

Fig. 1 is the structure automatically plucking platform according to the pomegranate tree electronization shown in embodiment of the present invention Block diagram, described pomegranate tree electronization harvesting platform automatically is positioned at the front of pomegranate tree to be plucked, including: CMOS vision sensor 1, image pre-processor 2, fruit information detector 3 and AT89C51 are mono- Sheet machine 4, described CMOS vision sensor 1 is used for treating harvesting pomegranate tree and shoots to obtain pomegranate tree Image, described image pre-processor 2 is for removing the haze composition in described pomegranate tree image to obtain Pretreatment image, described fruit information detector 3 is used for described pretreatment image is performed image procossing, With each fruit on pomegranate tree to be plucked described in determining, the most ripe and physical location, described AT89C51 single-chip microcomputer 4 is connected with described fruit information detector 3, based on described pomegranate tree to be plucked On whether each fruit ripe and physical location determines the harvesting strategy of corresponding fruit.

Then, the concrete structure continuing the electronization of the pomegranate tree to present invention harvesting platform automatically enters The explanation of one step.

Described pomegranate tree electronization is automatically plucked platform and is also included: power supply, including solar powered Device, accumulator, switching switch and electric pressure converter, described switching switch is solar powered with described Device and described accumulator connect respectively, according to accumulator dump energy decide whether to be switched to described in too Sun can power supply device to be powered by described solar powered device, described electric pressure converter and described switching Switch connects, will be converted to 3.3V voltage by the 5V voltage of switching switch input.

Described pomegranate tree electronization is automatically plucked platform and is also included: plucks execution equipment, is used for plucking institute State the fruit on pomegranate tree to be plucked;Pluck driving equipment, be used for driving described harvesting execution equipment; Real-time positioning equipment, is positioned on described harvesting execution equipment, sets for plucking execution described in real-time positioning Standby current location.

Described pomegranate tree electronization is automatically plucked platform and is also included: transceiver, with the agricultural of far-end Management console sets up two-way wireless communication link, is used for receiving described agricultural management console The control instruction sent, described control instruction includes the current location of each strain pomegranate tree, also with described AT89C51 single-chip microcomputer 4 connects plucks end signal with wireless transmission combination picture and pomegranate tree.

Described pomegranate tree electronization is automatically plucked platform and is also included: the Big Dipper localizer, for connecing in real time Receive the current the Big Dipper of the described pomegranate tree electronization harvesting platform automatically that the Big Dipper position location satellite sends Data.

Described pomegranate tree electronization is automatically plucked platform and is also included: pomegranate tree electronization plucks platform automatically Driving equipment, is connected, including unidirectional current respectively with described transceiver and described the Big Dipper localizer Motivation, for the current location according to each strain pomegranate tree and current the Big Dipper data, drives described stone Pomegranate tree electronization plucks the front that platform arrives the current location of each strain pomegranate tree automatically.

Described pomegranate tree electronization is automatically plucked platform and is also included: storage device, is used for prestoring pre- If Maturity threshold value and default judgement amount threshold, described preset ripeness degree threshold value is a gray value, also For prestoring pomegranate tree upper limit gray threshold, pomegranate tree lower limit gray threshold, fruit upper limit gray scale Threshold value and fruit lower limit gray threshold, described pomegranate tree upper limit gray threshold and described pomegranate tree lower limit ash Degree threshold value for by the pomegranate tree in image and background separation, described fruit upper limit gray threshold and described Fruit lower limit gray threshold, for by the fruit in image and background separation, is additionally operable to prestore demarcation Line upper limit gray threshold and calibration line lower limit gray threshold, described calibration line upper limit gray threshold and described Calibration line lower limit gray threshold is for by the calibration line in image and background separation, and calibration line is being taken Position in target is given data.

Described image pre-processor 2 also includes with lower component:

Store sub-device, be used for prestoring sky upper limit gray threshold and sky lower limit gray threshold, Described sky upper limit gray threshold and described sky lower limit gray threshold are for isolating the sky in image Dummy section, is additionally operable to prestore presetted pixel value threshold value, and described presetted pixel value threshold value value is 0 Between 255;

The sub-device of haze Concentration Testing, is positioned in air, detects described pomegranate tree electronization in real time Automatically pluck the haze concentration of platform position, and determine that intensity removed by haze according to haze concentration, Described haze removes intensity value between 0 to 1;

Molecular device is drawn in region, connects described CMOS vision sensor 1 to receive described Punica granatum L. tree graph Picture, carries out gray processing and processes to obtain gray processing area image, also with storage described pomegranate tree image Sub-device connects, by gray value in described gray processing area image at described sky upper limit gray threshold and Pixel identification between described sky lower limit gray threshold also forms gray processing sky sub pattern, from described Gray processing area image is partitioned into described gray processing sky sub pattern to obtain gray processing non-sky null subgraph Picture, obtains based on described gray processing non-sky subimage correspondence position in described beat image The colour non-sky subimage that sky subimage non-with described gray processing is corresponding;

Black channel obtains sub-device, draws molecular device with described region and is connected to obtain described colour non- Sky subimage, for each pixel in described colour non-sky subimage, calculates its R, G, B Three Color Channel pixel values, the R, G, B tri-of all pixels in described colour non-sky subimage Color Channel pixel value extracts the Color Channel at the minimum Color Channel pixel value place of a numerical value As black channel;

Overall air light value obtains sub-device, and device with described storage is connected to obtain presetted pixel value Threshold value, draws molecular device with described region and described black channel obtains sub-device and is connected respectively to obtain Described pomegranate tree image and described black channel, by big for black channel pixel value in described pomegranate tree image Set of pixels to be tested is formed, by described pixel to be tested in the multiple pixels equal to presetted pixel value threshold value Concentrate the gray value of the pixel with maximum gradation value as overall air light value;

Atmospheric scattering light value obtains sub-device, draws molecular device and the inspection of described haze concentration with described region Survey sub-device to connect respectively, each pixel to described pomegranate tree image, extract its R, G, B In three Color Channel pixel values, minima is as target pixel value, uses the Gaussian smoothing filter keeping edge Ripple device EPGF (edge-preserving gaussian filter) is filtered place to described target pixel value Target pixel value, to obtain filtered target pixel value, is deducted filtered target pixel value to obtain target by reason Pixel value difference, uses EPGF to be filtered object pixel difference processing to obtain filtered target pixel Difference, deducts filtered target pixel value filtered target pixel value difference to obtain haze and removes reference value, Haze is removed intensity be multiplied by haze remove reference value with obtain haze remove threshold value, take haze remove threshold Minima in value and target pixel value, as comparison reference, takes the maximum in comparison reference and 0 It is worth the atmospheric scattering light value as each pixel;

Medium transmission rate obtains sub-device, obtains sub-device and described air with described overall air light value Scattering light value obtains sub-device and connects respectively, by big divided by entirety for the atmospheric scattering light value of each pixel Gas light value, to obtain except value, deducts described except value is to obtain the medium transmission rate of each pixel by 1;

The sub-device of sharpening Image Acquisition, draws molecular device, described overall air light value with described region Obtain sub-device and described medium transmission rate obtains sub-device and connects respectively, deduct each pixel by 1 Medium transmission rate to obtain the first difference, described first difference is multiplied by overall air light value to obtain Product value, deducts described product value to obtain by the pixel value of each pixel in described pomegranate tree image Second difference, by described second difference divided by the medium transmission rate of each pixel to obtain each picture The sharpening pixel value of element, in described pomegranate tree image, the pixel value of each pixel includes described Punica granatum L. The R of each pixel in tree Image, G, B tri-Color Channel pixel value, correspondingly, it is thus achieved that every The sharpening pixel value of one pixel includes the R of each pixel, G, B tri-Color Channel sharpening Pixel value, the sharpening pixel value composition pretreatment image of all pixels.

As in figure 2 it is shown, described fruit information detector 3 and described image pre-processor 2 and described deposit Storage equipment connects respectively, and described fruit information detector 3 includes with lower component:

The sub-device of wavelet filtering 31, is connected with described image pre-processor 2, to described pretreatment image Perform wavelet filtering based on Harr Wavelets Filtering Algorithm, output filtering pomegranate tree image;

Gray processing processes sub-device 32, and device 31 sub-with described wavelet filtering is connected, to described filtering Pomegranate tree image performs gray processing and processes, it is thus achieved that gray processing pomegranate tree image;

The sub-device of pomegranate tree identification 33, processes sub-device 32 and described storage device with described gray processing Connect respectively, by gray value in described gray processing pomegranate tree image at described pomegranate tree upper limit gray threshold And pixel identification between described pomegranate tree lower limit gray threshold form pomegranate tree pattern;

The sub-device of calibration line identification 34, processes sub-device 32 and described storage device with described gray processing Connect respectively, by gray value in described gray processing pomegranate tree image at described calibration line upper limit gray threshold And pixel identification between described calibration line lower limit gray threshold form calibration line pattern;

The sub-device of fruit identification 35, divides with the described sub-device of pomegranate tree identification 33 and described storage device Do not connect, by gray value in described pomegranate tree pattern at described fruit upper limit gray threshold and described fruit Pixel identification between lower limit gray threshold also forms multiple fruit pattern;

The sub-device of fruit information gathering 36, knows with the described sub-device of calibration line identification 34, described fruit Small pin for the case device 35 and described storage device connect respectively, measure multiple fruit pattern respectively with described mark The relative position of alignment pattern is to determine the physical location of each fruit, for each fruit figure Case, statistical pixel gray value is less than or equal to the pixel quantity of described preset ripeness degree threshold value, when statistics When pixel quantity is more than or equal to described default judgement amount threshold, determine the fruit that described fruit pattern is corresponding Actually ripe, when described pixel quantity is less than described default judgement amount threshold, determine described fruit The fruit that pattern is corresponding is immaturity.

Described AT89C51 single-chip microcomputer 4 drives equipment, institute with described harvesting execution equipment, described harvesting State real-time positioning equipment, described CMOS vision sensor 1, the described sub-device of pomegranate tree identification 33, The described sub-device of calibration line identification 34, the described sub-device of fruit identification 35 and described fruit information gathering Sub-device 36 connects respectively, by described pomegranate tree pattern, described calibration line pattern, the plurality of fruit Real pattern, the most ripe and physical location of each fruit are compound in described pretreatment image with shape One-tenth combination picture, and provide the driving signal of corresponding fruit when determining corresponding fruit maturation, based on right The current location answering fruit physical location and described harvesting to perform equipment determines the driving letter of corresponding fruit Number content, do not provide the driving signal of corresponding fruit when determining corresponding fruit immaturity, described right The driving signal answering fruit drives harvesting execution equipment described in device drives to arrive for controlling described harvesting Reach the physical location of corresponding fruit to realize the harvesting to corresponding fruit.

Wherein, described AT89C51 single-chip microcomputer 4 sends multiple fruit patterns correspondence respectively by preset order The driving signal of multiple corresponding fruits, and after the driving signal being sent all corresponding fruits, Send pomegranate tree and pluck end signal.

Alternatively, automatically pluck in platform in described pomegranate tree electronization, the sub-device of described wavelet filtering 31, described gray processing processes sub-device 32, the described sub-device of pomegranate tree identification 33, described calibration line Identify sub-device 34, the described sub-device of fruit identification 35 and the described sub-device of fruit information gathering 36 points Different fpga chips is not used to realize, or the sub-device of described wavelet filtering 31, described gray scale Change process sub-device 32, the described sub-device of pomegranate tree identification 33, the described sub-device of calibration line identification 34, The described sub-device of fruit identification 35 and the described sub-device of fruit information gathering 36 be integrated into one piece integrated On circuit board, such as, it is integrated in one piece of fpga chip, and alternatively, described pomegranate tree The resolution of image and described pretreatment image all elects 3840 × 2160 as.

It addition, haze image can remove haze by what a series of images processing equipment realized image, To obtain the image of sharpening, improve the visibility of image.These image processing equipments perform not respectively Same image processing function, the principle formed based on haze, reach to remove the effect of haze.Haze figure The sharpening of picture processes all has great using value, military domain bag for dual-use field Including military and national defense, remote sensing navigation etc., civil area includes road monitoring, target following and automatic Pilot Deng.

The process that haze image is formed can be described by atmospheric attenuation process, in haze image and reality The medium of the available overall air light value of the relation between image i.e. sharpening image and each pixel passes Defeated rate is stated, i.e. in the case of known haze image, according to overall air light value and each picture The medium transmission rate of element, can solve sharpening image.

There are some and have in the solving of medium transmission rate for overall air light value and each pixel Effect and through the means of checking, such as, for the medium transmission rate of each pixel, need to obtain whole Body atmosphere light value and the atmospheric scattering light value of each pixel, and the atmospheric scattering light value of each pixel Can be at the Gaussian smoothing that each pixel pixel value in haze image is carried out twice holding edge Filtering and obtain, therebetween, the intensity that haze is removed is adjustable;And the acquisition pattern of entirety air light value has Two kinds, a kind of mode is, (i.e. can make in haze image by obtaining the black channel of haze image The black channel value of some pixels is the lowest, black channel is R, and G, B tri-is in Color Channel A kind of), in haze image, the multiple pixels bigger than normal by finding black channel pixel value are found The pixel of gray value maximum obtains, and gray value that will search out, gray value is maximum pixel is made For overall air light value, participate in the sharpening of each pixel in haze image and process;It addition, it is overall Air light value also can obtain in the following manner: calculates the gray value of each pixel in haze image, will The gray value of the pixel that gray value is maximum is as overall air light value.

Relation between concrete haze image and real image i.e. sharpening image, and parameters Between relation can be found in above content.

By the discussion to haze image formation basic theory, build between haze image and sharpening image Relation, represent this relation by multiple parameters, subsequently by the multiple parameter values obtained and haze figure The image that picture the most reducible acquisition definition is higher, owing to some statistical means have been used in the acquisition of parameter And empirical means, the image that the most described definition is higher can not be fully equivalent to real image, but Have and considerable degree of gone haze effect, provide effectively for the every field operation under haze weather Ensure.

The pomegranate tree electronization using the present invention plucks platform, automatically for existing manually to pluck pattern Be main pomegranate tree pluck platform inefficiency, relatively costly and use electronics Softening cannot gram Take the technical problem of haze weather impact, by introducing wireless technology, location technology and motor technology be Pomegranate tree electronization is automatically plucked platform and is made reliable electromechanical facility, more it is essential that for Punica granatum L. The feature that tree is plucked, has formulated high-precision image procossing scheme targetedly to identify same strain The Maturity of all pomegranate trees on pomegranate tree and physical location, lay base for pomegranate tree picking mechanical Plinth, improves the automatization level of pomegranate tree picking operations, more it is essential that pass through high-precision mist Haze composition removal mechanisms at work, effectively overcomes the adverse effect that electronics is plucked by various haze weather.

Although it is understood that the present invention discloses as above with preferred embodiment, but above-mentioned enforcement Example is not limited to the present invention.For any those of ordinary skill in the art, without departing from Under technical solution of the present invention ambit, all may utilize the technology contents of the disclosure above to the technology of the present invention Scheme makes many possible variations and modification, or is revised as the Equivalent embodiments of equivalent variations.Therefore, Every content without departing from technical solution of the present invention, the technical spirit of the foundation present invention is to above example Any simple modification, equivalent variations and the modification done, all still falls within technical solution of the present invention protection In the range of.

Claims (2)

1. a pomegranate tree electronization picking method automatically, the method comprises the following steps:
1) the pomegranate tree electronization in a kind of front being positioned at pomegranate tree to be plucked is provided automatically to pluck platform, Described pomegranate tree electronization automatically pluck platform include CMOS vision sensor, image pre-processor, Fruit information detector and AT89C51 single-chip microcomputer, described CMOS vision sensor is used for treating to be adopted Plucking pomegranate tree to shoot to obtain pomegranate tree image, described image pre-processor is used for removing described pomegranate tree Haze composition in image is to obtain pretreatment image, and described fruit information detector is for described pre- Process image and perform image procossing, whether become with each fruit on pomegranate tree to be plucked described in determining Ripe and physical location, described AT89C51 single-chip microcomputer is connected with described fruit information detector, based on Each fruit on described pomegranate tree to be plucked is the most ripe and physical location determines corresponding fruit Harvesting strategy;
2) described platform is run.
2. the method for claim 1, it is characterised in that described pomegranate tree electronization is automatically Pluck platform also to include:
Power supply, including solar powered device, accumulator, switching switch and electric pressure converter, Described switching switch is connected, according to accumulator respectively with described solar powered device and described accumulator Dump energy decides whether to be switched to described solar powered device with by described solar powered device Power supply, described electric pressure converter is connected with described switching switch, with by the 5V by switching switch input Voltage is converted to 3.3V voltage;
Pluck execution equipment, the fruit on pomegranate tree to be plucked described in plucking;
Pluck driving equipment, be used for driving described harvesting execution equipment;
Real-time positioning equipment, is positioned on described harvesting execution equipment, holds for plucking described in real-time positioning The current location of row equipment;
Transceiver, sets up two-way wireless communication link with the agricultural management console of far-end, For receiving the control instruction that described agricultural management console sends, described control instruction includes each The current location of strain pomegranate tree, is also connected with described AT89C51 single-chip microcomputer with wireless transmission combination picture End signal is plucked with pomegranate tree;
The Big Dipper localizer, the described pomegranate tree electronics sent for real-time reception the Big Dipper position location satellite Change the current the Big Dipper data automatically plucking platform;
Pomegranate tree electronization is automatically plucked platform and is driven equipment, with described transceiver and the described Big Dipper Star localizer connects respectively, including dc motor, for the current location according to each strain pomegranate tree With current the Big Dipper data, drive described pomegranate tree electronization automatically to pluck platform and arrive each strain Punica granatum L. The front of the current location of tree;
Storage device, is used for prestoring preset ripeness degree threshold value and presetting judgement amount threshold, described Preset ripeness degree threshold value is a gray value, is additionally operable to prestore pomegranate tree upper limit gray threshold, Punica granatum L. Tree lower limit gray threshold, fruit upper limit gray threshold and fruit lower limit gray threshold, on described pomegranate tree Limit gray threshold and described pomegranate tree lower limit gray threshold are for dividing the pomegranate tree in image and background From, described fruit upper limit gray threshold and described fruit lower limit gray threshold are for by the fruit in image And background separation, it is additionally operable to prestore calibration line upper limit gray threshold and calibration line lower limit gray scale threshold Value, described calibration line upper limit gray threshold and described calibration line lower limit gray threshold are for by image Calibration line and background separation, calibration line is given data in the position being taken in target;
Described image pre-processor also includes:
Store sub-device, be used for prestoring sky upper limit gray threshold and sky lower limit gray scale threshold Value, described sky upper limit gray threshold and described sky lower limit gray threshold are for isolating in image Sky areas, is additionally operable to prestore presetted pixel value threshold value, and described presetted pixel value threshold value value exists Between 0 to 255;
The sub-device of haze Concentration Testing, is positioned in air, detects described pomegranate tree electricity in real time Sonization plucks platform automatically The haze concentration of position, and determine that intensity removed by haze according to haze concentration, described haze is removed Intensity value is between 0 to 1;
Molecular device is drawn in region, connects described CMOS vision sensor to receive described pomegranate tree Image, described pomegranate tree image is carried out gray processing process to obtain gray processing area image, also with deposit Store up sub-device to connect, by gray value in described gray processing area image at described sky upper limit gray threshold And pixel identification between described sky lower limit gray threshold form gray processing sky sub pattern, from institute State gray processing area image and be partitioned into described gray processing sky sub pattern to obtain gray processing non-sky gap Image, obtains based on described gray processing non-sky subimage correspondence position in described beat image Obtain the colour non-sky subimage that sky subimage non-with described gray processing is corresponding;
Black channel obtains sub-device, draws molecular device with described region and is connected to obtain described coloured silk Color non-sky subimage, for each pixel in described colour non-sky subimage, calculates its R, G, B tri-Color Channel pixel value, R, the G of all pixels in described colour non-sky subimage, The color extracting the minimum Color Channel pixel value place of a numerical value in B tri-Color Channel pixel value is led to Road is as black channel;
Overall air light value obtains sub-device, and device with described storage is connected presets picture to obtain Element value threshold value, draw with described region molecular device and described black channel obtain sub-device be connected respectively with Obtain described pomegranate tree image and described black channel, by black channel pixel in described pomegranate tree image Value forms set of pixels to be tested, by described to be tested more than or equal to multiple pixels of presetted pixel value threshold value Set of pixels has the gray value of pixel of maximum gradation value as overall air light value;
Atmospheric scattering light value obtains sub-device, draws molecular device with described region and described haze is dense Degree detects sub-device and connects respectively, and each pixel to described pomegranate tree image extracts its R, G, In B tri-Color Channel pixel value, minima is as target pixel value, uses the Gaussian smoothing keeping edge Described target pixel value is filtered processing to obtain filtered target pixel value by wave filter EPGF, will Target pixel value deducts filtered target pixel value to obtain object pixel difference, uses EPGF to target Pixel value difference is filtered processing to obtain filtered target pixel value difference, is deducted by filtered target pixel value Filtered target pixel value difference removes reference value to obtain haze, haze is removed intensity and is multiplied by haze removal Reference value removes threshold value to obtain haze, takes the minima work that haze is removed in threshold value and target pixel value For comparison reference, take the atmospheric scattering as each pixel of the maximum in comparison reference and 0 Light value;
Medium transmission rate obtains sub-device, obtains sub-device and described with described overall air light value Atmospheric scattering light value obtains sub-device and connects respectively, by the atmospheric scattering light value of each pixel divided by whole Body atmosphere light value, to obtain except value, deducts described except value is to obtain the medium transmission of each pixel by 1 Rate;
The sub-device of sharpening Image Acquisition, draws molecular device, described overall air with described region Light value obtains sub-device and described medium transmission rate obtains sub-device and connects respectively, deducts each by 1 The medium transmission rate of pixel to obtain the first difference, described first difference is multiplied by overall air light value with Obtain product value, the pixel value of each pixel in described pomegranate tree image is deducted described product value with Obtain the second difference, described second difference is each to obtain divided by the medium transmission rate of each pixel The sharpening pixel value of individual pixel, in described pomegranate tree image, the pixel value of each pixel includes described The R of each pixel in pomegranate tree image, G, B tri-Color Channel pixel value, correspondingly, it is thus achieved that The sharpening pixel value of each pixel include the R of each pixel, G, B tri-Color Channels are clear Clearization pixel value, the sharpening pixel value composition pretreatment image of all pixels;
Described fruit information detector is connected respectively with described image pre-processor and described storage device, Described fruit information detector includes:
The sub-device of wavelet filtering, is connected with described image pre-processor, to described pretreatment image Perform wavelet filtering based on Harr Wavelets Filtering Algorithm, output filtering pomegranate tree image;
Gray processing processes sub-device, and device with described wavelet filtering is connected, to described filtering stone Pomegranate tree Image performs gray processing and processes, it is thus achieved that gray processing pomegranate tree image;
The sub-device of pomegranate tree identification, processes sub-device with described gray processing and described storage device is divided Do not connect, by gray value in described gray processing pomegranate tree image at described pomegranate tree upper limit gray threshold and Pixel identification between described pomegranate tree lower limit gray threshold also forms pomegranate tree pattern;
The sub-device of calibration line identification, processes sub-device with described gray processing and described storage device is divided Do not connect, by gray value in described gray processing pomegranate tree image at described calibration line upper limit gray threshold and Pixel identification between described calibration line lower limit gray threshold also forms calibration line pattern;
The sub-device of fruit identification, with the described sub-device of pomegranate tree identification and described storage device difference Connect, by gray value in described pomegranate tree pattern under described fruit upper limit gray threshold and described fruit Limit the pixel identification between gray threshold and form multiple fruit pattern;
The sub-device of fruit information gathering, with the described sub-device of calibration line identification, described fruit identification Sub-device and described storage device connect respectively, measure multiple fruit pattern respectively with described demarcation line chart The relative position of case is to determine the physical location of each fruit, for each fruit pattern, statistics Grey scale pixel value is less than or equal to the pixel quantity of described preset ripeness degree threshold value, when the pixel quantity of statistics During more than or equal to described default judgement amount threshold, determine that fruit that described fruit pattern is corresponding is for becoming Ripe, when described pixel quantity is less than described default judgement amount threshold, determine described fruit pattern pair The fruit answered is immaturity;
Described AT89C51 single-chip microcomputer and described harvesting execution equipment, described harvesting drive equipment, described Real-time positioning equipment, described CMOS vision sensor, the described sub-device of pomegranate tree identification, described mark The sub-device of alignment identification, the described sub-device of fruit identification and the described sub-device of fruit information gathering connect respectively Connect, by described pomegranate tree pattern, described calibration line pattern, the plurality of fruit pattern, each fruit The most ripe real and physical location is compound in described pretreatment image form combination picture, and Provide the driving signal of corresponding fruit when determining corresponding fruit maturation, based on corresponding fruit physical location and The current location of described harvesting execution equipment determines the content driving signal of corresponding fruit, right determining Not providing the driving signal of corresponding fruit when answering fruit immaturity, the driving signal of described corresponding fruit is used Harvesting execution equipment described in device drives is driven to arrive the actual bit of corresponding fruit in controlling described harvesting Put to realize the harvesting to corresponding fruit;
Wherein, described AT89C51 single-chip microcomputer sends multiple fruit patterns correspondence respectively by preset order The driving signal of multiple corresponding fruits, and after the driving signal being sent all corresponding fruits, send out Go out pomegranate tree and pluck end signal;
The sub-device of described wavelet filtering, described gray processing process sub-device, the described sub-device of pomegranate tree identification Part, the described sub-device of calibration line identification, the described sub-device of fruit identification and described fruit information gathering Device is respectively adopted different fpga chips and realizes;
The resolution of described pomegranate tree image and described pretreatment image is all 3840 × 2160.
CN201610319750.4A 2015-04-08 2015-04-08 Electronic and automatic pomegranate picking method CN105850376A (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201510164663.1A CN104704990B (en) 2015-04-08 2015-04-08 A kind of pomegranate tree electronization picking method automatically
CN201610319750.4A CN105850376A (en) 2015-04-08 2015-04-08 Electronic and automatic pomegranate picking method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610319750.4A CN105850376A (en) 2015-04-08 2015-04-08 Electronic and automatic pomegranate picking method

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
CN201510164663.1A Division CN104704990B (en) 2015-04-08 2015-04-08 A kind of pomegranate tree electronization picking method automatically

Publications (1)

Publication Number Publication Date
CN105850376A true CN105850376A (en) 2016-08-17

Family

ID=53405097

Family Applications (3)

Application Number Title Priority Date Filing Date
CN201610319750.4A CN105850376A (en) 2015-04-08 2015-04-08 Electronic and automatic pomegranate picking method
CN201510164663.1A CN104704990B (en) 2015-04-08 2015-04-08 A kind of pomegranate tree electronization picking method automatically
CN201610300687.XA CN105875066A (en) 2015-04-08 2015-04-08 Electronic and automatic pomegranate tree picking method

Family Applications After (2)

Application Number Title Priority Date Filing Date
CN201510164663.1A CN104704990B (en) 2015-04-08 2015-04-08 A kind of pomegranate tree electronization picking method automatically
CN201610300687.XA CN105875066A (en) 2015-04-08 2015-04-08 Electronic and automatic pomegranate tree picking method

Country Status (1)

Country Link
CN (3) CN105850376A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108718709A (en) * 2018-06-05 2018-11-02 宁波大学 Automate strawberry picking machine

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105929752A (en) * 2016-06-22 2016-09-07 吴童 Robot-based lychee picking control system
CN106941879B (en) * 2017-04-27 2018-05-18 居国斌 Picker

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102170574A (en) * 2011-05-23 2011-08-31 北京工业大学 Real-time video defogging system
CN102165880A (en) * 2011-01-19 2011-08-31 南京农业大学 Automatic-navigation crawler-type mobile fruit picking robot and fruit picking method
CN103039200A (en) * 2012-12-31 2013-04-17 辛慰 Tomato picker used for greenhouse
CN104199453A (en) * 2014-09-27 2014-12-10 江苏华宏实业集团有限公司 Intelligent robot used for inspecting electric power meter
CN104317302A (en) * 2014-09-28 2015-01-28 江苏华宏实业集团有限公司 Intellectualized underwater robot system
CN104330410A (en) * 2014-11-04 2015-02-04 无锡北斗星通信息科技有限公司 Crop pest detection system positioned on unmanned aerial vehicle

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN100591202C (en) * 2008-05-05 2010-02-24 江苏大学 Apparatus and method for flexible pick of orange picking robot
CN101493313B (en) * 2009-02-27 2011-01-05 中国农业大学 Image processing process for ripe fruit identification and positioning
CN201600330U (en) * 2009-09-23 2010-10-06 中国农业大学 System for recognizing and locating mature pineapples
CN102124866B (en) * 2011-01-19 2013-05-29 南京农业大学 Wheel type mobile fruit picking robot and fruit picking method

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102165880A (en) * 2011-01-19 2011-08-31 南京农业大学 Automatic-navigation crawler-type mobile fruit picking robot and fruit picking method
CN102170574A (en) * 2011-05-23 2011-08-31 北京工业大学 Real-time video defogging system
CN103039200A (en) * 2012-12-31 2013-04-17 辛慰 Tomato picker used for greenhouse
CN104199453A (en) * 2014-09-27 2014-12-10 江苏华宏实业集团有限公司 Intelligent robot used for inspecting electric power meter
CN104317302A (en) * 2014-09-28 2015-01-28 江苏华宏实业集团有限公司 Intellectualized underwater robot system
CN104330410A (en) * 2014-11-04 2015-02-04 无锡北斗星通信息科技有限公司 Crop pest detection system positioned on unmanned aerial vehicle

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108718709A (en) * 2018-06-05 2018-11-02 宁波大学 Automate strawberry picking machine

Also Published As

Publication number Publication date
CN104704990A (en) 2015-06-17
CN105875066A (en) 2016-08-24
CN104704990B (en) 2016-09-14

Similar Documents

Publication Publication Date Title
Chen et al. Counting apples and oranges with deep learning: A data-driven approach
Payne et al. Estimation of mango crop yield using image analysis–segmentation method
Oberti et al. Selective spraying of grapevines for disease control using a modular agricultural robot
Tian et al. Development of a precision sprayer for site-specific weed management
Stajnko et al. Estimation of number and diameter of apple fruits in an orchard during the growing season by thermal imaging
Sanz et al. Relationship between tree row LIDAR-volume and leaf area density for fruit orchards and vineyards obtained with a LIDAR 3D Dynamic Measurement System
Zhou et al. Using colour features of cv.‘Gala’apple fruits in an orchard in image processing to predict yield
CA2740503C (en) Variable rate sprayer system and method of variably applying agrochemicals
US10568316B2 (en) Apparatus and methods for in-field data collection and sampling
Abbott et al. Growth of subterranean clover in relation to the formation of endomycorrhizas by introduced and indigenous fungi in a field soil
Li et al. Review on fruit harvesting method for potential use of automatic fruit harvesting systems
CN106258209B (en) A kind of olive fruit picking
EP2243353B1 (en) System and method for managing resource use
Hayashi et al. Robotic harvesting system for eggplants
US8150554B2 (en) Resource use management in yards and gardens
CN105787446A (en) Smart agricultural insect disease remote automatic diagnosis system
US7854108B2 (en) Agricultural robot system and method
Goward et al. Visible-near infrared spectral reflectance of landscape components in western Oregon
Yu et al. Automatic image-based detection technology for two critical growth stages of maize: Emergence and three-leaf stage
CN106406403B (en) A kind of agriculture managing and control system based on augmented reality
US8321365B2 (en) Horticultural knowledge base for managing yards and gardens
CN106200683B (en) Unmanned plane plant protection system and plant protection method
Matese et al. Technology in precision viticulture: A state of the art review
Räsänen et al. Pollen deposition in mosses and in a modified ‘Tauber trap’from Hailuoto, Finland: what exactly do the mosses record?
Hall et al. Optical remote sensing applications in viticulture‐a review

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination