CN112715159A - Automatic citrus picking method and device based on mechanical arm - Google Patents
Automatic citrus picking method and device based on mechanical arm Download PDFInfo
- Publication number
- CN112715159A CN112715159A CN202011642676.2A CN202011642676A CN112715159A CN 112715159 A CN112715159 A CN 112715159A CN 202011642676 A CN202011642676 A CN 202011642676A CN 112715159 A CN112715159 A CN 112715159A
- Authority
- CN
- China
- Prior art keywords
- citrus
- picking
- orange
- image
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01D—HARVESTING; MOWING
- A01D46/00—Picking of fruits, vegetables, hops, or the like; Devices for shaking trees or shrubs
- A01D46/30—Robotic devices for individually picking crops
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01D—HARVESTING; MOWING
- A01D91/00—Methods for harvesting agricultural products
- A01D91/04—Products growing above the soil
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
Abstract
The invention discloses an automatic picking method and device of oranges based on mechanical arms, which determines a target area range according to current position information, searches for orange varieties corresponding to the target area range and mature orange color value intervals corresponding to the orange varieties, intercepts an orange image from an initial image and performs color detection to obtain current orange color values, judges whether a target orange corresponding to the orange image is a mature orange or not according to the current orange color values and the mature orange color value intervals, determines target branches corresponding to the target orange and determines a cutting position according to the initial image when the target orange is the mature orange, controls a first mechanical arm to move a picking basket to a lower area of the orange, controls a second mechanical arm to move a cutting device to the cutting position, controls the cutting device to cut the target branches to enable the target orange to fall into the picking basket, in order to reach the effect that oranges and tangerines were picked to intelligence, avoided appearing the mistake and plucked, caused the problem of having wasted.
Description
Technical Field
The invention relates to the technical field of automatic picking, in particular to an automatic citrus picking method and device based on a mechanical arm.
Background
Picking the mode of oranges and tangerines among the prior art, mostly picking through the manual work, but along with the increase of labour cost and the increase of orchard output, the mode of manual work picking is wasted time and energy, and efficiency hardly improves moreover. Therefore, in order to improve picking efficiency, the mode of picking oranges automatically through mechanical equipment still exists at present, however, the existing automatic picking cannot automatically identify the varieties and the maturity of oranges, immature oranges are easily picked in the process of picking oranges, and therefore mistaken picking is easy to occur, and waste is caused.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
The invention mainly aims to provide an automatic citrus picking method and device based on a mechanical arm, and aims to solve the technical problem that in the prior art, when citrus is picked automatically, wrong picking is easy to occur, and waste is caused.
In order to achieve the above object, the present invention provides a mechanical arm-based automated picking method for citrus fruit, which is based on an automated picking apparatus for citrus fruit, the automated picking apparatus for citrus fruit comprising: the automatic citrus picking method comprises the following steps of positioning a chip, camera equipment, mechanical arms, a cutting device and picking baskets, wherein each mechanical arm comprises a first mechanical arm and a second mechanical arm, each picking basket is arranged at the tail end of the first mechanical arm, the cutting device is arranged at the tail end of the second mechanical arm, and the automatic citrus picking method based on the mechanical arms comprises the following steps:
determining the current position information of the automatic citrus picking equipment through the positioning chip, and determining a target area range according to the current position information;
searching a citrus variety corresponding to the target area range, and searching a mature citrus color value interval corresponding to the citrus variety;
shooting an initial image through the camera equipment, and intercepting a citrus image from the initial image;
performing color detection on the citrus image to obtain a current citrus color value;
judging whether the target orange corresponding to the orange image is a mature orange or not according to the current orange color value and the mature orange color value interval;
when the target citrus is mature citrus, determining a target branch corresponding to the target citrus according to the initial image, and determining a cutting position according to the target branch;
controlling the first robotic arm to move the picking basket to the area below the citrus fruit and controlling the second robotic arm to move the cutting device to the cutting position;
and controlling the cutting device to cut the target branch so that the target citrus can fall into the picking basket.
Optionally, the automated citrus picking apparatus further comprises a basket;
the controlling the cutting device to cut the target branch so that the target citrus fruit falls into the picking basket further comprises:
searching the citrus volume corresponding to the citrus variety, and acquiring the picking basket volume of the picking basket;
determining the quantity of the citrus fruit according to the volume of the citrus fruit and the volume of the picking basket, and determining the target cutting times according to the quantity of the citrus fruit;
recording the cutting times of the cutting device, and comparing the cutting times with the target cutting times;
when the cutting times are consistent with the target cutting times, controlling the first mechanical arm to move the picking basket to an area above the storage basket, and moving the oranges in the picking basket into the storage basket for storage;
and carrying out zero clearing treatment on the cutting times.
Optionally, the positioning chip is a Beidou positioning chip;
before determining the current position information of the automatic citrus picking equipment through the positioning chip and determining the target area range according to the current position information, the method further comprises the following steps:
when an intelligent picking instruction input by a user is received, picking information is determined according to the intelligent picking instruction;
determining a picking position according to the picking information, and planning a path according to the picking position to obtain a picking path;
controlling the automatic citrus picking equipment to move according to the picking path through the Beidou positioning chip and the picking path;
controlling the citrus automatic picking device to enter a picking mode when the citrus automatic picking device moves to the picking position;
and in the picking mode, executing the step of determining the current position information of the automatic citrus picking equipment through the positioning chip and determining the range of a target area according to the current position information.
Optionally, the capturing an initial image by the imaging device and capturing a citrus image from the initial image includes:
shooting an initial image through the camera equipment, wherein the initial image is an image in an RGB format;
carrying out format conversion on the initial image to obtain an image to be processed, wherein the image to be processed is an image in an HSI format;
extracting hue characteristics and saturation characteristics from the image to be processed;
performing data fusion through a preset resonance excitation method according to the hue characteristic and the saturation characteristic to obtain a fusion image;
determining a foreground region based on a preset maximum inter-class difference method and the fused image;
and determining a citrus region in the initial image according to the foreground region, and intercepting a citrus image from the initial image according to the citrus region.
Optionally, the performing color detection on the citrus image to obtain a current citrus color value includes:
detecting the number of pixel points of the pixel points in the citrus image, and acquiring the color value of each pixel point;
calculating an average color value according to the color value and the number of the pixel points;
determining a current citrus color value from the averaged color value;
correspondingly, the judging whether the target orange corresponding to the orange image is the mature orange according to the current orange color value and the mature orange color value interval includes:
comparing the current orange color value with the mature orange color value interval to judge whether the current orange color value is in the mature orange color value interval or not, and obtaining a judgment result;
and judging whether the target orange corresponding to the orange image is a mature orange or not according to the judgment result.
Optionally, the searching for the citrus variety corresponding to the target region range and the searching for the mature citrus color value interval corresponding to the citrus variety include:
matching the target area range with a to-be-selected area range in a preset first mapping list to obtain a first matching result;
determining the citrus varieties corresponding to the target area range according to the first matching result;
matching the orange variety with a color value interval of the mature orange to be selected in a preset second mapping list to obtain a second matching result;
and determining a mature citrus color value interval corresponding to the citrus variety according to the second matching result.
Optionally, before searching for the citrus variety corresponding to the target region range and searching for the mature citrus color value interval corresponding to the citrus variety, the method further includes:
obtaining a region range to be selected and a citrus variety to be selected corresponding to citrus planted in the region range to be selected;
establishing a preset first mapping list according to the to-be-selected area range and the to-be-selected citrus variety;
acquiring a sample orange image corresponding to the orange variety to be selected, and determining a color value interval of mature oranges to be selected according to the sample orange image;
and establishing a preset second mapping list according to the orange variety to be selected and the color value interval of the mature orange to be selected.
In addition, in order to achieve the above object, the present invention further provides an automatic picking device for oranges based on a mechanical arm, comprising:
the positioning module is used for determining the current position information of the automatic citrus picking equipment through a positioning chip and determining a target area range according to the current position information;
the color value interval module is used for searching the citrus variety corresponding to the target area range and searching the mature citrus color value interval corresponding to the citrus variety;
the image processing module is used for shooting an initial image through camera equipment and intercepting a citrus image from the initial image;
the color detection module is used for carrying out color detection on the citrus image so as to obtain a current citrus color value;
the mature detection module is used for judging whether the target citrus corresponding to the citrus image is mature citrus according to the current citrus color value and the mature citrus color value interval;
the cutting position module is used for determining a target branch corresponding to the target citrus according to the initial image when the target citrus is mature citrus, and determining a cutting position according to the target branch;
the mechanical arm control module is used for controlling the first mechanical arm to move the picking basket to the area below the citrus fruit and controlling the second mechanical arm to move the cutting device to the cutting position;
and the picking control module is used for controlling the cutting device to cut the target branches so as to enable the target oranges to fall into the picking basket.
In addition, in order to achieve the above object, the present invention further provides an automatic picking device for citrus based on a mechanical arm, comprising: positioning chip, camera equipment, arm, cutting device and adopt the basket, the arm includes first arm and second arm, it is in to adopt the basket setting first arm is terminal, cutting device sets up the second arm is terminal, the automatic equipment of picking of oranges and tangerines still includes: a memory, a processor, and a robotic arm-based citrus automated picking program stored on the memory and operable on the processor, the robotic arm-based citrus automated picking program configured with steps to implement the robotic arm-based citrus automated picking method as described above.
In addition, to achieve the above object, the present invention further provides a storage medium having stored thereon a robot-based citrus automated picking program, which when executed by a processor, implements the steps of the robot-based citrus automated picking method as described above.
The invention provides a mechanical arm-based automatic citrus picking method, which comprises the steps of determining current position information of automatic citrus picking equipment through a positioning chip, determining a target area range according to the current position information, searching citrus varieties corresponding to the target area range, searching mature citrus color value intervals corresponding to the citrus varieties, shooting an initial image through camera equipment, intercepting a citrus image from the initial image, carrying out color detection on the citrus image to obtain a current citrus color value, judging whether target citrus corresponding to the citrus image is mature citrus or not according to the current citrus color value and the mature citrus color value intervals, determining a target branch corresponding to the target citrus according to the initial image when the target citrus is mature citrus, determining a cutting position according to the target branch, controlling a first mechanical arm to move a picking basket to a lower area of the citrus, and control second arm and remove cutting device to cutting position controls cutting device and cuts target branch to make the target oranges and tangerines fall into to adopt in the basket, in order to reach the effect that oranges and tangerines were picked to intelligence, avoided appearing the mistake and picked, caused extravagant problem.
Drawings
FIG. 1 is a schematic diagram of a robotic arm-based automated citrus picking apparatus in a hardware environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow diagram of a first embodiment of the robotic arm-based automated citrus picking process of the present invention;
FIG. 3 is a schematic structural view of an automated citrus picking apparatus according to an embodiment of the robotic-arm-based automated citrus picking process of the present invention;
fig. 4 is a schematic view of the area range of an orchard according to one embodiment of the mechanical arm-based citrus automatic picking method;
FIG. 5 is a schematic flow diagram of a second embodiment of the robotic arm-based automated citrus picking process of the present invention;
FIG. 6 is a schematic flow diagram of a third embodiment of a robotic arm-based automated citrus picking process according to the present invention;
fig. 7 is a functional block diagram of a first embodiment of the robotic-arm-based automated citrus picking apparatus of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a robotic arm-based citrus automated picking apparatus in a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the robotic arm-based automated citrus picking apparatus may comprise: positioning chip, camera equipment, arm, cutting device and adopt the basket, the arm includes first arm and second arm, it is in to adopt the basket setting first arm is terminal, cutting device sets up the second arm is terminal, the automatic equipment of picking of oranges and tangerines can also include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may comprise a Display screen (Display), an input unit such as keys, and the optional user interface 1003 may also comprise a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The Memory 1005 may be a Random Access Memory (RAM) Memory or a non-volatile Memory (e.g., a magnetic disk Memory). The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the apparatus configuration shown in fig. 1 does not constitute a limitation of robotic arm-based citrus automated picking apparatus and may include more or fewer components than those shown, or some components in combination, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a storage medium, may include an operating system, a network communication module, a user interface module, and a robotic arm-based citrus automated picking program.
In the robotic arm-based automated citrus picking apparatus shown in fig. 1, the network interface 1004 is used primarily for connecting to an external network for data communication with other network devices; the user interface 1003 is mainly used for connecting to a user equipment and performing data communication with the user equipment; the device calls the automatic citrus picking program based on the mechanical arm stored in the memory 1005 through the processor 1001 and executes the automatic citrus picking method based on the mechanical arm provided by the embodiment of the invention.
Based on the hardware structure, the embodiment of the automatic citrus picking method based on the mechanical arm is provided.
Referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of the automated picking method for citrus based on a mechanical arm according to the invention.
In a first embodiment, the automated citrus picking apparatus comprises: the automatic citrus picking method comprises the following steps of positioning a chip, camera equipment, mechanical arms, a cutting device and picking baskets, wherein each mechanical arm comprises a first mechanical arm and a second mechanical arm, each picking basket is arranged at the tail end of the first mechanical arm, the cutting device is arranged at the tail end of the second mechanical arm, and the automatic citrus picking method based on the mechanical arms comprises the following steps:
and step S10, determining the current position information of the automatic citrus picking equipment through the positioning chip, and determining the target area range according to the current position information.
It should be noted that the executing main body of the present embodiment may be a controller of an automated citrus picking apparatus, where the controller may be a remote controller, a local controller, or another apparatus capable of implementing the same or similar functions, and the present embodiment does not limit this.
It will be appreciated that picking baskets are provided at the end of the first robotic arm and cutting means are provided at the end of the second robotic arm, the position of the picking baskets being adjustable by control of the first robotic arm and the position of the cutting means being adjustable by control of the second robotic arm. The picking basket may be a picking basket of various shapes, which is not limited in this embodiment. The cutting device may be a blade type cutting device, a scissor type cutting device, or other types of cutting devices, which is not limited in this embodiment.
It should be understood that the image capturing apparatus, the first mechanical arm, the second mechanical arm, the cutting device, and the picking basket in this embodiment may be single or multiple, and this embodiment is not limited thereto. In the present embodiment, the above-described apparatuses are all described as a single example.
In a specific implementation, as shown in fig. 3, fig. 3 is a schematic structural diagram of an automated citrus picking apparatus, in which a is a camera, B is a storage basket, C is an apparatus main body, D is a picking basket, E is a cutting device, F is a first mechanical arm, and G is a second mechanical arm. The automatic citrus picking device further comprises a plurality of guide wheels, and the movement of the automatic citrus picking device is controlled through the guide wheels.
It will be appreciated that, because of the difference in color between mature citrus and immature citrus, for example, immature citrus is generally green and mature citrus is generally orange, that the color of citrus can be used to determine whether the citrus is mature, and that the citrus can be picked only when it is mature. Wherein, the color of the citrus of different varieties is different when the citrus is mature, therefore, in order to improve the detection accuracy, the citrus variety of the citrus can be determined firstly. Because this scheme can be used in the orchard, and fruit grower generally can plant by district when planting the fruit tree, plants the oranges of the same variety in a slice regional scope promptly, so the oranges and tangerines variety of the oranges and tangerines in the accessible mode of location in the present scope.
It should be understood that, in order to achieve a better positioning effect, the positioning chip in this embodiment is preferably a beidou positioning chip, the current position information of the automatic citrus picking device can be determined through the positioning chip, and then the current target area range where the automatic citrus picking device is located is determined according to the current position information.
In a specific implementation, as shown in fig. 4, fig. 4 is a schematic diagram of a region range of an orchard, for example, a planting region of the orchard may be divided into six region ranges as shown in the figure, i.e., O1, O2, O3, O4, O5, and O6, and a corresponding variety of citrus is planted in each region. The target area range where the automatic citrus picking equipment is located can be determined according to the current position information of the automatic citrus picking equipment and the current position information, and when the automatic citrus picking equipment is located in the O1 area range, the citrus varieties corresponding to the O1 area range can be searched.
And S20, searching the orange variety corresponding to the target area range, and searching the color value interval of the mature orange corresponding to the orange variety.
It should be understood that, since the varieties of the citrus fruit planted in different area ranges are different, the variety of the citrus fruit corresponding to the target area range can be found, that is, the variety of the citrus fruit planted in the target area range can be found. Then, because the colors of the mature oranges of different varieties are different, after the orange varieties are determined, the color value intervals of the mature oranges corresponding to the orange varieties can be searched.
It should be understood that, because the color of the mature citrus is not exactly the same, and the mature period of some citrus is longer and can change with time, the color interval of the mature citrus can be set for different varieties of citrus, and as long as the color value of the citrus is within the color interval of the mature citrus, the citrus can be judged to be the mature citrus.
And step S30, shooting an initial image through the camera equipment, and intercepting a citrus image from the initial image.
It should be appreciated that the citrus image may be captured from an initial image captured by the camera device and the citrus region determined from the initial image. The number of the citrus images may be one or multiple, which is not limited in this embodiment. For example, when one citrus image exists in the initial image, one citrus image can be cut out, and when a plurality of citrus images exist in the initial image, a plurality of citrus images can be cut out.
And step S40, carrying out color detection on the citrus image to obtain the current citrus color value.
It should be appreciated that after the citrus image is obtained, the citrus image may be color-detected to obtain a current citrus color value. Wherein, in order to reach better detection effect, can acquire the colour value of all pixel points in the oranges and tangerines image, then calculate their average colour value to confirm current oranges and tangerines colour value.
And step S50, judging whether the target orange corresponding to the orange image is mature orange or not according to the current orange color value and the mature orange color value interval.
It can be understood that, after determining current oranges and tangerines colour value and ripe oranges and tangerines colour value interval, can compare current oranges and tangerines colour value and ripe oranges and tangerines colour value interval to judge whether current oranges and tangerines colour value is in ripe oranges and tangerines colour value interval, and then judge whether the target oranges and tangerines that the oranges and tangerines image corresponds are ripe oranges and tangerines.
And step S60, when the target citrus is mature citrus, determining a target branch corresponding to the target citrus according to the initial image, and determining a cutting position according to the target branch.
It will be appreciated that where the target citrus fruit is mature citrus fruit, then the target citrus fruit may be harvested. When picking citrus, there are generally two picking modes, the first is single picking, i.e., one citrus at a time; and the other is multiple picking, i.e., a string of citrus fruit is picked at a time. Because this scheme is in order to improve the precision of picking, avoids the mistake to pluck, consequently, what this scheme adopted is the mode of single picking.
It will be appreciated that because each fruit has a corresponding branch, the fruit can be picked by cutting the branches to avoid fruit damage. Therefore, the target branch corresponding to the target citrus can be determined according to the initial image, and then the cutting position can be determined according to the target branch.
And step S70, controlling the first mechanical arm to move the picking basket to the lower area of the citrus fruit, and controlling the second mechanical arm to move the cutting device to the cutting position.
It should be understood that the first robotic arm may be controlled to move the picking basket to a lower region of the fruit, and in particular, to a lower region that is a predetermined distance from the fruit, where the predetermined distance may be set according to time conditions, such as 5CM, 10CM, etc., and the embodiment is not limited thereto.
It will be appreciated that the second robotic arm may be controlled to move the cutting device to the cutting position at the same time as the first robotic arm is controlled.
And step S80, controlling the cutting device to cut the target branch so that the target citrus can fall into the picking basket.
It should be appreciated that after the picking basket and the cutting device are moved to the above positions by the first and second robotic arms, the cutting device can be controlled to cut the target branch so that the target citrus fruit falls into the picking basket to achieve the intelligent picking effect.
In the embodiment, the current position information of the automatic orange picking device is determined through the positioning chip, the target area range is determined according to the current position information, the orange variety corresponding to the target area range is searched, the mature orange color value interval corresponding to the orange variety is searched, the initial image is shot through the camera device, the orange image is intercepted from the initial image, color detection is carried out on the orange image to obtain the current orange color value, whether the target orange corresponding to the orange image is mature orange or not is judged according to the current orange color value and the mature orange color value interval, when the target orange is mature orange, the target branch corresponding to the target orange is determined according to the initial image, the cutting position is determined according to the target branch, the first mechanical arm is controlled to move the picking basket to the lower area of the orange, and the second mechanical arm is controlled to move the cutting device to the cutting position, control cutting device cuts target branch to make the target oranges and tangerines fall into to adopt in the basket, in order to reach the effect that the oranges and tangerines were picked to the intelligence, avoided appearing the mistake and picked, caused extravagant problem.
In an embodiment, as shown in fig. 5, the second embodiment of the automated picking method for citrus based on mechanical arm according to the present invention is proposed based on the first embodiment, the automated picking apparatus for citrus further comprises a basket, and after the step S80, the method further comprises:
step S901, finding a citrus volume corresponding to the citrus variety, and obtaining a picking basket volume of the picking basket.
It will be appreciated that the same citrus species will have a relatively consistent citrus volume at the mature stage, whereas citrus species of different citrus species will have different citrus volumes at the mature stage. Therefore, after determining the citrus variety, the citrus volume corresponding to the citrus variety can be searched. Wherein the citrus volume is the average volume of citrus of the citrus variety at maturity.
It should be appreciated that since the position movement of the picking basket is controlled by the first robotic arm, the picking basket cannot be set too large in order to avoid excessive force on the first robotic arm, and cannot be set too small in order to avoid the robotic arm moving back and forth which would affect picking efficiency. Therefore, a picking basket of an appropriate size can be set, and the picking basket volume of the picking basket is acquired. The picking basket volume in this embodiment refers to the volumetric volume of the picking basket, since the picking basket is open at the upper portion.
Step S902, determining the quantity of the citrus fruit according to the volume of the citrus fruit and the volume of the picking basket, and determining the target cutting times according to the quantity of the citrus fruit.
It will be appreciated that after determining the fruit volume and picking basket volume, the amount of fruit that can be loaded by the picking basket can be determined based on the fruit volume and picking basket volume, and that if this amount is exceeded, fruit may spill. Therefore, during the picking process, when the number of picked oranges reaches the number of the oranges, the oranges in the picking basket can be moved into the storage basket for storage.
It will be appreciated that, since the present arrangement is for individual picking of citrus fruit, one citrus fruit falls into the picking basket for each cut performed by the cutting device. Therefore, the number of cuts by the cutting device corresponds to the number of the citrus fruit, and thus, after the number of the citrus fruit is determined, the target number of cuts can be determined according to the number of the citrus fruit.
And step S903, recording the cutting times of the cutting device, and comparing the cutting times with the target cutting times.
It will be appreciated that in the course of performing intelligent picking, the number of cuts by the cutting device may be recorded and compared to a target number of cuts.
And step S904, when the cutting times are consistent with the target cutting times, controlling the first mechanical arm to move the picking basket to the area above the storage basket, and moving the oranges in the picking basket into the storage basket for storage.
It will be appreciated that when the number of cuts corresponds to the target number of cuts, indicating that the citrus fruit in the picking basket is to be moved into the basket, the first robotic arm may be controlled to move the picking basket to the upper region of the basket and to move the citrus fruit in the picking basket into the basket for storage, wherein the transfer may be performed in a dumping manner. For example, the first robotic arm is controlled to invert the picking basket as it moves into the upper region of the basket to move citrus fruit in the picking basket into the basket for storage.
And step S905, carrying out zero clearing processing on the cutting times.
It should be appreciated that after the citrus fruit in the picking basket is moved into the basket, the cut count may be cleared for the next cycle count.
Further, the positioning chip is a beidou positioning chip, and before determining the current position information of the automatic orange picking device through the positioning chip and determining the target area range according to the current position information, the method further comprises:
when an intelligent picking instruction input by a user is received, picking information is determined according to the intelligent picking instruction; determining a picking position according to the picking information, and planning a path according to the picking position to obtain a picking path; controlling the automatic citrus picking equipment to move according to the picking path through the Beidou positioning chip and the picking path; controlling the citrus automatic picking device to enter a picking mode when the citrus automatic picking device moves to the picking position; and in the picking mode, executing the step of determining the current position information of the automatic citrus picking equipment through the positioning chip and determining the range of a target area according to the current position information.
It should be understood that the user may designate the automated citrus picking apparatus to different locations for picking, and upon receiving an intelligent picking instruction input by the user, may determine picking information according to the intelligent picking instruction, determine a picking location according to the picking information, and perform path planning according to the picking location to obtain a picking path. The picking positions are designated by a user, and can be one or multiple, and when the picking positions are multiple, the automatic citrus picking equipment is controlled to sequentially reach the picking positions for picking.
It can be understood that accessible big dipper location chip removes according to picking the route with the automatic equipment of picking of route control oranges and tangerines, when the automatic equipment of picking of oranges and tangerines removed to picking the position, and the automatic equipment of picking of control oranges and tangerines gets into picking the mode, under picking the mode, confirms the current position information of the automatic equipment of picking of oranges and tangerines through the location chip to according to the regional scope of current position information determination target.
In the embodiment, the picking basket volume of the picking basket is obtained by searching the citrus volume corresponding to the citrus variety; determining the quantity of the citrus fruit according to the volume of the citrus fruit and the volume of the picking basket, and determining the target cutting times according to the quantity of the citrus fruit; recording the cutting times of the cutting device, and comparing the cutting times with the target cutting times; when the cutting times are consistent with the target cutting times, controlling the first mechanical arm to move the picking basket to an area above the storage basket, and moving the oranges in the picking basket into the storage basket for storage; and carrying out zero clearing treatment on the cutting times. Can use rationally to pick the basket, when the oranges and tangerines quantity in picking the basket reaches a certain quantity, move into oranges and tangerines to the storing basket in and save, avoided the arm atress too big, also avoided oranges and tangerines to spill over, improved the efficiency that oranges and tangerines were picked, also avoided the waste of picking the in-process.
In an embodiment, as shown in fig. 6, the third embodiment of the automated picking method for citrus based on a mechanical arm according to the present invention is proposed based on the first embodiment or the second embodiment, and in this embodiment, the step S30 includes:
step S301, shooting an initial image by the image pickup apparatus, where the initial image is an image in an RGB format.
It should be understood that the image captured by the image capturing apparatus is generally an image in RGB format, and therefore, the initial image captured by the image capturing apparatus is an image in RGB format.
Step S302, carrying out format conversion on the initial image to obtain an image to be processed, wherein the image to be processed is an image in an HSI format.
It should be noted that the digital image collected by the camera is expressed in a red, green, blue (RGB) color system. The RGB color system is not dependent on hardware of an operating system, and does not accord with human visual characteristics, so that the RGB color system can be converted into a color system similar to human visual habits when describing the color characteristics.
In this embodiment, an HSI color system is selected for color description, and the HSI color system directly takes three quantities of color features: the hue H, the saturation S and the brightness I describe the color, and the color is relatively in line with the second-speed habit of people to the color. The method of converting the RGB color space into the HSI color space includes a sphere method, a cylinder method, a biconical method, and the like, which is not limited in this embodiment.
Step S303, extracting hue characteristics and saturation characteristics from the image to be processed.
Note that, since the image may include an image of an object such as a ground, weeds, and dead leaves, the citrus fruit may be partially covered, and in this case, the target and the background cannot be distinguished well only by the color tone feature. However, when the saturation image is processed, the target and the background have a large difference, and the image can be segmented by using the saturation characteristic because the ground is weak in illumination and low in saturation. However, since the image is divided only by the saturation and the immature fruit is treated as a target, the two must be organically combined. Linearly combining hue and saturation can be expressed as:
Fout＝αH+βS
wherein, alpha and beta are combination coefficients, and practice can be given by training generation or experience, and different parameter combinations are required to be provided according to different scenes. If there is more shadow on the object in the image, then α > β; if there is more gray background in the image, α < β should be made.
And S304, performing data fusion through a preset resonance excitation method according to the hue characteristic and the saturation characteristic to obtain a fusion image.
It should be understood that the saturation is mainly related to the purity of the color, considering that the hue parameter is mainly related to the color area the object has. Therefore, if the H value is small, indicating that the object is not in the target area, the weight of the S value should be reduced; if the S value is small, the color purity of the object is low, the object can be the earth surface or other backgrounds, and the weight of H is reduced; when both H and S have a larger value, indicating that the object has the target region hue feature with a larger purity, the respective weighting coefficients are to be enhanced. If the two parameters are mutually weighted, effective complementation can be realized by data fusion, and the method is called a resonance excitation method. The resonance excitation method has a better ability to highlight the target region, and can be expressed as:
Fout＝HS
and performing data fusion through a preset resonance excitation method according to the hue characteristic and the saturation characteristic to obtain a fused image.
And S305, determining a foreground region based on a preset maximum inter-class difference method and the fused image.
It should be understood that the foreground region and the background region may be determined based on a preset maximum inter-class difference method and a fused image, and specifically, according to the gray characteristics of the image, the image is divided into a background portion and a target portion, the background portion is used as the background region, and the target portion is used as the foreground region.
Step S306, determining a citrus region in the initial image according to the foreground region, and intercepting a citrus image from the initial image according to the citrus region.
It should be understood that, since the fused image is obtained by processing the initial image, and the object position features in the fused image are not changed, after the foreground region is determined, the citrus region may be determined in the initial image according to the foreground region, and then the citrus image may be cut out from the initial image according to the citrus region.
Further, the color detecting the citrus image to obtain a current citrus color value comprises:
detecting the number of pixel points of the pixel points in the citrus image, and acquiring the color value of each pixel point; calculating an average color value according to the color value and the number of the pixel points; determining a current citrus color value from the averaged color value;
correspondingly, the judging whether the target orange corresponding to the orange image is the mature orange according to the current orange color value and the mature orange color value interval includes:
comparing the current orange color value with the mature orange color value interval to judge whether the current orange color value is in the mature orange color value interval or not, and obtaining a judgment result; and judging whether the target orange corresponding to the orange image is a mature orange or not according to the judgment result.
It should be understood that, after obtaining the oranges and tangerines image, the pixel number of all pixels in the detectable oranges and tangerines image to obtain the colour value of each pixel, and then calculate the average colour value of each pixel according to the colour value of each pixel and the pixel number, regard average colour value as current oranges and tangerines colour value.
It can be understood that current citrus color value and ripe citrus color value interval can be compared to judge whether current citrus color value is in ripe citrus color value interval, and judge whether the target citrus that the citrus image corresponds is ripe citrus according to the judged result. For example, when the current citrus color value is within the mature citrus color value interval, the target citrus corresponding to the citrus image can be determined to be mature citrus. When present oranges and tangerines colour value is not in ripe oranges and tangerines colour value interval, can judge that the target oranges and tangerines that the oranges and tangerines image corresponds are not ripe oranges and tangerines.
Further, the searching for the citrus variety corresponding to the target area range and the searching for the color value interval of the mature citrus corresponding to the citrus variety include:
matching the target area range with a to-be-selected area range in a preset first mapping list to obtain a first matching result; determining the citrus varieties corresponding to the target area range according to the first matching result; matching the orange variety with a color value interval of the mature orange to be selected in a preset second mapping list to obtain a second matching result; and determining a mature citrus color value interval corresponding to the citrus variety according to the second matching result.
It should be understood that in order to improve the efficiency and accuracy of finding the color value ranges of citrus varieties and mature citrus. The method comprises the steps of establishing a preset first mapping list and a preset second mapping list in advance, determining a citrus variety corresponding to a target area range through the preset first mapping list and the target area range, and determining a color value interval of mature citrus corresponding to the citrus variety through the preset second mapping list and the citrus variety.
Further, before searching for the citrus variety corresponding to the target region range and searching for the mature citrus color value interval corresponding to the citrus variety, the method further includes:
obtaining a region range to be selected and a citrus variety to be selected corresponding to citrus planted in the region range to be selected; establishing a preset first mapping list according to the to-be-selected area range and the to-be-selected citrus variety; acquiring a sample orange image corresponding to the orange variety to be selected, and determining a color value interval of mature oranges to be selected according to the sample orange image; and establishing a preset second mapping list according to the orange variety to be selected and the color value interval of the mature orange to be selected.
It should be understood that the first mapping list may be established by obtaining a range of a to-be-selected area in an orchard, obtaining a variety of the to-be-selected citrus fruit corresponding to the citrus fruit planted in each range of the to-be-selected area, and establishing a preset first mapping list according to the range of the to-be-selected area and the variety of the to-be-selected citrus fruit, wherein a corresponding relationship between the range of the to-be-selected area and the variety of the to-be-selected citrus fruit is recorded in the preset first mapping list.
It should be understood that the second mapping list may be established by acquiring sample citrus images corresponding to a plurality of citrus varieties to be selected, where the sample citrus images are images of citrus in a mature period, and the larger the number of the sample citrus images, the better the number of the sample citrus images. Through carrying out color detection on the sample citrus image, counting and sorting detection results, finally determining a color value interval of the mature citrus to be selected, and establishing a preset second mapping list according to the color value interval of the citrus to be selected and the color value interval of the mature citrus to be selected, wherein the corresponding relation between the citrus to be selected and the color value interval of the mature citrus to be selected is recorded in the preset second mapping list.
In the embodiment, an initial image is shot by the camera device, and the initial image is an image in an RGB format; carrying out format conversion on the initial image to obtain an image to be processed, wherein the image to be processed is an image in an HSI format; extracting hue characteristics and saturation characteristics from the image to be processed; performing data fusion through a preset resonance excitation method according to the hue characteristic and the saturation characteristic to obtain a fusion image; determining a foreground region based on a preset maximum inter-class difference method and the fused image; and determining a citrus region in the initial image according to the foreground region, intercepting a citrus image from the initial image according to the citrus region, and accurately intercepting the citrus image through format conversion and the image processing mode to improve the image segmentation precision.
In addition, the present invention further provides a storage medium, on which a robot-based citrus automatic picking program is stored, which when executed by a processor implements the steps of the robot-based citrus automatic picking method as described above.
Since the storage medium adopts all technical solutions of all the embodiments, at least all the beneficial effects brought by the technical solutions of the embodiments are achieved, and no further description is given here.
In addition, referring to fig. 7, the present invention further provides a mechanical arm-based citrus automatic picking apparatus, including:
and the positioning module 10 is used for determining the current position information of the automatic citrus picking equipment through a positioning chip and determining the target area range according to the current position information.
And the color value interval module 20 is configured to find a citrus variety corresponding to the target area range, and find a color value interval of a mature citrus corresponding to the citrus variety.
And the image processing module 30 is used for shooting an initial image through the camera equipment and intercepting a citrus image from the initial image.
And the color detection module 40 is configured to perform color detection on the citrus image to obtain a current citrus color value.
And the mature detection module 50 is used for judging whether the target citrus corresponding to the citrus image is mature citrus according to the current citrus color value and the mature citrus color value interval.
And a cutting position module 60, configured to determine, when the target citrus fruit is a mature citrus fruit, a target branch corresponding to the target citrus fruit according to the initial image, and determine a cutting position according to the target branch.
A robot control module 70 for controlling the first robot to move picking baskets to the area beneath the citrus fruit and the second robot to move the cutting device to the cutting position.
And the picking control module 80 is used for controlling the cutting device to cut the target branches so as to enable the target oranges to fall into the picking baskets.
In the embodiment, the current position information of the automatic orange picking device is determined through the positioning chip, the target area range is determined according to the current position information, the orange variety corresponding to the target area range is searched, the mature orange color value interval corresponding to the orange variety is searched, the initial image is shot through the camera device, the orange image is intercepted from the initial image, color detection is carried out on the orange image to obtain the current orange color value, whether the target orange corresponding to the orange image is mature orange or not is judged according to the current orange color value and the mature orange color value interval, when the target orange is mature orange, the target branch corresponding to the target orange is determined according to the initial image, the cutting position is determined according to the target branch, the first mechanical arm is controlled to move the picking basket to the lower area of the orange, and the second mechanical arm is controlled to move the cutting device to the cutting position, control cutting device cuts target branch to make the target oranges and tangerines fall into to adopt in the basket, in order to reach the effect that the oranges and tangerines were picked to the intelligence, avoided appearing the mistake and picked, caused extravagant problem.
In an embodiment, the automatic citrus picking device based on the mechanical arm further comprises a storage module, which is used for searching the citrus volume corresponding to the citrus variety and acquiring the picking basket volume of the picking basket; determining the quantity of the citrus fruit according to the volume of the citrus fruit and the volume of the picking basket, and determining the target cutting times according to the quantity of the citrus fruit; recording the cutting times of the cutting device, and comparing the cutting times with the target cutting times; when the cutting times are consistent with the target cutting times, controlling the first mechanical arm to move the picking basket to an area above the storage basket, and moving the oranges in the picking basket into the storage basket for storage; and carrying out zero clearing treatment on the cutting times.
In one embodiment, the automated citrus picking apparatus based on a robotic arm further comprises a path module for determining picking information according to an intelligent picking instruction input by a user upon receiving the intelligent picking instruction; determining a picking position according to the picking information, and planning a path according to the picking position to obtain a picking path; controlling the automatic citrus picking equipment to move according to the picking path through the Beidou positioning chip and the picking path; controlling the citrus automatic picking device to enter a picking mode when the citrus automatic picking device moves to the picking position; and in the picking mode, executing the step of determining the current position information of the automatic citrus picking equipment through the positioning chip and determining the range of a target area according to the current position information.
In an embodiment, the image processing module 30 is further configured to capture an initial image by the image capturing apparatus, where the initial image is an image in an RGB format; carrying out format conversion on the initial image to obtain an image to be processed, wherein the image to be processed is an image in an HSI format; extracting hue characteristics and saturation characteristics from the image to be processed; performing data fusion through a preset resonance excitation method according to the hue characteristic and the saturation characteristic to obtain a fusion image; determining a foreground region based on a preset maximum inter-class difference method and the fused image; and determining a citrus region in the initial image according to the foreground region, and intercepting a citrus image from the initial image according to the citrus region.
In an embodiment, the color detection module 40 is further configured to detect the number of pixels of a pixel in the citrus image, and obtain a color value of each pixel; calculating an average color value according to the color value and the number of the pixel points; determining a current citrus color value from the averaged color value; the mature detection module 50 is further configured to compare the current citrus color value with the mature citrus color value interval, so as to determine whether the current citrus color value is within the mature citrus color value interval, and obtain a determination result; and judging whether the target orange corresponding to the orange image is a mature orange or not according to the judgment result.
In an embodiment, the color value interval module 20 is further configured to match the target region range with a region range to be selected in a preset first mapping list, so as to obtain a first matching result; determining the citrus varieties corresponding to the target area range according to the first matching result; matching the orange variety with a color value interval of the mature orange to be selected in a preset second mapping list to obtain a second matching result; and determining a mature citrus color value interval corresponding to the citrus variety according to the second matching result.
In an embodiment, the automatic picking device for oranges based on the mechanical arm further comprises a mapping list module, which is used for acquiring a to-be-selected area range and a to-be-selected orange variety corresponding to oranges planted in the to-be-selected area range; establishing a preset first mapping list according to the to-be-selected area range and the to-be-selected citrus variety; acquiring a sample orange image corresponding to the orange variety to be selected, and determining a color value interval of mature oranges to be selected according to the sample orange image; and establishing a preset second mapping list according to the orange variety to be selected and the color value interval of the mature orange to be selected.
Other embodiments or specific implementation methods of the automatic citrus picking device based on the mechanical arm can refer to the above embodiments, and are not described herein again.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on this understanding, the technical solutions of the present invention may be embodied in the form of software products stored in an estimator readable storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above, and including instructions for enabling an intelligent device (e.g., a mobile phone, an estimator, a robot-based citrus automatic picking device, or a network robot-based citrus automatic picking device, etc.) to perform the methods according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. An automated citrus picking method based on a mechanical arm, characterized in that the automated citrus picking method based on a mechanical arm is based on an automated citrus picking apparatus, the automated citrus picking apparatus comprising: the automatic citrus picking method comprises the following steps of positioning a chip, camera equipment, mechanical arms, a cutting device and picking baskets, wherein each mechanical arm comprises a first mechanical arm and a second mechanical arm, each picking basket is arranged at the tail end of the first mechanical arm, the cutting device is arranged at the tail end of the second mechanical arm, and the automatic citrus picking method based on the mechanical arms comprises the following steps:
determining the current position information of the automatic citrus picking equipment through the positioning chip, and determining a target area range according to the current position information;
searching a citrus variety corresponding to the target area range, and searching a mature citrus color value interval corresponding to the citrus variety;
shooting an initial image through the camera equipment, and intercepting a citrus image from the initial image;
performing color detection on the citrus image to obtain a current citrus color value;
judging whether the target orange corresponding to the orange image is a mature orange or not according to the current orange color value and the mature orange color value interval;
when the target citrus is mature citrus, determining a target branch corresponding to the target citrus according to the initial image, and determining a cutting position according to the target branch;
controlling the first robotic arm to move the picking basket to the area below the citrus fruit and controlling the second robotic arm to move the cutting device to the cutting position;
and controlling the cutting device to cut the target branch so that the target citrus can fall into the picking basket.
2. A robotic arm-based citrus automated picking process according to claim 1 wherein the citrus automated picking apparatus further comprises a basket;
the controlling the cutting device to cut the target branch so that the target citrus fruit falls into the picking basket further comprises:
searching the citrus volume corresponding to the citrus variety, and acquiring the picking basket volume of the picking basket;
determining the quantity of the citrus fruit according to the volume of the citrus fruit and the volume of the picking basket, and determining the target cutting times according to the quantity of the citrus fruit;
recording the cutting times of the cutting device, and comparing the cutting times with the target cutting times;
when the cutting times are consistent with the target cutting times, controlling the first mechanical arm to move the picking basket to an area above the storage basket, and moving the oranges in the picking basket into the storage basket for storage;
and carrying out zero clearing treatment on the cutting times.
3. The automated mechanical arm-based citrus picking method according to claim 1, wherein the positioning chip is a beidou positioning chip;
before determining the current position information of the automatic citrus picking equipment through the positioning chip and determining the target area range according to the current position information, the method further comprises the following steps:
when an intelligent picking instruction input by a user is received, picking information is determined according to the intelligent picking instruction;
determining a picking position according to the picking information, and planning a path according to the picking position to obtain a picking path;
controlling the automatic citrus picking equipment to move according to the picking path through the Beidou positioning chip and the picking path;
controlling the citrus automatic picking device to enter a picking mode when the citrus automatic picking device moves to the picking position;
and in the picking mode, executing the step of determining the current position information of the automatic citrus picking equipment through the positioning chip and determining the range of a target area according to the current position information.
4. A robotic arm based automated citrus picking process as claimed in claim 1 wherein said capturing an initial image by said camera and capturing a citrus image from said initial image comprises:
shooting an initial image through the camera equipment, wherein the initial image is an image in an RGB format;
carrying out format conversion on the initial image to obtain an image to be processed, wherein the image to be processed is an image in an HSI format;
extracting hue characteristics and saturation characteristics from the image to be processed;
performing data fusion through a preset resonance excitation method according to the hue characteristic and the saturation characteristic to obtain a fusion image;
determining a foreground region based on a preset maximum inter-class difference method and the fused image;
and determining a citrus region in the initial image according to the foreground region, and intercepting a citrus image from the initial image according to the citrus region.
5. A robotic arm based automated citrus picking process as claimed in claim 1 wherein said color sensing the citrus image to obtain current citrus color values comprises:
detecting the number of pixel points of the pixel points in the citrus image, and acquiring the color value of each pixel point;
calculating an average color value according to the color value and the number of the pixel points;
determining a current citrus color value from the averaged color value;
correspondingly, the judging whether the target orange corresponding to the orange image is the mature orange according to the current orange color value and the mature orange color value interval includes:
comparing the current orange color value with the mature orange color value interval to judge whether the current orange color value is in the mature orange color value interval or not, and obtaining a judgment result;
and judging whether the target orange corresponding to the orange image is a mature orange or not according to the judgment result.
6. A robot arm-based automated citrus picking process according to any one of claims 1 to 5 wherein said finding a citrus variety corresponding to said target area range and finding a mature citrus color value range corresponding to said citrus variety comprises:
matching the target area range with a to-be-selected area range in a preset first mapping list to obtain a first matching result;
determining the citrus varieties corresponding to the target area range according to the first matching result;
matching the orange variety with a color value interval of the mature orange to be selected in a preset second mapping list to obtain a second matching result;
and determining a mature citrus color value interval corresponding to the citrus variety according to the second matching result.
7. A robotic arm based automated citrus picking process as defined in claim 6 wherein, prior to locating a citrus variety corresponding to the target area and locating a mature citrus color value range corresponding to the citrus variety, further comprising:
obtaining a region range to be selected and a citrus variety to be selected corresponding to citrus planted in the region range to be selected;
establishing a preset first mapping list according to the to-be-selected area range and the to-be-selected citrus variety;
acquiring a sample orange image corresponding to the orange variety to be selected, and determining a color value interval of mature oranges to be selected according to the sample orange image;
and establishing a preset second mapping list according to the orange variety to be selected and the color value interval of the mature orange to be selected.
8. The utility model provides a device is picked in automation of oranges and tangerines based on arm which characterized in that, device includes is picked in automation of oranges and tangerines based on arm:
the positioning module is used for determining the current position information of the automatic citrus picking equipment through a positioning chip and determining a target area range according to the current position information;
the color value interval module is used for searching the citrus variety corresponding to the target area range and searching the mature citrus color value interval corresponding to the citrus variety;
the image processing module is used for shooting an initial image through camera equipment and intercepting a citrus image from the initial image;
the color detection module is used for carrying out color detection on the citrus image so as to obtain a current citrus color value;
the mature detection module is used for judging whether the target citrus corresponding to the citrus image is mature citrus according to the current citrus color value and the mature citrus color value interval;
the cutting position module is used for determining a target branch corresponding to the target citrus according to the initial image when the target citrus is mature citrus, and determining a cutting position according to the target branch;
the mechanical arm control module is used for controlling the first mechanical arm to move the picking basket to the area below the citrus fruit and controlling the second mechanical arm to move the cutting device to the cutting position;
and the picking control module is used for controlling the cutting device to cut the target branches so as to enable the target oranges to fall into the picking basket.
9. An automatic equipment of picking of oranges based on arm, its characterized in that, automatic equipment of picking of oranges includes: positioning chip, camera equipment, arm, cutting device and adopt the basket, the arm includes first arm and second arm, it is in to adopt the basket setting first arm is terminal, cutting device sets up the second arm is terminal, the automatic equipment of picking of oranges and tangerines still includes: a memory, a processor and a robotic arm-based citrus automated picking program stored on the memory and executable on the processor, the robotic arm-based citrus automated picking program when executed by the processor implementing the steps of the robotic arm-based citrus automated picking method of any one of claims 1 to 7.
10. A storage medium having stored thereon a robotic arm-based citrus automated picking program that, when executed by a processor, performs the steps of the robotic arm-based citrus automated picking method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011642676.2A CN112715159A (en) | 2020-12-30 | 2020-12-30 | Automatic citrus picking method and device based on mechanical arm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011642676.2A CN112715159A (en) | 2020-12-30 | 2020-12-30 | Automatic citrus picking method and device based on mechanical arm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112715159A true CN112715159A (en) | 2021-04-30 |
Family
ID=75609125
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011642676.2A Pending CN112715159A (en) | 2020-12-30 | 2020-12-30 | Automatic citrus picking method and device based on mechanical arm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112715159A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114766197A (en) * | 2022-04-14 | 2022-07-22 | 重庆市农业科学院 | Identification method of mature cabbages and cabbage picking method |
| CN114847011A (en) * | 2022-06-01 | 2022-08-05 | 上海非夕机器人科技有限公司 | Picking method, picking apparatus, computer device, storage medium, and program product |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008022737A (en) * | 2006-07-19 | 2008-02-07 | Kochi Univ Of Technology | Harvesting robot |
| CN105123127A (en) * | 2015-10-16 | 2015-12-09 | 北方民族大学 | Wolfberry picking robot and control method thereof |
| CN108064560A (en) * | 2016-11-14 | 2018-05-25 | 广东技术师范学院 | The automatic picker system of fruit and method based on Kinect depth of field cameras |
| CN109220226A (en) * | 2018-10-31 | 2019-01-18 | 哈尔滨理工大学 | Fruit automatic recognition classification and the orchard intellectualizing system of picking |
-
2020
- 2020-12-30 CN CN202011642676.2A patent/CN112715159A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008022737A (en) * | 2006-07-19 | 2008-02-07 | Kochi Univ Of Technology | Harvesting robot |
| CN105123127A (en) * | 2015-10-16 | 2015-12-09 | 北方民族大学 | Wolfberry picking robot and control method thereof |
| CN108064560A (en) * | 2016-11-14 | 2018-05-25 | 广东技术师范学院 | The automatic picker system of fruit and method based on Kinect depth of field cameras |
| CN109220226A (en) * | 2018-10-31 | 2019-01-18 | 哈尔滨理工大学 | Fruit automatic recognition classification and the orchard intellectualizing system of picking |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114766197A (en) * | 2022-04-14 | 2022-07-22 | 重庆市农业科学院 | Identification method of mature cabbages and cabbage picking method |
| CN114766197B (en) * | 2022-04-14 | 2024-03-12 | 重庆市农业科学院 | Cabbage picking method |
| CN114847011A (en) * | 2022-06-01 | 2022-08-05 | 上海非夕机器人科技有限公司 | Picking method, picking apparatus, computer device, storage medium, and program product |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhou et al. | Using colour features of cv.‘Gala’apple fruits in an orchard in image processing to predict yield | |
| CN112136505B (en) | Fruit picking sequence planning method based on visual attention selection mechanism | |
| CN109447945B (en) | Quick counting method for basic wheat seedlings based on machine vision and graphic processing | |
| CN110223349A (en) | A kind of picking independent positioning method | |
| CN105701829B (en) | A kind of bagging green fruit image partition method | |
| CN112715159A (en) | Automatic citrus picking method and device based on mechanical arm | |
| CN104239886B (en) | The extracting method on lawn and background line of demarcation based on graphical analysis | |
| CN110163810A (en) | A kind of image processing method, device and terminal | |
| CN104949981A (en) | Automatic detection method and system for cotton five-euphylla period | |
| CN114067207A (en) | Vegetable seedling field weed detection method based on deep learning and image processing | |
| CN113191334B (en) | Plant canopy dense leaf counting method based on improved CenterNet | |
| CN111199192A (en) | Method for detecting integral maturity of field red globe grapes by adopting parallel line sampling | |
| CN112990103A (en) | String mining secondary positioning method based on machine vision | |
| CN111462058A (en) | Method for quickly detecting effective ears of rice | |
| JP4961555B2 (en) | Method for locating target part of plant, target part locating device by the method, and working robot using the device | |
| Zhang et al. | Yield estimation of citrus fruit using rapid image processing in natural background | |
| Fernando et al. | Ai based greenhouse farming support system with robotic monitoring | |
| Al-Mashhadani et al. | Autonomous ripeness detection using image processing for an agricultural robotic system | |
| CN108961295A (en) | Purple soil image segmentation extracting method based on normal distribution H threshold value | |
| CN116863452A (en) | Plant disease identification method, storage medium, and identification system | |
| CN115937314A (en) | Camellia oleifera fruit growth posture detection method | |
| CN117036926A (en) | Weed identification method integrating deep learning and image processing | |
| CN114700941B (en) | Strawberry picking method based on binocular vision and robot system | |
| CN110232345A (en) | The program and weed identification device of weed identification model are generated using computer | |
| CN110111263A (en) | A kind of tobacco planting based on image procossing instructs system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210430 |