CN117495947B - Pineapple flower-dropping method, electronic equipment and computer readable storage medium - Google Patents
Pineapple flower-dropping method, electronic equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN117495947B CN117495947B CN202311374349.7A CN202311374349A CN117495947B CN 117495947 B CN117495947 B CN 117495947B CN 202311374349 A CN202311374349 A CN 202311374349A CN 117495947 B CN117495947 B CN 117495947B
- Authority
- CN
- China
- Prior art keywords
- flower
- pineapple
- information
- spray
- pose
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 241000234671 Ananas Species 0.000 title claims abstract description 101
- 235000007119 Ananas comosus Nutrition 0.000 title claims abstract description 99
- 238000000034 method Methods 0.000 title claims abstract description 44
- 241001244920 Eucomis bicolor Species 0.000 claims abstract description 124
- 238000005507 spraying Methods 0.000 claims abstract description 88
- 238000000605 extraction Methods 0.000 claims abstract description 11
- 239000007921 spray Substances 0.000 claims description 110
- 239000003814 drug Substances 0.000 claims description 34
- 239000007788 liquid Substances 0.000 claims description 20
- 238000010276 construction Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 13
- 241000521948 Acmella Species 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 239000000575 pesticide Substances 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 5
- 238000004891 communication Methods 0.000 description 6
- 238000003062 neural network model Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 238000005259 measurement Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 238000012377 drug delivery Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Manipulator (AREA)
Abstract
The application relates to the technical field of pineapple flower dropping, and in particular provides a pineapple flower dropping method, electronic equipment and a computer readable storage medium, wherein the method comprises the following steps: analyzing whether pineapple flower centers exist in the first image information based on a first recognition model trained in advance, and acquiring pose information when the pineapple flower centers exist in the first image information; when pineapple flower centers do not exist in the first image information, extracting pineapple leaf information according to the first image information based on a pre-trained pineapple leaf information extraction model, and acquiring pose information according to the pineapple leaf information; extracting a spraying scheme from a pre-constructed spraying scheme database according to pose information, and controlling a flower-spraying robot to perform flower-spraying treatment on pineapple flower centers according to the spraying scheme and the pose information; the method can acquire pose information of the pineapple flower heart when the pineapple flower heart cannot be accurately identified or can not be identified, so that the flower-pointing effect of the flower-pointing robot is effectively improved.
Description
Technical Field
The application relates to the technical field of pineapple flower dropping, in particular to a pineapple flower dropping method, electronic equipment and a computer readable storage medium.
Background
In the prior art, a pineapple flower-dropping robot is used for dropping pineapple flowers, and the work flow of the pineapple flower-dropping robot is as follows: the pineapple flower-pointing robot moves according to a preset map, after moving to the vicinity of the pineapple flower center needing flower-pointing, the pose information of the pineapple flower center is obtained according to the image information, and then the position of the spray head is adjusted according to the pose information of the pineapple flower center, so that the spray head is moved to the position right above the pineapple flower center needing flower-pointing, and flower-pointing processing is carried out on the pineapple flower center needing flower-pointing. Because the prior art needs to identify the pineapple flower heart and can analyze and acquire the pose information of the pineapple flower heart, and when the pineapple flower heart obliquely grows or the pineapple leaf grows abnormally, the pineapple leaf can shield the pineapple flower heart, namely the prior art cannot accurately identify or cannot identify the pineapple flower heart, the prior art has the problem that the pose information cannot be acquired or the acquired pose information cannot accurately reflect the actual pose of the pineapple flower heart due to the fact that the pineapple flower heart cannot be accurately identified or cannot be identified, so that spraying dead zones are generated in the process of spraying liquid medicine by a spray head, and the flower-spot effect of the pineapple flower-spot robot is poor.
In view of the above problems, no effective technical solution is currently available.
Disclosure of Invention
The application aims to provide a pineapple flower-pointing method, electronic equipment and a computer readable storage medium, which can acquire the pose relation of pineapple flower centers when the pineapple flower centers cannot be accurately identified or can not be identified, so that the flower-pointing effect of a flower-pointing robot is effectively improved.
In a first aspect, the present application provides a pineapple flower-spot method for positioning pose information of a pineapple flower core and performing flower-spot processing, which is applied to a flower-spot robot, the pineapple flower-spot method comprising the steps of:
Controlling the spot robot to reach the target position based on a preset spot map;
acquiring first image information, wherein the first image information is a depth image acquired when the spot flower robot reaches a target position;
analyzing whether pineapple flower centers exist in the first image information based on a first recognition model trained in advance, and acquiring pose information when the pineapple flower centers exist in the first image information;
When pineapple flower centers do not exist in the first image information, extracting pineapple leaf information according to the first image information based on a pre-trained pineapple leaf information extraction model, and acquiring pose information according to the pineapple leaf information;
Extracting a spraying scheme from a pre-constructed spraying scheme database according to pose information;
And controlling the flower-spotting robot to perform flower-spotting treatment on the pineapple flower cores according to the pesticide spraying scheme and the pose information.
According to the pineapple flower-pointing method, the pose information of the pineapple flower heart is directly obtained when the pineapple flower heart exists in the first image information, and the accurate pose of the pineapple flower heart is deduced by utilizing the pineapple leaf information when the pineapple flower heart does not exist in the first image information, namely the method can obtain the pose relation of the pineapple flower heart when the pineapple flower heart cannot be accurately identified or cannot be identified.
Optionally, the number of pineapple blades is multiple, the pose information includes position information and orientation information, the pineapple blade information includes blade profile information, and the step of obtaining the pose information according to the pineapple blade information includes:
acquiring construction line information of each pineapple leaf according to the leaf profile information;
And taking the position of the convergence point of at least two construction line information as position information and taking the unit vector or tangential extension direction of the construction line information at the convergence point as orientation information.
Optionally, the step of obtaining pose information according to pineapple leaf information includes:
And analyzing and acquiring pose information according to pineapple leaf information based on a second recognition model trained in advance.
The technical scheme is equivalent to acquiring the pose information of the pineapple flower heart by utilizing the neural network model, and the accuracy of the pose information acquired when the pineapple flower heart does not exist in the first image information can be effectively improved because the neural network model can be continuously trained and optimized and the pose information is acquired by utilizing the second recognition model according to the pineapple leaf information analysis.
Optionally, the step of extracting the spray scheme from the pre-constructed spray scheme database according to the pose information comprises the following steps:
Acquiring inclination angle information according to the pose information, wherein the inclination angle information is an angle of an included angle between the direction of the pineapple flower center and a horizontal plane;
and extracting the spraying scheme from a pre-constructed spraying scheme database according to the inclination angle information.
Optionally, if the inclination angle information is in a preset first threshold range, the spraying scheme is vertical downward spraying, if the inclination angle information is in a preset second threshold range, the spraying scheme is inclined spraying, if the inclination angle information is in a preset third threshold range, the spraying scheme rotates around the pineapple flower center to spray the medicine, the minimum value of the first threshold range is larger than the maximum value of the second threshold range, and the minimum value of the second threshold range is larger than the maximum value of the third threshold range.
Optionally, the flower-lighting robot includes a spray head, the inclination angle information is located in a first threshold range, and the step of controlling the flower-lighting robot to perform flower-lighting processing on the pineapple flower cores according to the spray scheme and the pose information includes:
Controlling the spray head to move according to the spray scheme and pose information corresponding to the inclination angle information, so that the distance between the spray head and the pineapple flower center is smaller than or equal to a preset distance threshold value and the spray head is positioned right above the pineapple flower center;
The spray head is controlled to spray the liquid medicine so as to perform the flower-lighting treatment on the pineapple flower cores.
Optionally, the flower-lighting robot includes a spray head, the inclination angle information is located in a second threshold range, and the step of controlling the flower-lighting robot to perform flower-lighting processing on the pineapple flower cores according to the spray scheme and the pose information includes:
controlling the spray head to move according to the spray scheme and pose information corresponding to the inclination angle information so that the spray head inclines towards the pineapple flower center and the distance between the spray head and the pineapple flower center is smaller than or equal to a preset distance threshold;
The spray head is controlled to spray the liquid medicine so as to perform the flower-lighting treatment on the pineapple flower cores.
Optionally, the flower-lighting robot includes a spray head, the inclination angle information is located in a third threshold range, and the step of controlling the flower-lighting robot to perform flower-lighting processing on the pineapple flower cores according to the spray scheme and the pose information includes:
controlling the spray head to move according to the spray scheme and pose information corresponding to the inclination angle information so that the distance between the spray head and the pineapple flower center is smaller than or equal to a preset distance threshold;
And controlling the spray head to rotate by taking the pineapple flower center as a rotation center according to the spray scheme and pose information corresponding to the inclination angle information, and controlling the spray head to spray liquid medicine in the rotation process so as to perform flower-spotting treatment on the pineapple flower center.
In a second aspect, the application provides an electronic device comprising a processor and a memory storing computer readable instructions which, when executed by the processor, perform the steps of the method as provided in the first aspect above.
In a third aspect, the application provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method as provided in the first aspect above.
As can be seen from the above, the pineapple flower method, the electronic device and the computer readable storage medium provided by the application can directly acquire the pose information of the pineapple flower when the pineapple flower heart exists in the first image information, and deduce the accurate pose of the pineapple flower heart by utilizing the pineapple leaf information when the pineapple flower heart does not exist in the first image information, namely, the method can acquire the pose relation of the pineapple flower heart when the pineapple flower heart cannot be accurately identified or cannot be identified, and because whether the pineapple flower heart exists in the first image information or not, the method can acquire the pose information of the pineapple flower heart, extract a spraying scheme from a spraying scheme database according to the pose information and control the spraying robot to perform the spot-spraying treatment on the pineapple flower heart according to the spraying scheme and the pose information, the technical scheme can effectively solve the problem that the pose relation cannot be acquired or the acquired pose relation cannot accurately reflect the actual pose of the pineapple flower heart due to the fact that the pineapple flower heart cannot be accurately identified, so that the situation that the spot-spraying robot effectively sprays the pineapple flower heart in the spot-spraying process of the pineapple flower heart is effectively avoided.
Drawings
Fig. 1 is a flowchart of a pineapple flower-lighting method according to an embodiment of the present application.
Fig. 2 is a schematic structural diagram of a spot flower robot according to an embodiment of the present application.
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Reference numerals: 1. a self-moving trolley; 2. a liquid medicine spraying assembly; 21. a spray head; 22. a medicine storage box; 23. a drug pump; 24. a drug delivery tube; 3. a mechanical arm; 4. a depth camera; 501. a processor; 502. a memory; 503. a communication bus.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by a person skilled in the art without making any inventive effort, are intended to be within the scope of the present application.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.
In a first aspect, as shown in fig. 1-2, the present application provides a pineapple flower-lighting method for positioning pose information of a pineapple flower core and performing flower-lighting processing, and the pineapple flower-lighting method is applied to a flower-lighting robot, and includes the following steps:
s1, controlling a spot robot to reach a target position based on a preset spot map;
s2, acquiring first image information, wherein the first image information is a depth image acquired when the spot flower robot reaches a target position;
S3, analyzing whether pineapple flower centers exist in the first image information based on a first recognition model trained in advance, and acquiring pose information when the pineapple flower centers exist in the first image information;
S4, when no pineapple flower heart exists in the first image information, extracting pineapple leaf information according to the first image information based on a pre-trained pineapple leaf information extraction model, and acquiring pose information according to the pineapple leaf information;
S5, extracting a spraying scheme from a pre-constructed spraying scheme database according to pose information;
and S6, controlling the flower-spotting robot to perform flower-spotting treatment on the pineapple flower cores according to the pesticide spraying scheme and the pose information.
The flower-lighting robot of this embodiment comprises a self-moving trolley 1, a liquid medicine spraying component 2, a mechanical arm 3 and a depth camera 4, wherein the liquid medicine spraying component 2 is arranged on the self-moving trolley 1, the mechanical arm 3 is arranged at the bottom of the self-moving trolley 1, a spray head 21 is arranged at the tail end of the mechanical arm 3, the mechanical arm 3 is used for driving the spray head 21 to move, the depth camera 4 is arranged at the rear side of the bottom of the self-moving trolley 1 in a forward inclined manner, and the depth camera 4 is used for collecting image information. The side of the linear forward direction of the self-moving trolley 1 is the front side of the self-moving trolley 1, and the side of the linear backward direction of the self-moving trolley 1 is the rear side of the self-moving trolley 1. Because the mechanical arm 3 is installed in the bottom of the self-moving trolley 1, the pineapple flower center can pass through the lower part of the self-moving trolley 1, and therefore the bottom of the self-moving trolley 1 is required to be higher than the top of the pineapple flower center, and the self-moving trolley 1 can be an AGV trolley or a trolley which can automatically navigate and move, such as an autonomous moving trolley. The liquid medicine spraying assembly 2 comprises a medicine storage box 22, a medicine pump 23 and a spray head 21, wherein the medicine storage box 22 is used for storing liquid medicine which needs to be used in the spot decoration treatment, the spray head 21 is connected with the medicine storage box 22 through a medicine delivery pipe 24, the medicine pump 23 is arranged on the medicine delivery pipe 24, and the medicine pump 23 can drive the liquid medicine in the medicine storage box 22 to flow unidirectionally towards the spray head 21 so as to spray the liquid medicine from the spray head 21. The mechanical arm 3 is installed at the bottom of the self-moving trolley 1, the spray head 21 of the liquid medicine spraying assembly 2 is installed at the tail end of the mechanical arm 3, and the mechanical arm 3 of the embodiment is a polar coordinate type mechanical arm or a multi-joint type mechanical arm and the like which can drive the spray head 21 to move in multiple degrees of freedom. The depth camera 4 is an existing camera, the working principle of which is not discussed in detail here, the depth camera 4 of this embodiment may be disposed forward on the rear side of the self-moving trolley 1, the depth camera 4 of this embodiment may also be disposed downward on the front side of the self-moving trolley 1, and the depth camera 4 is used to collect image information, which includes depth information.
The spot map in step S1 is a preset map, and the spot map may be a map constructed according to a high-definition image or measurement data collected by an unmanned aerial vehicle in a manual manner, or may be a map automatically generated according to a high-definition image or measurement data collected by an unmanned aerial vehicle based on existing map generation software. The target positions of this embodiment are positions where pineapple flower centers requiring flower-dropping are located, and it should be understood that a plurality of pineapple plants are planted in a pineapple planting field or a pineapple planting garden, i.e., the number of pineapple flower centers requiring flower-dropping is a plurality, so the flower-dropping map of this embodiment includes a plurality of target positions, each pineapple flower center requiring flower-dropping corresponding to one target position.
Step S2 obtains first image information by the depth camera 4, where the first image information in this embodiment is a depth image acquired when the spot robot reaches the target position. The first recognition model in the step S3 is a pre-trained model, and the first recognition model can analyze whether pineapple flower centers exist in the first image information, and obtain pose information when the pineapple flower centers exist in the first image information, that is, the first recognition model in the embodiment is equivalent to an integrated model of an existing target object recognition model and an existing pose acquisition model.
The pineapple leaf information extraction model in the step S4 is a pre-trained model, the pineapple leaf information extraction model is equivalent to the existing image feature extraction model, the pineapple leaf information extraction model can extract pineapple leaf information from the first image information, and the pineapple leaf information can reflect the contour of pineapple leaf and the growth direction of pineapple leaf. The workflow of step S4 is: firstly, pineapple leaf information is extracted from first image information by using a pineapple leaf information extraction model, and then pose information is obtained according to the pineapple leaf information. The working principle of the step S4 is as follows: a pineapple plant consists of a pineapple flower core and a plurality of pineapple leaves, wherein the pineapple flower core is positioned at the junction of the plurality of pineapple leaves, and the orientation of the pineapple flower core is the same as or highly similar to the growth orientation of the pineapple leaves at the junction because the information of the pineapple leaves can reflect the outline of the pineapple leaves and the growth orientation of the pineapple leaves, so that even if the pineapple flower core is shielded by the pineapple leaves, the embodiment can acquire pose information of the pineapple flower core by utilizing the pineapple leaves. Step S4 is equivalent to utilizing pineapple leaves to deduce the accurate pose of the pineapple flower core when the pineapple flower core cannot be identified. It should be understood that if the step S3 can determine pose information of the pineapple flower core, the step S4 is skipped and the step S5 is directly performed.
The spraying scheme database in step S5 is a pre-constructed database, in which a plurality of spraying schemes are stored, the spraying schemes are schemes for performing the spraying treatment on the pineapple flower centers, for example, the spraying schemes can be oblique spraying, vertical spraying, rotary spraying or horizontal spraying, so that the spraying schemes can reflect the pose of the spray head 21 when the pineapple flower centers are subjected to the spraying treatment, for example, the spraying schemes are vertical spraying, the spray head 21 is vertical downward and is located right above the pineapple flower centers when the pineapple flower centers are subjected to the spraying treatment, that is, the spraying schemes comprise a preset spraying path, and the spraying path is used for adjusting the pose of the spray head 21 before and after spraying. The working principle of the step S5 is as follows: because the pose information is the pose of the pineapple flower center, and the pose change of the pineapple flower center may cause the used spraying scheme to be changed, the step S5 needs to extract the spraying scheme corresponding to the pose information from the pre-constructed spraying scheme database according to the pose information.
The working principle of the step S6 is as follows: because the spraying scheme can reflect the pose of the spray head 21 when the pineapple flower center is subjected to the flower-spotting treatment, before the pineapple flower center is subjected to the flower-spotting treatment by the flower-spotting robot, the pose of the spray head 21 needs to be adjusted by the mechanical arm 3 according to the spraying scheme and pose information in step S6, for example, the spraying scheme comprises a preset spraying path which is used for adjusting the pose of the spray head 21 before spraying and after spraying, the starting position of the spraying path or the scaling of the spraying path is adjusted according to the pose information in step S6, and after the adjustment is completed, the pineapple flower center is subjected to the flower-spotting treatment according to the adjusted spraying path. In step S6, the posture of the nozzle 21 and the distance between the nozzle 21 and the pineapple flower center are adjusted, and then the chemical liquid is delivered to the nozzle 21 by the chemical pump 23.
The working principle of the embodiment is as follows: according to the pineapple flower-pointing method, the pose information of the pineapple flower heart is directly obtained when the pineapple flower heart exists in the first image information, and the accurate pose of the pineapple flower heart is deduced by utilizing the pineapple leaf information when the pineapple flower heart does not exist in the first image information, namely the method can obtain the pose relation of the pineapple flower heart when the pineapple flower heart cannot be accurately identified or cannot be identified.
In some embodiments, the number of pineapple blades is a plurality, the pose information includes position information and orientation information, the pineapple blade information includes blade profile information, and the step of obtaining the pose information from the pineapple blade information includes:
acquiring construction line information of each pineapple leaf according to the leaf profile information;
And taking the position of the convergence point of at least two construction line information as position information and taking the unit vector or tangential extension direction of the construction line information at the convergence point as orientation information.
The orientation information of this embodiment corresponds to the posture information. The blade profile information of this embodiment is the profile of the pineapple blade, the construction line information of this embodiment may be the continuous normal line of the profile of the pineapple blade, the construction line information of this embodiment may also be the continuous tangent line of the profile of the pineapple blade, since the blade profile information can reflect the left profile and the right profile of the pineapple blade, the construction line information of this embodiment may also be the line connected by a plurality of midpoints defined by the left profile and the right profile, and the construction line information of this embodiment corresponds to the substitution line of the pineapple blade. The working principle of the embodiment is as follows: since the pineapple flower center is located at the junction of the plurality of pineapple leaves, and the construction line information of the embodiment corresponds to the substitution line of the pineapple leaves, the embodiment can determine the pineapple flower center only by determining the convergence point of the construction line information according to at least two construction line information, wherein the position of the convergence point is the position information of the pineapple flower center, and since the orientation of the pineapple flower center is the same as or highly similar to the growth orientation of the pineapple leaves at the junction, the embodiment can take the unit vector or the tangential extension direction of the construction line information at the convergence point as the orientation information of the pineapple flower center. This embodiment corresponds to the use of specific control logic to obtain pose information for the pineapple flower heart.
In some embodiments, the step of obtaining pose information from pineapple leaf information includes:
And analyzing and acquiring pose information according to pineapple leaf information based on a second recognition model trained in advance.
The second recognition model of the embodiment is a pre-trained model, specifically, the embodiment trains the second recognition model by using an image in which no pineapple flower heart exists but the predicted position of the pineapple flower heart is marked, so the second recognition model of the embodiment can acquire pose information according to pineapple leaf information analysis. The embodiment is equivalent to obtaining the pose information of the pineapple flower heart by using the neural network model, and because the neural network model can be continuously trained and optimized, the embodiment obtains the pose information by using the second recognition model according to the pineapple leaf information analysis, so that the embodiment can effectively improve the accuracy of the pose information obtained when the pineapple flower heart does not exist in the first image information.
In some embodiments, step S5 comprises:
s51, acquiring inclination angle information according to pose information, wherein the inclination angle information is an angle of an included angle between the direction of the pineapple flower center and a horizontal plane;
S52, extracting a spraying scheme from a pre-constructed spraying scheme database according to the inclination angle information.
Since the pose information includes the position information and the orientation information, the step S51 may acquire the inclination angle information from the pose information. The working principle of this embodiment is similar to that of the above-described step S5 and will not be discussed in detail here. This example corresponds to the selection of a suitable spray regimen depending on the degree of inclination of the pineapple flower core.
In some embodiments, if the inclination angle information is within a preset first threshold range, the spray scheme is to spray the medicine vertically downwards, if the inclination angle information is within a preset second threshold range, the spray scheme is to spray the medicine obliquely, if the inclination angle information is within a preset third threshold range, the spray scheme rotates around the pineapple flower center to spray the medicine, the minimum value of the first threshold range is greater than the maximum value of the second threshold range, and the minimum value of the second threshold range is greater than the maximum value of the third threshold range. The first threshold range, the second threshold range and the third threshold range of this embodiment are all preset ranges, and the minimum value of the first threshold range is larger than the maximum value of the second threshold range, and the minimum value of the second threshold range is larger than the maximum value of the third threshold range, and it should be understood that those skilled in the art can adjust the first threshold range, the second threshold range and the third threshold range according to actual needs. The first threshold range of this embodiment is preferably 75 ° or more and 90 ° or less, the second threshold range of this embodiment is preferably 75 ° or less and 35 ° or more, and the second threshold range of this embodiment is preferably 35 ° or less.
In some embodiments, the flower-dispensing robot includes a spray head 21, the tilt angle information is within a first threshold range, and step S6 includes:
S61, controlling the spray head 21 to move according to the spray scheme and pose information corresponding to the inclination angle information, so that the distance between the spray head 21 and the pineapple flower center is smaller than or equal to a preset distance threshold value, and the spray head 21 is positioned right above the pineapple flower center;
and S61, controlling the spray head 21 to spray the liquid medicine so as to perform spot-flower treatment on the pineapple flower centers.
In some embodiments, the spot flower robot includes a spray head 21, the inclination angle information is within a second threshold range, and step S6 includes:
S61', controlling the spray head 21 to move according to the spray scheme and pose information corresponding to the inclination angle information, so that the spray head 21 inclines towards the pineapple flower center, and the distance between the spray head 21 and the pineapple flower center is smaller than or equal to a preset distance threshold;
S62', controlling the spray head 21 to spray the liquid medicine so as to perform spot-flower treatment on the pineapple flower cores.
In some embodiments, the spot flower robot includes a spray head 21, the inclination angle information is within a third threshold range, and step S6 includes:
S61'', controlling the spray head 21 to move according to the spray scheme and pose information corresponding to the inclination angle information so that the distance between the spray head 21 and the pineapple flower center is smaller than or equal to a preset distance threshold;
and S62'', controlling the spray head 21 to rotate by taking the pineapple flower center as a rotation center according to the spray scheme and the pose information corresponding to the inclination angle information, and controlling the spray head 21 to spray the liquid medicine in the rotation process so as to perform spot-flower processing on the pineapple flower center.
In step S62″, the rotation speed of the spray head 21 under the pineapple flower center is preferably smaller than that of the spray head 21 over the pineapple flower center to ensure that enough chemical liquid is sprayed to the side of the pineapple flower center away from the flower-dispensing robot, thereby further improving the flower-dispensing effect of the flower-dispensing robot.
According to the automatic flower-pointing method, the pose information of the pineapple flower heart is directly obtained when the pineapple flower heart exists in the first image information, and the accurate pose of the pineapple flower heart is deduced by utilizing the pineapple leaf information when the pineapple flower heart does not exist in the first image information, namely the method can obtain the pose relation of the pineapple flower heart when the pineapple flower heart cannot be accurately identified or cannot be identified.
In a second aspect, referring to fig. 3, fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application, where the electronic device includes: processor 501 and memory 502, the processor 501 and memory 502 being interconnected and in communication with each other by a communication bus 503 and/or other form of connection mechanism (not shown), the memory 502 storing computer readable instructions executable by the processor 501, which when executed by an electronic device, the processor 501 executes the computer readable instructions to perform the methods in any of the alternative implementations of the above embodiments to perform the functions of: s1, controlling a spot robot to reach a target position based on a preset spot map; s2, acquiring first image information, wherein the first image information is a depth image acquired when the spot flower robot reaches a target position; s3, analyzing whether pineapple flower centers exist in the first image information based on a first recognition model trained in advance, and acquiring pose information when the pineapple flower centers exist in the first image information; s4, when no pineapple flower heart exists in the first image information, extracting pineapple leaf information according to the first image information based on a pre-trained pineapple leaf information extraction model, and acquiring pose information according to the pineapple leaf information; s5, extracting a spraying scheme from a pre-constructed spraying scheme database according to pose information, and S6, controlling a flower-spraying robot to perform flower-spraying treatment on pineapple flower centers according to the spraying scheme and the pose information.
In a third aspect, embodiments of the present application further provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs a method in any of the alternative implementations of the above embodiments to implement the following functions: s1, controlling a spot robot to reach a target position based on a preset spot map; s2, acquiring first image information, wherein the first image information is a depth image acquired when the spot flower robot reaches a target position; s3, analyzing whether pineapple flower centers exist in the first image information based on a first recognition model trained in advance, and acquiring pose information when the pineapple flower centers exist in the first image information; s4, when no pineapple flower heart exists in the first image information, extracting pineapple leaf information according to the first image information based on a pre-trained pineapple leaf information extraction model, and acquiring pose information according to the pineapple leaf information; s5, extracting a spraying scheme from a pre-constructed spraying scheme database according to pose information, and S6, controlling a flower-spraying robot to perform flower-spraying treatment on pineapple flower centers according to the spraying scheme and the pose information. The computer readable storage medium may be implemented by any type or combination of volatile or non-volatile Memory devices, such as static random access Memory (Static Random Access Memory, SRAM for short), electrically erasable Programmable Read-Only Memory (ELECTRICALLY ERASABLE PROGRAMMABLE READ-Only Memory, EEPROM for short), erasable Programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM for short), programmable Read-Only Memory (PROM for short), read-Only Memory (ROM for short), magnetic Memory, flash Memory, magnetic disk, or optical disk.
As can be seen from the above, the pineapple flower method, the electronic device and the computer readable storage medium provided by the application are capable of directly obtaining the pose information of the pineapple flower when the pineapple flower heart exists in the first image information, deriving the accurate pose of the pineapple flower heart by using the pineapple leaf information when the pineapple flower heart does not exist in the first image information, namely, the method is capable of obtaining the pose relation of the pineapple flower heart when the pineapple flower heart cannot be accurately identified or cannot be identified, and because whether the pineapple flower heart exists in the first image information or not, the method is capable of obtaining the pose information of the pineapple flower heart, extracting the spraying scheme from the spraying scheme database according to the pose information, and controlling the spraying robot to perform the spraying processing on the pineapple flower heart according to the spraying scheme and the pose information, the embodiment is capable of effectively solving the problem that the pose relation cannot be obtained or the obtained pose relation cannot accurately reflect the actual pose of the pineapple flower heart due to the fact that the pineapple flower heart cannot be accurately identified, so that the situation that the spraying robot performs the spraying processing on the pineapple flower heart effectively occurs, and the effect of the spraying robot is prevented from being further.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. The above described embodiments of the apparatus are only illustrative, e.g. the above described division of units is only one logical function division, and there may be another division in practice, and e.g. multiple units or components may be combined or integrated into another robot, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some communication interface, device or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form.
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.
The above description is only an example of the present application and is not intended to limit the scope of the present application, and various modifications and variations will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (10)
1. The pineapple flower-spot method is used for positioning pose information of pineapple flower centers and carrying out flower-spot processing and is characterized by being applied to a flower-spot robot, and comprises the following steps of:
controlling the spot robot to reach a target position based on a preset spot map;
Acquiring first image information, wherein the first image information is a depth image acquired when the spot flower robot reaches a target position;
analyzing whether the pineapple flower centers exist in the first image information or not based on a first pre-trained recognition model, and acquiring the pose information when the pineapple flower centers exist in the first image information;
When the pineapple flower center does not exist in the first image information, extracting pineapple leaf information according to the first image information based on a pre-trained pineapple leaf information extraction model, and acquiring pose information according to the pineapple leaf information, wherein the pineapple leaf information can reflect the contour of pineapple leaves and the growth direction of the pineapple leaves;
extracting a spraying scheme from a pre-constructed spraying scheme database according to the pose information;
And controlling the flower-lighting robot to perform flower-lighting treatment on the pineapple flower cores according to the pesticide spraying scheme and the pose information.
2. The pineapple flower method according to claim 1, wherein a plurality of pineapple leaves are provided, the pose information includes position information and orientation information, the pineapple leaf information includes leaf profile information, and the step of obtaining the pose information according to the pineapple leaf information includes:
Acquiring construction line information of each pineapple leaf according to the leaf profile information;
And taking the position of the convergence point of at least two construction line information as the position information, and taking the unit vector or tangential extension direction of the construction line information at the convergence point as the orientation information.
3. The pineapple flower-nodding method of claim 1, wherein the step of obtaining the pose information from the pineapple leaf information comprises:
and analyzing and acquiring the pose information according to the pineapple leaf information based on a second recognition model trained in advance.
4. The pineapple flower-nodding method of claim 1, wherein the extracting the spray pattern from the pre-constructed spray pattern database according to the pose information comprises:
acquiring inclination angle information according to the pose information, wherein the inclination angle information is an angle of an included angle between the direction of the pineapple flower center and a horizontal plane;
and extracting a spraying scheme from a pre-constructed spraying scheme database according to the inclination angle information.
5. The pineapple flower-nodding method of claim 4, wherein the spray scheme is a vertical downward spray if the tilt angle information is within a preset first threshold range, wherein the spray scheme is an inclined spray if the tilt angle information is within a preset second threshold range, wherein the spray scheme rotates around the pineapple flower center if the tilt angle information is within a preset third threshold range, wherein a minimum value of the first threshold range is greater than a maximum value of the second threshold range, and wherein a minimum value of the second threshold range is greater than a maximum value of the third threshold range.
6. The pineapple flower-nodding method of claim 5, wherein the flower-nodding robot includes a spray head, the inclination angle information is within the first threshold range, and the step of controlling the flower-nodding robot to perform flower-nodding processing on the pineapple flower core according to the spray scheme and the pose information includes:
controlling the spray head to move according to a spray scheme corresponding to the inclination angle information and the pose information, so that the distance between the spray head and the pineapple flower center is smaller than or equal to a preset distance threshold value, and the spray head is positioned right above the pineapple flower center;
And controlling the spray head to spray the liquid medicine so as to perform flower-lighting treatment on the pineapple flower cores.
7. The pineapple flower-nodding method of claim 5, wherein the flower-nodding robot includes a spray head, the inclination angle information is located within the second threshold range, and the step of controlling the flower-nodding robot to perform flower-nodding processing on the pineapple flower core according to the spray scheme and the pose information includes:
controlling the spray head to move according to a spray scheme corresponding to the inclination angle information and the pose information, so that the spray head is inclined towards the pineapple flower center, and the distance between the spray head and the pineapple flower center is smaller than or equal to a preset distance threshold;
And controlling the spray head to spray the liquid medicine so as to perform flower-lighting treatment on the pineapple flower cores.
8. The pineapple flower-nodding method of claim 5, wherein the flower-nodding robot includes a spray head, the inclination angle information is located within the third threshold range, and the step of controlling the flower-nodding robot to perform flower-nodding processing on the pineapple flower centers according to the spray scheme and the pose information includes:
Controlling the spray head to move according to a spray scheme corresponding to the inclination angle information and the pose information so that the distance between the spray head and the pineapple flower center is smaller than or equal to a preset distance threshold;
And controlling the spray head to rotate by taking the pineapple flower center as a rotation center according to a medicine spraying scheme corresponding to the inclination angle information and the pose information, and controlling the spray head to spray medicine liquid in the rotation process so as to perform flower-lighting treatment on the pineapple flower center.
9. An electronic device comprising a processor and a memory storing computer readable instructions that, when executed by the processor, perform the steps in the method of any of claims 1-8.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, performs the steps of the method according to any of claims 1-8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311374349.7A CN117495947B (en) | 2023-10-23 | 2023-10-23 | Pineapple flower-dropping method, electronic equipment and computer readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311374349.7A CN117495947B (en) | 2023-10-23 | 2023-10-23 | Pineapple flower-dropping method, electronic equipment and computer readable storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117495947A CN117495947A (en) | 2024-02-02 |
CN117495947B true CN117495947B (en) | 2024-06-07 |
Family
ID=89675465
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311374349.7A Active CN117495947B (en) | 2023-10-23 | 2023-10-23 | Pineapple flower-dropping method, electronic equipment and computer readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117495947B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021219486A1 (en) * | 2020-05-01 | 2021-11-04 | Apisprotect Ltd | Systems and methods for monitoring pollination activity |
CN115617050A (en) * | 2022-12-02 | 2023-01-17 | 华南理工大学 | Automatic flower dotting method, robot, electronic equipment and storage medium |
CN115760991A (en) * | 2022-12-15 | 2023-03-07 | 华南理工大学 | Pineapple flower core positioning method, pesticide filling method, device, electronic equipment and medium |
CN115760990A (en) * | 2023-01-10 | 2023-03-07 | 华南理工大学 | Identification and positioning method of pineapple pistil, electronic equipment and storage medium |
CN116385780A (en) * | 2023-03-31 | 2023-07-04 | 滁州职业技术学院 | Chuzhou chrysanthemum classification method based on digital image processing technology |
CN116901070A (en) * | 2023-07-28 | 2023-10-20 | 青岛科技大学 | Path planning method, equipment and medium for flower pollination |
-
2023
- 2023-10-23 CN CN202311374349.7A patent/CN117495947B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021219486A1 (en) * | 2020-05-01 | 2021-11-04 | Apisprotect Ltd | Systems and methods for monitoring pollination activity |
CN115617050A (en) * | 2022-12-02 | 2023-01-17 | 华南理工大学 | Automatic flower dotting method, robot, electronic equipment and storage medium |
CN115760991A (en) * | 2022-12-15 | 2023-03-07 | 华南理工大学 | Pineapple flower core positioning method, pesticide filling method, device, electronic equipment and medium |
CN115760990A (en) * | 2023-01-10 | 2023-03-07 | 华南理工大学 | Identification and positioning method of pineapple pistil, electronic equipment and storage medium |
CN116385780A (en) * | 2023-03-31 | 2023-07-04 | 滁州职业技术学院 | Chuzhou chrysanthemum classification method based on digital image processing technology |
CN116901070A (en) * | 2023-07-28 | 2023-10-20 | 青岛科技大学 | Path planning method, equipment and medium for flower pollination |
Also Published As
Publication number | Publication date |
---|---|
CN117495947A (en) | 2024-02-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11596139B2 (en) | Method for autonomously weeding crops in an agricultural field | |
US9603300B2 (en) | Autonomous gardening vehicle with camera | |
US10845810B2 (en) | Method for autonomous detection of crop location based on tool depth and location | |
AU2019201537B2 (en) | Crop stand optimization systems, methods and apparatus | |
EP3907469A1 (en) | Automatic driving system for grain processing, and automatic driving method and path planning method therefor | |
JP6635910B2 (en) | Information processing device, water supply system, information processing system and program | |
CN103988824A (en) | Automatic targeting and spraying system based on binocular vision technology | |
CN113597874B (en) | Weeding robot and weeding path planning method, device and medium thereof | |
CN103309310B (en) | Method for monitoring operation of plug seedling transplanting robot based on laser scanning | |
CN113207675B (en) | Airflow vibration type facility crop automatic pollination device and method | |
Vikram | Agricultural Robot–A pesticide spraying device | |
Xiang et al. | Field‐based robotic leaf angle detection and characterization of maize plants using stereo vision and deep convolutional neural networks | |
CN117495947B (en) | Pineapple flower-dropping method, electronic equipment and computer readable storage medium | |
Fei et al. | Row‐sensing templates: A generic 3D sensor‐based approach to robot localization with respect to orchard row centerlines | |
CN112020981B (en) | Intelligent weeding robot system based on machine vision | |
CN115097833A (en) | Automatic obstacle avoidance method and system for pesticide application robot and storage medium | |
CN216982989U (en) | Automatic pollination device of air flow vibration type facility crop | |
Shamshiri et al. | An overview of visual servoing for robotic manipulators in digital agriculture | |
Luna-Santamaria et al. | LIDAR-based detection of furrows for agricultural robot autonomous navigation | |
TENG | Research on Grapevine Recognition, Manipulation and Winter Pruning Automation | |
Shaik et al. | 7 Autonomous Robot for Smart Agriculture Farming | |
TR2021019627A2 (en) | AUTONOMOUS PESTICIDE SYSTEM CONTROLLED BY ARTIFICIAL INTELLIGENCE | |
CN118230160A (en) | Weed center cutting recognition and laser weeding device | |
CN117044496A (en) | Broccoli selective harvesting robot and control method thereof | |
CN118235586A (en) | Machine vision-based pesticide spraying and fertilizer applying method and device for vine fruit trees |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant |