CN116295421A - Orchard variable drug application prescription chart generation method and device - Google Patents
Orchard variable drug application prescription chart generation method and device Download PDFInfo
- Publication number
- CN116295421A CN116295421A CN202310275626.2A CN202310275626A CN116295421A CN 116295421 A CN116295421 A CN 116295421A CN 202310275626 A CN202310275626 A CN 202310275626A CN 116295421 A CN116295421 A CN 116295421A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- orchard
- fruit tree
- map
- dimensional point
- 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
- 239000002420 orchard Substances 0.000 title claims abstract description 140
- 238000000034 method Methods 0.000 title claims abstract description 61
- 239000003814 drug Substances 0.000 title claims abstract description 7
- 229940079593 drug Drugs 0.000 title claims abstract description 7
- 235000013399 edible fruits Nutrition 0.000 claims abstract description 147
- 239000000575 pesticide Substances 0.000 claims abstract description 79
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 41
- 238000005192 partition Methods 0.000 claims abstract description 41
- 238000005457 optimization Methods 0.000 claims abstract description 28
- 238000001914 filtration Methods 0.000 claims abstract description 22
- 230000008569 process Effects 0.000 claims abstract description 22
- 238000012377 drug delivery Methods 0.000 claims abstract description 19
- 238000004590 computer program Methods 0.000 claims description 20
- 230000006870 function Effects 0.000 claims description 20
- 238000010586 diagram Methods 0.000 claims description 15
- 238000003860 storage Methods 0.000 claims description 13
- 238000005507 spraying Methods 0.000 claims description 9
- 238000013519 translation Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000009434 installation Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 3
- 238000013316 zoning Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 description 6
- 230000004044 response Effects 0.000 description 5
- 210000000038 chest Anatomy 0.000 description 4
- 238000010276 construction Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 239000007921 spray Substances 0.000 description 2
- 241000238631 Hexapoda Species 0.000 description 1
- 241000607479 Yersinia pestis Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 210000000481 breast Anatomy 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000035558 fertility Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01M—CATCHING, TRAPPING OR SCARING OF ANIMALS; APPARATUS FOR THE DESTRUCTION OF NOXIOUS ANIMALS OR NOXIOUS PLANTS
- A01M7/00—Special adaptations or arrangements of liquid-spraying apparatus for purposes covered by this subclass
- A01M7/0089—Regulating or controlling systems
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01M—CATCHING, TRAPPING OR SCARING OF ANIMALS; APPARATUS FOR THE DESTRUCTION OF NOXIOUS ANIMALS OR NOXIOUS PLANTS
- A01M99/00—Subject matter not provided for in other groups of this subclass
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
- G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
- G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
- G01C21/165—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation combined with non-inertial navigation instruments
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
- G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
- G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
- G01C21/165—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation combined with non-inertial navigation instruments
- G01C21/1652—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation combined with non-inertial navigation instruments with ranging devices, e.g. LIDAR or RADAR
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- 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
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/86—Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
-
- 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
- G01S19/45—Determining position by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement
-
- 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
- G01S19/45—Determining position by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement
- G01S19/47—Determining position by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement the supplementary measurement being an inertial measurement, e.g. tightly coupled inertial
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Automation & Control Theory (AREA)
- Environmental Sciences (AREA)
- Zoology (AREA)
- Wood Science & Technology (AREA)
- Software Systems (AREA)
- Geometry (AREA)
- Pest Control & Pesticides (AREA)
- Insects & Arthropods (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Computer Graphics (AREA)
- Electromagnetism (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention relates to the technical field of variable drug delivery, and provides a method and a device for generating an orchard variable drug delivery prescription graph, wherein the method comprises the following steps: acquiring point cloud information of an orchard environment and longitude and latitude information of a calibration ball in the orchard by using a scanning device; in the acquisition process, constructing an orchard three-dimensional point cloud map based on point cloud information by utilizing an SLAM algorithm and an SLAM map optimization model, and filtering ground point cloud to obtain a three-dimensional point cloud model of the fruit tree; dividing a three-dimensional point cloud model of the fruit tree by using a clustering algorithm, constructing a boundary frame to determine longitude and latitude information of the fruit tree, and reconstructing the three-dimensional point cloud model of the fruit tree to obtain the area density of the canopy partition volume and canopy partition leaf of the fruit tree; calculating a pesticide application prescription value of each canopy partition based on the volume and leaf area density of the canopy partition; and importing the calibration sphere longitude and latitude information, the orchard three-dimensional point cloud map, the fruit tree longitude and latitude information and the fruit tree variable pesticide application prescription value into a GIS system to generate an orchard variable pesticide application prescription map. The method can meet the requirement of diversified drug application.
Description
Technical Field
The invention belongs to the technical field of variable pesticide application, and particularly relates to a method, a device, computer equipment and a storage medium for generating an orchard variable pesticide application prescription chart.
Background
The fruit tree industry is one of the most important industries in many areas of China, and provides important power for the development of agricultural economy. The traditional orchard application mode generally adopts a rough continuous spraying strategy, but the pesticide effectively deposited on the target fruit tree by the application mode is less than 30%, so that the pesticide utilization rate is low, the fog drop drifting residue is serious, and the problems of environmental pollution, fruit quality degradation, ecological system unbalance and the like are easily caused.
In order to solve the problems and realize accurate pesticide application in orchards, variable pesticide application technology is mostly adopted at present. However, the existing orchard variable pesticide application technology usually adopts a real-time sensor to detect the position, volume, leaf area density and the like of the fruit tree canopy to perform variable operation. The following problems are likely to occur: the performance requirement on the non-contact sensor is high, and a certain delay exists in the response time of the application. Meanwhile, the deviation of the sprayer route can cause the failure to acquire accurate fruit tree canopy information, and the variable decision feature is single, so that the application requirements of diversified pesticide application cannot be met.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a method, apparatus, computer device, and storage medium for an orchard variable drug delivery prescription map that can improve response speed and meet diversified drug delivery requirements.
The invention provides a method for an orchard variable drug delivery prescription map, which comprises the following steps:
acquiring point cloud information of an orchard environment and longitude and latitude information of a calibration ball in the orchard by using a scanning device;
in the acquisition process, constructing an orchard three-dimensional point cloud map based on the point cloud information by utilizing an SLAM algorithm and an SLAM map optimization model, and filtering ground point clouds in the orchard three-dimensional point cloud map to obtain a fruit tree three-dimensional point cloud model;
dividing the three-dimensional point cloud model of the fruit tree by using a clustering algorithm to construct a boundary box of the three-dimensional point cloud model of the fruit tree, determining longitude and latitude information of the fruit tree according to the boundary box, and reconstructing the three-dimensional point cloud model of the fruit tree to obtain the area and the leaf area density of a canopy partition of the fruit tree;
calculating the pesticide application prescription value of each canopy partition based on the canopy partition volume and the canopy partition leaf area density to obtain a fruit tree variable pesticide application prescription value;
and importing the calibration sphere longitude and latitude information, the orchard three-dimensional point cloud map, the fruit tree longitude and latitude information and the fruit tree variable pesticide application prescription value into a GIS system to generate an orchard variable pesticide application prescription map.
In one embodiment, in the collecting process, constructing an orchard three-dimensional point cloud map based on the point cloud information by using a SLAM algorithm and a SLAM graph optimization model includes:
in the acquisition process, the acquired point cloud information is subjected to reprojection and converted into a depth image, and the ground point cloud is filtered according to the included angle between adjacent points in the depth image, and the noise point cloud is filtered by traversing the included angle between the computing point cloud and the neighborhood point;
estimating the pose of the point cloud by using a laser odometer model, and storing the point cloud under a world coordinate system by using a voxel grid method in combination with the estimated pose to obtain an orchard three-dimensional point cloud map with geographic position information;
and optimizing the three-dimensional point cloud map of the orchard by using a back-end diagram optimization model.
In one embodiment, the laser odometer model is represented as follows:
wherein X represents pose;
representing a key point cloud extracted from a new frame of point cloud; ρ(s) is a loss function; lerp represents an interpolation function; n is n i Is->
A normal to the neighborhood; />
Is a lidar measurement; />
Is a local point cloud map; alpha i Is a linear interpolation pose, a, between a start pose and an end pose i (s) is a neighborhood planarization function; c (C) loc (X) is a position consistency function, expressed as +.>
C vel (X) is a speed consistency function, expressed as
R b And t b Is the rotation and translation of the initial pose, R e And t e Ending the rotation and translation of the pose;
the back-end graph optimization model is expressed as follows:
wherein,,
and->
Is a trunk point cloud factor,/->
C n Representing a trunk point cloud.
In one embodiment, after the trunk point cloud set extracts the feature dot cloud of the chest height of the fruit tree of the orchard three-dimensional point cloud map through an European clustering algorithm, the feature dot cloud belonging to the chest height of the same fruit tree is segmented by using a judgment formula, and the judgment formula is as follows:
wherein Δd ij Is the distance between the centers of the characteristic dot clouds i and j; Δd max The distance between the centers of the characteristic dot clouds i and j is the maximum value; r is the radius of the feature circle; Δt (delta t) ij Is the observed time difference of the feature circles i and j; a and b are constants.
In one embodiment, the filtering the ground point cloud in the three-dimensional point cloud map of the orchard to obtain the three-dimensional point cloud model of the fruit tree includes:
and filtering the ground point cloud in the three-dimensional point cloud map of the orchard based on a rotation constraint method and the installation height of the laser radar in the scanning device, or fitting and filtering the ground point cloud in the three-dimensional point cloud map of the orchard to obtain a three-dimensional point cloud model of the fruit tree.
In one embodiment, the formula for the prescription of the cap zone administration is as follows:
wherein,,
the prescription value of the drug application of the canopy i partition of the fruit tree n; ρ leaf Zoning leaf area density for canopy i; v is the moving speed of the spraying device; a. b is the spraying flow coefficient; v (V) canopy The volume of the canopy i of the fruit tree is partitioned.
In one embodiment, the importing the calibration sphere longitude and latitude information, the orchard three-dimensional point cloud map, the fruit tree longitude and latitude information and the fruit tree variable pesticide application prescription value into a GIS system to generate an orchard variable pesticide application prescription map includes:
registering the satellite map with the three-dimensional point cloud map of the orchard based on the position of the calibration sphere point cloud model in the three-dimensional point cloud map of the orchard and the geographic position in the satellite map corresponding to the longitude and latitude information of the calibration sphere, so as to obtain a geographic information map layer and a ground object space map layer;
creating XYZ/prescription value data according to the longitude and latitude information of the fruit tree and the pesticide application prescription value of each canopy partition in the fruit tree variable pesticide application prescription value, constructing a columnar voxel grid by using a spatial interpolation algorithm based on the XYZ/prescription value data, expressing a fruit tree canopy model by using the columnar voxel grid, and adjusting the height of the columnar voxel grid to obtain a voxel grid layer;
and the voxel grid layer, the geographic information layer and the ground object space layer are led into a GIS working space together to obtain an orchard variable pesticide application prescription diagram.
An orchard variable drug delivery prescription map apparatus comprising:
the acquisition module is used for acquiring point cloud information of an orchard environment and longitude and latitude information of a calibration ball in the orchard by using the scanning device;
the composition module is used for constructing an orchard three-dimensional point cloud map based on the point cloud information by utilizing an SLAM algorithm and an SLAM map optimization model in the acquisition process, and filtering ground point clouds in the orchard three-dimensional point cloud map to obtain a three-dimensional point cloud model of the fruit tree;
the reconstruction module is used for dividing the three-dimensional point cloud model of the fruit tree by using a clustering algorithm to construct a boundary box of the three-dimensional point cloud model of the fruit tree, determining longitude and latitude information of the fruit tree according to the boundary box, and reconstructing the three-dimensional point cloud model of the fruit tree to obtain the area density of the canopy subareas and the area density of the canopy subareas of the fruit tree;
the pesticide application calculation module is used for calculating pesticide application prescription values of all canopy partitions based on the volume and the leaf area density of the canopy partitions to obtain fruit tree variable pesticide application prescription values;
the generation module is used for importing the calibration sphere longitude and latitude information, the orchard three-dimensional point cloud map, the fruit tree longitude and latitude information and the fruit tree variable pesticide application prescription value into a GIS system to generate an orchard variable pesticide application prescription map.
The invention also provides a computer device comprising a processor and a memory storing a computer program, the processor implementing the steps of the orchard variable drug delivery prescription-map method of any one of the above when executing the computer program.
The invention also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the orchard variable drug delivery prescription method of any one of the above.
According to the orchard variable pesticide application prescription map method, device, computer equipment and storage medium, the fruit canopy information such as canopy volume, canopy leaf area density and the like is efficiently and massively obtained by utilizing the SLAM algorithm and the improved SLAM map optimization model, and the pesticide application amount required by a target fruit tree is calculated by utilizing the fruit canopy information, so that the operation effect can be improved, the diversified pesticide application requirements can be met, and the response speed is improved. In addition, the three-dimensional GIS technology is adopted to manufacture an orchard variable pesticide application prescription map, so that the fruit tree variable pesticide application prescription map with geographic features, ground feature features and pesticide application features can be generated, and accurate target pesticide application can be realized.
Drawings
FIG. 1 is a flow chart of a method for applying a prescription chart of orchard variables in one embodiment.
Fig. 2 is a schematic diagram of a scanning method and a calibration ball placement position of a scanning device according to an embodiment.
FIG. 3 is a schematic diagram of an SLAM algorithm map optimization model in one embodiment.
Fig. 4 is a schematic diagram of a Bounding BOX of a fruit tree point cloud model in one embodiment.
Fig. 5 is a schematic diagram of reconstructing a point cloud model of a fruit tree in one embodiment.
Fig. 6 is a schematic diagram of reconstructing a point cloud model of a fruit tree in one embodiment.
Fig. 7 is a block diagram of an orchard variable drug delivery prescription device according to one embodiment.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
In one embodiment, as shown in fig. 1, there is provided a method for generating an orchard variable administration prescription map, including the steps of:
step S101, acquiring point cloud information of an orchard environment and longitude and latitude information of a calibration ball in the orchard by using a scanning device.
Specifically, a scanning device for scanning an orchard environment is firstly built on a self-propelled mobile robot platform, wherein the scanning device comprises sensor hardware such as a 16-line 3D laser radar, a 9-axis IMU, a GNSS receiver, an English-to-Chinese Jeston embedded computer system and the like. The GNSS receiver is connected with the 3D laser radar junction box, and the GNSS signals are resolved by using the network RTK differential service to obtain RTK-GNSS positioning information, so as to provide GNSS factors for the SLAM optimization model. The IMU is connected with the embedded computer and used for measuring pose information of the mobile robot platform and providing IMU factors for the SLAM graph optimization model. It is noted that when the hardware is installed, no obstacle is ensured within the vertical viewing angle (-15 deg. +15 deg.) of the laser beam of the 16-line lidar. And when the 9-axis IMU is installed, the IMU is preferentially installed right below the laser radar for conveniently performing external parameter calibration with the laser radar, and a lidar_alignment tool is used for calibrating.
And then, acquiring point cloud information of the structured orchard environment by using the scanning device. In order to make the distribution of the point clouds of the fruit trees uniform and dense, the scanning device in the orchard environment performs circular motion to collect data when passing through the fruit trees, and a specific scanning method is shown in fig. 2. The calibration balls are arranged at the boundary of the structured orchard plant protection operation area in advance, the arrangement of the calibration balls can be shown in fig. 2, and longitude and latitude information of the calibration balls can be obtained by using GNSS equipment when the orchard environment is scanned. In practical application, the laser reflection mark can be set to replace the calibration ball, and the longitude and latitude information of the laser reflection mark can be obtained to achieve the same effect.
Step S102, in the acquisition process, an orchard three-dimensional point cloud map is constructed based on point cloud information by utilizing an SLAM algorithm and an SLAM map optimization model, and a three-dimensional point cloud model of the fruit tree is obtained by filtering ground point clouds in the orchard three-dimensional point cloud map.
Specifically, in the acquisition process, that is, in the execution process of step S101, the front-end odometer model may be used to construct a local point cloud map in real time based on the acquired point cloud information to obtain a preliminary three-dimensional point cloud map of the orchard, and after the acquisition is completed, the three-dimensional point cloud map of the orchard is optimized by using the rear-end map optimization model. The method comprises the steps of running an SLAM algorithm based on an ROS operating system in an Injeston embedded computer system, and constructing an SLAM map optimization model to obtain a globally consistent three-dimensional point cloud map of an orchard with geographic position information. And then, filtering out the ground point cloud in the three-dimensional point cloud map of the orchard to obtain a three-dimensional point cloud model of the fruit tree. In the embodiment, aiming at the problems of difficult extraction of point cloud characteristic information, poor point cloud map construction precision and the like of a LiDAR-SLAM algorithm under a dynamic orchard scene, a laser odometer model with elastic characteristics is constructed based on a pose continuity principle, and a back-end map optimization model is constructed by introducing laser odometer factors, trunk point cloud factors and the like so as to improve the estimation precision of the pose of a point cloud frame in the dynamic environment, thereby improving the map construction robustness of the SLAM algorithm in a structured orchard environment.
In one embodiment, in the process of acquisition, constructing an orchard three-dimensional point cloud map based on point cloud information by using a SLAM algorithm and a SLAM map optimization model comprises the following steps:
and step 1, in the acquisition process, re-projecting and converting the acquired point cloud information into a depth image, filtering the ground point cloud according to the included angle between adjacent points in the depth image, and filtering the noise point cloud by traversing the included angle between the calculated point cloud and the neighborhood point.
Specifically, in the step, the laser radar scans at a rotation rate of 10Hz to obtain point cloud information of an orchard environment, and the 9-axis IMU and the GNSS receiver sample at 10KHz and 200Hz respectively. The point cloud information is preprocessed after sampling, and the method mainly comprises the steps of dividing the ground point cloud and filtering environmental noise. First, the original point cloud information is subjected to reprojection and converted into a depth image, and the depth image can be represented by an array, wherein coordinates are x and y, and z are converted into depth information. And judging whether the included angle between adjacent points in the depth image is smaller than 10 degrees or not to judge whether the included angle is the ground point cloud, and if the included angle is smaller than 10 degrees, determining the included angle as the ground point cloud and filtering. After the ground point cloud is filtered, depth-first traversal is performed on the depth image, namely, traversing a frame of point cloud from coordinates [0,0], calculating angles between the depth image and a neighborhood point by traversing 4 points in the neighborhood of the certain point, if the angles are larger than 60 degrees, the depth image is considered to be the same point cloud, and if the number of point cloud points in the point cloud is smaller than 30, the depth image is judged to be noise point cloud, and filtering is performed.
And 2, optimizing the pose of the point cloud by using a laser odometer model, and storing the point cloud under a world coordinate system by combining with the estimated pose to obtain the three-dimensional point cloud map of the orchard with geographic position information.
Specifically, the laser odometer model with elastic characteristics is built based on continuity of pose in a frame data acquisition process and discontinuity of pose in an inter-frame data acquisition process. The front-end laser odometer model is utilized, a first frame acquired by a laser radar is taken as an original local point cloud map, and the initial pose of one frame of point cloud data is adopted
And ending pose->
To estimate the pose of the frame, and the pose at the middle moment is processed by using a linear interpolation algorithm. Assume that the start pose of the nth frame is +.>
The n-1 th frame end pose is +.>
In theory, 2 poses are the same, so Proximity processing is performed on the poses by using a Proximity-constraint algorithm. Extracting local point cloud map by sampling algorithm
And a new frame point cloud->
Part of the point cloud->
As a key point cloud, pose optimization is performed based on the key point cloud, and pose change between a new frame of point cloud and a local point cloud map is estimated, and the laser odometer model in the embodiment is represented as follows:
wherein X represents pose;
representing a key point cloud extracted from a new frame of point cloud; ρ(s) is a loss function; lerp represents an interpolation function; n is n i Is->
A normal to the neighborhood; />
Is a lidar measurement; />
Is a local point cloud map; alpha i Is a linear interpolation pose, a, between a start pose and an end pose i (s) is a neighborhood planarization function; c (C) loc (X) is a position consistency function, expressed as +.>
C vel (X) is a speed consistency function, expressed as
R b And t b Is the rotation and translation of the initial pose, R e And t e The rotation and translation of the pose are ended.
And then, storing a world coordinate system point cloud map by using a voxel grid method, wherein each grid stores at most 20 points, so that the orchard three-dimensional point cloud map with geographic position information is constructed and obtained based on frame pose estimation. The construction process of the front-end odometer on the three-dimensional point cloud map of the orchard can be simply understood as that firstly, the collected first frame of point cloud is taken as an original local point cloud map, the next frame of point cloud is taken as a new frame of point cloud to carry out pose estimation to obtain the point cloud map, the point cloud map is taken as a new local point cloud map, the next frame of point cloud is taken as a new frame of point cloud to carry out pose estimation to obtain a new local point cloud map, and the like, each frame of point cloud collected later carries out pose estimation according to the mode, and the point cloud map obtained after the last frame of point cloud pose estimation is the three-dimensional point cloud map obtained initially. Meanwhile, in the pose estimation process, the approach processing is also required to be carried out on the starting pose of each frame of point cloud and the ending pose of the corresponding previous frame of point cloud.
And 3, optimizing the three-dimensional point cloud map of the orchard by using the back-end diagram optimizing model.
Specifically, after the preliminary three-dimensional point cloud map of the orchard is obtained in step 2, a back-end map optimization model is built, and in this embodiment, the SLAM map optimization model is shown in fig. 3. And the position and pose estimation error is minimized through the graph optimization model at the rear end, so that the graph construction precision is improved. The diagram optimization model of the embodiment mainly comprises a laser odometer factor, a trunk point cloud factor, an IMU factor, a GNSS factor and the like. The back-end graph optimization model is represented as follows:
wherein,,
and->
Is a trunk point cloud factor,/->
C n Representing a trunk point cloud.
In one embodiment, trunk point cloud C n Extracting feature dot clouds at the chest height of the fruit tree of the three-dimensional point cloud map of the orchard through an European clustering algorithm, and calculating the distance delta d between circle centers of the feature dot clouds ij And the difference value of the radius judges whether the fruit tree chest is the same as the fruit tree chestThe high feature dot cloud is divided into the same trunk dot cloud set C if the feature dot cloud is the same trunk dot cloud n 。
Wherein Δd ij Is the distance between the centers of the characteristic dot clouds i and j; Δd max The distance between the centers of the characteristic dot clouds i and j is the maximum value; r is the radius of the feature circle; Δt (delta t) ij Is the observed time difference of the feature circles i and j; a and b are constants.
In one embodiment, filtering the ground point cloud in the three-dimensional point cloud map of the orchard to obtain the three-dimensional point cloud model of the fruit tree comprises: and filtering the ground point cloud in the three-dimensional point cloud map of the orchard based on a rotation constraint method and the installation height of the laser radar in the scanning device, or fitting and filtering the ground point cloud in the three-dimensional point cloud map of the orchard to obtain the three-dimensional point cloud model of the fruit tree.
Specifically, after the global consistent three-dimensional point cloud map with geographic position information is obtained, if the structuring degree of the orchard is higher, the three-dimensional point cloud model of the fruit tree is obtained by filtering the ground point cloud based on a rotation constraint method and the laser radar mounting height. If the structuring degree of the orchard is low, the PLS algorithm, the RANSAC algorithm and the like can be adopted to fit the ground point cloud, the ground point cloud is filtered, and the three-dimensional point cloud model of the fruit tree can be obtained on a large scale after the ground point cloud in the three-dimensional point cloud map of the orchard is filtered.
And step S103, dividing the three-dimensional point cloud model of the fruit tree by using a clustering algorithm to construct a boundary box of the three-dimensional point cloud model of the fruit tree, determining longitude and latitude information of the fruit tree according to the boundary box, and reconstructing the three-dimensional point cloud model of the fruit tree to obtain the area density of the canopy subareas and the area density of the canopy subareas of the fruit tree.
Specifically, after a three-dimensional point cloud model of a fruit tree is obtained, the three-dimensional point cloud model of the fruit tree is segmented through a clustering algorithm, a boundin BOX (Bounding BOX) of the point cloud model of the fruit tree is constructed through an OBB algorithm, and a boundin BOX vertex coordinate A is extracted 1 A 2 B 1 B 2 As longitude and latitude information of the fruit tree, fig. 4 shows. Then, the Alpha-Shape algorithm or convex hull algorithm is adoptedAnd reconstructing a point cloud model of the fruit tree, wherein the crown layer of the fruit tree is divided into an upper partition, a middle partition and a lower partition as shown in fig. 5. The height of the fruit tree can be obtained by calculating the height of the fruit tree point cloud Bounding BOX, the canopy partition volume is obtained according to the reconstructed fruit tree point cloud model, and the canopy partition leaf area density can be obtained according to the functional relation between the canopy partition point cloud quantity and the canopy leaf area density, so that the acquisition of the fruit tree canopy information is realized.
And step S104, calculating the pesticide application prescription value of each canopy partition based on the volume and leaf area density of the canopy partition, and obtaining the variable pesticide application prescription value of the fruit tree.
Specifically, a fruit tree pesticide application rate model is introduced, and the pesticide application prescription value of each canopy partition is calculated based on the volume and leaf area density of the canopy partition. The fruit tree pesticide application rate model is as follows:
wherein,,
the prescription value of the drug application is in unit L for the canopy i partition of the fruit tree n; ρ leaf Zoning leaf area density for canopy i, unit m 2 /m 3 The method comprises the steps of carrying out a first treatment on the surface of the v is the moving speed of the spraying device, and the unit is m/s; a. b is a spraying flow coefficient, and is determined by a spray head flow model; v (V) canopy For the partition volume of the canopy i of the fruit tree, the unit is m 3 。
In addition, the fruit tree pesticide application amount model can also calculate the pesticide application amount required by the fruit tree based on multi-type decision information, including information such as fruit tree height, fruit tree breast diameter, fruit tree soil fertility, fruit tree diseases and insect pests and the like.
Step S105, importing the calibration sphere longitude and latitude information, the orchard three-dimensional point cloud map, the fruit tree longitude and latitude information and the fruit tree variable pesticide application prescription value into a GIS system to generate an orchard variable pesticide application prescription map.
Specifically, the orchard variable drug delivery prescription map of the embodiment is generated by utilizing a SLAM technology to carry out three-dimensional point cloud mapping on an orchard environment, obtaining fruit tree canopy information on a large scale as input of a fruit tree drug delivery model to calculate a prescription value, and combining longitude and latitude information of a fruit tree based on the prescription value.
In one embodiment, step S105 includes: registering the satellite map with the three-dimensional point cloud map of the orchard based on the position of the calibration sphere point cloud model in the three-dimensional point cloud map of the orchard and the geographic position in the satellite map corresponding to the longitude and latitude information of the calibration sphere, so as to obtain a geographic information layer and a ground object space layer; creating XYZ/prescription value data according to the longitude and latitude information of the fruit tree and the pesticide application prescription value of each canopy partition in the fruit tree variable pesticide application prescription value, constructing a columnar element grid by using a spatial interpolation algorithm based on the XYZ/prescription value data, representing a fruit tree canopy model by using the columnar element grid, and adjusting the height of the columnar element grid to obtain a voxel grid layer; and the voxel grid layer, the geographic information layer and the ground object space layer are led into a GIS working space together to obtain an orchard variable pesticide application prescription diagram.
Specifically, a GIS working space is firstly created, a spherical scene is newly created, after an orchard three-dimensional point cloud map is converted into a las file or a ply file, a point cloud cache is newly built, the orchard three-dimensional point cloud map file is set as a source file, a plane coordinate system is selected through projection setting, so that generation of the point cloud cache is achieved, and the point cloud cache is used as a three-dimensional slice cache layer to be loaded into the spherical scene. And newly creating an online map data source, selecting the type of the MapWorld data source, and loading the satellite map into the spherical scene. Setting an orchard three-dimensional point cloud map as a registration layer, using a satellite map as a reference layer, calibrating the position of a calibration sphere point cloud model in the orchard three-dimensional point cloud map by using a cross-shaped sight, and enabling longitude and latitude information of the calibration sphere to correspond to the geographic position in the satellite map, and carrying out geographic position alignment on the satellite map and the orchard three-dimensional point cloud map to realize registration of the orchard three-dimensional point cloud map and the satellite map, thereby obtaining a geographic information layer and a ground object space information layer.
Then, an xls data table is created according to longitude and latitude coordinates of all fruit tree Bounding BOXs in an orchard plant protection operation area and pesticide application prescription value information of all canopy partitions in fruit tree variable pesticide application prescription values, the xls data table is loaded into a working space, a spatial interpolation algorithm is utilized to interpolate a body element grid based on different canopy partition prescription values, so that a corresponding body element grid layer (prescription value information) is obtained, the fruit tree variable pesticide application prescription value is used as a characteristic value of a body element grid model, a columnar body element grid model is used for representing a fruit tree canopy model, and the height of the body element grid model is adjusted. In addition, the longitude and latitude coordinates of the fruit tree marking BOX and the pesticide application prescription value information of each canopy partition in the fruit tree variable pesticide application prescription value can be used for creating xls data tables, then the xls data tables are loaded into a working space, two-dimensional grids are constructed, a columnar model is constructed by three-dimensional stretching of the two-dimensional grids, the minimum and maximum heights are set, and the pesticide application prescription value information of each canopy partition is used as a characteristic value for rendering. Finally, all the layers are led into a GIS working space to obtain an orchard variable drug delivery prescription chart, as shown in fig. 6. Therefore, the orchard variable pesticide application prescription diagram is a three-dimensional voxel grid fruit tree variable pesticide application prescription diagram with three-dimensional characteristics, and comprises 3 layers of information such as a satellite map (geographic information), an orchard three-dimensional point cloud map (ground feature space information), a voxel grid map (prescription value information) and the like, and the spatial difference of fruit tree crowns is described by utilizing a voxel grid interpolation algorithm, so that accurate variable pesticide application can be performed on different subareas of fruit tree crowns.
Compared with the prior art, the orchard variable drug application prescription chart generation method has the following advantages:
1. the SLAM is improved based on the structural orchard environment, an SLAM image optimization model is improved, a laser odometer factor with elastic characteristics is adopted, based on the continuity of the pose in the process of collecting frame data and the discontinuity of the pose in the process of collecting inter-frame data, two-pose parameterization is adopted for one-frame point cloud data, and the trunk point cloud factor is introduced for further improving the modeling precision of a three-dimensional point cloud map of an orchard, so that information such as fruit tree height, canopy volume, canopy leaf area density and the like can be obtained efficiently and on a large scale, a multi-type pesticide application amount decision information fruit tree pesticide application amount calculation model is constructed, and a target fruit tree prescription value is calculated. On the other hand, the precision of crop information acquisition is improved, and the response speed of spraying is improved. Solves the problems of poor variable operation precision, limited spray response speed, single application dosage decision feature and the like of the current orchard variable application technology.
2. And (3) manufacturing an orchard variable pesticide application prescription map by adopting a three-dimensional GIS technology, and generating the fruit tree variable pesticide application prescription map with geographic features, ground feature features and pesticide application features by establishing 3 layers of information such as a satellite map, an orchard three-dimensional point cloud map, a voxel grid map and the like. And the orchard spraying area is positioned by adopting an OBB algorithm based on an orchard planting mode, so that target pesticide application can be accurately performed, and pesticide drift and ground loss are reduced. The volume element grid interpolation algorithm is adopted to process the fruit tree variable pesticide application prescription value, the spatial difference of the fruit tree canopy can be accurately described by utilizing the three-dimensional characteristics, and the accurate variable pesticide application can be carried out on different subareas of the fruit tree canopy.
In one embodiment, as shown in fig. 7, there is provided an orchard variable administration prescription map generating apparatus including:
the acquisition module 701 is configured to acquire point cloud information of an orchard environment and longitude and latitude information of a calibration ball in the orchard by using a scanning device
The composition module 702 is configured to construct an orchard three-dimensional point cloud map based on the point cloud information by using a SLAM algorithm and a SLAM graph optimization model in the collection process, and filter the ground point cloud in the orchard three-dimensional point cloud map to obtain a three-dimensional point cloud model of the fruit tree.
The reconstruction module 703 is configured to construct a bounding box of the three-dimensional point cloud model of the fruit tree by using a clustering algorithm to divide the three-dimensional point cloud model of the fruit tree, determine longitude and latitude information of the fruit tree according to the bounding box, and reconstruct the three-dimensional point cloud model of the fruit tree to obtain a canopy partition volume and a canopy partition leaf area density of the fruit tree.
And the pesticide application calculation module 704 is used for calculating pesticide application prescription values of all the canopy partitions based on the volume and leaf area density of the canopy partitions to obtain variable pesticide application prescription values of the fruit trees.
The generating module 705 is configured to introduce the calibration sphere longitude and latitude information, the orchard three-dimensional point cloud map, the fruit tree longitude and latitude information and the fruit tree variable pesticide application prescription value into the GIS system to generate an orchard variable pesticide application prescription map.
Specific limitations of the orchard variable drug delivery prescription device can be found in the above description of the method of applying the drug delivery prescription to the orchard variable, and will not be described in detail herein. All or part of each module in the orchard variable drug delivery prescription map device can be realized by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules. Based on such understanding, the present invention may implement all or part of the above-described embodiments of the method, or may be implemented by a computer program for instructing related hardware, where the computer program may be stored on a computer readable storage medium, and the computer program may implement the steps of the above-described embodiments of the method for applying a prescription to various orchard variables when executed by a processor. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc.
In one embodiment, a computer device is provided, which may be a server, including a processor, a memory, and a network interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is for storing data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by the processor to implement an orchard variable drug delivery prescription method. For example, a computer program may be split into one or more modules, one or more modules stored in memory and executed by a processor to perform the present invention. One or more modules may be a series of computer program instruction segments capable of performing particular functions to describe the execution of a computer program in a computer device. The processor may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like that is a control center of the computer device, connecting various parts of the overall computer device using various interfaces and lines.
The memory may be used to store the computer program and/or modules, and the processor may implement various functions of the computer device by running or executing the computer program and/or modules stored in the memory, and invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data (such as audio data, phonebook, etc.) created according to the use of the handset, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart Media Card (SMC), secure Digital (SD) Card, flash Card (Flash Card), at least one disk storage device, flash memory device, or other volatile solid-state storage device.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (10)
1. The method for generating the orchard variable drug delivery prescription graph is characterized by comprising the following steps of:
acquiring point cloud information of an orchard environment and longitude and latitude information of a calibration ball in the orchard by using a scanning device;
in the acquisition process, constructing an orchard three-dimensional point cloud map based on the point cloud information by utilizing an SLAM algorithm and an SLAM map optimization model, and filtering ground point clouds in the orchard three-dimensional point cloud map to obtain a fruit tree three-dimensional point cloud model;
dividing the three-dimensional point cloud model of the fruit tree by using a clustering algorithm to construct a boundary box of the three-dimensional point cloud model of the fruit tree, determining longitude and latitude information of the fruit tree according to the boundary box, and reconstructing the three-dimensional point cloud model of the fruit tree to obtain the area and the leaf area density of a canopy partition of the fruit tree;
calculating the pesticide application prescription value of each canopy partition based on the canopy partition volume and the canopy partition leaf area density to obtain a fruit tree variable pesticide application prescription value;
and importing the calibration sphere longitude and latitude information, the orchard three-dimensional point cloud map, the fruit tree longitude and latitude information and the fruit tree variable pesticide application prescription value into a GIS system to generate an orchard variable pesticide application prescription map.
2. The method of claim 1, wherein constructing an orchard three-dimensional point cloud map based on the point cloud information using a SLAM algorithm and a SLAM graph optimization model during the acquisition process comprises:
in the acquisition process, the acquired point cloud information is subjected to reprojection and converted into a depth image, and the ground point cloud is filtered according to the included angle between adjacent points in the depth image, and the noise point cloud is filtered by traversing the included angle between the computing point cloud and the neighborhood point;
estimating the pose of the point cloud by using a laser odometer model, and storing the point cloud under a world coordinate system by using a voxel grid method in combination with the estimated pose to obtain an orchard three-dimensional point cloud map with geographic position information;
and optimizing the three-dimensional point cloud map of the orchard by using a back-end diagram optimization model.
3. The method of claim 2, wherein the laser odometer model is represented as follows:
wherein X represents pose;
representing a key point cloud extracted from a new frame of point cloud; ρ(s) is a loss function; lerp represents an interpolation function; n is n i Is->
A normal to the neighborhood; />
Is a lidar measurement; />
Is a local point cloud map; alpha i Is a linear interpolation pose, a, between a start pose and an end pose i (s) is a neighborhood planarization function; c (C) loc (X) is a position consistency function, expressed as +.>
C vel (X) is a speed consistency function, expressed as
R b And t b Is the rotation and translation of the initial pose, R e And t e Ending the rotation and translation of the pose;
the back-end graph optimization model is expressed as follows:
wherein,,
and->
Is a trunk point cloud factor,/->
C n Representing a trunk point cloud.
4. The method according to claim 3, wherein after the trunk point cloud set extracts the feature dot cloud of the chest height of the fruit tree of the orchard three-dimensional point cloud map through an European clustering algorithm, the feature dot cloud belonging to the same chest height of the fruit tree is segmented by using a judgment formula, and the judgment formula is as follows:
wherein Δd ij Is the distance between the centers of the characteristic dot clouds i and j; Δd max The distance between the centers of the characteristic dot clouds i and j is the maximum value; r is the radius of the feature circle; Δt (delta t) ij Is the observed time difference of the feature circles i and j; a and b are constants.
5. The method according to claim 1, wherein the filtering the ground point cloud in the orchard three-dimensional point cloud map to obtain a three-dimensional point cloud model of the fruit tree comprises:
and filtering the ground point cloud in the three-dimensional point cloud map of the orchard based on a rotation constraint method and the installation height of the laser radar in the scanning device, or fitting and filtering the ground point cloud in the three-dimensional point cloud map of the orchard to obtain a three-dimensional point cloud model of the fruit tree.
6. The method of claim 1, wherein the formula for the prescription of the cap zone administration is as follows:
wherein,,
the prescription value of the drug application of the canopy i partition of the fruit tree n; ρ leaf Zoning leaf area density for canopy i; v is the moving speed of the spraying device; a. b is the spraying flow coefficient; v (V) canopy The volume of the canopy i of the fruit tree is partitioned.
7. The method of claim 1, wherein said importing the calibration sphere latitude and longitude information, the orchard three-dimensional point cloud map, the fruit tree latitude and longitude information, and the fruit tree variable administration prescription value into a GIS system to generate an orchard variable administration prescription map comprises:
registering the satellite map with the three-dimensional point cloud map of the orchard based on the position of the calibration sphere point cloud model in the three-dimensional point cloud map of the orchard and the geographic position in the satellite map corresponding to the longitude and latitude information of the calibration sphere, so as to obtain a geographic information map layer and a ground object space map layer;
creating XYZ/prescription value data according to the longitude and latitude information of the fruit tree and the pesticide application prescription value of each canopy partition in the variable pesticide application prescription value of the fruit tree, constructing a columnar voxel grid by using a spatial interpolation algorithm based on the XYZ/prescription value data, representing a fruit tree canopy model by using the columnar voxel grid, and adjusting the height of the columnar voxel grid to obtain a voxel grid layer;
and the voxel grid layer, the geographic information layer and the ground object space layer are led into a GIS working space together to obtain an orchard variable pesticide application prescription diagram.
8. An orchard variable drug delivery prescription graph generating device, which is characterized by comprising:
the acquisition module is used for acquiring point cloud information of an orchard environment and longitude and latitude information of a calibration ball in the orchard by using the scanning device;
the composition module is used for constructing an orchard three-dimensional point cloud map based on the point cloud information by utilizing an SLAM algorithm and an SLAM map optimization model in the acquisition process, and filtering ground point clouds in the orchard three-dimensional point cloud map to obtain a three-dimensional point cloud model of the fruit tree;
the reconstruction module is used for dividing the three-dimensional point cloud model of the fruit tree by using a clustering algorithm to construct a boundary box of the three-dimensional point cloud model of the fruit tree, determining longitude and latitude information of the fruit tree according to the boundary box, and reconstructing the three-dimensional point cloud model of the fruit tree to obtain the area density of the canopy subareas and the area density of the canopy subareas of the fruit tree;
the pesticide application calculation module is used for calculating pesticide application prescription values of all canopy partitions based on the volume and the leaf area density of the canopy partitions to obtain fruit tree variable pesticide application prescription values;
the generation module is used for importing the calibration sphere longitude and latitude information, the orchard three-dimensional point cloud map, the fruit tree longitude and latitude information and the fruit tree variable pesticide application prescription value into a GIS system to generate an orchard variable pesticide application prescription map.
9. A computer device comprising a processor and a memory, the memory storing a computer program, characterized in that the processor is configured to implement the method for generating an orchard variable drug delivery prescription map according to any one of claims 1-7 when executing the computer program.
10. A computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the method of generating an orchard variable administration prescription map according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310275626.2A CN116295421A (en) | 2023-03-20 | 2023-03-20 | Orchard variable drug application prescription chart generation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310275626.2A CN116295421A (en) | 2023-03-20 | 2023-03-20 | Orchard variable drug application prescription chart generation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116295421A true CN116295421A (en) | 2023-06-23 |
Family
ID=86823765
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310275626.2A Pending CN116295421A (en) | 2023-03-20 | 2023-03-20 | Orchard variable drug application prescription chart generation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116295421A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117911906A (en) * | 2024-03-06 | 2024-04-19 | 海南大学 | Unmanned aerial vehicle gridding intelligent pesticide application method |
-
2023
- 2023-03-20 CN CN202310275626.2A patent/CN116295421A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117911906A (en) * | 2024-03-06 | 2024-04-19 | 海南大学 | Unmanned aerial vehicle gridding intelligent pesticide application method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110221311B (en) | Method for automatically extracting tree height of high-canopy-closure forest stand based on TLS and UAV | |
| CN108319655B (en) | Method and device for generating grid map | |
| CN111275750B (en) | Indoor space panoramic image generation method based on multi-sensor fusion | |
| Rosell et al. | Obtaining the three-dimensional structure of tree orchards from remote 2D terrestrial LIDAR scanning | |
| JP2020035448A (en) | Method, apparatus, device, storage medium for generating three-dimensional scene map | |
| CN105354883B (en) | The quick subtle three-dimensional modeling methods of 3ds Max and system based on a cloud | |
| CN108763287A (en) | On a large scale can traffic areas driving map construction method and its unmanned application process | |
| CN107977992A (en) | A kind of building change detecting method and device based on unmanned plane laser radar | |
| CN106503060A (en) | A kind of transmission line of electricity three dimensional point cloud is processed and hands over across thing acquisition methods | |
| CN104778744A (en) | Establishing technique of visualized scenes of large-scale three-dimension forests based on Lidar data | |
| WO2020109666A1 (en) | Method and system for generating forestry data | |
| CN112327326A (en) | Two-dimensional map generation method, system and terminal with three-dimensional information of obstacles | |
| CN102298793A (en) | Method for obtaining three-dimensional figure data of cultural relic | |
| CN116295421A (en) | Orchard variable drug application prescription chart generation method and device | |
| CN112906719A (en) | Standing tree factor measuring method based on consumption-level depth camera | |
| Li et al. | Feature extraction and modeling of urban building from vehicle-borne laser scanning data | |
| CN114937130B (en) | Topographic map mapping method, device, equipment and storage medium | |
| CN114548277B (en) | Method and system for ground point fitting and crop height extraction based on point cloud data | |
| CN115984490A (en) | Modeling analysis method and system for wind field characteristics, unmanned aerial vehicle equipment and storage medium | |
| CN110348067B (en) | Method, system, medium and equipment for extracting physical parameters of airflow characterization | |
| Dong et al. | Drone-based three-dimensional photogrammetry and concave hull by slices algorithm for apple tree volume mapping | |
| CN117786189A (en) | Visual interactive system of three-dimensional map | |
| CN113960614A (en) | Elevation map construction method based on frame-map matching | |
| Rebelo et al. | Building 3D city models: Testing and comparing Laser scanning and low-cost UAV data using FOSS technologies | |
| Mayr et al. | Object-based point cloud analysis for landslide and erosion monitoring |
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 |