CN112614193B - Intelligent calibration method for wheat green-turning stage spraying region of interest based on machine vision - Google Patents
Intelligent calibration method for wheat green-turning stage spraying region of interest based on machine vision Download PDFInfo
- Publication number
- CN112614193B CN112614193B CN202011558495.1A CN202011558495A CN112614193B CN 112614193 B CN112614193 B CN 112614193B CN 202011558495 A CN202011558495 A CN 202011558495A CN 112614193 B CN112614193 B CN 112614193B
- Authority
- CN
- China
- Prior art keywords
- coordinate system
- image
- spray
- ground
- nozzle
- 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
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000005507 spraying Methods 0.000 title claims abstract description 29
- 241000209140 Triticum Species 0.000 title claims abstract description 16
- 235000021307 Triticum Nutrition 0.000 title claims abstract description 11
- 239000007921 spray Substances 0.000 claims abstract description 174
- 238000001514 detection method Methods 0.000 claims abstract description 60
- 238000013507 mapping Methods 0.000 claims abstract description 8
- 239000011159 matrix material Substances 0.000 claims description 44
- 238000012937 correction Methods 0.000 claims description 22
- 239000003086 colorant Substances 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 238000005192 partition Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 claims description 3
- 238000000638 solvent extraction Methods 0.000 claims description 3
- 239000000575 pesticide Substances 0.000 description 11
- 238000005516 engineering process Methods 0.000 description 8
- 241000196324 Embryophyta Species 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000009333 weeding Methods 0.000 description 2
- 244000025254 Cannabis sativa Species 0.000 description 1
- 241000238631 Hexapoda Species 0.000 description 1
- 241000607479 Yersinia pestis Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 238000003306 harvesting Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000010899 nucleation Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- 230000000007 visual 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
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30204—Marker
- G06T2207/30208—Marker matrix
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention relates to an intelligent calibration method for a wheat turning green stage spraying region of interest based on machine vision, which is used for calibrating cameras of a boom sprayer before the wheat plant protection operation in the turning green stage, and determining the position of each spray head corresponding to a detection region in an image. The method comprises the following steps: preparing before calibration; acquiring a ground checkerboard image and a mark plate plane checkerboard image; identifying a marking plate and determining the position of a spray head in an image; mapping the intersection point of the spray heads in the image to a coordinate system of the identification plate; projecting the intersection point of the spray heads to the ground; introducing parameters and determining a corresponding area of the spray head; and returning the detection area corresponding to the spray head to an image coordinate system to obtain the region of interest of the image. According to the invention, a three-dimensional coordinate system is established by the black-and-white checkerboard image, the position of the corresponding area of the spray head in the image, namely the region of interest, is rapidly determined by the identification plate and the black-and-white checkerboard image, and the information such as the height, pitch angle and the like of the camera is not required to be measured manually, so that the artificial error is reduced, and the method has the characteristics of good universality and high accuracy.
Description
Technical Field
The invention relates to an intelligent calibration method based on machine vision, in particular to an intelligent calibration method based on machine vision for a wheat turning green period spraying region of interest.
Background
Along with the continuous development of accurate agriculture, the variable spraying technology becomes an important component of the accurate intelligent pesticide application technology, and the application of the variable spraying technology can change the traditional large-area average spraying mode in China, effectively reduce the pesticide usage amount, promote the reasonable use of the pesticide, help to protect the environment and reduce the harm to green food crops. Among them, the perception technology based on visual sensors is becoming a hot spot of research. The machine vision technology is widely applied to various farmland operations (such as weeding, pesticide spraying, seeding, harvesting and the like), and the operation effect directly influences the efficiency, reliability and stability of agricultural machinery.
Compared with the advanced agricultural countries in the world, the precise intelligent pesticide spraying technology level in China is still relatively behind, the traditional plant protection machinery for spraying the pesticide does not consider the situation of the diseased, insect and grass damage of different plots, and a large-area average-input pesticide spraying method is adopted, so that the pesticide is insufficient in the part of the fields and excessive in the part of the fields. The main application ways of the existing variable spraying medicine are as follows: 1. judging the diseases, the weeds and the pests of the farmland by using a prescription chart, and spraying different doses at different positions, wherein the method of the prescription chart needs to collect and judge points in the farmland in the early stage of weeding, so that the efficiency is low; 2. the variable spraying mode of spraying the target is used, the weeds and crops are segmented by using an image segmentation technology, and then the target spraying is carried out on the weeds, but the actual operation effect is poor on dense crops similar to wheat. 3. The crown variable pesticide spraying mode of the laser radar is utilized, the laser radar is utilized to detect and collect the distance between the crown boundaries on two sides of the tree row and the laser scanning sensor, so that the copying variable pesticide spraying is realized, but most of the mode is applied to pesticide spraying of crops with high crown equidistance identifiability, and the actual operation effect on farmland crops on the ground is poor. Aiming at dense ground crops such as wheat in the green-returning period, a variable spraying technology is used for the areas with missing seedlings, broken seedlings and no seedlings, and a good variable spraying method is not available.
Calibration of a camera can be divided into two ways: self-calibration and calibration dependent on a reference. The camera self-calibration is to adjust camera parameters by shooting surrounding objects according to a digital image processing related method, a digital image processing related method and geometric calculation, so that the calibration result has larger error and is not suitable for high-precision application occasions. The camera calibration by the reference object has higher precision than the self-calibration method, and the conversion matrix from the three-dimensional world coordinate to the two-dimensional plane coordinate is obtained by calculating the internal and external parameter matrix of the camera by the camera imaging and the digital image processing method. In order to obtain such a matrix, it is generally necessary to measure information such as a camera height and a pitch angle, so as to obtain a conversion relationship between a camera coordinate system and a predetermined world coordinate system, and this method only involves a projection conversion relationship from a plane of a three-dimensional world to a pixel plane, but does not involve a projection conversion relationship from multiple planes, and for multiple planes, a method for manually measuring a height and a pitch angle is relatively complex.
Disclosure of Invention
Aiming at the problem that the positions of a spraying point and an actual ground operation area are different in an image during the wheat plant protection operation in the turning green period, the invention aims to provide an intelligent calibration method for a spraying region of interest in the wheat turning green period based on machine vision.
In order to achieve the above object, the present invention provides the following technical solutions:
an intelligent calibration method for a wheat turning-green stage spraying region of interest based on machine vision is used for calibrating each camera 1 of a spray boom sprayer 6 before the turning-green stage wheat plant protection operation to determine the position of each spray head corresponding to a detection region 5 in an image, wherein the spray boom sprayer 6 comprises a spray boom 4 with a plurality of spray heads 7 perpendicular to the advancing direction of a machine tool and a plurality of cameras 1 facing the ground crops and positioned above the spray boom 4. The method comprises the following steps:
s1, preparing before calibration;
a nozzle marking plate 2 parallel to the advancing direction of the machine tool is respectively arranged right above each nozzle 7; a spray rod marking plate 3 parallel to the spray rod 4 is arranged in the acquisition area of each camera 1, and the spray rod marking plate 2 and the spray rod marking plate 3 are positioned in the same horizontal marking plate plane 11; the black-and-white checkerboard calibration plates 9 are respectively arranged in the acquisition areas of the cameras 1, the cameras 1 respectively acquire a clear image with the black-and-white checkerboard calibration plates 9, a camera coordinate system 8 and an image coordinate system are established, angular point information of checkerboards in the image is extracted, and pixel coordinates of angular points of each checkerboard are arranged corresponding to the size of the black-and-white checkerboard calibration plates 9; obtaining internal parameters and distortion parameters of a camera by a Zhang calibration method;
the colors of the spray head marking plate 2 and the spray rod marking plate 3 are different;
s2, acquiring a ground checkerboard image and a marking plate plane checkerboard image;
the black-and-white checkerboard calibration plates 9 which are the same as the step S1 are respectively arranged in the ground 13 and the marking plate plane 11 in the acquisition area of each camera 1, each camera 1 respectively shoots a ground checkerboard image with the black-and-white checkerboard calibration plates 9 arranged on the ground 13 and the marking plate plane 11 and a marking plate plane checkerboard image, the corner point information of the checkerboard of the black-and-white checkerboard calibration plates 9 in the two images is extracted, the pixel coordinates of each checkerboard corner point are set according to the size of the black-and-white checkerboard calibration plates 9, a ground coordinate system 12 and a marking plate coordinate system 10 are established, the internal parameters of the camera obtained in the step S1 are used for estimating the external parameter matrix of the checkerboards in the two images, and the external parameter matrix M of the ground coordinate system 12 is obtained f_c And an extrinsic matrix M of a sign board coordinate system 10 p_c ；
S3, identifying the identification plate and determining the position of the spray head in the image;
s3.1, performing distortion correction on the ground checkerboard image and the mark plate plane checkerboard image of each camera 1 obtained in the step S2 to obtain a ground checkerboard correction image and a mark plate plane checkerboard correction image;
s3.2, identifying the spray boom identification plates 3 in the identification plate plane checkerboard correction images of the cameras 1 obtained in the step S3.1 according to the corresponding color identification mode selected by the colors of the spray boom identification plates 3, and performing binary processing; fitting the truth points of the binary image of the obtained spray rod identification plate 3 by using a least square method to obtain a spray rod fitting straight line of the spray rod identification plate 3 and a spray rod fitting straight line equation of the straight line under an image coordinate system;
s3.3, identifying the nozzle identification plates 2 in the identification plate plane checkerboard correction images of the cameras 1 obtained in the step S3.1 according to the corresponding color identification mode selected by the colors of the nozzle identification plates 2, and performing binary processing; partitioning the obtained binary images containing a plurality of nozzle identification plates 2, wherein each partition only contains one binary image of the nozzle identification plate 2, and performing straight line fitting on the binary image of each partition by using a minimum binary method to obtain a nozzle fitting straight line of each nozzle identification plate 2 and a nozzle fitting straight line equation of the straight line under an image coordinate system;
s3.4, carrying out simultaneous solving on each nozzle fitting linear equation obtained in the step S3.3 and the spray rod fitting linear equation obtained in the step S3.2 to obtain a plurality of intersection points, wherein the intersection points are nozzle intersection points, and the nozzle intersection points are positions of nozzles in the plane checkerboard image of the identification plate;
s4, mapping the intersection points of the spray heads in the image to a coordinate system of the identification plate;
the identification plate plane checkerboard correction image obtained by step S3.1 obtains a homography matrix R of image coordinates to an identification plate coordinate system 10 3×3 The method comprises the steps of carrying out a first treatment on the surface of the Mapping the nozzle intersection point under the image coordinate system obtained in the step S3.4 to the position under the marking plate coordinate system 10 through a formula 1 to obtain the nozzle intersection point coordinate under the marking plate coordinate system 10;
wherein x and y are respectively x-axis coordinate values and y-axis coordinate values of the nozzle intersection point coordinates under the coordinate system 10 of the marking plate, and the unit is mm; x, Y are the x-axis coordinate values and the y-axis coordinate values of the nozzle intersection points under the image coordinate system, respectively, and the units are pixels; s is a scale factor, R 3×3 Is a homography matrix;
s5, projecting the intersection point of the spray heads to the ground;
converting the nozzle intersection point coordinate under the marking plate coordinate system 10 obtained in the step S4 to the ground coordinate system 12 through a formula 2 to obtain the nozzle intersection point coordinate under the ground coordinate system 12;
wherein M is p_c To identify the extrinsic matrix of the plate coordinate system 10, M f_c -1 An extrinsic inverse matrix of the ground coordinate system 12; (X) pw ，Y pw ，Z pw ) To identify the coordinates of the spray head intersection point under the plate coordinate system 10, X pw 、Y pw 、Z pw The coordinate values of the X-axis, the Y-axis and the Z-axis of the nozzle intersection point coordinate under the coordinate system 10 of the marking plate are respectively in mm; (X) f ，Y f ，Z f ) X is the intersection point coordinate of the spray nozzle under the ground coordinate system 12 f 、Y f 、Z f The x-axis coordinate value, the y-axis coordinate value and the z-axis coordinate value of the nozzle intersection point coordinate under the ground coordinate system 12 are respectively expressed in mm;
s6, introducing parameters and determining a corresponding area of the spray head;
z of the coordinates of the intersection point of the spray heads in the ground coordinate system 12 f Equal to 0, obtaining the projection coordinates of the spray head with the spray head intersection point under the ground coordinate system 12; the effective spray width w of the spray head 7 and the distance h between the detection area corresponding to the spray head 7 and the spray rod 4 are respectively set 1 The width h of the detection area corresponding to the nozzle 7 2 Determining the coordinates of the detection area 5 corresponding to the spray head under the ground coordinate system 12 through the formula 3 and the formula 4;
wherein (X) f1 ,Y f1 ) X is the projection coordinate of the spray nozzle with the spray nozzle intersection point under the ground coordinate system 12 f1 ,Y f1 Respectively x-axis coordinate values and y-axis coordinate values of the spray head projection coordinates of the spray head intersection point under the ground coordinate system 12, wherein the units are mm; alpha is the included angle between the projection straight line of the spray boom of the ground coordinate system 12 and the transverse axis of the coordinate system, and the unit is degree; (X' f1 ,Y′ f1 ) Is (X) f1 ,Y f1 ) The intersection point coordinate of the spray nozzle after the rotation angle alpha of the ground coordinate system, X' f1 、Y′ f1 Respectively (X) f1 ,Y f1 ) The x-axis coordinate value and the y-axis coordinate value of the nozzle intersection point coordinate after the rotation angle alpha of the ground coordinate system are in mm; (X) f2 ,Y f2 )，(X f3 ,Y f3 )，(X f4 ,Y f4 )，(X f5 ,Y f5 ) X is the coordinates of four boundary points of the corresponding detection area 5 of the spray head in the ground coordinate system 12 f2 、X f3 、X f4 、X f5 For the x-axis coordinate value, Y of the four boundary points of the nozzle corresponding detection area 5 in the ground coordinate system 12 f2 、Y f3 、Y f4 、Y f5 The y-axis coordinate values of four boundary points of the detection area 5 corresponding to the spray head under the ground coordinate system 12 are given in mm; h is a 1 The unit is mm for the distance between the detection area corresponding to the spray head 7 and the spray rod 4; h is a 2 The unit is mm for the width of the detection area corresponding to the spray head 7; w is the effective width of the spray nozzle 7, and the unit is mm;
s7, returning the detection area corresponding to the spray head to an image coordinate system to obtain an image region of interest;
returning the detection area 5 corresponding to the spray head under the ground coordinate system 12 obtained in the step S6 to the image coordinate system through the formula 5 and the formula 6 to obtain corresponding pixel coordinate values, and obtaining an image region of interest;
wherein M is f_c Is an extrinsic matrix of the ground coordinate system 12, (X) f ,Y f 0) is the correspondence checkCoordinates of the measuring region 5 in the ground coordinate system 12, X f 、Y f 0 is an x-axis coordinate value, a y-axis coordinate value and a z-axis coordinate value of the corresponding detection area 5 under the ground coordinate system 12, and the unit is mm; (X) cf ,Y cf ,Z cf ) X is the coordinate of the spray head corresponding to the detection area 5 under the camera coordinate system 8 cf 、Y cf 、Z cf The x-axis coordinate value, the y-axis coordinate value and the z-axis coordinate value of the sprayer corresponding to the detection area 5 under the camera coordinate system 8 are respectively expressed in mm;
wherein A is an internal reference matrix of the camera; s is a proportionality coefficient; (X) cf ,Y cf ,Z cf ) X is the coordinate of the spray head corresponding to the detection area 5 under the camera coordinate system 8 cf 、Y cf 、Z cf The x-axis coordinate value, the y-axis coordinate value and the z-axis coordinate value of the sprayer corresponding to the detection area 5 under the camera coordinate system 8 are respectively expressed in mm; u and v are the abscissa and ordinate of the detection region in the image coordinate system, respectively.
The pixels of the camera 1 are set to 1920×1080, and the acquired image pixels are 1920×1080.
In the step S1, the internal reference is a transformation matrix of the image converted from the camera coordinate system 8 to the image coordinate system, and is used for calculating the position of the coordinate point in the camera coordinate system 8 in the image.
In the step S1, the distortion parameter is distortion generated during the process of manufacturing the camera and the process of converting the camera coordinate system 8 into the image coordinate system.
In the step S2, the external reference matrix is a matrix in which the coordinate system determined by the black-and-white checkerboard calibration plate 9 is converted into the camera coordinate system 8.
In the step S3.1, the distortion correction corrects the distorted image by using the distortion parameters obtained in the step S1, and eliminates the distortion.
In the step S3.2, the identification and binarization processing are carried out on the green area of the image by adopting a 2g-r-b sum-Ojin method.
In the step S3.3, the identification plate 2 of the spray head is red, and the red area of the image is identified and binarized by adopting a 2r-g-b sum-Ojin method.
In the step S4, the uniplanar matrix is a conversion matrix for converting the image coordinate points into the coordinate system of the identification plate.
In the step S6, the determination process of the included angle α between the boom projection line of the ground coordinate system 12 and the horizontal axis of the coordinate system is as follows:
the coordinates of the spray head projection points under two ground coordinate systems 12 are selected at will, and a spray rod projection straight line l in the ground coordinate system 12 is obtained: y=kx+b; wherein k is the slope of a straight line; and obtaining the included angle between the projection straight line of the spray rod and the transverse axis of the coordinate system through the slope k of the straight line. Compared with the prior art, the invention has the beneficial effects that:
according to the invention, a three-dimensional coordinate system is established by the black-and-white checkerboard image, the position of the corresponding area of the spray head in the image, namely the region of interest, is rapidly determined by the identification plate and the black-and-white checkerboard image, and the information such as the height, pitch angle and the like of the camera is not required to be measured manually, so that the artificial error is reduced, and the method has the characteristics of good universality and high accuracy.
Drawings
FIG. 1 is a flow chart of an intelligent calibration method of a wheat turning green stage spraying region of interest based on machine vision;
FIG. 2 is a schematic illustration of the operation of the boom sprayer 6 of the present invention;
FIG. 3 is a schematic view of an image acquisition and coordinate system for spray region of interest calibration according to the present invention.
Wherein the reference numerals are as follows:
1. camera 2 nozzle identification plate
3. Spray rod of spray rod identification plate 4
5. Spray head corresponds 6 spray lance sprayers in detection zone
7. Spray head 8 camera coordinate system
9. Black and white checkerboard calibration plate 10 identification plate coordinate system
11. Marking plate plane 12 ground coordinate system
13. Ground surface
Effective width of spray width of w spray head 7
h 1 Distance between detection area corresponding to the nozzle 7 and the boom 4
h 2 The nozzle 7 corresponds to the width of the detection area
Detailed Description
The invention will be further described with reference to the drawings and examples.
An intelligent calibration method for a wheat turning-green stage spraying region of interest based on machine vision is used for calibrating each camera 1 of a spray rod sprayer 6 before the turning-green stage wheat plant protection operation, and determining the position of each spray head corresponding to a detection region 5 in an image. As shown in fig. 2, the boom sprayer 6 includes a boom 4 having a plurality of spray heads 7 perpendicular to the implement advancing direction and a plurality of cameras 1 facing the ground crop and located above the boom 4; the distance between the camera 1 and the spray rod 4 is 900-1100 mm, the inclination angle of the camera 1 relative to the ground is 25-35 degrees, and the height of the spray head is 400-600 mm.
As shown in fig. 1, the method comprises the steps of:
s1, preparing before calibration;
a nozzle marking plate 2 parallel to the advancing direction of the machine tool is respectively arranged right above each nozzle 7; a spray rod marking plate 3 parallel to the spray rod 4 is arranged in the acquisition area of each camera 1, and the spray rod marking plate 2 and the spray rod marking plate 3 are positioned in the same horizontal marking plate plane 11; the black-and-white checkerboard calibration plates 9 are respectively arranged in the acquisition areas of the cameras 1, the cameras 1 respectively acquire a clear image with the black-and-white checkerboard calibration plates 9, a camera coordinate system 8 and an image coordinate system are established, angular point information of checkerboards in the image is extracted, and pixel coordinates of angular points of each checkerboard are arranged corresponding to the size of the black-and-white checkerboard calibration plates 9; obtaining internal parameters and distortion parameters of the camera by a Zhang calibration method. The Zhang's calibration method is common knowledge in the art, and is not described in detail herein.
In this embodiment, the pixels of the camera 1 are 1920×1080, and the pixels of the image acquired below are 1920×1080.
The colors of the nozzle mark plate 2 and the nozzle bar mark plate 3 are different. In this embodiment, the nozzle marking plate 2 adopts a red marking, and the boom marking plate 3 adopts a green marking. The length of the spray rod marking plate 3 is 300mm, and the width is 90mm; the length of the shower nozzle identification plate 2 is 190mm and the width is 50mm.
In the black and white checkered calibration plate 9, the side length of each black and white checkered is 30mm, and the black and white checkered array is 12 multiplied by 9.
The internal reference is a transformation matrix of the image from the camera coordinate system 8 to the image coordinate system. This parameter is used to calculate the position of the coordinate point in the image under the camera coordinate system 8.
The distortion parameters are distortions generated during the camera manufacturing process and during the conversion of the camera coordinate system 8 into the image coordinate system.
S2, acquiring a ground checkerboard image and a marking plate plane checkerboard image;
the black-and-white checkerboard calibration plates 9 which are the same as the step S1 are respectively arranged in the ground 13 and the marking plate plane 11 in the acquisition area of each camera 1, each camera 1 respectively shoots a ground checkerboard image with the black-and-white checkerboard calibration plates 9 arranged on the ground 13 and the marking plate plane 11 and a marking plate plane checkerboard image, the corner point information of the checkerboard of the black-and-white checkerboard calibration plates 9 in the two images is extracted, the pixel coordinates of each checkerboard corner point are set according to the size of the black-and-white checkerboard calibration plates 9, a ground coordinate system 12 and a marking plate coordinate system 10 are established, the internal parameters of the camera obtained in the step S1 are used for estimating the external parameter matrix of the checkerboards in the two images, and the external parameter matrix M of the ground coordinate system 12 is obtained f_c And an extrinsic matrix M of a sign board coordinate system 10 p_c 。
The external reference matrix is a matrix which is converted into a camera coordinate system 8 by a coordinate system determined by a black-white checkerboard calibration plate 9.
S3, identifying the identification plate and determining the position of the spray head in the image;
s3.1, performing distortion correction on the ground checkerboard image and the mark plate plane checkerboard image of each camera 1 obtained in the step S2 to obtain a ground checkerboard correction image and a mark plate plane checkerboard correction image;
the distortion correction is to correct the distorted image by using the distortion parameters obtained by calibration in the step S1, so as to eliminate distortion. Distortion correction belongs to common technical means in the art, and is not described herein.
S3.2, identifying the spray boom identification plates 3 in the identification plate plane checkerboard correction images of the cameras 1 obtained in the step S3.1 according to the corresponding color identification mode selected by the colors of the spray boom identification plates 3, and performing binary processing; and fitting the true value points of the obtained binary image of the spray rod identification plate 3 by using a least square method to obtain a spray rod fitting straight line of the spray rod identification plate 3 and a spray rod fitting straight line equation of the straight line under an image coordinate system.
In the embodiment, the spray rod marking plate 3 is green, and the green area of the image is identified and binarized by adopting a 2g-r-b sum-Ojin method.
S3.3, identifying the nozzle identification plates 2 in the identification plate plane checkerboard correction images of the cameras 1 obtained in the step S3.1 according to the corresponding color identification mode selected by the colors of the nozzle identification plates 2, and performing binary processing; partitioning the obtained binary images containing a plurality of nozzle identification plates 2, wherein each partition only contains one binary image of the nozzle identification plate 2, and performing straight line fitting on the binary images of each partition by using a minimum binary method to obtain nozzle fitting straight lines of the nozzle identification plates 2 and nozzle fitting straight line equations of the straight lines under an image coordinate system.
In the embodiment, the nozzle identification plate 2 is red, and the red area of the image is identified and binarized by adopting a 2r-g-b sum-Ojin method.
And S3.4, carrying out simultaneous solving on each nozzle fitting linear equation obtained in the step S3.3 and the spray rod fitting linear equation obtained in the step S3.2 to obtain a plurality of intersection points, wherein the intersection points are nozzle intersection points, and the nozzle intersection points are positions of nozzles in the plane checkerboard image of the marking plate.
S4, mapping the intersection points of the spray heads in the image to a coordinate system of the identification plate;
the identification plate plane checkerboard correction image obtained by step S3.1 obtains a homography matrix R of image coordinates to an identification plate coordinate system 10 3×3 The method comprises the steps of carrying out a first treatment on the surface of the Mapping the nozzle intersection point under the image coordinate system obtained in the step S3.4 to the position under the marking plate coordinate system 10 through a formula (1) to obtain the nozzle intersection point coordinate under the marking plate coordinate system 10;
wherein x and y are respectively x-axis coordinate values and y-axis coordinate values of the nozzle intersection point coordinates under the coordinate system 10 of the marking plate, and the unit is mm; x, Y are the x-axis coordinate values and the y-axis coordinate values of the nozzle intersection points under the image coordinate system, respectively, and the units are pixels; s is a scale factor, R 3×3 Is a homography matrix.
The uniplanar matrix is a projection mapping from one plane to another, and is represented in this embodiment as a transformation matrix for transforming image coordinate points into a coordinate system of the sign board.
S5, projecting the intersection point of the spray heads to the ground;
converting the nozzle intersection point coordinate under the marking plate coordinate system 10 obtained in the step S4 into the ground coordinate system 12 through a formula (2) to obtain the nozzle intersection point coordinate under the ground coordinate system 12;
wherein M is p_c To identify the extrinsic matrix of the plate coordinate system 10, M f_c -1 An extrinsic inverse matrix of the ground coordinate system 12; (X) pw ，Y pw ，Z pw ) To identify the coordinates of the spray head intersection point under the plate coordinate system 10, X pw 、Y pw 、Z pw The X-axis coordinate value, the y-axis coordinate value and the z-axis coordinate value of the nozzle intersection point coordinate in the marking plate coordinate system 10 are respectively in mm, (X f ，Y f ，Z f ) X is the intersection point coordinate of the spray nozzle under the ground coordinate system 12 f 、Y f 、Z f The x-axis coordinate value, the y-axis coordinate value and the z-axis coordinate value of the nozzle intersection point coordinate in the ground coordinate system 12 are respectively expressed in mm.
S6, introducing parameters and determining a corresponding area of the spray head
Z of the coordinates of the intersection point of the spray heads in the ground coordinate system 12 f Equal to 0, obtaining the projection coordinates of the spray head with the spray head intersection point under the ground coordinate system 12; the effective spray width w of the spray head 7 and the distance h between the detection area corresponding to the spray head 7 and the spray rod 4 are respectively set 1 The width h of the detection area corresponding to the nozzle 7 2 The coordinates of the detection area 5 corresponding to the head under the ground coordinate system 12 are determined by the formula (3) and the formula (4).
Wherein (X) f1 ,Y f1 ) X is the projection coordinate of the spray nozzle with the spray nozzle intersection point under the ground coordinate system 12 f1 ,Y f1 Respectively x-axis coordinate values and y-axis coordinate values of the spray head projection coordinates of the spray head intersection point under the ground coordinate system 12, wherein the units are mm; alpha is the included angle between the projection straight line of the spray boom of the ground coordinate system 12 and the transverse axis of the coordinate system, and the unit is degree; (X' f1 ,Y′ f1 ) Is (X) f1 ,Y f1 ) The intersection point coordinate, X 'of the spray nozzle after alpha angle rotation in the ground coordinate system' f1 、Y′ f1 Respectively (X) f1 ,Y f1 ) The x-axis coordinate value and the y-axis coordinate value of the nozzle intersection point coordinate after rotating an alpha angle in the ground coordinate system are in mm; (X) f2 ,Y f2 )，(X f3 ,Y f3 )，(X f4 ,Y f4 )，(X f5 ,Y f5 ) X is the coordinates of four boundary points of the corresponding detection area 5 of the spray head in the ground coordinate system 12 f2 、X f3 、X f4 、X f5 Four boundary points corresponding to the detection area 5 for the spray head are on the groundX-axis coordinate value, Y, in coordinate system 12 f2 、Y f3 、Y f4 、Y f5 The y-axis coordinate values of four boundary points of the detection area 5 corresponding to the spray head under the ground coordinate system 12 are given in mm; h is a 1 The unit is mm for the distance between the detection area corresponding to the spray head 7 and the spray rod 4; h is a 2 The width of the detection area corresponding to the spray head 7 is in mm, and w is the effective spray width of the spray head 7 in mm.
The determining process of the included angle alpha between the boom projection straight line of the ground coordinate system 12 and the transverse axis of the coordinate system is as follows:
the coordinates of the spray head projection points under two ground coordinate systems 12 are selected at will, and a spray rod projection straight line l in the ground coordinate system 12 is obtained: y=kx+b; wherein k is the slope of a straight line; and obtaining the included angle between the projection straight line of the spray rod and the transverse axis of the coordinate system through the slope k of the straight line.
In this embodiment, the effective width w of the nozzle 7 is 600mm, and the distance h between the detection area corresponding to the nozzle 7 and the spray bar 4 is 1 200mm, the nozzle 7 corresponds to the width h of the detection area 2 200mm.
S7, returning the detection area corresponding to the spray head to an image coordinate system to obtain an image region of interest;
returning the detection region 5 corresponding to the spray head under the ground coordinate system 12 obtained in the step S6 to the image coordinate system through the formula (5) and the formula (6) to obtain a corresponding pixel coordinate value, and obtaining an image region of interest;
wherein M is f_c Is an extrinsic matrix of the ground coordinate system 12, (X) f ,Y f 0) is the coordinate of the corresponding detection area 5 in the ground coordinate system 12, X f 、Y f 0 is an x-axis coordinate value, a y-axis coordinate value and a z-axis coordinate value of the corresponding detection area 5 under the ground coordinate system 12, and the unit is mm; (X) cf ,Y cf ,Z cf ) X is the coordinate of the spray head corresponding to the detection area 5 under the camera coordinate system 8 cf 、Y cf 、Z cf The x-axis coordinate value, the y-axis coordinate value and the z-axis coordinate value of the nozzle corresponding to the detection area 5 under the camera coordinate system 8 are respectively expressed in mm.
Wherein A is an internal reference matrix of the camera; s is a proportionality coefficient; (X) cf ,Y cf ,Z cf ) X is the coordinate of the spray head corresponding to the detection area 5 under the camera coordinate system 8 cf 、Y cf 、Z cf The x-axis coordinate value, the y-axis coordinate value and the z-axis coordinate value of the sprayer corresponding to the detection area 5 under the camera coordinate system 8 are respectively expressed in mm; u and v are the abscissa and ordinate of the detection region in the image coordinate system, respectively.
Claims (10)
1. The utility model provides a wheat turns green stage spraying region of interest intelligent calibration method based on machine vision for before turning green stage wheat plant protection operation, carry out the demarcation to each camera (1) of spray lance spraying machine (6), confirm that each shower nozzle corresponds the position of detection region (5) in the image, spray lance spraying machine (6) include perpendicular to the machine direction of advance have spray lance (4) of a plurality of shower nozzles (7) and a plurality of towards ground crop and be located camera (1) of spray lance (4) top, characterized in that, this method includes the following steps:
s1, preparing before calibration;
a nozzle marking plate (2) parallel to the advancing direction of the machine tool is arranged above each nozzle (7); a spray rod marking plate (3) parallel to the spray rod (4) is arranged in the collecting area of each camera (1), and the spray rod marking plate (2) and the spray rod marking plate (3) are positioned in the same horizontal marking plate plane (11); the black-and-white checkerboard calibration plates (9) are respectively arranged in the acquisition areas of the cameras (1), the cameras (1) respectively acquire a clear image with the black-and-white checkerboard calibration plates (9), a camera coordinate system (8) and an image coordinate system are established, angular point information of checkerboards in the image is extracted, and pixel coordinates of angular points of each checkerboard are set corresponding to the size of the black-and-white checkerboard calibration plates (9); obtaining internal parameters and distortion parameters of a camera by a Zhang calibration method;
the colors of the spray head marking plate (2) and the spray rod marking plate (3) are different;
s2, acquiring a ground checkerboard image and a marking plate plane checkerboard image;
the black and white checkerboard calibration plates (9) which are the same as the step S1 are respectively arranged in the ground (13) and the marking plate plane (11) in the acquisition area of each camera (1), each camera (1) respectively shoots a ground checkerboard image and a marking plate plane checkerboard image with the black and white checkerboard calibration plates (9) arranged on the ground (13) and the marking plate plane (11), angular point information of the checkerboard of the black and white checkerboard calibration plates (9) in the two images is extracted, pixel coordinates of each checkerboard angular point are set according to the size of the black and white checkerboard calibration plates (9), a ground coordinate system (12) and a marking plate coordinate system (10) are established, internal parameters of the camera obtained in the step S1 are used for estimating external reference matrixes of the checkerboards in the two images, and an external reference matrix M of the ground coordinate system (12) is obtained f_c And an external matrix M of the coordinate system (10) of the identification panel p_c ；
S3, identifying the identification plate and determining the position of the spray head in the image;
s3.1, performing distortion correction on the ground checkerboard image and the mark plate plane checkerboard image of each camera (1) obtained in the step S2 to obtain a ground checkerboard correction image and a mark plate plane checkerboard correction image;
s3.2, identifying the spray boom identification plates (3) in the identification plate plane checkerboard correction images of the cameras (1) obtained in the step S3.1 according to a corresponding color identification mode selected by the colors of the spray boom identification plates (3), and performing binary processing; fitting true value points of the binary image of the obtained spray rod identification plate (3) by using a least square method to obtain a spray rod fitting straight line of the spray rod identification plate (3) and a spray rod fitting straight line equation of the straight line under an image coordinate system;
s3.3, identifying the nozzle identification plate (2) in the identification plate plane checkerboard correction image of each camera (1) obtained in the step S3.1 according to a corresponding color identification mode selected by the colors of the nozzle identification plate (2), and performing binary processing; partitioning the obtained binary images comprising a plurality of nozzle identification plates (2), wherein each partition only comprises a binary image of one nozzle identification plate (2), and performing straight line fitting on the binary image of each partition by using a minimum binary method to obtain a nozzle fitting straight line of each nozzle identification plate (2) and a nozzle fitting straight line equation of the straight line under an image coordinate system;
s3.4, carrying out simultaneous solving on each nozzle fitting linear equation obtained in the step S3.3 and the spray rod fitting linear equation obtained in the step S3.2 to obtain a plurality of intersection points, wherein the intersection points are nozzle intersection points, and the nozzle intersection points are positions of nozzles in the plane checkerboard image of the identification plate;
s4, mapping the intersection points of the spray heads in the image to a coordinate system of the identification plate;
the identification plate plane checkerboard correction image obtained by step S3.1 obtains a homography matrix R of image coordinates to an identification plate coordinate system (10) 3×3 The method comprises the steps of carrying out a first treatment on the surface of the Mapping the nozzle intersection point under the image coordinate system obtained in the step S3.4 to the position under the marking plate coordinate system (10) through a formula 1 to obtain the nozzle intersection point coordinate under the marking plate coordinate system (10);
wherein, x and y are respectively x-axis coordinate values and y-axis coordinate values of the nozzle intersection point coordinate under the coordinate system (10) of the marking plate, and the unit is mm; x, Y are the x-axis coordinate values and the y-axis coordinate values of the nozzle intersection points under the image coordinate system, respectively, and the units are pixels; s is a scale factor, R 3×3 Is a homography matrix;
s5, projecting the intersection point of the spray heads to the ground;
converting the nozzle intersection point coordinate under the marking plate coordinate system (10) obtained in the step S4 into a ground coordinate system (12) through a formula 2 to obtain the nozzle intersection point coordinate under the ground coordinate system (12);
wherein M is p_c To identify the external matrix of the plate coordinate system (10), M f_c -1 Is an extrinsic inverse matrix of a ground coordinate system (12); (X) pw ，Y pw ，Z pw ) To identify the coordinates of the intersection point of the spray heads in the plate coordinate system (10), X pw 、Y pw 、Z pw Respectively an x-axis coordinate value, a y-axis coordinate value and a z-axis coordinate value of the nozzle intersection point coordinate under the coordinate system (10) of the marking plate, wherein the unit is mm; (X) f ，Y f ，Z f ) X is the intersection point coordinate of the spray nozzle under the ground coordinate system (12) f 、Y f 、Z f The coordinate values are respectively an x-axis coordinate value, a y-axis coordinate value and a z-axis coordinate value of the intersection point coordinate of the spray nozzle under a ground coordinate system (12), and the unit is mm;
s6, introducing parameters and determining a corresponding area of the spray head;
z of the coordinates of the intersection point of the spray heads in the ground coordinate system (12) f Equal to 0, obtaining the projection coordinates of the spray heads of the spray head intersection points under a ground coordinate system (12); the effective width w of the spray width of the spray head (7) and the distance h between the detection area corresponding to the spray head (7) and the spray rod (4) are respectively arranged 1 The width h of the detection area corresponding to the nozzle (7) 2 Determining the coordinates of a detection area (5) corresponding to the spray head under a ground coordinate system (12) through a formula 3 and a formula 4;
wherein (X) f1 ,Y f1 ) For the projection coordinates of the spray head intersection point under the ground coordinate system (12), X f1 ,Y f1 Respectively an x-axis coordinate value and a y-axis coordinate value of a spray head projection coordinate of the spray head intersection point under a ground coordinate system (12), wherein the units are mm; alpha is the included angle between the projection straight line of the spray boom of the ground coordinate system (12) and the transverse axis of the coordinate system, and the unit is degree; (X' f1 ,Y′ f1 ) Is (X) f1 ,Y f1 ) Rotated in a ground coordinate systemSpray nozzle intersection point coordinate after angle alpha, X' f1 、Y′ f1 Respectively (X) f1 ,Y f1 ) The x-axis coordinate value and the y-axis coordinate value of the nozzle intersection point coordinate after the rotation angle alpha of the ground coordinate system are in mm; (X) f2 ,Y f2 )，(X f3 ,Y f3 )，(X f4 ,Y f4 )，(X f5 ,Y f5 ) Is the coordinates of four boundary points of the detection area (5) corresponding to the spray head in the ground coordinate system (12), X f2 、X f3 、X f4 、X f5 Is the x-axis coordinate value, Y of four boundary points of the corresponding detection area (5) of the spray head in the ground coordinate system (12) f2 、Y f3 、Y f4 、Y f5 The y-axis coordinate values of four boundary points of the detection area (5) corresponding to the spray head under the ground coordinate system (12) are given in mm; h is a 1 The unit is mm for the distance between the detection area corresponding to the spray head (7) and the spray rod (4); h is a 2 The unit is mm for the width of the detection area corresponding to the spray head (7); w is the effective spray width of the spray head (7), and the unit is mm;
s7, returning the detection area corresponding to the spray head to an image coordinate system to obtain an image region of interest;
returning the detection area (5) corresponding to the spray head under the ground coordinate system (12) obtained in the step S6 to the image coordinate system through the formula 5 and the formula 6 to obtain corresponding pixel coordinate values, and obtaining an image region of interest;
wherein M is f_c Is an extrinsic matrix of a ground coordinate system (12), (X) f ,Y f 0) is the coordinate of the corresponding detection area (5) in the ground coordinate system (12), X f 、Y f 0 are respectively an x-axis coordinate value, a y-axis coordinate value and a z-axis coordinate value of the corresponding detection area (5) under a ground coordinate system (12), and the unit is mm; (X) cf ,Y cf ,Z cf ) For the coordinates of the detection area (5) corresponding to the spray head under the camera coordinate system (8), X cf 、Y cf 、Z cf Respectively corresponding detection areas of the spray heads-the x-axis, y-axis and z-axis coordinate values of the field (5) in mm in the camera coordinate system (8);
wherein A is an internal reference matrix of the camera; s is a proportionality coefficient; (X) cf ,Y cf ,Z cf ) For the coordinates of the detection area (5) corresponding to the spray head under the camera coordinate system (8), X cf 、Y cf 、Z cf Respectively an x-axis coordinate value, a y-axis coordinate value and a z-axis coordinate value of the sprayer corresponding to the detection area (5) under a camera coordinate system (8), wherein the units are mm; u and v are the abscissa and ordinate of the detection region in the image coordinate system, respectively.
2. The method according to claim 1, characterized in that the pixels of the camera (1) are set to 1920 x 1080 and the acquired image pixels are each 1920 x 1080.
3. Method according to claim 1, characterized in that in step S1, the internal reference is a transformation matrix of the image from the camera coordinate system (8) to the image coordinate system for calculating the position of coordinate points in the image under the camera coordinate system (8).
4. Method according to claim 1, characterized in that in step S1 the distortion parameter is the distortion generated during the camera manufacturing process and during the conversion of the camera coordinate system (8) into the image coordinate system.
5. Method according to claim 1, characterized in that in step S2 the external reference matrix is a matrix whose coordinate system determined by the black and white checkerboard calibration plate (9) is converted into the camera coordinate system (8).
6. The method according to claim 1, wherein in the step S3.1, the distortion correction corrects the distorted image using the distortion parameters obtained in the step S1 to eliminate distortion.
7. The method according to claim 1, characterized in that the boom identification plate (3) is green, and in step S3.2, the image green area is identified and binarized using 2g-r-b sum-of-body method.
8. Method according to claim 1, characterized in that the nozzle identification plate (2) is red, and in step S3.3 the red area of the image is identified and binarized using the 2r-g-b sum-mangostin method.
9. The method according to claim 1, wherein in the step S4, the uniqueness matrix is a conversion matrix for converting the image coordinate points to the coordinate system of the sign board.
10. The method according to claim 1, wherein in the step S6, the angle α between the boom projection line of the ground coordinate system (12) and the horizontal axis of the coordinate system is determined as follows:
arbitrarily selecting the coordinates of the projection points of the spray heads under two ground coordinate systems (12), and solving a projection straight line l of the spray rod in the ground coordinate systems (12): y=kx+b; wherein k is the slope of a straight line; and obtaining the included angle between the projection straight line of the spray rod and the transverse axis of the coordinate system through the slope k of the straight line.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011558495.1A CN112614193B (en) | 2020-12-25 | 2020-12-25 | Intelligent calibration method for wheat green-turning stage spraying region of interest based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011558495.1A CN112614193B (en) | 2020-12-25 | 2020-12-25 | Intelligent calibration method for wheat green-turning stage spraying region of interest based on machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112614193A CN112614193A (en) | 2021-04-06 |
| CN112614193B true CN112614193B (en) | 2024-03-22 |
Family
ID=75245047
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011558495.1A Active CN112614193B (en) | 2020-12-25 | 2020-12-25 | Intelligent calibration method for wheat green-turning stage spraying region of interest based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112614193B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114565683B (en) * | 2022-03-02 | 2022-09-27 | 禾多科技（北京）有限公司 | Precision determination method, device, equipment, medium and product |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107655664A (en) * | 2017-08-29 | 2018-02-02 | 农业部南京农业机械化研究所 | Spraying machine spray lance dynamical property test system and method based on binocular image collection |
| WO2019080229A1 (en) * | 2017-10-25 | 2019-05-02 | 南京阿凡达机器人科技有限公司 | Chess piece positioning method and system based on machine vision, storage medium, and robot |
| CN110490940A (en) * | 2019-08-15 | 2019-11-22 | 北京迈格威科技有限公司 | Camera calibration method and apparatus based on gridiron pattern single image |
| CN111028297A (en) * | 2019-12-11 | 2020-04-17 | 凌云光技术集团有限责任公司 | Calibration method of surface structured light three-dimensional measurement system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180116556A1 (en) * | 2016-10-27 | 2018-05-03 | Nanjing Avatarmind Robot Technology Co., Ltd. | Height measurement method based on monocular machine vision |
-
2020
- 2020-12-25 CN CN202011558495.1A patent/CN112614193B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107655664A (en) * | 2017-08-29 | 2018-02-02 | 农业部南京农业机械化研究所 | Spraying machine spray lance dynamical property test system and method based on binocular image collection |
| WO2019080229A1 (en) * | 2017-10-25 | 2019-05-02 | 南京阿凡达机器人科技有限公司 | Chess piece positioning method and system based on machine vision, storage medium, and robot |
| CN110490940A (en) * | 2019-08-15 | 2019-11-22 | 北京迈格威科技有限公司 | Camera calibration method and apparatus based on gridiron pattern single image |
| CN111028297A (en) * | 2019-12-11 | 2020-04-17 | 凌云光技术集团有限责任公司 | Calibration method of surface structured light three-dimensional measurement system |
Non-Patent Citations (1)
| Title |
|---|
| 玉米行间定点扎穴深施追肥机的设计与试验;胡红;李洪文;王庆杰;何进;张翼夫;陈婉芝;王宪良;;农业工程学报;20161223(第24期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112614193A (en) | 2021-04-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112669393B (en) | Laser radar and camera combined calibration method | |
| CN110118528B (en) | Line structure light calibration method based on chessboard target | |
| CN108053450B (en) | High-precision binocular camera calibration method based on multiple constraints | |
| CN109215071B (en) | Intelligent rice and wheat harvester swath measuring method based on vision | |
| Liu et al. | Evaluation of a laser scanning sensor in detection of complex-shaped targets for variable-rate sprayer development | |
| Andersen et al. | Geometric plant properties by relaxed stereo vision using simulated annealing | |
| CN111486864B (en) | Multi-source sensor combined calibration method based on three-dimensional regular octagon structure | |
| CN106225774B (en) | A kind of unmanned agriculture tractor road measuring device and method based on computer vision | |
| CN113137920A (en) | Underwater measurement equipment and underwater measurement method | |
| CN109920006B (en) | Calibration method for pose transformation matrix of automatic throwing system of green feeder | |
| CN107886547A (en) | A kind of fisheye camera scaling method and system | |
| CN112614193B (en) | Intelligent calibration method for wheat green-turning stage spraying region of interest based on machine vision | |
| CN109255818B (en) | Novel target and extraction method of sub-pixel level angular points thereof | |
| WO2021017352A1 (en) | Laser radar-camera joint calibration target and joint calibration method | |
| CN112395984A (en) | Method for detecting seedling guide line of unmanned agricultural machine | |
| CN115205466A (en) | Structured light-based three-dimensional reconstruction method and system for power transmission channel | |
| CN115201883A (en) | Moving target video positioning and speed measuring system and method | |
| CN112435290A (en) | Leaf area image measuring method based on saturation segmentation | |
| CN108917722B (en) | Vegetation coverage degree calculation method and device | |
| KR102023087B1 (en) | Method for camera calibration | |
| CN115546266B (en) | Multi-strip airborne laser point cloud registration method based on local normal correlation | |
| Cho et al. | Vision-based uncut crop edge detection for automated guidance of head-feeding combine | |
| CN112837314A (en) | Fruit tree canopy parameter detection system and method based on 2D-LiDAR and Kinect | |
| Shanmugam et al. | A machine-vision-based real-time sensor system to control weeds in agricultural fields | |
| CN117058051A (en) | Method and device based on fusion of laser point cloud and low-light-level image |
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 | ||
| GR01 | Patent grant |