CN111815704B - Granary volume measurement and calculation method based on binocular camera - Google Patents

Granary volume measurement and calculation method based on binocular camera Download PDF

Info

Publication number
CN111815704B
CN111815704B CN202010684845.2A CN202010684845A CN111815704B CN 111815704 B CN111815704 B CN 111815704B CN 202010684845 A CN202010684845 A CN 202010684845A CN 111815704 B CN111815704 B CN 111815704B
Authority
CN
China
Prior art keywords
pile
valley
coordinate system
camera
binocular
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
Application number
CN202010684845.2A
Other languages
Chinese (zh)
Other versions
CN111815704A (en
Inventor
李佳
李博
赵博
牛康
周利明
吕程序
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chinese Academy of Agricultural Mechanization Sciences
Original Assignee
Chinese Academy of Agricultural Mechanization Sciences
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Chinese Academy of Agricultural Mechanization Sciences filed Critical Chinese Academy of Agricultural Mechanization Sciences
Priority to CN202010684845.2A priority Critical patent/CN111815704B/en
Publication of CN111815704A publication Critical patent/CN111815704A/en
Application granted granted Critical
Publication of CN111815704B publication Critical patent/CN111815704B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • 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
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • 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
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Geometry (AREA)
  • Image Analysis (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

A granary volume measurement method based on a binocular camera comprises the following steps: setting a binocular camera, taking a grain pile of a granary as a center, arranging three binocular cameras around the grain pile according to a triangle, wherein the height of the binocular cameras is larger than that of the grain pile, the view angle of the binocular camera completely covers the grain pile, and the grain pile is positioned at the center of a view field of the binocular camera; RGBD images acquired by three binocular cameras are used as input data simultaneously, and valley pile feature point detection, coordinate system conversion and distance calculation of the valley piles are respectively carried out; and estimating the geometric shape of the pile, and calculating the volume of the pile by using a pre-established pile geometric model. The invention can perform early warning aiming at the storage capacity of the granary, avoids the physical constraint of manual measurement and mechanical sensor measurement, improves the defects of poor generality and low flexibility, improves the measurement efficiency, realizes the online estimation of the operation flow of the harvester, and avoids direct economic loss.

Description

Granary volume measurement and calculation method based on binocular camera
Technical Field
The invention relates to a test measurement technology, in particular to a granary volume measurement method based on a binocular camera.
Background
In order to improve the monitoring capability of the grain barn of the combine harvester in China, the problem of dynamic detection of the grain yield needs to be solved. In the prior art, the detection of the grain loading condition of the granary mainly comprises mechanical sensors, including a scale, an ultrasonic sensor, a three-dimensional laser scanning sensor, a pressure sensor and the like, and the calculation of the grain loading condition is performed according to an established model. The method has the problems of complex metering process, poor measurement precision, inflexibility, universality and the like. Existing mechanical, acoustic, optical and electronic sensors have the defects of high fault rate, poor stability, poor capability of resisting severe environments and the like.
Disclosure of Invention
The invention aims to solve the technical problem of providing a granary volume measuring and calculating method based on a binocular camera aiming at the defects of the prior art.
In order to achieve the above purpose, the invention provides a granary and grain pile volume measuring and calculating method based on a binocular camera, which comprises the following steps:
S100, setting a binocular camera, wherein three binocular cameras are arranged around a grain pile of a granary in a triangular arrangement manner, the height of each binocular camera is larger than that of the grain pile, the view angle of each binocular camera completely covers the grain pile, and the grain pile is located at the center of the view field of each binocular camera;
s200, adopting RGBD images acquired by three binocular cameras as input data simultaneously, and respectively detecting valley pile characteristic points of the valley piles, converting a coordinate system and calculating the distance; and
S300, estimating the geometric shape of the grain pile, and calculating the volume of the grain pile by using a pre-established geometric model of the grain pile.
The method for measuring and calculating the volume of the grain pile of the granary based on the binocular camera, wherein the geometric shape of the grain pile is estimated to be conical, and the step S200 further comprises:
S201, detecting valley-pile characteristic points, respectively calculating valley-pile characteristic points S 0,s1,s2,s3,s0 obtained from three binocular cameras as the middle point of an S 1,s2 connecting line by adopting an image valley-pile characteristic point detection method, and respectively obtaining valley-pile characteristic point coordinates { u i,vi }, i=0, 1,2 and 3 under an image coordinate system of the valley-pile characteristic points S 0,s1,s2,s3;
S202, converting a coordinate system, namely converting the valley pile feature point coordinates { u i,vi }, i=0, 1,2 and 3 from an image coordinate system to a camera coordinate system respectively to obtain the corresponding coordinate { x i,yi,zi }, i=0, 1,2 and 3 under the camera coordinate system;
S203, calculating the distance, and respectively calculating the bottom circle diameter and the height of the valley pile under the binocular camera view field according to the coordinate and the geometric relation of the valley pile characteristic points under the camera coordinate system, so as to obtain the final valley pile bottom circle diameter d and the final Gu Duigao degrees h.
In the method for measuring and calculating the volume of the grain pile of the granary based on the binocular camera, in step S203, the diameters of the bottom circles of the grain pile under the view field of the three binocular cameras are respectively:
The diameters of the stacks obtained by the three binocular cameras are averaged as the final stack bottom circle diameter d:
Find the straight line distance of s 0,s3 And calculating the straight line distance l 1,l2 of s 1,s3,s2,s3 by the same method to obtain the heights of the valley stacks under the field of the binocular camera, wherein the heights are respectively as follows:
the heights of three of the stacks were averaged as the final stack height h:
In the method for measuring and calculating the volume of the grain pile of the granary based on the binocular camera, in the step S300, the final grain pile bottom circle radius R and the final Gu Duigao degrees h are adopted to calculate the volume of the grain pile as follows:
the method for measuring and calculating the volume of the grain pile of the granary based on the binocular camera, wherein the geometric shape of the grain pile is estimated to be rectangular, and the step S200 further comprises:
S201, detecting valley-pile feature points, respectively calculating valley-pile feature points S 1,s2,s3,s4 acquired from three binocular cameras by adopting an image valley-pile feature point detection method, and respectively acquiring valley-pile feature point coordinates { u i,vi }, i=1, 2,3,4 under an image coordinate system of the valley-pile feature points S 1,s2,s3,s4;
S202, converting a coordinate system, namely converting the valley pile feature point coordinates { u i,vi }, i=1, 2,3,4 from an image coordinate system to a camera coordinate system respectively to obtain the corresponding coordinate { x i,yi,zi }, i=1, 2,3,4 under the camera coordinate system;
S203, calculating the distance, and respectively calculating the average value d s1s2,ds2s3,ds2s4 of each side length of the rectangle according to the coordinate and the geometric relation of the valley pile feature points under the camera coordinate system.
In the method for measuring and calculating the volume of the grain pile of the granary based on the binocular camera, in step S300, the average value d s1s2,ds2s3,ds2s4 of each side length is adopted to calculate the volume of the grain pile as follows: v=d s1s2ds2s3ds2s4.
The method for measuring and calculating the volume of the grain pile of the granary based on the binocular camera, wherein the geometric shape of the grain pile is estimated to be a cylinder, and the step S200 further comprises:
S201, detecting valley-pile feature points, respectively calculating valley-pile feature points S 1,s2,s3 acquired from three binocular cameras by adopting an image valley-pile feature point detection method, and respectively acquiring valley-pile feature point coordinates { u i,vi }, i=1, 2,3 under an image coordinate system of the valley-pile feature points S 1,s2,s3;
S202, converting a coordinate system, namely converting the valley pile feature point coordinates { u i,vi }, i=1, 2 and 3 from an image coordinate system to a camera coordinate system respectively to obtain the corresponding coordinate of { x i,yi,zi }, i=1, 2 and 3 in the camera coordinate system;
S203, calculating the distance, and respectively calculating the average value d s1s2,ds2s3 of each side length of the cylinder according to the coordinate and the geometric relation of the valley pile feature points under the camera coordinate system.
In the method for measuring and calculating the volume of the grain pile of the granary based on the binocular camera, in step S300, the average value d s1s2,ds2s3 of each side length is adopted to calculate the volume of the grain pile as follows: v=pi d s1s2 2ds2s3.
According to the granary and grain pile volume measuring and calculating method based on the binocular camera, the height of the binocular camera is 1.5 times of that of the grain pile.
The granary volume measurement method based on the binocular camera, wherein the conversion between the image coordinate system and the camera coordinate system is performed by using the following formula:
Wherein K C2I is a camera reference matrix, u and v are coordinates in an image coordinate system, the image coordinate is scaled by α in the u axis, the image coordinate is scaled by β in the v axis, f is a distance from a physical imaging plane to an optical center, f x＝αf,fy =βf, X, Y, Z are coordinates in the camera coordinate system, and P c is a P-point camera coordinate.
The invention has the technical effects that:
According to the invention, RGBD images are acquired by using a binocular camera, and grain pile yield measurement of the three-dimensional spatial granary is performed based on camera internal reference matrixes and image feature point detection. The method avoids the physical constraint of manual measurement and mechanical sensor measurement, overcomes the defects of poor generality and low flexibility, improves the measurement efficiency, further realizes the on-line estimation of the harvester operation flow, can early warn the storage capacity of the granary, and avoids direct economic loss.
The invention will now be described in more detail with reference to the drawings and specific examples, which are not intended to limit the invention thereto.
Drawings
FIG. 1 is a schematic diagram of a binocular camera ranging scheme of the present invention;
FIG. 2 is a diagram showing a camera mounting position distribution according to an embodiment of the present invention;
FIG. 3 is a flow chart of a volume measurement of a pile according to an embodiment of the present invention;
FIG. 4 is a schematic illustration of SURF feature point matching in accordance with one embodiment of the present invention;
FIG. 5 is a schematic diagram illustrating detection of feature points of a valley pile image according to an embodiment of the present invention;
FIG. 6 is a schematic side view of a pile according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of a rectangular valley stack in accordance with an embodiment of the present invention;
fig. 8 is a schematic view of a cylindrical valley stack in accordance with an embodiment of the present invention.
Wherein reference numerals are used to refer to
1. Binocular camera
2. Rice heap
Detailed Description
The structural and operational principles of the present invention are described in detail below with reference to the accompanying drawings:
The invention relates to a granary grain stacking yield measuring method based on RGBD images, which utilizes a binocular camera to acquire RGBD images and carries out yield estimation of crops in a granary based on a binocular camera internal reference matrix and a camera motion state matrix.
Referring to fig. 1, fig. 1 is a schematic diagram of a binocular camera 1 ranging according to the present invention. As shown in fig. 1 below, P is a certain point on the object to be measured, O R and O T are optical centers of the two binocular cameras 1, respectively, and imaging points of the point P on photoreceptors of the two binocular cameras 1 are P and P', respectively. (the imaging plane of the binocular camera 1 is rotated and placed in front of the lens), f is the focal length of the camera, B is the center distance of the two cameras, z is the depth information to be obtained, and the distance from the point p to the point p' is d
d＝B-(xR-xT)；
Where x R、xT is the distance from the imaging point to the imaging plane edge in the illustration.
According to the principle of similar triangles, it is possible to:
Accordingly, depth information can be obtained from the parallax d of the imaged image.
Let the coordinates of the target point P in the camera coordinate system be P C＝[X,Y,Z]T, P ' be the target imaging point, let the coordinates be P ' = [ X ', Y ', Z ' ] T, and let the distance from the physical imaging plane to the optical center be f, i.e. the camera focal length. From the similar triangle relationship:
Since the pixels in the image are sampled and quantized in the imaging plane, it is assumed that the image coordinate system o-u-v is fixed to the physical imaging plane, the origin o' is located at the upper left corner of the image, the u-axis is parallel to the x-axis to the right, and the v-axis is parallel to the y-axis. The image coordinate system and the imaging plane differ by a scaling and translation, assuming that the image coordinate scales a in the u-axis and β in the v-axis, the imaging plane origin translates [ c x,cy]T ]. The homogeneous coordinate relationship can be obtained as follows:
The conversion between the image coordinate system and the camera coordinate system can be performed using the above formula. Wherein K C2I is a camera reference matrix, which can be obtained by camera calibration, u and v are coordinates under an image coordinate system, f x＝αf,fy =βf, X, Y, Z are coordinates under the camera coordinate system, and P c is a P-point camera coordinate.
Referring to fig. 2 and 3, fig. 2 is a diagram illustrating a camera mounting position distribution diagram according to an embodiment of the present invention, and fig. 3 is a flow chart illustrating a volume measurement of a valley pile 2 according to an embodiment of the present invention. The invention is based on image processing technology and calculation measurement technology, and uses a binocular camera as a main measurement sensor to calculate the volume of the valley pile 2 in real time. The invention relates to a granary grain pile 2 volume measuring and calculating method based on a binocular camera 1, which comprises the following steps of:
Step S100, setting a binocular camera 1, wherein three binocular cameras 1 are arranged around a grain pile 2 of a granary in a triangular arrangement manner by taking the grain pile 2 as a center, the heights of cameras of the binocular cameras 1 are larger than those of the grain pile 2, preferably the heights of the cameras of the binocular cameras 1 are 1.5 times as high as those of the grain pile 2, the view angle of the binocular camera 1 completely covers the grain pile 2, and the grain pile 2 is positioned in the center of the view field of the binocular camera 1, as shown in fig. 2;
step 200, adopting RGBD images acquired by three binocular cameras 1 as input data simultaneously, and respectively performing valley pile feature point detection, coordinate system conversion and distance calculation of the valley pile 2; and
Step S300, estimating the geometric shape of the pile 2, such as a regular solid geometry including a cylinder, a cone, a rectangle, etc., and calculating the volume of the pile 2 by using a pre-established geometric model of the pile 2.
Referring to fig. 4, fig. 4 is a schematic diagram of SURF feature point matching according to an embodiment of the present invention. Volume measurement of the valley stack 2 mainly relies on imaging with three cameras at different positions. For the measurement of key parameters, the same feature point can be imaged at different positions under different cameras, and the detection and matching of the valley stack feature points are required. The present invention uses SURF feature points in image processing to detect SURF feature points of the valley pile 2 first, and then performs feature point matching, as shown in fig. 4. The left and right images are respectively from images of the same subject acquired by two different binocular cameras 1. And (3) detecting the available key feature points s 1,s2,s3,s4 by using SURF feature points, matching the feature points of the two images, pairing all the feature points, and calculating the average value of the key parameters.
With reference to fig. 5, fig. 5 is a schematic diagram illustrating detection of feature points of a valley pile 2 image of the valley pile 2 according to an embodiment of the present invention. In an embodiment of the present invention, the geometry of the pile 2 is conical, and step S200 further includes:
Step S201, detecting valley-pile feature points, respectively calculating valley-pile feature points S 0,s1,s2,s3,s0 obtained from three binocular cameras 1 as the midpoint of an S 1,s2 connecting line by adopting an image valley-pile feature point detection method, and respectively obtaining valley-pile feature point coordinates { u i,vi } i, =0, 1,2 under an image coordinate system of the valley-pile feature points S 0,s1,s2,s3;
Step S202, converting the coordinate system, and converting the corresponding valley pile feature point coordinates { u i,vi }, i=0, 1,2,3 from the image coordinate system to the camera coordinate system according to the formula, so as to obtain the corresponding camera coordinate system lower coordinate { x i,yi,zi }, i=0, 1,2,3;
Step 203, calculating the distance, and respectively calculating the bottom circle diameter d 1,d2,d3 and the height h 1,h2,h3 of the valley pile 2 under the view of the binocular camera 1 according to the coordinates and the geometric relationship of the valley pile feature points under the camera coordinate system, and obtaining the bottom circle diameter d of the final valley pile 2 and the height h of the final valley pile 2.
As shown in fig. 5, the base length of the triangle may be approximately the diameter of the base circle of the cone, and in step S203, the base circle diameters d 1,d2,d3 of the valley stacks 2 under the view of the binocular camera 1 are calculated as follows:
The diameters of the mounds 2 obtained by the three binocular cameras 1 are averaged as the final mound 2 bottom circle diameter d:
s 0 is the midpoint of the s 1,s2 line, and s 0 can be converted from the image coordinate system to the camera coordinate system according to the coordinate system conversion principle, so as to obtain the linear distance of s 0,s3 The linear distance l 1,l2 of s 1,s3,s2,s3 is obtained by the same method, according to the schematic side view of the valley pile 2 shown in fig. 6, the height of the valley pile 2 can be calculated according to the side length relationship of the right triangle, and the heights h 1,h2,h3 of the valley pile 2 under the view of the three binocular cameras 1 are respectively:
the heights of three of the stacks 2 are averaged as the final stack 2 height h:
finally, in step S300, the volume of the pile 2 is calculated by using the bottom radius R of the final pile 2 and the height h of the final pile 2, and is:
An image of the valley pile 2 can be obtained by using a binocular camera, and fig. 7 is a schematic diagram of the image of the valley pile 2 obtained by using a binocular camera 1. In another embodiment of the present invention, the geometric shape of the pile 2 is estimated to be rectangular, taking a cuboid as an example, and the volume of the pile 2 is calculated by a cuboid volume formula, and step S200 further includes:
Step S201, detecting a valley-pile characteristic point, and detecting the valley-pile characteristic point by adopting an image valley-pile characteristic point detection method to respectively obtain three valley-pile characteristic points S 1,s2,s3,s4 acquired by the binocular camera 1, and respectively acquiring valley-pile characteristic point coordinates { u i,vi }, i=1, 2,3,4 under an image coordinate system of the valley-pile characteristic points S 1,s2,s3,s4;
step S202, converting a coordinate system, namely converting the valley pile feature point coordinates { u i,vi }, i=1, 2,3,4 from an image coordinate system to a camera coordinate system according to a formula to obtain a corresponding camera coordinate system lower coordinate { x i,yi,zi }, i=1, 2,3,4;
And step 203, calculating the distance, namely respectively calculating the average value d s1s2,ds2s3,ds2s4 of each side length of the rectangle after respectively performing feature matching on the images acquired by the three cameras according to the coordinates and the geometric relation of the valley pile feature points under the camera coordinate system.
In step S300, the average d s1s2,ds2s3,ds2s4 of each side length is used to calculate the volume V of the valley pile 2 as follows: v=d s1s2ds2s3ds2s4.
An image of the valley pile 2 can be obtained by using a binocular camera, and fig. 8 is a schematic diagram of the image of the valley pile 2 obtained by using a binocular camera 1. In another embodiment of the present invention, the geometry of the pile 2 is cylindrical, and the volume of the pile 2 is calculated by a long cylinder volume formula, and the step S200 further includes:
Step 201, detecting valley-pile feature points, wherein by adopting an image valley-pile feature point detection method, three valley-pile feature points S 1,s2,s3 acquired by the binocular camera 1 can be respectively obtained, and valley-pile feature point coordinates { u i,vi }, i=1, 2,3 under an image coordinate system of the valley-pile feature points S 1,s2,s3 are respectively acquired;
Step S202, converting the coordinate system, and converting the valley pile feature point coordinates { u i,vi }, i=1, 2,3 from the image coordinate system to the camera coordinate system according to the formula, so as to obtain the corresponding coordinate of { x i,yi,zi }, i=1, 2,3 in the camera coordinate system;
In step S203, the distances are calculated, as shown in fig. 8, according to the coordinates and geometric relations of the valley pile feature points S 1,s2,s3 under the camera coordinate system, the average value d s1s2,ds1s3 of each side length of the cylinder can be calculated after feature matching is performed on the images acquired by the three cameras, and d s1s2 is the height of the cylinder, and d s1s3 is approximately the diameter of the cylinder.
In step S300, the average d s1s2,ds1s3 of each side length is used to calculate the volume V of the valley pile 2 as follows: v=pi d s1s3 2ds1s2.
According to the invention, RGBD images are acquired by using a binocular camera, and grain pile yield measurement of the three-dimensional spatial granary is performed based on camera internal reference matrixes and image feature point detection. The method avoids the physical constraint of manual measurement and mechanical sensor measurement, overcomes the defects of poor generality and low flexibility, improves the measurement efficiency, further realizes the on-line estimation of the harvester operation flow, can early warn the storage capacity of the granary, and avoids direct economic loss.
Of course, the present invention is capable of other various embodiments and its several details are capable of modification and variation in light of the present invention, as will be apparent to those skilled in the art, without departing from the spirit and scope of the invention as defined in the appended claims.

Claims (5)

1. The granary volume measurement and calculation method based on the binocular camera is characterized by comprising the following steps of:
S100, setting a binocular camera, wherein three binocular cameras are arranged around a grain pile of a granary in a triangular arrangement manner, the height of each binocular camera is larger than that of the grain pile, the view angle of each binocular camera completely covers the grain pile, and the grain pile is located at the center of the view field of each binocular camera;
s200, adopting RGBD images acquired by three binocular cameras as input data simultaneously, and respectively detecting valley pile characteristic points of the valley piles, converting a coordinate system and calculating the distance; and
S300, estimating the geometric shape of the grain pile, and calculating the volume of the grain pile by using a pre-established geometric model of the grain pile;
wherein the geometry of the mound is estimated to be conical, step S200 further comprises:
S201, detecting valley-pile characteristic points, respectively calculating valley-pile characteristic points S 0,s1,s2,s3,s0 obtained from three binocular cameras as the middle point of an S 1,s2 connecting line by adopting an image valley-pile characteristic point detection method, and respectively obtaining valley-pile characteristic point coordinates { u i,vi }, i=0, 1,2 and 3 under an image coordinate system of the valley-pile characteristic points S 0,s1,s2,s3;
S202, converting a coordinate system, namely converting the valley pile feature point coordinates { u i,vi }, i=0, 1,2 and 3 from an image coordinate system to a camera coordinate system respectively to obtain the corresponding coordinate { x i,yi,zi }, i=0, 1,2 and 3 under the camera coordinate system;
s203, calculating distances, namely respectively calculating the bottom circle diameter and the height of the valley pile under the vision field of the three binocular cameras according to the coordinates and the geometric relation of the valley pile characteristic points under the camera coordinate system, and obtaining the final valley pile bottom circle diameter d and the final Gu Duigao DEG h;
In step S203, the bottom circle diameters of the valley stacks under the field of the three binocular cameras are respectively:
The diameters of the stacks obtained by the three binocular cameras are averaged as the final stack bottom circle diameter d:
Find the straight line distance of s 0,s3 And calculating the straight line distance l 1,l2 of s 1,s3,s2,s3 by the same method to obtain the heights of the valley stacks under the field of the binocular camera, wherein the heights are respectively as follows:
the heights of three of the stacks were averaged as the final stack height h:
in step S300, the volume of the pile is calculated by using the final bottom circle radius R and the final Gu Duigao degrees h, and is:
2. The granary volume measurement and calculation method based on the binocular camera is characterized by comprising the following steps of:
S100, setting a binocular camera, wherein three binocular cameras are arranged around a grain pile of a granary in a triangular arrangement manner, the height of each binocular camera is larger than that of the grain pile, the view angle of each binocular camera completely covers the grain pile, and the grain pile is located at the center of the view field of each binocular camera;
s200, adopting RGBD images acquired by three binocular cameras as input data simultaneously, and respectively detecting valley pile characteristic points of the valley piles, converting a coordinate system and calculating the distance; and
S300, estimating the geometric shape of the grain pile, and calculating the volume of the grain pile by using a pre-established geometric model of the grain pile;
Wherein the geometry of the valley stack is estimated to be rectangular, step S200 further comprises:
S201, detecting valley-pile feature points, respectively calculating valley-pile feature points S 1,s2,s3,s4 acquired from three binocular cameras by adopting an image valley-pile feature point detection method, and respectively acquiring valley-pile feature point coordinates { u i,vi }, i=1, 2,3,4 under an image coordinate system of the valley-pile feature points S 1,s2,s3,s4;
S202, converting a coordinate system, namely converting the valley pile feature point coordinates { u i,vi }, i=1, 2,3,4 from an image coordinate system to a camera coordinate system respectively to obtain the corresponding coordinate { x i,yi,zi }, i=1, 2,3,4 under the camera coordinate system;
s203, calculating the distance, and respectively calculating the average value d s1s2,ds2s3,ds2s4 of each side length of the rectangle according to the coordinate and the geometric relation of the valley pile feature points under the camera coordinate system;
In step S300, the average d s1s2,ds2s3,ds2s4 of each side length is used to calculate the volume of the pile as follows: v=d s1s2ds2s3ds2s4.
3. The granary volume measurement and calculation method based on the binocular camera is characterized by comprising the following steps of:
S100, setting a binocular camera, wherein three binocular cameras are arranged around a grain pile of a granary in a triangular arrangement manner, the height of each binocular camera is larger than that of the grain pile, the view angle of each binocular camera completely covers the grain pile, and the grain pile is located at the center of the view field of each binocular camera;
s200, adopting RGBD images acquired by three binocular cameras as input data simultaneously, and respectively detecting valley pile characteristic points of the valley piles, converting a coordinate system and calculating the distance; and
S300, estimating the geometric shape of the grain pile, and calculating the volume of the grain pile by using a pre-established geometric model of the grain pile;
wherein the geometry of the mound is estimated to be a cylinder, step S200 further comprises:
S201, detecting valley-pile feature points, respectively calculating valley-pile feature points S 1,s2,s3 acquired from three binocular cameras by adopting an image valley-pile feature point detection method, and respectively acquiring valley-pile feature point coordinates { u i,vi }, i=1, 2,3 under an image coordinate system of the valley-pile feature points S 1,s2,s3;
S202, converting a coordinate system, namely converting the valley pile feature point coordinates { u i,vi }, i=1, 2 and 3 from an image coordinate system to a camera coordinate system respectively to obtain the corresponding coordinate of { x i,yi,zi }, i=1, 2 and 3 in the camera coordinate system;
S203, calculating the distance, and respectively calculating the average value d s1s2,ds2s3 of each side length of the cylinder according to the coordinate and the geometric relation of the valley pile feature points under the camera coordinate system;
In step S300, the average d s1s2,ds2s3 of each side length is used to calculate the volume of the pile as follows: v=pi d s1s2 2ds2s3.
4. A binocular camera based grain bin stack volume measuring method according to any one of claims 1-3, wherein the binocular camera has a height of 1.5 times the height of the grain stack.
5. A binocular camera based grain bin volume measurement method according to any one of claims 1 to 3, wherein the conversion between the image and camera coordinate systems is performed using the following formula:
Wherein K C2I is a camera reference matrix, u and v are coordinates in an image coordinate system, the image coordinate is scaled by α in the u axis, the image coordinate is scaled by β in the v axis, f is a distance from a physical imaging plane to an optical center, f x＝αf,fy =βf, X, Y, Z are coordinates in the camera coordinate system, and P c is a P-point camera coordinate.
CN202010684845.2A 2020-07-16 2020-07-16 Granary volume measurement and calculation method based on binocular camera Active CN111815704B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010684845.2A CN111815704B (en) 2020-07-16 2020-07-16 Granary volume measurement and calculation method based on binocular camera

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010684845.2A CN111815704B (en) 2020-07-16 2020-07-16 Granary volume measurement and calculation method based on binocular camera

Publications (2)

Publication Number Publication Date
CN111815704A CN111815704A (en) 2020-10-23
CN111815704B true CN111815704B (en) 2024-05-03

Family

ID=72864987

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010684845.2A Active CN111815704B (en) 2020-07-16 2020-07-16 Granary volume measurement and calculation method based on binocular camera

Country Status (1)

Country Link
CN (1) CN111815704B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114485434B (en) * 2022-01-27 2022-10-21 南京航空航天大学 Installation detection method for guide rod of flexible three-dimensional weaving equipment based on multi-view distance measurement

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107192348A (en) * 2016-03-14 2017-09-22 武汉小狮科技有限公司 A kind of high-precision 3D vision measuring methods
CN108734744A (en) * 2018-04-28 2018-11-02 国网山西省电力公司电力科学研究院 A kind of remote big field-of-view binocular scaling method based on total powerstation
CN109272547A (en) * 2018-09-17 2019-01-25 南京阿凡达机器人科技有限公司 A kind of package circumscribed volume measurement method, system, storage medium and mobile terminal
EA201700618A1 (en) * 2017-07-12 2019-01-31 Кайрат Темирбаевич Кошеков METHOD FOR DETERMINING GRAIN VOLUME IN GRAIN DEPOTS ON THE BASIS OF CONTACTLESS 3D MEASUREMENTS
CN109598762A (en) * 2018-11-26 2019-04-09 江苏科技大学 A kind of high-precision binocular camera scaling method
CN110132226A (en) * 2019-05-14 2019-08-16 广东电网有限责任公司 The distance and azimuth angle measurement system and method for a kind of unmanned plane line walking

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107192348A (en) * 2016-03-14 2017-09-22 武汉小狮科技有限公司 A kind of high-precision 3D vision measuring methods
EA201700618A1 (en) * 2017-07-12 2019-01-31 Кайрат Темирбаевич Кошеков METHOD FOR DETERMINING GRAIN VOLUME IN GRAIN DEPOTS ON THE BASIS OF CONTACTLESS 3D MEASUREMENTS
CN108734744A (en) * 2018-04-28 2018-11-02 国网山西省电力公司电力科学研究院 A kind of remote big field-of-view binocular scaling method based on total powerstation
CN109272547A (en) * 2018-09-17 2019-01-25 南京阿凡达机器人科技有限公司 A kind of package circumscribed volume measurement method, system, storage medium and mobile terminal
CN109598762A (en) * 2018-11-26 2019-04-09 江苏科技大学 A kind of high-precision binocular camera scaling method
CN110132226A (en) * 2019-05-14 2019-08-16 广东电网有限责任公司 The distance and azimuth angle measurement system and method for a kind of unmanned plane line walking

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
基于双目视觉的不规则堆料体积测量研究;丁嗣禹;苗红霞;齐本胜;张衡;;计算机测量与控制(第04期);全文 *

Also Published As

Publication number Publication date
CN111815704A (en) 2020-10-23

Similar Documents

Publication Publication Date Title
CN109146980B (en) Monocular vision based optimized depth extraction and passive distance measurement method
CN109035320B (en) Monocular vision-based depth extraction method
US11699247B2 (en) System and method for runtime determination of camera miscalibration
CN110118528B (en) Line structure light calibration method based on chessboard target
CN109269430B (en) Multi-standing-tree breast height diameter passive measurement method based on deep extraction model
US8438991B2 (en) System for connecting a teat cup to a teat
CN110378969B (en) Convergent binocular camera calibration method based on 3D geometric constraint
CN110455222B (en) High-precision rotation angle measuring method, device and equipment
CN109579695B (en) Part measuring method based on heterogeneous stereoscopic vision
CN112258583B (en) Distortion calibration method for close-range image based on equal distortion partition
CN109255818B (en) Novel target and extraction method of sub-pixel level angular points thereof
CN112880642A (en) Distance measuring system and distance measuring method
CN112991460B (en) Binocular measurement system, method and device for obtaining size of automobile part
CN111815704B (en) Granary volume measurement and calculation method based on binocular camera
CN111829439B (en) High-precision translation measuring method and device
CN112362034A (en) Solid engine multi-cylinder section butt joint guiding measurement algorithm based on binocular vision
CN215639489U (en) Calibration board
WO2023060717A1 (en) High-precision positioning method and system for object surface
CN115705621A (en) Monocular vision real-time distance measurement method and distance measurement system based on embedded platform
CN111815703B (en) Handheld grain pile measuring device and grain pile measuring method based on binocular camera
CN113494927A (en) Vehicle multi-sensor calibration method and device and vehicle
CN116449393B (en) Multi-sensor measurement method and system for large and medium-sized stockpiles
CN112743524B (en) Target device, and pose detection system and method based on binocular vision measurement
CN2645034Y (en) Object space pose detection apparatus
Chen et al. A New Method for Error Analysis of Binocular Stereo Vision System

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant