CN115326805A - Image acquisition device and IBMR-based tobacco crop growth analysis method - Google Patents
Image acquisition device and IBMR-based tobacco crop growth analysis method Download PDFInfo
- Publication number
- CN115326805A CN115326805A CN202211245297.9A CN202211245297A CN115326805A CN 115326805 A CN115326805 A CN 115326805A CN 202211245297 A CN202211245297 A CN 202211245297A CN 115326805 A CN115326805 A CN 115326805A
- Authority
- CN
- China
- Prior art keywords
- tobacco
- box body
- crop
- images
- crops
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 235000002637 Nicotiana tabacum Nutrition 0.000 title claims abstract description 156
- 241000208125 Nicotiana Species 0.000 title claims abstract description 150
- 238000004458 analytical method Methods 0.000 title claims abstract description 15
- 238000000034 method Methods 0.000 claims abstract description 22
- 230000005540 biological transmission Effects 0.000 claims abstract description 14
- 230000007246 mechanism Effects 0.000 claims description 53
- 241000196324 Embryophyta Species 0.000 claims description 12
- 238000004891 communication Methods 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 239000004744 fabric Substances 0.000 claims description 5
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 244000061176 Nicotiana tabacum Species 0.000 abstract description 6
- 230000009286 beneficial effect Effects 0.000 abstract description 4
- 230000033001 locomotion Effects 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000002360 preparation method Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 244000038559 crop plants Species 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/757—Matching configurations of points or features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N2021/8466—Investigation of vegetal material, e.g. leaves, plants, fruits
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Biochemistry (AREA)
- Multimedia (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Chemical & Material Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Analytical Chemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Manufacture Of Tobacco Products (AREA)
Abstract
The invention belongs to the technical field of tobacco machinery, and relates to an image acquisition device and an IBMR-based tobacco crop growth analysis method. The image acquisition device comprises a plurality of cameras, a box body bracket, a field track, a mobile platform, an electric control cabinet and a power supply unit; the electric control cabinet comprises a power supply unit, a control unit and a data transmission unit. The invention can carry out remote tobacco leaf crop characteristic data acquisition, realize the rapid movement of the device and is beneficial to improving the efficiency of acquiring the tobacco leaf crop image; the accuracy of acquiring the growth characteristic data of the tobacco crops is improved by acquiring the tobacco crop images at a plurality of angles; the IBMR-based three-dimensional image modeling method is adopted to complete three-dimensional modeling of tobacco plants, so that growth characteristic data of tobacco crops can be accurately obtained, and real-time reliable data is provided for tobacco planting and growth analysis.
Description
Technical Field
The invention belongs to the technical field of tobacco machinery, and particularly relates to a tobacco crop image acquisition device and an IBMR-based tobacco crop growth analysis method.
Background
The plant height, leaf number, leaf area and other physical characteristics of tobacco plants have planting benefits. The plant phenotype technology can accurately obtain the physiological and biochemical properties of tobacco crop plants through imaging and spectrum technology, but the equipment price is high, the equipment is inconvenient to be arranged in the field for a long time, and the capacity of long-term rapid high-frequency acquisition is not realized; at present, common plant phenotype scanning equipment is handheld or large-scale scanning equipment arranged in a gantry crane, and the equipment is complicated in power supply and operation and cannot acquire high-frequency and high-efficiency data.
The existing mode of analyzing the growth characteristics of tobacco crops by artificial software modeling is suitable for modeling virtual objects or large buildings, the model accuracy is low, and the image reality sense is poor; the method of modeling by utilizing the instrument and equipment is suitable for industrial production of numerical control machines and the like, and has large data processing capacity and poor texture color. Therefore, the existing method for analyzing the growth characteristics of the tobacco crops is low in accuracy, large in data quantity and low in data reliability.
Disclosure of Invention
In order to solve the technical problems, the invention provides an image acquisition device and an IBMR-based tobacco crop growth analysis method.
In a first aspect, the present disclosure provides an image acquisition apparatus comprising:
the cameras are used for acquiring tobacco crop images at multiple angles;
a box body bracket; each camera is arranged on the box body bracket around the center of the box body bracket; tobacco crops enter the box body support, and the cameras acquire tobacco crop images of the tobacco crops at multiple angles;
a field track;
the mobile platform is arranged on the field track and moves on the field track; a moving mechanism is fixedly arranged on the moving platform; the box body support is arranged on the moving mechanism, and the moving mechanism drives the box body support to move close to the tobacco leaf crops;
the electric control cabinet is fixed on the mobile platform and comprises a power supply unit, a control unit and a data transmission unit; the power supply unit is used for supplying power to the moving mechanism and the control unit; the control unit is used for sending a control instruction to the moving mechanism to adjust the working state of the moving mechanism; the data transmission unit is in electric signal connection with the control unit and is used for transmitting the tobacco crop image;
and the power supply unit is arranged on the mobile platform and used for supplying power to the power supply unit.
In a second aspect, the present disclosure provides a method for IBMR-based tobacco crop growth analysis, comprising:
collecting tobacco leaf crop images of a single tobacco leaf crop at multiple angles by using an image collecting device;
uploading the tobacco crop image to a cloud server terminal;
constructing a three-dimensional model of the tobacco crop image by using the tobacco crop images at a plurality of angles;
measuring and analyzing the characteristics of the three-dimensional model, and extracting growth characteristic data of tobacco crops;
and analyzing the growth characteristic data.
The invention has the beneficial effects that: the device can be used for collecting remote tobacco leaf crop characteristic data, automatic control of the front-end moving mechanism and the camera is realized, before images are collected, the box body support is controlled to move to the periphery of a plant, preparation work before shooting is completed, rapid movement of the device is completed, and the efficiency of obtaining tobacco leaf crop images is improved; by acquiring tobacco leaf crop images at multiple angles, the image modeling precision is improved, and the accuracy of acquiring the growth characteristic data of the tobacco leaf crops is improved; the IBMR-based three-dimensional image modeling method is adopted to complete three-dimensional modeling of tobacco plants, so that growth characteristic data of tobacco crops can be accurately obtained, and real-time reliable data are provided for tobacco planting and growth analysis.
On the basis of the technical scheme, the invention can be improved as follows.
Furthermore, the box body bracket is provided with shading cloth for shading a light source outside the box body; the box body support is provided with an LED line light source used for providing light sources for the cameras to collect tobacco crop images at various angles.
Further, the moving mechanism comprises a supporting seat, a gear guide rail and an electric mechanism; the supporting seats are fixed on two sides of the mobile platform; the gear guide rail is fixed on the supporting seat; the electric mechanism is provided with a gear; the gear is meshed with the gear guide rail; the box body bracket is fixed on the electric mechanism; the electric mechanism drives the box body support to move on the gear guide rail.
Further, the electric mechanism comprises a shell, a motor driver, a stepping motor, a bearing sleeved on the outer side of an output shaft of the stepping motor, a bearing seat and a gear; the bearing seat is fixed on the shell; the box body bracket is fixed on the outer side of the shell; the gear is sleeved on the outer side of the output shaft of the stepping motor; the control unit is in electric signal connection with the motor driver; the motor driver is electrically connected with the stepping motor.
Further, the data transmission unit includes a communication module; the electric control cabinet is provided with a relay;
the output end of the control unit is in electric signal connection with the communication module; the control unit is electrically connected with the moving mechanism through the relay.
Further, a storage battery is arranged in the electric control cabinet; the power supply unit comprises a vertical rod, a solar panel and a charge-discharge controller; the solar panel and the charge and discharge controller are fixed on the upright rod; the upright stanchion is fixed on the mobile platform; the solar panel is electrically connected with the charge and discharge controller; the charge and discharge controller is electrically connected with the storage battery.
Further, constructing a three-dimensional model of the tobacco crop image by using the tobacco crop images at a plurality of angles, comprising:
extracting a plurality of characteristic points of the tobacco crop image;
carrying out feature point matching on the plurality of tobacco leaf crop images to obtain a plurality of tobacco leaf crop images matched with a plurality of groups of feature points;
and estimating the pose of the camera by utilizing the multiple images of the tobacco crops matched with the characteristic points of each group, and reconstructing a three-dimensional coordinate point.
Further, estimating the pose of a camera by utilizing a plurality of tobacco crop images matched with each group of feature points, and reconstructing a three-dimensional coordinate point, wherein the method comprises the following steps:
determining an essential matrix by using the matched characteristic points in the tobacco crop images;
decomposing the essential matrix and determining an optimal solution after decomposition;
calculating according to camera internal parameters to obtain a plurality of projection matrixes corresponding to the tobacco crop images;
reconstructing three-dimensional point coordinates by using a trigonometry method based on the matched feature points of the two projection matrixes and the plurality of tobacco crop images;
and optimizing the camera pose and the three-dimensional point coordinate by using a binding adjustment method.
Further, the growth characteristic data comprises plant height data, leaf quantity data, leaf area data, leaf width data and leaf length data.
Drawings
Fig. 1 is a schematic structural diagram of a tobacco crop image acquisition device provided in embodiment 1 of the present invention;
FIG. 2 is a schematic view of the structure of a moving mechanism in embodiment 1 of the present invention;
FIG. 3 is a schematic diagram of an architecture of a tobacco crop growth analysis system based on IBMR in embodiment 2 of the present invention;
FIG. 4 is a flow chart of a method for analyzing the growth vigor of tobacco crops based on IBMR in example 2 of the present invention;
FIG. 5 is a schematic diagram of a method for constructing a three-dimensional model of a tobacco plant image using tobacco plant images from multiple angles according to embodiment 2 of the present invention;
FIG. 6 is a schematic diagram of estimating a camera pose and reconstructing three-dimensional coordinate points using a plurality of tobacco crop images matched with each group of feature points in embodiment 2 of the present invention;
fig. 7 is a schematic diagram of feature point selection in embodiment 2 of the present invention.
Icon: 1-a camera; 101-a first camera; 102-a second camera; 103-a third camera; 2-a box body bracket; 3-moving the platform; 4-an electric control cabinet; 5-a moving mechanism; 6-erecting a rod; 7-a solar panel; 8-a charge-discharge controller; 9-a monitoring camera; 501-supporting seat; 502-gear guide; 503-an electric mechanism; 1001-tobacco leaf crop image acquisition device; 1002-a cloud server; 1003-visual monitor terminal; 701 — first target point; 703-a third target point; 704-fourth target point; 705-fifth target point; 706-sixth target point; 707-seventh target point; 708-a first feature point; 709-a second feature point; 710-third feature point.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Example 1
As an embodiment, as shown in fig. 1, to solve the above technical problem, the present embodiment provides an image capturing device for tobacco crops, including:
the cameras 1 are used for collecting tobacco crop images at multiple angles;
a box body support 2; each camera 1 is arranged on the box body bracket 2 around the center of the box body bracket 2; tobacco crops enter the box body support 2, and the cameras 1 acquire tobacco crop images of the tobacco crops at multiple angles;
a field track;
the mobile platform 3 is arranged on the field track and moves on the field track; a moving mechanism 5 is fixedly arranged on the moving platform 3; the box body support 2 is arranged on the moving mechanism 5, and the moving mechanism 5 drives the box body support 2 to move close to the tobacco leaf crops;
the electric control cabinet 4 is fixed on the mobile platform 3, and the electric control cabinet 4 comprises a power supply unit, a control unit and a data transmission unit; the power supply unit is used for supplying power to the moving mechanism 5 and the control unit; the control unit is used for sending a control instruction to the moving mechanism 5 to adjust the working state of the moving mechanism 5; the data transmission unit is in electric signal connection with the control unit and is used for transmitting the tobacco crop image;
and the power supply unit is arranged on the mobile platform 3 and used for supplying power to the power supply unit.
In the practical application process, a plurality of cameras 1 are arranged on a box body support 2, the shooting angle of each camera 1 faces the interior of a box body, and a plurality of cameras 1 simultaneously acquire tobacco crop images in the box body support 2; the box body support 2 moves on the moving platform 3 through the moving mechanism 5, and the moving platform 3 moves on the field track; the initial position of the box body support 2 is positioned right above the moving platform 3, and after the box body support 2 moves in the direction vertical to the field track, the main body part of the box body support 2 deviates from the position right above the moving platform 3 and is sleeved with tobacco crops; the multiple cameras 1 simultaneously acquire tobacco crop images at multiple angles and transmit the tobacco crop images to the data transmission unit; and the data transmission unit transmits the tobacco crop image to an external terminal for processing.
Optionally, the controller sends a control command to the stepping motor driver, and the stepping motor driver drives the stepping motor to work; the moving platform 3 is driven by a stepping motor to move on the field track. Specifically, the bottom of the moving platform 3 is provided with a rotating wheel, and an output shaft of the stepping motor drives the rotating wheel to rotate on the field track, so that the moving platform 3 moves on the field track. The moving efficiency of the moving platform 3 is improved, and therefore the efficiency of obtaining the tobacco crop images is improved.
The electric control cabinet 4 is provided with a control unit, the moving mechanism 5 drives the box body support 2 to move relative to the moving platform 3, the control unit sends a control instruction to control the moving mechanism 5 to move, and the moving mechanism 5 drives the box body support 2 to move back and forth on the moving platform 3 in a direction perpendicular to the field track direction.
The field rail is positioned in the tobacco crop planting area and arranged along the direction of the tobacco crops; the mobile platform 3 moves on the field rail along the field rail, and the collection efficiency of the tobacco crop images is improved.
Optionally, the box body support 2 is provided with a shading cloth for shading a light source outside the box body; the box body support 2 is provided with an LED line light source for providing light sources for the cameras 1 to collect tobacco crop images at various angles.
After the box body support 2 is used for sheathing tobacco leaf crops, the LED line light source provides light sources for collecting images of the tobacco leaf crops at various angles for the cameras 1 in the box body support 2, and the shading cloth shades the light sources outside the box body, so that the image quality of the tobacco leaf crops is improved. The shading cloth is used for shading an external light source, so that the influence of nearby plants is reduced, the contrast is enhanced, and the emissivity of the surrounding environment is reduced; through LED line source directional reflection, reduce the effect of ambient light interference, improve the image quality of shooting to improve image modeling precision, improve the degree of accuracy of obtaining tobacco leaf crop growth characteristic data.
Optionally, as shown in fig. 2, the moving mechanism 5 includes a supporting base 501, a gear guide 502 and an electric mechanism 503; the supporting seats 501 are fixed on both sides of the mobile platform 3; the gear guide 502 is fixed on the support seat 501; the electric mechanism 503 is provided with gears; the gears mesh with gear guide 502; the box body bracket 2 is fixed on the electric mechanism 503; the electric mechanism 503 moves the casing support 2 on the gear guide 502.
The box body support 2 is fixed on the electric mechanism 503, the electric mechanism 503 drives the box body support 2 to move linearly on the gear guide rail 502, and in the actual working process, the moving mechanism 5 drives the box body support 2 to move close to the tobacco leaf crops, so that the box body support 2 covers the tobacco leaf crops, the cameras 1 at a plurality of angles arranged on the box body support 2 surround the tobacco leaf crops, and images of the tobacco leaf crops are collected.
Optionally, the electric mechanism 503 includes a housing, a motor driver, a step motor, a bearing sleeved outside an output shaft of the step motor, a bearing seat, and a gear; the bearing seat is fixed on the shell; the box body bracket 2 is fixed at the outer side of the shell; the gear is sleeved outside the output shaft of the stepping motor; the control unit is in electric signal connection with the motor driver; the motor driver is electrically connected with the stepping motor.
The output shaft of the stepper motor drives the gear to rotate, and the gear is meshed with the gear guide rail 502. The electric mechanism 503 moves the casing support 2 on the gear guide 502.
Optionally, the data transmission unit includes a communication module; the electric control cabinet 4 is provided with a relay;
the output end of the control unit is in electric signal connection with the communication module; the control unit is connected with the moving mechanism 5 through a relay in an electric signal mode.
The communication module is used for data transmission, so that remote data acquisition can be realized,
optionally, a storage battery is arranged in the electric control cabinet 4; the power supply unit comprises a vertical rod 6, a solar panel 7 and a charge-discharge controller 8; the solar panel 7 and the charge and discharge controller 8 are fixed on the upright rod 6; the upright rod 6 is fixed on the movable platform 3; the solar panel 7 is electrically connected with the charge and discharge controller 8; the charge and discharge controller 8 is electrically connected to the battery.
The upright stanchion 6 supports the solar panel 7 and the charge and discharge controller 8, and in the actual application process, the lighting effect of the solar panel 7 is favorably improved by adjusting the angle between the solar panel 7 and the upright stanchion 6. The charge and discharge controller 8 adjusts the power of the storage battery which is transmitted to the electric control cabinet 4 by the solar panel 7. The solar energy power supply mode is adopted, and the energy-saving effect is achieved.
Optionally, set up surveillance camera 9 on the pole setting 6, surveillance camera 9 and controller signal of telecommunication are connected, and surveillance camera 9 collection system's video data realizes the remote visual control of operation process with data transmission to remote terminal through communication module.
The remote control device can be used for collecting the characteristic data of the tobacco crops remotely, realizes the automatic control of the front-end moving mechanism 5 and the camera 1, controls the box body support 2 to move to the periphery of the plants before collecting images, finishes the preparation work before shooting, finishes the quick movement of the device, and is beneficial to improving the efficiency of obtaining the images of the tobacco crops; by acquiring the tobacco leaf crop images at multiple angles, the image modeling precision is improved, and the accuracy of acquiring the growth characteristic data of the tobacco leaf crops is improved.
In the embodiment of the invention, the equipment such as the camera, the stepping motor and the like has low cost, high feasibility, easy maintenance and strong practicability, achieves better data acquisition effect in a short time, is beneficial to completing 3D modeling of plants and improves the efficiency of acquiring images of tobacco crops.
Example 2
The same principle as that of embodiment 1 of the present invention is that, as shown in fig. 4, an embodiment of the present invention further provides an IBMR-based method for analyzing growth vigor of tobacco crops, including:
acquiring tobacco leaf crop images of a plurality of angles of a single tobacco leaf crop by using a tobacco leaf crop image acquisition device;
uploading the tobacco crop image to a cloud server terminal;
constructing a three-dimensional model of the tobacco crops by using the tobacco crop images at a plurality of angles;
measuring and analyzing the characteristics of the three-dimensional model, and extracting growth characteristic data of tobacco crops;
and analyzing the growth characteristic data.
Optionally, based on the framework of the IBMR-based tobacco crop growth analysis system shown in fig. 3, the image acquisition device 1001 acquires images of tobacco crops at multiple angles and sends the images of the tobacco crops to the cloud server 1002; the cloud server 1002 draws a three-dimensional model of the tobacco crops according to the collected tobacco crop images at multiple angles, analyzes the growth characteristics of the tobacco crops by using the three-dimensional model, and obtains growth characteristic data of the tobacco crops; the visual monitoring terminal 1003 sends a control instruction to the tobacco crop image acquisition device 1001, and obtains and displays growth characteristic data of the cloud server 1002.
Optionally, the growth characteristic data includes plant height data, leaf number data, leaf area data, leaf width data and leaf length data.
Specifically, the tobacco crop image acquisition device is provided with 12 cameras, tobacco crop images at 12 different angles are obtained and transmitted back to the field to acquire the tobacco crop images, modeling is carried out through the cloud server end, so that a 3D model of a plant is formed, and growth characteristic data of the tobacco crops are measured. And analyzing and judging whether the growth condition of the tobacco crops is normal or not according to whether the growth condition characteristic data of the tobacco crops are in a set range or not, wherein if the growth condition characteristic data of the tobacco crops are in the set range, the growth condition of the tobacco crops is normal, otherwise, the growth condition of the tobacco crops is abnormal.
The image acquisition device can be used for acquiring characteristic data of tobacco crops remotely, automatic control of the front-end moving mechanism and the camera is realized, before the images are acquired, the box body support is controlled to move to the periphery of a plant, preparation work before shooting is completed, the device is moved quickly, and the efficiency of acquiring the images of the tobacco crops is improved; by acquiring the tobacco leaf crop images at multiple angles, the image modeling precision is improved, and the accuracy of acquiring the growth characteristic data of the tobacco leaf crops is improved.
IBMR (Image Base Modeling and Rendering) refers to the representation of the shape and appearance of a scene with a series of images (synthetic or real) acquired in advance. The synthesis of new images is realized by combining and processing a series of original images, and the photos in different sight directions and different positions are organized to represent scenes, such as images (panoramic images) and light fields (light fields), so that the appearance and the details of real scenes can be directly reflected, the geometric characteristics, the motion characteristics and the like of objects can be extracted from the photos, the shapes, rich light and shade, rich materials and texture details of the scenes can be more truly represented, and stronger reality can be obtained; by adopting the IBMR image processing method, only discrete picture sampling is needed, only the image adjacent to the current viewpoint is processed during drawing, the drawing calculation amount does not depend on the scene complexity, but is only related to the image resolution required by the generated picture, so that the drawing requirement on the calculation resources is not high, only a small calculation amount is needed, and the operation efficiency of the system is improved.
Optionally, as shown in fig. 5, constructing a three-dimensional model of a tobacco leaf crop image by using the tobacco leaf crop images at multiple angles includes:
extracting a plurality of characteristic points of the tobacco crop image;
carrying out feature point matching on the plurality of tobacco leaf crop images to obtain a plurality of tobacco leaf crop images matched with a plurality of groups of feature points;
and estimating the pose of the camera by utilizing the plurality of tobacco crop images matched with each group of characteristic points, and reconstructing a three-dimensional coordinate point.
Optionally, as shown in fig. 6, estimating a camera pose and reconstructing a three-dimensional coordinate point by using a plurality of tobacco crop images matched with each group of feature points, where the method includes:
determining an essential matrix by using the matched characteristic points in the tobacco crop images;
decomposing the essential matrix and determining an optimal solution after decomposition;
calculating according to camera internal parameters to obtain a plurality of projection matrixes corresponding to the tobacco crop images;
reconstructing three-dimensional point coordinates by using a trigonometry method based on the matched feature points of the two projection matrixes and the plurality of tobacco crop images;
and optimizing the camera pose and the three-dimensional point coordinate by using a binding adjustment method.
As shown in fig. 7, a plurality of target points exist on the target tobacco leaf crop, including a first target point 701, a third target point 703, a fourth target point 704, a fifth target point 705, a sixth target point 706 and a seventh target point 707, the first camera 101, the second camera 102 and the third camera 103 collect an image of the first target point 701, and the image corresponds to a first feature point 708, a second feature point 709 and a third feature point 710. Similarly, the positions of the third target point 703, the fourth target point 704, the fifth target point 705, the sixth target point 706 and the seventh target point 707 in the image are acquired by the first camera 101, the second camera 102 and the third camera 103.
According to the method, the IBMR-based three-dimensional image modeling method is adopted, images in the same position are captured through the camera from different visual angles, then the depth information of an object is obtained by using the triangulation principle, a three-dimensional model of the object is reconstructed through the depth information, and the three-dimensional image modeling of tobacco plants is completed, so that the growth characteristic data of tobacco crops can be accurately obtained, and real-time and reliable data are provided for tobacco planting and growth analysis.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes will occur to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. Image acquisition device, its characterized in that includes:
the cameras are used for acquiring tobacco crop images at multiple angles;
a box body bracket; each camera is arranged on the box body bracket around the center of the box body bracket; tobacco crops enter the box body support, and the cameras acquire tobacco crop images of the tobacco crops at multiple angles;
a field track;
the mobile platform is arranged on the field track and moves on the field track; a moving mechanism is fixedly arranged on the moving platform; the box body support is arranged on the moving mechanism, and the moving mechanism drives the box body support to move close to the tobacco crops;
the electric control cabinet is fixed on the mobile platform and comprises a power supply unit, a control unit and a data transmission unit; the power supply unit is used for supplying power to the moving mechanism and the control unit; the control unit is used for sending a control instruction to the moving mechanism to adjust the working state of the moving mechanism; the data transmission unit is in electric signal connection with the control unit and is used for transmitting the tobacco crop image;
and the power supply unit is arranged on the mobile platform and used for supplying power to the power supply unit.
2. The image acquisition device according to claim 1, wherein the box body support is provided with a shading cloth for shading a light source outside the box body; the box body support is provided with an LED line light source used for providing light sources for the cameras to acquire tobacco crop images at all angles.
3. The image capturing device as claimed in claim 1, wherein the moving mechanism comprises a supporting base, a gear guide and an electric mechanism; the supporting seats are fixed on two sides of the mobile platform; the gear guide rail is fixed on the supporting seat; the electric mechanism is provided with a gear; the gear is meshed with the gear guide rail; the box body bracket is fixed on the electric mechanism; the electric mechanism drives the box body support to move on the gear guide rail.
4. The image acquisition device according to claim 3, wherein the electric mechanism comprises a housing, a motor driver, a stepping motor, a bearing sleeved outside an output shaft of the stepping motor, a bearing seat and a gear; the bearing seat is fixed on the shell; the box body bracket is fixed on the outer side of the shell; the gear is sleeved on the outer side of the output shaft of the stepping motor; the control unit is in electric signal connection with the motor driver; the motor driver is electrically connected with the stepping motor.
5. The image acquisition device according to claim 1, wherein the data transmission unit comprises a communication module; the electric control cabinet is provided with a relay;
the output end of the control unit is in electric signal connection with the communication module; the control unit is electrically connected with the moving mechanism through the relay.
6. The image acquisition device according to claim 1, wherein a storage battery is arranged in the electric control cabinet; the power supply unit comprises a vertical rod, a solar panel and a charge-discharge controller; the solar panel and the charge and discharge controller are fixed on the upright rod; the upright stanchion is fixed on the mobile platform; the solar panel is electrically connected with the charge and discharge controller; the charge and discharge controller is electrically connected with the storage battery.
7. The IBMR-based tobacco crop growth analysis method is characterized by comprising the following steps:
acquiring tobacco crop images of a single tobacco crop at a plurality of angles by using the image acquisition device according to claim 1;
uploading the tobacco crop image to a cloud server terminal;
constructing a three-dimensional model of the tobacco leaf crop image by using the tobacco leaf crop images at a plurality of angles;
measuring and analyzing the three-dimensional model, and extracting growth characteristic data of tobacco crops;
and analyzing the growth characteristic data.
8. The IBMR-based tobacco crop growth analysis method according to claim 7, wherein constructing a three-dimensional model of tobacco crop images using the tobacco crop images from a plurality of angles comprises:
extracting a plurality of characteristic points of the tobacco crop image;
carrying out feature point matching on the plurality of tobacco leaf crop images to obtain a plurality of tobacco leaf crop images matched with a plurality of groups of feature points;
and estimating the pose of the camera by utilizing the multiple images of the tobacco crops matched with the characteristic points of each group, and reconstructing a three-dimensional coordinate point.
9. The IBMR-based tobacco crop growth analysis method according to claim 7, wherein the estimating of the camera pose and the reconstructing of the three-dimensional coordinate points using the plurality of tobacco crop images for each set of feature point matching comprises:
determining an essential matrix by using the matched characteristic points in the tobacco crop images;
decomposing the essential matrix and determining an optimal solution after decomposition;
calculating according to camera internal parameters to obtain a plurality of projection matrixes corresponding to the tobacco crop images;
reconstructing three-dimensional point coordinates by using a trigonometry method based on the matched feature points of the two projection matrixes and the plurality of tobacco crop images;
and optimizing the camera pose and the three-dimensional point coordinate by using a binding adjustment method.
10. The IBMR-based tobacco crop growth analysis method according to claim 7, wherein the growth characteristic data comprises plant height data, leaf number data, leaf area data, leaf width data and leaf length data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211245297.9A CN115326805A (en) | 2022-10-12 | 2022-10-12 | Image acquisition device and IBMR-based tobacco crop growth analysis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211245297.9A CN115326805A (en) | 2022-10-12 | 2022-10-12 | Image acquisition device and IBMR-based tobacco crop growth analysis method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115326805A true CN115326805A (en) | 2022-11-11 |
Family
ID=83914334
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211245297.9A Pending CN115326805A (en) | 2022-10-12 | 2022-10-12 | Image acquisition device and IBMR-based tobacco crop growth analysis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115326805A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103699095A (en) * | 2013-12-25 | 2014-04-02 | 北京交通大学 | Greenhouse plant growth posture monitoring system based on binocular stereo vision and greenhouse plant growth posture monitoring method based on binocular stereo vision |
| CN110415332A (en) * | 2019-06-21 | 2019-11-05 | 上海工程技术大学 | Complex textile surface three dimensional reconstruction system and method under a kind of non-single visual angle |
| CN111724433A (en) * | 2020-06-24 | 2020-09-29 | 广西师范大学 | Crop phenotype parameter extraction method and system based on multi-view vision |
| CN112200854A (en) * | 2020-09-25 | 2021-01-08 | 华南农业大学 | Leaf vegetable three-dimensional phenotype measurement method based on video image |
| CN113189015A (en) * | 2021-04-23 | 2021-07-30 | 宿州学院 | Hyperspectral remote sensing-based insect pest monitoring system and method |
| CN114240866A (en) * | 2021-12-09 | 2022-03-25 | 广东省农业科学院环境园艺研究所 | Tissue culture seedling grading method and device based on two-dimensional image and three-dimensional growth information |
| CN114659463A (en) * | 2022-03-14 | 2022-06-24 | 华南农业大学 | Plant phenotype acquisition device and acquisition method thereof |
| CN115035327A (en) * | 2022-08-15 | 2022-09-09 | 北京市农林科学院信息技术研究中心 | Plant production line phenotype acquisition platform and plant phenotype fusion analysis method |
-
2022
- 2022-10-12 CN CN202211245297.9A patent/CN115326805A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103699095A (en) * | 2013-12-25 | 2014-04-02 | 北京交通大学 | Greenhouse plant growth posture monitoring system based on binocular stereo vision and greenhouse plant growth posture monitoring method based on binocular stereo vision |
| CN110415332A (en) * | 2019-06-21 | 2019-11-05 | 上海工程技术大学 | Complex textile surface three dimensional reconstruction system and method under a kind of non-single visual angle |
| CN111724433A (en) * | 2020-06-24 | 2020-09-29 | 广西师范大学 | Crop phenotype parameter extraction method and system based on multi-view vision |
| CN112200854A (en) * | 2020-09-25 | 2021-01-08 | 华南农业大学 | Leaf vegetable three-dimensional phenotype measurement method based on video image |
| CN113189015A (en) * | 2021-04-23 | 2021-07-30 | 宿州学院 | Hyperspectral remote sensing-based insect pest monitoring system and method |
| CN114240866A (en) * | 2021-12-09 | 2022-03-25 | 广东省农业科学院环境园艺研究所 | Tissue culture seedling grading method and device based on two-dimensional image and three-dimensional growth information |
| CN114659463A (en) * | 2022-03-14 | 2022-06-24 | 华南农业大学 | Plant phenotype acquisition device and acquisition method thereof |
| CN115035327A (en) * | 2022-08-15 | 2022-09-09 | 北京市农林科学院信息技术研究中心 | Plant production line phenotype acquisition platform and plant phenotype fusion analysis method |
Non-Patent Citations (1)
| Title |
|---|
| 史维杰 等: "基于三维重建技术的植物表型分析", 《物联网技术》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109218702B (en) | Camera rotation type 3D measurement and information acquisition device | |
| CN102967373B (en) | Three-dimensional (3D) infrared temperature monitoring method and system for substation | |
| CN103690191B (en) | A kind of ultrasonic probe intelligence continuous sweep device and scan method thereof | |
| CN104954746A (en) | Intelligentized mobile vehicle-mounted remote crop digital image acquisition system and method thereof | |
| CN110290350A (en) | A kind of real-time status monitoring method, system and the storage medium of crusing robot | |
| CN108648147B (en) | Super-resolution image acquisition method and system of human eye retina mechanism | |
| CN108332660B (en) | Robot three-dimensional scanning system and scanning method | |
| CN104374374B (en) | 3D environment dubbing system and 3D panoramas display method for drafting based on active panoramic vision | |
| CN109215110A (en) | Whole scene scanning means and 3-D scanning modeling | |
| CN213812165U (en) | Three-dimensional scanning imaging system applied underwater | |
| CN110864725A (en) | Panoramic three-dimensional color laser scanning system and method based on lifting motion | |
| CN110849269A (en) | System and method for measuring geometric dimension of field corn cobs | |
| CN201101524Y (en) | Portable three-dimensional human body scanning device | |
| CN106886758B (en) | Insect identification device and method based on 3 d pose estimation | |
| CN209297361U (en) | Human body rapid modeling equipment based on three-dimensional reconstruction | |
| CN205105340U (en) | Interactive display device of 3D of transformer substation | |
| CN109579910A (en) | Crop water consumption rule phenotype monitors system and method | |
| CN115326805A (en) | Image acquisition device and IBMR-based tobacco crop growth analysis method | |
| CN105468154A (en) | Interactive panorama display system for power system operation | |
| CN112804452A (en) | Intelligent phenotype collection trolley and collection method based on high-stalk crops | |
| CN210374998U (en) | High-flux photographing system for acquiring crop phenotype | |
| CN215420559U (en) | Annular three-dimensional image acquisition device for small and medium-sized scenes | |
| CN209132573U (en) | The holder of camera and adjustable camera angle | |
| CN214747806U (en) | Three-dimensional scanning imaging device applied to underwater | |
| CN109612440B (en) | Calibration object profile analysis method based on oblique photography |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20221111 |