Intelligent agricultural plant full view measurement calibration method and system based on computer vision

Abstract

The invention relates to the technical field of smart agriculture, in particular to a smart agricultural plant full view measurement and calibration method and system based on computer vision, and the method comprises the steps: building a region simulation model for a planting region, and measuring the longitudinal distance between any adjacent target plants in the region simulation model according to the development starting time of the target plants, the region division module sets an independent growth region based on a longitudinal distance value; the image analysis module further identifies a relationship between branches and leaves and growth points in a unit image, distinguishes associated branches and leaves from irrelevant branches and leaves, accurately judges an interference state, and then marks and measures the associated branches and leaves according to the interference state; accurate plant growth information is obtained, so that the measurement result can more truly reflect the actual growth condition of a single plant, and further accurate measurement of the full view of the plant is realized.

Description

Technical Field

[0001] The present invention relates to the field of smart agriculture technology, and in particular to a computer vision-based smart agriculture plant panorama measurement and calibration method and system. Background Art

[0002] In the field of smart agriculture, accurate measurement and calibration of plant growth conditions are the key to achieving scientific planting management and improving crop yield and quality.

[0003] The prior art CN111578837A discloses a plant morphology visual tracking and measurement method for agricultural robot operations, including: obtaining main stem image information of a plant in multiple fields of view, and determining the three-dimensional morphology information of the plant main stem based on the multiple main stem image information; wherein, each main stem image information includes a tracking target reference point at the lowest end of the center line of the plant main stem within the corresponding field of view and a tracking start reference point located in the middle of the plant main stem; obtaining the main stem image information of the plant in multiple fields of view includes: using the tracking start reference point in the i-th field of view as the tracking target reference point in the i+1-th field of view.

[0004] However, plants are often planted in large numbers. When measuring and calibrating plants, the average value of the region is often used instead of the measurement result. It is difficult to systematically measure and calibrate the entire picture of a single plant, and it is impossible to accurately judge the status of plants at different growth stages. This leads to large errors in the measurement results and cannot provide accurate and reliable data support for agricultural production. Summary of the Invention

[0005] The purpose of the present invention is to solve the problems in the background technology and propose a computer vision-based smart agricultural plant panorama measurement and calibration method and system.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] A computer vision-based smart agricultural plant panorama measurement and calibration method includes the following steps:

[0008] Step 1: Using image acquisition equipment, real-time growth images of the planting area are collected;

[0009] Step 2: Based on the growth image, build a regional simulation model of the planting area;

[0010] Step 3: According to the start time of the target plant's development, a starting time point is set, a regional simulation model is obtained, and the target plant in the regional simulation model is identified. When the target plant is identified, the longitudinal distance between any adjacent target plants in the regional simulation model is measured, and a normal growth signal is generated based on the longitudinal distance;

[0011] Step 4: When a normal growth signal is detected, an independent growth area is set for the target plant based on the longitudinal distance value;

[0012] Step 5: Obtain a unit image of the independent growth area, set the growth point of the target plant in the unit image, identify the plant branches and leaves in the unit image, determine whether there is a positional connection between the plant branches and leaves and the growth point, determine the associated branches and leaves and the irrelevant branches and leaves, and set the interference state for the independent growth area based on the associated branches and leaves and the irrelevant branches and leaves in the unit image;

[0013] Step 6: Mark the associated branches and leaves in the unit image according to the interference status of the independent growth area. Based on the marked position, measure the target plants in the independent growth area to obtain growth information.

[0014] As a further solution of the present invention, the start development time refers to the time when the target plant starts to grow. If the target plant is an annual plant, the initial planting time of the target plant is marked as the start time point. If the target plant is a perennial plant, the start time of the budding period is marked as the start time point.

[0015] As a further solution of the present invention, a method for measuring the longitudinal distance value includes:

[0016] S1: Starting from the start time point, the growth images of the target plants in the planting area are obtained, the growth images collected at the same time are obtained, and the growth images are spliced ​​according to the acquisition position of each growth image, and the regional simulation model is constructed based on the image pictures in the growth images;

[0017] S2: Based on the basic planting information of the target plants, the planting distance of the target plants is extracted. The planting distance includes the standard row spacing and the standard plant spacing. The standard plant spacing refers to the scientific planting space distance between plants, and the standard row spacing refers to the scientific planting distance between rows.

[0018] Acquiring a regional simulation model and identifying a target plant in the regional simulation model, and generating a measurement signal when the target plant is detected in the regional simulation model;

[0019] When the measurement signal is detected, the regional simulation model is obtained, and the position of the target plant is marked with a particle in the regional simulation model. The distance between any adjacent particles is measured using a measuring tool, and the measured data is marked as a lateral distance value DHi, wherein the lateral distance value DHi represents the plant spacing between the target plants, and i represents the number of different plant spacing intervals. At the same time, the longitudinal distance in the regional simulation model is measured, and the midpoint position of the longitudinal distance is taken, and this position is marked as the longitudinal boundary position, wherein the longitudinal distance is the distance between rows in the planting area.

[0020] As a further embodiment of the present invention, a method for generating a normal growth signal includes:

[0021] When the lateral distance value DHi is obtained, the lateral distance value DHi is first compared with the standard plant spacing of the target plant. If the lateral distance value DHi is within the standard plant spacing range, a normal growth signal is generated. Conversely, if the lateral distance value DHi is not within the standard plant spacing range, a growth abnormality signal is generated and transmitted to the terminal display module.

[0022] As a further solution of the present invention, multiple acquisition devices are installed in the planting area, and one acquisition device is corresponding to acquiring a regional image of a local area in the planting area. The regional images acquired by multiple acquisition devices are spliced ​​together to form a complete regional image of the complete planting area. Thereafter, a regional simulation model is constructed based on the complete regional image, and the regional simulation model is scaled with the actual planting area according to a preset ratio. At the same time, the regional simulation model is updated in real time according to the growth image acquired in real time.

[0023] As a further solution of the present invention, if the target plant is initially planted in the planting area in the form of seeds, in the initial stage, since the seeds are buried in the soil, the specific position of the target plant in the planting area cannot be identified during image acquisition. Therefore, it is necessary to monitor the planting area in real time until the seedlings of the target plant are detected and then generate a measurement signal.

[0024] As a further solution of the present invention, a method for setting up independent growth areas includes:

[0025] When a normal growth signal is detected, a regional simulation model is obtained. In the regional simulation model, adjacent particles are connected with line segments to obtain distance segments. The midpoint of the distance segment is taken, the position of the midpoint is identified, and the position is marked as a horizontal local demarcation point.

[0026] Use straight lines to extend at the longitudinal dividing position and the horizontal local dividing point respectively, so that the straight lines intersect, and based on the intersection points, obtain the areas enclosed by the straight lines. At this time, there is only one target plant between each area, and then this area is marked as the independent growth area of ​​this target plant.

[0027] As a further solution of the present invention, a method for setting the interference state of an independent growth region includes:

[0028] SS1: Acquire real-time growth images and update the regional simulation model in real time based on the growth images;

[0029] An independent growth area is arbitrarily selected as a unit analysis area. The measurement signal generation time is taken as the starting time. From the starting time, the image of the unit analysis module is separately collected in the regional simulation model and marked as a unit image.

[0030] Starting from the starting time, the collected unit images are arranged in chronological order to obtain an image sequence, wherein the collection interval between any two adjacent unit images in the image sequence is a fixed value;

[0031] SS2: First, the first unit image is selected in the image sequence. Based on this unit image, the growth point of the target plant in the unit image is identified. The growth point refers to the initial growth position of the target plant.

[0032] Selecting the unit image at the second position according to the image sequence, identifying all plant branches and leaves in the second unit image, and sequentially identifying whether the plant branches and leaves at each position are connected to the growth point, wherein the position connection refers to the connection between the plant branches and leaves and the growth point through the stem or branch;

[0033] If there is a position connection, the plant branches and leaves at this position are marked as associated branches and leaves. Otherwise, if there is no position connection, the plant branches and leaves at this position are marked as unrelated branches and leaves. The plant branches and leaves in the unit image are traversed. When all the plant branches and leaves in the unit image are associated branches and leaves, the interference state of the independent growth area corresponding to this unit image is marked as convergent growth. Otherwise, if there are unrelated branches and leaves in the unit image, the interference state of the independent growth area corresponding to this unit image is marked as cross growth.

[0034] As a further embodiment of the present invention, a method for associating branch and leaf labels in a unit image includes:

[0035] Identify the interference state of the independent growth area at this time. If the interference state is convergent growth, directly mark the position of the plant branches and leaves in this unit image, and measure according to the marked position to obtain the real-time growth information of the target plant in this independent growth area;

[0036] If the interference state is cross-growth, obtain the associated branches and leaves in the unit image, process them according to the above-mentioned convergent growth processing method, then obtain the irrelevant branches and leaves, identify the orientation of the irrelevant branches and leaves in the unit image, and simultaneously select the independent growth area adjacent to this orientation, obtain the unit image of this independent growth area, and mark it as the adjacent edge image, and mark the image where the irrelevant branches and leaves are located as the main image;

[0037] The main image and the adjacent image are spliced ​​according to the image acquisition position to obtain a spliced ​​image. Then, in the spliced ​​image, the positions of irrelevant branches and leaves in the main image are obtained, and the associated branches and leaves in the adjacent image are identified. At the same time, the associated branches and leaves at the position connected to the main image are selected, and the associated branches and leaves are image matched with the irrelevant branches and leaves. The intelligent algorithm is used to calculate the matching results of the associated branches and leaves and the irrelevant branches and leaves at the splicing position. If the matching result shows irrelevant, a corresponding abnormal signal is generated based on the irrelevant branches and leaves and transmitted to the equipment terminal of the relevant management personnel. On the contrary, if the matching result shows relevant, the irrelevant branches and leaves in the main image are marked as associated branches and leaves of the adjacent image. At the same time, when marking the target plant in the independent growth area of ​​the adjacent image, the marked positions of all associated branches and leaves of the target plant are obtained, and the target plant is measured according to the marked positions, thereby obtaining the real-time growth information of the target plant in this independent growth area.

[0038] The computer vision-based smart agricultural plant panorama measurement and calibration system includes:

[0039] Information collection module, used to collect basic planting information of the planting area;

[0040] An image acquisition module, used to acquire growth images of the planting area;

[0041] A model building module is used to build a regional simulation model of the planting area based on the growth image;

[0042] The node setting module is used to set the starting time point according to the start development time of the target plant;

[0043] A growth detection module is used to obtain a regional simulation model after the start time point and identify target plants, then measure the longitudinal distance between any adjacent target plants in the regional simulation model and generate a normal growth signal based on the longitudinal distance;

[0044] A region division module is used to detect normal growth signals and set independent growth regions based on longitudinal distance values;

[0045] An image analysis module is used to obtain a unit image of an independent growth area, set the growth point of the target plant, then identify the plant branches and leaves in the unit image, determine whether there is a positional connection between the plant branches and leaves and the growth point, and determine the associated branches and leaves and the irrelevant branches and leaves. Based on the associated branches and leaves and the irrelevant branches and leaves in the unit image, an interference state is set for the independent growth area;

[0046] The measurement processing module is used to mark the associated branches and leaves in the unit image according to the interference status of the independent growth area, and measure the target plants in each independent growth area according to the marked position to obtain growth information;

[0047] The terminal display module is used to display the growth information of the target plants, so that managers in the planting area can understand the growth information of the target plants in real time.

[0048] Compared with the existing technology, the advantages of the present invention are:

[0049] The present invention builds a regional simulation model for the planting area, measures the longitudinal distance of any adjacent target plants in the regional simulation model according to the start development time of the target plants, generates a normal growth signal based on the longitudinal distance, and the regional division module sets an independent growth area based on the longitudinal distance value. The image analysis module further identifies the relationship between the branches and leaves and the growth point in the unit image, distinguishes between related branches and leaves and irrelevant branches and leaves, and accurately judges the interference state. This process realizes a refined analysis of the plant growth environment, effectively eliminates the interference of environmental factors on the measurement results, so that the measurement results can more truly reflect the actual growth status of individual plants, and improves the accuracy and reliability of the measurement. Afterwards, the related branches and leaves are marked and measured according to the interference state to obtain accurate plant growth information, thereby realizing accurate measurement of the overall picture of the plant, providing accurate data support for management measures such as precise fertilization, irrigation, and pest control in smart agriculture, which helps to improve the efficiency of agricultural resource utilization and reduce production costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 Schematic diagram of the method flow of the present invention;

[0051] Figure 2 Schematic diagram of the system structure of the present invention. DETAILED DESCRIPTION

[0052] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0053] Reference Figure 1 and Figure 2 , a computer vision-based smart agricultural plant panorama measurement and calibration method, the method specifically includes the following steps:

[0054] Step 1: Collect basic planting information of the planting area, where the basic planting information includes the plant species planted in the planting area and the corresponding growth information of the plant species, including planting distance, plant growth curve, ambient humidity, ambient temperature, and light intensity and duration;

[0055] Step 2: Install multiple image acquisition devices in the planting area. The multiple image acquisition devices are used to capture images of the plants in the planting area and mark the captured images as growth images. The positions captured by the multiple image acquisition devices fully cover the planting area, thereby preventing blind spots in the planting area.

[0056] Step 3: Mark the time when the target plant starts to develop as the starting time point, where the target plant refers to the plant currently planted in the planting area, and the starting time refers to the time when the target plant starts to grow. For example, if the target plant is an annual plant (wheat, rice, corn, etc.), the starting time of the target plant is marked as the starting time point. If the target plant is a perennial plant (apple tree, peach tree, pear tree, etc.), the starting time of the budding period is marked as the starting time point;

[0057] Starting from the start time point, the growth image of the target plant in the planting area is obtained and marked as the target analysis image. The independent growth area in the target analysis image is identified using computer vision technology. Specifically, the independent growth area identification method includes:

[0058] S1: Acquire growth images collected at the same time, and splice the growth images according to the collection position of each growth image, and build a regional simulation model based on the image screen in the growth image. Then, update the regional simulation model in real time according to the real-time collected growth images;

[0059] Furthermore, among the multiple acquisition devices installed in the planting area, one acquisition device correspondingly acquires a regional image of a local area in the planting area, and the regional images acquired by the multiple acquisition devices are spliced ​​together to form a complete regional image of the complete planting area. Thereafter, a regional simulation model is constructed based on the complete regional image, and the regional simulation model is scaled with the actual planting area according to a preset ratio. The specific preset ratio is set by those skilled in the art based on big data experience.

[0060] S2: Based on the basic planting information of the target plants, the planting distance of the target plants is extracted. The planting distance includes the standard row spacing and the standard plant spacing. The standard plant spacing refers to the scientific planting space distance between plants, and the standard row spacing refers to the scientific planting distance between rows. For example, the standard row spacing of tomatoes is 50-60 cm, and the standard plant spacing is 30-40 cm. The standard row spacing of rice is 20-30 cm, and the standard plant spacing is 15-20 cm.

[0061] Acquiring a regional simulation model and identifying a target plant in the regional simulation model, and generating a measurement signal when the target plant is detected in the regional simulation model;

[0062] When the system detects a measurement signal, it obtains a regional simulation model and marks the position of the target plant with a particle in the regional simulation model. It uses a measuring tool to measure the distance between any adjacent particle points and marks the measured data as a transverse distance value DHi, where the transverse distance value DHi represents the plant spacing between the target plants and i represents the number of the different plant spacing intervals. At the same time, it measures the longitudinal distance in the regional simulation model and takes the midpoint position of the longitudinal distance, marking this position as the longitudinal boundary position, where the longitudinal distance is the distance between rows in the planting area.

[0063] It should be further explained that if the target plant is initially planted in the planting area in the form of seeds, in the initial stage, since the seeds are buried in the soil, the specific location of the target plant in the planting area cannot be identified during image acquisition. Therefore, it is necessary to monitor the planting area in real time until the seedlings of the target plant are detected and then generate a measurement signal;

[0064] S3: When the lateral distance value DHi is obtained, the lateral distance value DHi is first compared with the standard plant spacing of the target plant. If the lateral distance value DHi is within the standard plant spacing range, a normal growth signal is generated. Conversely, if the lateral distance value DHi is not within the standard plant spacing range, a growth abnormality signal is generated and transmitted to the terminal display module. The terminal response module generates corresponding sound and light reminder information according to the growth abnormality signal and reminds relevant management personnel in real time;

[0065] When a normal growth signal is detected, a regional simulation model is obtained. In the regional simulation model, adjacent particles are connected with line segments to obtain distance segments. The midpoint of the distance segment is taken, the position of the midpoint is identified, and the position is marked as a horizontal local demarcation point.

[0066] S4: Use straight lines to extend at the longitudinal boundary position and the horizontal local boundary point respectively, so that the straight lines intersect, and based on the intersection point, obtain the area enclosed by the straight lines. At this time, there is only one target plant between each area, and then mark this area as the independent growth area of ​​the target plant;

[0067] Step 4: After all independent growth areas in the planting area are determined, the growth process of a single target plant in each independent growth area is tracked in real time, and the interference state in each independent growth area is identified. The interference state includes convergent growth and cross growth. The specific method for identifying the interference state includes:

[0068] SS1: Acquire real-time growth images and update the regional simulation model in real time based on the growth images;

[0069] An independent growth area is arbitrarily selected as a unit analysis area. Taking this unit analysis area as an example, the time when the measurement signal is generated is taken as the starting time. Starting from the starting time, the image of the unit analysis module is separately collected in the regional simulation model and marked as a unit image.

[0070] Starting from the starting time, the collected unit images are arranged in chronological order to obtain an image sequence. In the image sequence, the collection interval between any two adjacent unit images is a fixed value, and the specific value of this fixed value is set by those skilled in the art based on big data experience;

[0071] SS2: First, the first unit image is selected in the image sequence. Based on this unit image, the growth point of the target plant in the unit image is identified. The growth point refers to the initial growth position of the target plant.

[0072] According to the image sequence, the unit image at the second position is selected, and all the plant branches and leaves in the second unit image are identified. Then, the plant branches and leaves at each position are sequentially identified to determine whether they are connected to the growth point. Positional connection refers to the connection between plant branches and leaves and the growth point through a stem or branch. For example, the leaves on the branches grow on the branches, and the branches are connected to the trunk (the growth point of the trunk). This connection relationship of leaves → branches → trunk is called positional connection.

[0073] If there is a position connection, the plant branches and leaves at this position are marked as associated branches and leaves. Otherwise, if there is no position connection, the plant branches and leaves at this position are marked as irrelevant branches and leaves. The plant branches and leaves in the unit image are traversed. When all the plant branches and leaves in the unit image are associated branches and leaves, the interference state of the independent growth area corresponding to this unit image is marked as convergent growth. Otherwise, if there are irrelevant branches and leaves in the unit image, the interference state of the independent growth area corresponding to this unit image is marked as cross growth.

[0074] Step 5: Obtain the interference status of each target plant's corresponding independent growth area, and measure the overall growth status of the target plant based on the interference status. The specific measurement methods include:

[0075] Acquire a real-time unit image of an independent growth area and identify the interference state of the independent growth area at that time. If the interference state is convergent growth, directly mark the position of the plant branches and leaves in this unit image and measure according to the marked position to obtain the real-time growth information of the target plant in this independent growth area;

[0076] If the interference state is cross-growth, first obtain the associated branches and leaves in the unit image, and process the associated branches and leaves according to the processing method in the above-mentioned convergent growth. Then obtain the irrelevant branches and leaves, and identify the orientation of the irrelevant branches and leaves in the unit image. At the same time, based on this orientation, select the independent growth area adjacent to this orientation, and obtain the unit image of this independent growth area. This unit image is marked as the adjacent edge image, and the image where the irrelevant branches and leaves are located is marked as the main trunk image;

[0077] The main image and the adjacent image are spliced ​​according to the image acquisition position to obtain a spliced ​​image. Then, in the spliced ​​image, the positions of irrelevant branches and leaves in the main image are obtained, and the associated branches and leaves in the adjacent image are identified. At the same time, the associated branches and leaves at the position connected to the main image are selected, and the associated branches and leaves are image matched with the irrelevant branches and leaves. The intelligent algorithm is used to calculate the matching results of the associated branches and leaves and the irrelevant branches and leaves at the splicing position. If the matching result shows irrelevant, a corresponding abnormal signal is generated based on the irrelevant branches and leaves and transmitted to the equipment terminal of the relevant management personnel. The relevant management personnel further manually process the irrelevant branches and leaves. On the contrary, if the matching result shows relevant, the irrelevant branches and leaves in the main image are marked as associated branches and leaves of the adjacent image. At the same time, when marking the target plant in the independent growth area of ​​the adjacent image, the marked positions of all associated branches and leaves of the target plant are obtained, and the target plant is measured according to the marked positions, thereby obtaining real-time growth information of the target plant in this independent growth area.

[0078] The computer vision-based smart agricultural plant panorama measurement and calibration system includes:

[0079] Information collection module, used to collect basic planting information of the planting area;

[0080] An image acquisition module, used to acquire growth images of the planting area;

[0081] A model building module is used to build a regional simulation model of the planting area based on the growth image;

[0082] The node setting module is used to set the starting time point according to the start development time of the target plant;

[0083] A growth detection module is used to obtain a regional simulation model after the start time point and identify target plants in the regional simulation model. When a target plant is identified, the module measures the longitudinal distance between any adjacent target plants in the regional simulation model and generates a normal growth signal based on the longitudinal distance.

[0084] A region division module is used to detect normal growth signals and set independent growth regions for target plants in the regional simulation model based on longitudinal distance values;

[0085] An image analysis module is used to obtain a unit image of an independent growth area, set the growth point of the target plant in the unit image, then identify the plant branches and leaves in the unit image, determine whether there is a positional connection between the plant branches and leaves and the growth point, and determine the associated branches and leaves and the irrelevant branches and leaves. Based on the associated branches and leaves and the irrelevant branches and leaves in the unit image, an interference state is set for the independent growth area;

[0086] The measurement processing module is used to mark the associated branches and leaves in the unit image according to the interference status of the independent growth area, and measure the target plants in each independent growth area according to the marked position to obtain growth information;

[0087] The terminal display module is used to display the growth information of the target plants, so that managers in the planting area can understand the growth information of the target plants in real time.

[0088] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A computer vision-based smart agricultural plant panorama measurement and calibration method, characterized by: The method specifically comprises the following steps: Step 1: Using image acquisition equipment, real-time growth images of the planting area are collected; Step 2: Based on the growth image, build a regional simulation model of the planting area; Step 3: According to the start time of the target plant's development, a starting time point is set, a regional simulation model is obtained, and the target plant in the regional simulation model is identified. When the target plant is identified, the longitudinal distance between any adjacent target plants in the regional simulation model is measured, and a normal growth signal is generated based on the longitudinal distance; Step 4: When a normal growth signal is detected, an independent growth area is set for the target plant based on the longitudinal distance value; Step 5: Obtain a unit image of the independent growth area, set the growth point of the target plant in the unit image, identify the plant branches and leaves in the unit image, determine whether there is a positional connection between the plant branches and leaves and the growth point, determine the associated branches and leaves and the irrelevant branches and leaves, and set the interference state for the independent growth area based on the associated branches and leaves and the irrelevant branches and leaves in the unit image; Step 6: Mark the associated branches and leaves in the unit image according to the interference status of the independent growth area. Based on the marked position, measure the target plants in the independent growth area to obtain growth information.

2. The computer vision-based smart agricultural plant panorama measurement and calibration method according to claim 1, characterized in that: The start of development time refers to the time when the target plant starts to grow. If the target plant is an annual plant, the initial planting time of the target plant is marked as the start time point. If the target plant is a perennial plant, the start time of the budding period is marked as the start time point.

3. The computer vision-based smart agricultural plant panorama measurement and calibration method according to claim 1, characterized in that: The measurement methods of longitudinal distance values ​​include: S1: Starting from the start time point, the growth images of the target plants in the planting area are obtained, the growth images collected at the same time are obtained, and the growth images are spliced ​​according to the acquisition position of each growth image, and the regional simulation model is constructed based on the image pictures in the growth images; S2: Based on the basic planting information of the target plants, the planting distance of the target plants is extracted. The planting distance includes the standard row spacing and the standard plant spacing. The standard plant spacing refers to the scientific planting space distance between plants, and the standard row spacing refers to the scientific planting distance between rows. Acquiring a regional simulation model and identifying a target plant in the regional simulation model, and generating a measurement signal when the target plant is detected in the regional simulation model; When the measurement signal is detected, the regional simulation model is obtained, and the position of the target plant is marked with a particle in the regional simulation model. The distance between any adjacent particles is measured using a measuring tool, and the measured data is marked as a lateral distance value DHi, wherein the lateral distance value DHi represents the plant spacing between the target plants, and i represents the number of different plant spacing intervals. At the same time, the longitudinal distance in the regional simulation model is measured, and the midpoint position of the longitudinal distance is taken, and this position is marked as the longitudinal boundary position, wherein the longitudinal distance is the distance between rows in the planting area.

4. The computer vision-based smart agricultural plant panorama measurement and calibration method according to claim 3, characterized in that: Methods for generating normal growth signals include: When the lateral distance value DHi is obtained, the lateral distance value DHi is first compared with the standard plant spacing of the target plant. If the lateral distance value DHi is within the standard plant spacing range, a normal growth signal is generated. Conversely, if the lateral distance value DHi is not within the standard plant spacing range, a growth abnormality signal is generated and transmitted to the terminal display module.

5. The computer vision-based smart agricultural plant panorama measurement and calibration method according to claim 3, characterized in that: Multiple acquisition devices are installed in the planting area, and one acquisition device is corresponding to collecting the regional image of a local area in the planting area. The regional images collected by multiple acquisition devices are spliced ​​together to form a complete regional image of the complete planting area. Then, a regional simulation model is constructed based on the regional complete image, and the regional simulation model is scaled with the actual planting area according to a preset ratio. At the same time, the regional simulation model is updated in real time according to the real-time collected growth image.

6. The computer vision-based smart agricultural plant panorama measurement and calibration method according to claim 4, characterized in that: If the target plant is initially planted in the planting area in the form of seeds, in the initial stage, the seeds are buried in the soil, and the specific location of the target plant in the planting area cannot be identified during image acquisition. Therefore, the planting area needs to be monitored in real time until the seedlings of the target plant are detected and then a measurement signal is generated.

7. The computer vision-based smart agricultural plant panorama measurement and calibration method according to claim 1, characterized in that: Methods for setting up independent growth areas include: When a normal growth signal is detected, a regional simulation model is obtained. In the regional simulation model, adjacent particles are connected with line segments to obtain distance segments. The midpoint of the distance segment is taken, the position of the midpoint is identified, and the position is marked as a horizontal local demarcation point. Use straight lines to extend at the longitudinal dividing position and the horizontal local dividing point respectively, so that the straight lines intersect, and based on the intersection points, obtain the areas enclosed by the straight lines. At this time, there is only one target plant between each area, and then this area is marked as the independent growth area of ​​this target plant.

8. The computer vision-based smart agricultural plant panorama measurement and calibration method according to claim 1, characterized in that: The interference state setting method of the independent growth area includes: SS1: Acquire real-time growth images and update the regional simulation model in real time based on the growth images; An independent growth area is arbitrarily selected as a unit analysis area. The measurement signal generation time is taken as the starting time. From the starting time, the image of the unit analysis module is separately collected in the regional simulation model and marked as a unit image. Starting from the starting time, the collected unit images are arranged in chronological order to obtain an image sequence, wherein the collection interval between any two adjacent unit images in the image sequence is a fixed value; SS2: First, the first unit image is selected in the image sequence. Based on this unit image, the growth point of the target plant in the unit image is identified. The growth point refers to the initial growth position of the target plant. Selecting the unit image at the second position according to the image sequence, identifying all plant branches and leaves in the second unit image, and sequentially identifying whether the plant branches and leaves at each position are connected to the growth point, wherein the position connection refers to the connection between the plant branches and leaves and the growth point through the stem or branch; If there is a position connection, the plant branches and leaves at this position are marked as associated branches and leaves. Otherwise, if there is no position connection, the plant branches and leaves at this position are marked as unrelated branches and leaves. The plant branches and leaves in the unit image are traversed. When all the plant branches and leaves in the unit image are associated branches and leaves, the interference state of the independent growth area corresponding to this unit image is marked as convergent growth. Otherwise, if there are unrelated branches and leaves in the unit image, the interference state of the independent growth area corresponding to this unit image is marked as cross growth.

9. The computer vision-based smart agricultural plant panorama measurement and calibration method according to claim 8, characterized in that: Methods for associating branch and leaf labels in unit images include: Identify the interference state of the independent growth area at this time. If the interference state is convergent growth, directly mark the position of the plant branches and leaves in this unit image, and measure according to the marked position to obtain the real-time growth information of the target plant in this independent growth area; If the interference state is cross-growth, obtain the associated branches and leaves in the unit image, process them according to the above-mentioned convergent growth processing method, then obtain the irrelevant branches and leaves, identify the orientation of the irrelevant branches and leaves in the unit image, and simultaneously select the independent growth area adjacent to this orientation, obtain the unit image of this independent growth area, and mark it as the adjacent edge image, and mark the image where the irrelevant branches and leaves are located as the main image; The main image and the adjacent image are spliced ​​according to the image acquisition position to obtain a spliced ​​image. Then, in the spliced ​​image, the positions of irrelevant branches and leaves in the main image are obtained, and the associated branches and leaves in the adjacent image are identified. At the same time, the associated branches and leaves at the position connected to the main image are selected, and the associated branches and leaves are image matched with the irrelevant branches and leaves. The intelligent algorithm is used to calculate the matching results of the associated branches and leaves and the irrelevant branches and leaves at the splicing position. If the matching result shows irrelevant, a corresponding abnormal signal is generated based on the irrelevant branches and leaves and transmitted to the equipment terminal of the relevant management personnel. On the contrary, if the matching result shows relevant, the irrelevant branches and leaves in the main image are marked as associated branches and leaves of the adjacent image. At the same time, when marking the target plant in the independent growth area of ​​the adjacent image, the marked positions of all associated branches and leaves of the target plant are obtained, and the target plant is measured according to the marked positions, thereby obtaining the real-time growth information of the target plant in this independent growth area.

10. A computer vision-based smart agricultural plant panorama measurement and calibration system, the system adopting the computer vision-based smart agricultural plant panorama measurement and calibration method according to any one of claims 1 to 9, characterized in that: include: Information collection module, used to collect basic planting information of the planting area; An image acquisition module, used to acquire growth images of the planting area; A model building module is used to build a regional simulation model of the planting area based on the growth image; The node setting module is used to set the starting time point according to the start development time of the target plant; A growth detection module is used to obtain a regional simulation model after the start time point and identify target plants, then measure the longitudinal distance between any adjacent target plants in the regional simulation model and generate a normal growth signal based on the longitudinal distance; A region division module is used to detect normal growth signals and set independent growth regions based on longitudinal distance values; An image analysis module is used to obtain a unit image of an independent growth area, set the growth point of the target plant, then identify the plant branches and leaves in the unit image, determine whether there is a positional connection between the plant branches and leaves and the growth point, and determine the associated branches and leaves and the irrelevant branches and leaves. Based on the associated branches and leaves and the irrelevant branches and leaves in the unit image, an interference state is set for the independent growth area; The measurement processing module is used to mark the associated branches and leaves in the unit image according to the interference status of the independent growth area, and measure the target plants in each independent growth area according to the marked position to obtain growth information; The terminal display module is used to display the growth information of the target plants, so that managers in the planting area can understand the growth information of the target plants in real time.

Images