An agricultural production capacity evaluation and monitoring system based on machine vision

Abstract

The present invention relates to the field of agricultural production technology, and in particular to an agricultural production capacity evaluation and monitoring system based on machine vision, comprising: a monitoring layer, an analysis layer and an evaluation layer; image processing acquisition and processing logic are set in the monitoring layer, image data of a planting area is acquired in real time by the monitoring layer based on the acquisition logic, and is further forwarded to the analysis layer after being processed by the processing logic, and the analysis layer receives the image data of the planting area. The present invention uses machine vision technology to perform global image acquisition of fruit trees in an orchard, and further optimizes and reorganizes fruit tree images through graphic processing technology, thereby effectively improving the quality of fruit tree images. Based on the acquisition of orchard environmental parameters and combined with comprehensive analysis of fruit tree images, an effective and fully covered evaluation of the production capacity of a fruit tree planting area in an orchard is performed, and certain visualization conditions are provided to assist orchard management users in performing real-time monitoring of orchard productivity more quickly, efficiently and accurately.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural production, and in particular to an agricultural production capacity evaluation and monitoring system based on machine vision. Background Art

[0002] Orchard production capacity management refers to the scientific planning and allocation of orchard resources to improve the yield and quality of fruit trees. It covers measures such as soil improvement, reasonable density planting, precision fertilization, integrated pest and disease control, etc. By optimizing planting varieties, adopting advanced cultivation techniques, and real-time monitoring of the orchard environment, the healthy growth of fruit trees can be guaranteed, and the orchard can achieve continuous and efficient output.

[0003] A Chinese invention patent with application number 202110646323.8 discloses a wheat production layout method based on food demand, including: determining the climate suitability index for wheat production; based on the climate suitability index, determining the climate suitable arable land distribution pattern for wheat production; calculating the socioeconomic advantage index for wheat production; based on the climate suitability index and the socioeconomic advantage index, calculating the layout optimization factor for wheat production and calculating the wheat production capacity per unit area of ​​arable land at a grid scale; based on the layout optimization factor and the wheat production capacity per unit area of ​​arable land at a grid scale, laying out the climate suitable arable land distribution pattern.

[0004] This application aims to solve the problem that "in the prior art, the maximum entropy model (MaxEnt) is applied to the crop climate suitability zoning. The model is based on the current crop distribution data and climate data, and selects the distribution with the largest entropy from the distributions that meet the conditions as the optimal distribution, so that the optimal crop production area can be selected spatially. However, the maximum entropy model (MaxEnt) only considers the climate suitability for wheat planting, and selects areas suitable for wheat production from the aspects of heat and precipitation, and does not consider the impact of socio-economic conditions, crop production capacity, resource and environmental limiting factors, etc. on the wheat production layout."

[0005] However, for orchard planting scenarios in agricultural production, most existing technologies focus on monitoring fruit tree pests. Although they can play a certain role in maintaining and managing orchard productivity, they are not as effective as the real-time monitoring and evaluation of the overall productivity of the orchard.

[0006] To this end, we proposed an agricultural production capacity assessment and monitoring system based on machine vision. Summary of the invention

[0007] In view of the above-mentioned shortcomings of the prior art, the present invention provides an agricultural production capacity evaluation and monitoring system based on machine vision, which solves the technical problems raised in the above-mentioned background technology.

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0009] An agricultural production capacity evaluation and monitoring system based on machine vision, comprising: a monitoring layer, an analysis layer and an evaluation layer;

[0010] The image processing acquisition and processing logic are set in the monitoring layer. The image data of the planting area is collected in real time by the monitoring layer based on the acquisition logic, and is further forwarded to the analysis layer after being processed by the processing logic. The analysis layer receives the image data of the planting area, and synchronously collects the environmental parameters of the planting area. The production capacity of the planting area is analyzed based on the environmental parameters of the planting area combined with the image data of the planting area. The monitoring layer synchronously receives the production capacity of the planting area analyzed in the analysis layer, records the received analysis results of the production capacity of the planting area, and generates a production capacity situation map of the planting area based on the recorded analysis results of the production capacity of the planting area to evaluate the health of the production capacity of the planting area.

[0011] The analysis layer includes a receiving module, a capturing module and an analyzing module. The receiving module is used to receive a global image of the planting area and forward the global image of the planting area to the analyzing module. The capturing module is used to capture the environmental parameters of the planting area during the acquisition phase of the global image of the planting area. The analyzing module is used to receive the environmental parameters of the planting area captured by the capturing module and analyze the production capacity of the planting area in combination with the global image of the planting area.

[0012] The production capacity analysis logic of the planting area in the analysis module is expressed as:

[0013] ;

[0014] Where: It is the production capacity performance value of the planting area; The number of fruit trees planted in the planting area; is the ideal number of fruit trees; It is the index of tree crown coverage; The number of fruits displayed in the global image of the planting area for the fruit trees planted in the planting area; , is a constant; is the ideal number of fruits per unit area of ​​the fruit tree at the current growth stage; To amend;

[0015] in, , For the ideal planting density, = is the planting area, the ideal number of fruits per unit area of ​​fruit trees at the current growth stage Defined by the system user, constant , The value range is 0~1, constant The value follows: The greater the slope of the planting area, the greater the constant The smaller the value, the more horizontal the planting area. The larger the value, the greater the constant The value is subject to: the higher the average height of fruit trees in the planting area, the higher the constant The larger the value, the smaller the constant The smaller the value, the higher the production capacity of the planting area. The larger it is, the better the production capacity of the planting area is; conversely, the smaller it is, the worse the production capacity of the planting area is. , Customized by system users.

[0016] Furthermore, the monitoring layer includes an acquisition module, a processing module and a reorganization module. The acquisition module is used to acquire the image data of the planting area. The processing module is used to receive the image data of the planting area acquired by the acquisition module and perform super-resolution processing on the image data. The reorganization module is used to receive the image data of the planting area processed in the processing module in real time and reorganize the image data of the planting area.

[0017] Among them, the image acquisition logic and the processing logic are stored in the acquisition module and the processing module respectively. The acquisition module acquires the image data of the planting area based on the image acquisition logic, and the processing module processes the image data of the planting area based on the processing logic. During the operation stage of the reorganization module, the image data of the planting area is reorganized based on the corresponding coordinates of the image data of the planting area, and the reorganized image is recorded as the global image of the planting area.

[0018] Furthermore, the acquisition module is integrated by a drone and a high-definition camera. The acquisition module performs the acquisition operation of the planting area image data based on the acquisition cycle customized by the system end user. The acquisition logic applied when the acquisition module runs to collect the planting area image data is:

[0019] ;

[0020] Where: The number of planting area image data collected on the edge of the planting area; The base number of image data collected in the planting area; The complexity of the planting area; is the area of ​​the planting area; Number of fruit trees planted for the planting area;

[0021] Among them, the number of collected image data of the planting area is The number of image data collected in the planting area is defined by the system user. The value of Any item in the table, the number of planting area image data collected on the edge of the planting area The value is rounded up. That is, the number of image data collected in the planting area and the complexity of the planting area The calculation formula is:

[0022] ;

[0023] Where: is the ratio of average tree height to average tree spacing; It is the ratio of the difference between the highest tree height and the lowest tree height in the orchard to the length of the orchard; It is the ratio of the difference between the highest tree height and the lowest tree height in the orchard to the width of the orchard; , are the coefficient of variation of sunshine duration and the coefficient of instability of wind speed and direction;

[0024] Among them, the coefficient of variation of sunshine duration and the coefficient of instability of wind speed and direction , It is defined by the system end user and is subject to: the values ​​are all in the range of 0~1. The greater the difference in daily light duration within the specified time threshold of the planting area, the greater the light duration variation coefficient. The larger the value, the smaller the value, the greater the difference in the daily average wind speed within the specified time threshold of the planting area, and the wind speed and wind direction instability coefficient. The larger the value, the smaller the value.

[0025] Furthermore, the number of planting area image data collected on the edge of the planting area After obtaining, based on The planting area is divided into sub-regions, so that each sub-region has the same size and shape, and collects image data above each sub-region to obtain Image data of the planting area;

[0026] Among them, after each planting area image data is collected, the boundary four corner coordinates of the planting area image data in the actual planting area are synchronously obtained, and the obtained boundary four corner coordinates are further marked at the corresponding four corner positions in the planting area image data.

[0027] Furthermore, the processing logic of the planting area image data in the processing module is expressed as:

[0028] Take each pixel in the planting area image data as the processing target, identify the grayscale value of each pixel in the 3×3 window surrounding the processing target, divide the processing target into 2×2 sub-pixels, obtain the grayscale value of the pixel in the window adjacent to the sub-pixel, and adjust the grayscale value of the sub-pixel based on the grayscale value of the pixel in the window adjacent to the sub-pixel:

[0029] ;

[0030] Where: is the adjusted target grayscale value of sub-pixel a; is the gray value of adjacent pixels in the window; is the gray value of the sub-pixel; Indicates the operation of rounding up;

[0031] Based on the above formula, the target grayscale value of each sub-pixel in the planting area image data is obtained, and the obtained grayscale value is used to iterate the original grayscale value of the sub-pixel to complete the super-resolution processing of the planting area image data;

[0032] No super-resolution processing is performed on the edge sub-pixels in the planting area image data; when the reorganization module reorganizes the planting area image data, the splicing association of the planting area image data during reorganization is determined based on the four-corner coordinates marked by the planting area image data, and when the planting area image data are spliced ​​and reorganized with each other, the edge sub-pixels of each planting area image data overlap with each other, and the grayscale value of the overlapping sub-pixel is taken as the average of its own grayscale value and the grayscale value of the overlapping sub-pixel below;

[0033] Among all the planting area image data, each planting area image has at least two associated planting area image data, and the judgment condition between the planting area image and the associated planting area image is that at least two of the four corner coordinates marked by the two planting area images are consistent.

[0034] Furthermore, the global image of the planting area received by the receiving module is sourced from the reorganization module, and the capturing module runs synchronously with the receiving module. Each time the receiving module receives the global image of the planting area, the capturing operation of the environmental parameters of the planting area is synchronously performed.

[0035] The environmental parameters of the planting area include: light, temperature, humidity, wind speed, precipitation, and soil nutrient content.

[0036] Furthermore, the canopy coverage index for:

[0037] ;

[0038] Where: It is the ratio of the canopy coverage area of ​​fruit trees to the total area of ​​the planting area in the global image of the planting area; The ideal canopy coverage range for the current fruit tree growth stage, which is customized by the system user;

[0039] The amendment The correction is set based on the environmental parameters of the planting area. The values ​​are:

[0040] ;

[0041] Where: is the weight; The ideal light duration, temperature, humidity, wind speed, precipitation, and the content of the vth soil nutrient element for the fruit tree in the current growth stage; The actual duration of sunlight, temperature, humidity, wind speed, precipitation, and content of the vth soil nutrient element in the current growth stage of the fruit tree; The types of nutrients required for the current growth of fruit trees;

[0042] Among them, the weight The values ​​are defined by the system user and are all positive numbers, and the weight The sum is 1.

[0043] Furthermore, the evaluation layer includes a recording module, a visualization module and an evaluation module. The recording module is used to receive the production capacity analysis results of the planting area in the analysis layer and record the received analysis results. The visualization module is used to continuously obtain the production capacity analysis results of the planting area recorded in the recording module and generate a trend chart representing the production capacity of the planting area based on the production capacity analysis results of the planting area. The evaluation module is used to evaluate whether the current production capacity of the planting area is healthy.

[0044] Among them, the trend chart generated based on the planting area production capacity analysis results in the visualization module is a line chart, the horizontal axis of which represents the time when the analysis layer outputs the planting area production capacity, and the vertical axis represents the planting area production capacity performance value output at the corresponding time.

[0045] Furthermore, when the evaluation module evaluates whether the production capacity of the planting area is healthy during the operation phase, the trend chart generated in the current visualization module is traversed. When the latest three consecutive line segments in the trend chart are continuously rising, it indicates that the production capacity of the planting area is healthy. Otherwise, it indicates that there is a health risk in the production capacity of the planting area.

[0046] Among them, the visualization module synchronously updates the trend graph representing the production capacity of the planting area after each recording module records the new analysis results of the production capacity of the planting area.

[0047] Furthermore, the receiving module is interactively connected to a capture module and an analysis module via a wireless network, the receiving module is interactively connected to a reorganization module via a wireless network, the reorganization module is interactively connected to a processing module and a collection module via a wireless network, the analysis module is interactively connected to a recording module via a wireless network, and the recording module is interactively connected to a visualization module and an evaluation module via a wireless network.

[0048] Compared with the known public technology, the technical solution provided by the present invention has the following beneficial effects:

[0049] The present invention provides an agricultural production capacity evaluation and monitoring system based on machine vision. During operation, the system uses machine vision technology to perform global image acquisition of fruit trees in an orchard, and further optimizes and reorganizes the fruit tree images through graphics processing technology, thereby effectively improving the quality of the fruit tree images. Based on the acquisition of orchard environmental parameters and combined with comprehensive analysis of fruit tree images, the system performs a full-coverage effective evaluation of the production capacity of fruit tree planting areas in the orchard, and provides certain visualization conditions to assist orchard management users in more rapid, efficient and accurate real-time monitoring of orchard productivity. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0051] Figure 1 It is a structural diagram of an agricultural production capacity evaluation and monitoring system based on machine vision;

[0052] Figure 2 This is a logical schematic diagram of global image reorganization of the planting area in the present invention. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution 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 part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] The present invention will be further described below in conjunction with the embodiments.

[0055] Example:

[0056] The present embodiment is a machine vision-based agricultural production capacity assessment and monitoring system, such as Figure 1 As shown, it includes: monitoring layer, analysis layer and evaluation layer;

[0057] The image processing acquisition and processing logic are set in the monitoring layer. The image data of the planting area is collected in real time by the monitoring layer based on the acquisition logic, and is further forwarded to the analysis layer after being processed by the processing logic. The analysis layer receives the image data of the planting area, and synchronously collects the environmental parameters of the planting area. The production capacity of the planting area is analyzed based on the environmental parameters of the planting area combined with the image data of the planting area. The monitoring layer synchronously receives the production capacity of the planting area analyzed in the analysis layer, records the received analysis results of the production capacity of the planting area, and generates a production capacity situation map of the planting area based on the recorded analysis results of the production capacity of the planting area to evaluate the health of the production capacity of the planting area.

[0058] The monitoring layer includes an acquisition module, a processing module and a reorganization module. The acquisition module is used to acquire the image data of the planting area. The processing module is used to receive the image data of the planting area acquired by the acquisition module and perform super-resolution processing on the image data. The reorganization module is used to receive the image data of the planting area processed by the processing module in real time and reorganize the image data of the planting area.

[0059] The image acquisition logic and the processing logic are stored in the acquisition module and the processing module respectively. The acquisition module acquires the image data of the planting area based on the image acquisition logic. The processing module processes the image data of the planting area based on the processing logic. During the operation phase of the reorganization module, the image data of the planting area is reorganized based on the corresponding coordinates of the image data of the planting area. The reorganized image is recorded as the global image of the planting area.

[0060] The acquisition module is integrated by the drone and the high-definition camera. The acquisition module performs the acquisition operation of the planting area image data based on the acquisition cycle customized by the system end user. The acquisition logic applied when the acquisition module runs to collect the planting area image data is:

[0061] ;

[0062] Where: The number of planting area image data collected on the edge of the planting area; The base number of image data collected in the planting area; The complexity of the planting area; is the area of ​​the planting area; Number of fruit trees planted for the planting area;

[0063] Among them, the number of collected image data of the planting area is The number of image data collected in the planting area is defined by the system user. The value of Any item in the table, the number of planting area image data collected on the edge of the planting area The value is rounded up. That is, the number of image data collected in the planting area and the complexity of the planting area The calculation formula is:

[0064] ;

[0065] Where: is the ratio of average tree height to average tree spacing; It is the ratio of the difference between the highest tree height and the lowest tree height in the orchard to the length of the orchard; It is the ratio of the difference between the highest tree height and the lowest tree height in the orchard to the width of the orchard; , are the coefficient of variation of sunshine duration and the coefficient of instability of wind speed and direction;

[0066] Among them, the coefficient of variation of sunshine duration and the coefficient of instability of wind speed and direction , It is defined by the system end user and is subject to: the values ​​are all in the range of 0~1. The greater the difference in daily light duration within the specified time threshold of the planting area, the greater the light duration variation coefficient. The larger the value, the smaller the value, the greater the difference in the daily average wind speed within the specified time threshold of the planting area, and the wind speed and wind direction instability coefficient. The larger the value, the smaller the value;

[0067] The number of planting area image data collected on the edge of the planting area is designed through the above-mentioned logical formula, so as to provide a specified acquisition logic limitation for the acquisition module when acquiring planting area image data.

[0068] The number of planting area image data collected on the edge of the planting area After obtaining, based on The planting area is divided into sub-regions, so that each sub-region has the same size and shape, and collects image data above each sub-region to obtain Image data of the planting area;

[0069] After each planting area image data is collected, the coordinates of the four corners of the boundary of the planting area image data in the actual planting area are obtained synchronously, and the obtained coordinates of the four corners of the boundary are further marked at the corresponding four corner positions in the planting area image data;

[0070] The processing logic of the planting area image data in the processing module is expressed as:

[0071] Take each pixel in the planting area image data as the processing target, identify the grayscale value of each pixel in the 3×3 window surrounding the processing target, divide the processing target into 2×2 sub-pixels, obtain the grayscale value of the pixel in the window adjacent to the sub-pixel, and adjust the grayscale value of the sub-pixel based on the grayscale value of the pixel in the window adjacent to the sub-pixel:

[0072] ;

[0073] Where: is the adjusted target grayscale value of sub-pixel a; is the gray value of adjacent pixels in the window; is the gray value of the sub-pixel; Indicates the operation of rounding up;

[0074] Based on the above formula, the target grayscale value of each sub-pixel in the planting area image data is obtained, and the obtained grayscale value is used to iterate the original grayscale value of the sub-pixel to complete the super-resolution processing of the planting area image data;

[0075] No super-resolution processing is performed on the edge sub-pixels in the planting area image data; when the reorganization module reorganizes the planting area image data, the splicing association of the planting area image data during reorganization is determined based on the four-corner coordinates marked by the planting area image data, and when the planting area image data are spliced ​​and reorganized with each other, the edge sub-pixels of each planting area image data overlap with each other, and the grayscale value of the overlapping sub-pixel is taken as the average of its own grayscale value and the grayscale value of the overlapping sub-pixel below;

[0076] Among all the planting area image data, each planting area image has at least two associated planting area image data, and the determination condition between the planting area image and the associated planting area image is: at least two of the four corner coordinates marked by the two planting area images are consistent;

[0077] Through the above logic formula and settings, the super-resolution processing logic of the planting area image data by the processing module in the system monitoring layer is limited, thereby improving the quality of the planting area image data.

[0078] The analysis layer includes a receiving module, a capturing module and an analyzing module. The receiving module is used to receive the global image of the planting area and forward the global image of the planting area to the analyzing module. The capturing module is used to capture the environmental parameters of the planting area during the acquisition phase of the global image of the planting area. The analyzing module is used to receive the environmental parameters of the planting area captured by the capturing module and analyze the production capacity of the planting area in combination with the global image of the planting area.

[0079] The logic of the production capacity analysis of the planting area in the analysis module is expressed as:

[0080] ;

[0081] Where: It is the production capacity performance value of the planting area; The number of fruit trees planted in the planting area; is the ideal number of fruit trees; It is the index of tree crown coverage; The number of fruits displayed in the global image of the planting area for the fruit trees planted in the planting area; , is a constant; is the ideal number of fruits per unit area of ​​the fruit tree at the current growth stage; To amend;

[0082] in, , For the ideal planting density, = is the planting area, the ideal number of fruits per unit area of ​​fruit trees at the current growth stage Defined by the system user, constant , The value range is 0~1, constant The value follows: The greater the slope of the planting area, the greater the constant The smaller the value, the more horizontal the planting area. The larger the value, the greater the constant The value is subject to: the higher the average height of fruit trees in the planting area, the higher the constant The larger the value, the smaller the constant The smaller the value, the higher the production capacity of the planting area. The larger it is, the better the production capacity of the planting area is; conversely, the smaller it is, the worse the production capacity of the planting area is. , Customized by system end users;

[0083] Tree crown coverage index for:

[0084] ;

[0085] Where: It is the ratio of the canopy coverage area of ​​fruit trees to the total area of ​​the planting area in the global image of the planting area; The ideal canopy coverage range for the current fruit tree growth stage, which is customized by the system user;

[0086] Correction Set and modify based on the environmental parameters of the planting area The values ​​are:

[0087] ;

[0088] Where: is the weight; The ideal light duration, temperature, humidity, wind speed, precipitation, and the content of the vth soil nutrient element for the fruit tree in the current growth stage; The actual duration of sunlight, temperature, humidity, wind speed, precipitation, and content of the vth soil nutrient element in the current growth stage of the fruit tree; The types of nutrients required for the current growth of fruit trees;

[0089] Among them, the weight The values ​​are defined by the system user and are all positive numbers, and the weight The sum is 1;

[0090] The production capacity of the planting area is calculated through the above logical formula, which provides necessary parameter support for the operation of the evaluation layer of the above system.

[0091] The evaluation layer includes a recording module, a visualization module and an evaluation module. The recording module is used to receive the production capacity analysis results of the planting area in the analysis layer and record the received analysis results. The visualization module is used to continuously obtain the production capacity analysis results of the planting area recorded in the recording module and generate a trend chart representing the production capacity of the planting area based on the production capacity analysis results of the planting area. The evaluation module is used to evaluate whether the current production capacity of the planting area is healthy.

[0092] Among them, the trend chart generated based on the analysis results of the planting area production capacity in the visualization module is a line chart, the horizontal axis of the trend chart represents the time when the analysis layer outputs the planting area production capacity, and the vertical axis represents the planting area production capacity performance value output at the corresponding time;

[0093] The receiving module is interactively connected to the capturing module and the analyzing module through a wireless network, the receiving module is interactively connected to the reorganizing module through a wireless network, the reorganizing module is interactively connected to the processing module and the collecting module through a wireless network, the analyzing module is interactively connected to the recording module through a wireless network, and the recording module is interactively connected to the visualization module and the evaluating module through a wireless network.

[0094] In this embodiment, the acquisition module runs to collect image data of the planting area, the processing module synchronously receives the image data of the planting area collected by the acquisition module, and performs super-resolution processing on the image data. The reorganization module further receives the image data of the planting area processed in the processing module in real time, and reorganizes the image data of the planting area. The receiving module post-operates to receive the global image of the planting area, and forwards the global image of the planting area to the analysis module. The capture module captures the environmental parameters of the planting area in the global image of the planting area in real time during the acquisition stage, and then the analysis module receives the environmental parameters of the planting area captured by the capture module, analyzes the production capacity of the planting area in combination with the global image of the planting area, the recording module synchronously receives the analysis results of the production capacity of the planting area in the analysis layer, and records the received analysis results. The visualization module runs to continuously obtain the analysis results of the production capacity of the planting area recorded in the recording module, and generates a trend chart representing the production capacity of the planting area based on the analysis results of the production capacity of the planting area. Finally, the evaluation module evaluates whether the current production capacity of the planting area is healthy.

[0095] The system operation in the above embodiment provides a real-time and comprehensive productivity assessment and monitoring service for the orchard fruit tree planting scene, effectively assisting orchard management users to manage and predict the real-time productivity status of the orchard more quickly, intelligently and accurately;

[0096] See also Figure 2 As shown, based on the arrow indications in the figure, the process of recombining the planting area image data to obtain the global image of the planting area is further demonstrated (different fillings are used in the figure to represent different planting area image data).

[0097] like Figure 1 As shown, the global image of the planting area received by the receiving module is sourced from the reorganization module, and the capture module runs synchronously with the receiving module. Each time the receiving module receives the global image of the planting area, the capture operation of the environmental parameters of the planting area is synchronously executed;

[0098] Environmental parameters of the planting area include: light, temperature, humidity, wind speed, precipitation, and soil nutrient content.

[0099] Through the above settings, further operation data support is provided for the operation of the system in the above embodiments, and the content of the environmental parameters of the planting area is limited.

[0100] like Figure 1 As shown, when the evaluation module evaluates whether the production capacity of the planting area is healthy during the operation phase, the trend chart generated in the current visualization module is traversed. When the latest three consecutive line segments in the trend chart rise continuously, it indicates that the production capacity of the planting area is healthy. Otherwise, it indicates that there is a health risk in the production capacity of the planting area.

[0101] Among them, the visualization module synchronously updates the trend graph representing the production capacity of the planting area after each recording module records the new analysis results of the production capacity of the planting area.

[0102] Through the above settings, the trend chart generated in the visualization module is given a specified generation logic, providing the system-side users of the system in the above embodiment with visualized dynamic reading conditions of the productivity of the planting area.

[0103] In summary, during the operation of the system in the above embodiment, the system uses machine vision technology to perform global image acquisition of fruit trees in the orchard, and further optimizes and reorganizes the fruit tree images through graphics processing technology, thereby effectively improving the quality of the fruit tree images. Based on the collection of orchard environmental parameters and combined with comprehensive analysis of fruit tree images, an effective and comprehensive assessment of the production capacity of the fruit tree planting area in the orchard is performed, and certain visualization conditions are provided to assist orchard management users in real-time monitoring of orchard productivity more quickly, efficiently and accurately.

[0104] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An agricultural production capacity assessment and monitoring system based on machine vision, characterized in that: include: Monitoring layer, analysis layer and evaluation layer; The image processing acquisition and processing logic are set in the monitoring layer. The image data of the planting area is collected in real time by the monitoring layer based on the acquisition logic, and is further forwarded to the analysis layer after being processed by the processing logic. The analysis layer receives the image data of the planting area, and synchronously collects the environmental parameters of the planting area. The production capacity of the planting area is analyzed based on the environmental parameters of the planting area and the image data of the planting area. The evaluation layer synchronously receives the production capacity of the planting area analyzed in the analysis layer, records the received analysis results of the production capacity of the planting area, and generates a production capacity situation map of the planting area based on the recorded analysis results of the production capacity of the planting area to evaluate the health of the production capacity of the planting area. The monitoring layer includes an acquisition module, a processing module and a reorganization module. The acquisition module is used to acquire the image data of the planting area. The processing module is used to receive the image data of the planting area acquired by the acquisition module and perform super-resolution processing on the image data. The reorganization module is used to receive the image data of the planting area processed by the processing module in real time and reorganize the image data of the planting area. The image acquisition logic and the processing logic are stored in the acquisition module and the processing module respectively. The acquisition module acquires the image data of the planting area based on the image acquisition logic. The processing module processes the image data of the planting area based on the processing logic. During the operation phase of the reorganization module, the image data of the planting area is reorganized based on the corresponding coordinates of the image data of the planting area. The reorganized image is recorded as the global image of the planting area. The acquisition module is integrated by a drone and a high-definition camera. The acquisition module performs the acquisition operation of the planting area image data based on the acquisition cycle customized by the system end user. The acquisition logic applied when the acquisition module runs to collect the planting area image data is: ； Where: The number of planting area image data collected on the edge of the planting area; The base number of image data collected in the planting area; The complexity of the planting area; is the area of ​​the planting area; Number of fruit trees planted for the planting area; Among them, the number of collected image data of the planting area is The number of planting area image data collected on the edge of the planting area is defined by the system end user The value is rounded up. That is, the number of image data collected in the planting area and the complexity of the planting area The calculation formula is: ； Where: is the ratio of average tree height to average tree spacing; It is the ratio of the difference between the highest tree height and the lowest tree height in the orchard to the length of the orchard; It is the ratio of the difference between the highest tree height and the lowest tree height in the orchard to the width of the orchard; , are the coefficient of variation of sunshine duration and the coefficient of instability of wind speed and direction; Among them, the coefficient of variation of sunshine duration and the coefficient of instability of wind speed and direction , It is defined by the system end user and is subject to: the values ​​are all in the range of 0~1. The greater the difference in daily light duration within the specified time threshold of the planting area, the greater the light duration variation coefficient. The larger the value, the smaller the value, the greater the difference in the daily average wind speed within the specified time threshold of the planting area, and the wind speed and wind direction instability coefficient. The larger the value, the smaller the value; The analysis layer includes a receiving module, a capturing module and an analyzing module. The receiving module is used to receive a global image of the planting area and forward the global image of the planting area to the analyzing module. The capturing module is used to capture the environmental parameters of the planting area during the acquisition phase of the global image of the planting area. The analyzing module is used to receive the environmental parameters of the planting area captured by the capturing module and analyze the production capacity of the planting area in combination with the global image of the planting area. The production capacity analysis logic of the planting area in the analysis module is expressed as: ； Where: It is the production capacity performance value of the planting area; The number of fruit trees planted in the planting area; is the ideal number of fruit trees; It is an indicator of tree crown coverage; The number of fruits displayed in the global image of the planting area for the fruit trees planted in the planting area; , is a constant; is the ideal number of fruits per unit area of ​​the fruit tree at the current growth stage; To amend; in, , For the ideal planting density, = is the planting area, the ideal number of fruits per unit area of ​​fruit trees at the current growth stage Defined by the system user, constant , The value range is 0~1, constant The value follows: The greater the slope of the planting area, the greater the constant The smaller the value, the more horizontal the planting area. The larger the value, the greater the constant The value is subject to: the higher the average height of fruit trees in the planting area, the higher the constant The larger the value, the smaller the constant The smaller the value, the higher the production capacity of the planting area. The larger it is, the better the production capacity of the planting area is; conversely, the smaller it is, the worse the production capacity of the planting area is. , Customized by system end users; The canopy coverage index for: ； Where: It is the ratio of the canopy coverage area of ​​fruit trees to the total area of ​​the planting area in the global image of the planting area; The ideal canopy coverage range for the current fruit tree growth stage, which is customized by the system user; The amendment The correction is set based on the environmental parameters of the planting area. The values ​​are: ； Where: is the weight; The ideal light duration, temperature, humidity, wind speed, precipitation, and the content of the vth soil nutrient element for the fruit tree in the current growth stage; The actual duration of sunlight, temperature, humidity, wind speed, precipitation, and content of the vth soil nutrient element in the current growth stage of the fruit tree; The types of nutrients required for the current growth of fruit trees; Among them, the weight The values ​​are defined by the system user and are all positive numbers, and the weight The sum is 1.

2. The agricultural production capacity evaluation and monitoring system based on machine vision according to claim 1 is characterized in that: The number of planting area image data collected on the edge of the planting area After obtaining, based on The planting area is divided into sub-regions, so that each sub-region has the same size and shape, and collects image data above each sub-region to obtain Image data of the planting area; Among them, after each planting area image data is collected, the boundary four corner coordinates of the planting area image data in the actual planting area are synchronously obtained, and the obtained boundary four corner coordinates are further marked at the corresponding four corner positions in the planting area image data.

3. The agricultural production capacity evaluation and monitoring system based on machine vision according to claim 1 is characterized in that: The processing logic of the planting area image data in the processing module is expressed as follows: Take each pixel in the planting area image data as the processing target, identify the grayscale value of each pixel in the 3×3 window surrounding the processing target, divide the processing target into 2×2 sub-pixels, obtain the grayscale value of the pixel in the window adjacent to the sub-pixel, and adjust the grayscale value of the sub-pixel based on the grayscale value of the pixel in the window adjacent to the sub-pixel: ； Where: is the adjusted target grayscale value of sub-pixel a; is the gray value of adjacent pixels in the window; is the gray value of the sub-pixel; Indicates the operation of rounding up; Based on the above formula, the target grayscale value of each sub-pixel in the planting area image data is obtained, and the obtained grayscale value is used to iterate the original grayscale value of the sub-pixel to complete the super-resolution processing of the planting area image data; No super-resolution processing is performed on the edge sub-pixels in the planting area image data; when the reorganization module reorganizes the planting area image data, the splicing association of the planting area image data during reorganization is determined based on the four-corner coordinates marked by the planting area image data, and when the planting area image data are spliced ​​and reorganized with each other, the edge sub-pixels of each planting area image data overlap with each other, and the grayscale value of the overlapping sub-pixel is taken as the average of its own grayscale value and the grayscale value of the overlapping sub-pixel below; Among all the planting area image data, each planting area image has at least two associated planting area image data, and the judgment condition between the planting area image and the associated planting area image is that at least two of the four corner coordinates marked by the two planting area images are consistent.

4. The agricultural production capacity evaluation and monitoring system based on machine vision according to claim 2 is characterized in that: The global image of the planting area received by the receiving module is sourced from the reorganization module, and the capturing module runs synchronously with the receiving module. Each time the receiving module receives the global image of the planting area, the capturing operation of the environmental parameters of the planting area is synchronously performed; The environmental parameters of the planting area include: light, temperature, humidity, wind speed, precipitation, and soil nutrient content.

5. The agricultural production capacity evaluation and monitoring system based on machine vision according to claim 1 is characterized in that: The evaluation layer includes a recording module, a visualization module and an evaluation module. The recording module is used to receive the production capacity analysis results of the planting area in the analysis layer and record the received analysis results. The visualization module is used to continuously obtain the production capacity analysis results of the planting area recorded in the recording module and generate a trend chart representing the production capacity of the planting area based on the production capacity analysis results of the planting area. The evaluation module is used to evaluate whether the current production capacity of the planting area is healthy. Among them, the trend chart generated based on the planting area production capacity analysis results in the visualization module is a line chart, the horizontal axis of which represents the time when the analysis layer outputs the planting area production capacity, and the vertical axis represents the planting area production capacity performance value output at the corresponding time.

6. The agricultural production capacity evaluation and monitoring system based on machine vision according to claim 5 is characterized in that: When the evaluation module evaluates whether the production capacity of the planting area is healthy during the operation phase, the trend chart generated in the current visualization module is traversed. When the latest three consecutive line segments in the trend chart rise continuously, it indicates that the production capacity of the planting area is healthy. Otherwise, it indicates that there is a health risk in the production capacity of the planting area. Among them, the visualization module synchronously updates the trend graph representing the production capacity of the planting area after each recording module records the new analysis results of the production capacity of the planting area.

7. The agricultural production capacity evaluation and monitoring system based on machine vision according to claim 1 is characterized in that: The receiving module is interactively connected to a capture module and an analysis module via a wireless network, the receiving module is interactively connected to a reorganization module via a wireless network, the reorganization module is interactively connected to a processing module and a collection module via a wireless network, the analysis module is interactively connected to a recording module via a wireless network, and the recording module is interactively connected to a visualization module and an evaluation module via a wireless network.

Images