Crop growth status and environment monitoring method and system based on image processing

Abstract

The application relates to the technical field of agricultural monitoring, and discloses a crop growth state and environment monitoring method based on picture processing, which comprises the following steps: real-time shooting of images of crops by a high-definition camera, synchronous acquisition of crop growth environment parameters by various environment monitoring sensors, extraction of crop growth state features based on acquired image parameters, analysis of crops from three directions of shape, color and diseases and insect pests, judgment of the growth state of crops according to analysis results, judgment of whether the current environment condition is suitable for crop growth based on sensor data, and quick identification of environment factors which are significantly related to each growth state problem in combination with the growth state of crops and environment parameters, so that the accuracy of crop growth state analysis is improved, the relationship between crop growth and environment can be comprehensively understood, and a more scientific and reasonable decision basis is provided for agricultural production management.

Description

Technical Field

[0001] This invention relates to the field of agricultural monitoring technology, specifically to a method and system for monitoring crop growth status and the environment based on image processing. Background Technology

[0002] With the rapid development of agricultural technology and the continuous advancement of large-scale production, timely and accurate understanding of crop growth status and environmental information is crucial for improving crop yield and quality.

[0003] Existing crop growth status monitoring methods largely rely on manual and intelligent monitoring: 1. Manual monitoring often relies on traditional experience to judge the growth status of crops and the environmental conditions. This method is easily affected by individual differences, thus affecting the final crop yield and quality; 2. Intelligent monitoring lacks the ability to integrate different data, comprehensively analyze crop growth status from multiple sources, and combine crop growth status with the environment to discover relevant environmental factors for different states. Therefore, this invention proposes a crop growth status and environmental monitoring method and system based on image processing to solve the problems existing in current monitoring methods. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for monitoring crop growth status and the environment based on image processing, thereby solving the aforementioned technical problems.

[0005] A method for monitoring crop growth status and the environment based on image processing, the method comprising the following steps:

[0006] Step S1: Deploy multiple mobile monitoring terminals in the crop planting area. Each monitoring terminal is equipped with a high-definition camera and various environmental monitoring sensors. The high-definition camera captures images of the crops in real time, and the various environmental monitoring sensors collect crop growth environment parameters synchronously.

[0007] Step S2: Process the image data and sensor data;

[0008] Step S3: Extract features from the processed crop images to extract various feature parameters of the crops;

[0009] Step S4: Normalize the extracted characteristic parameters of crops, and analyze the growth and health status of crops based on the normalized characteristic parameters.

[0010] Step S5: Analyze the processed sensor data to determine whether the current environmental conditions are suitable for crop growth.

[0011] As a further description of the present invention, the working process of step S1 includes:

[0012] The monitoring terminal moves within the planting area according to a preset time interval and movement path, and transmits the collected images and environmental data to the data processing center via a wireless network.

[0013] The preset movement path is determined by dividing the planting area into a grid. The planting area is divided into multiple grids of equal size, and the monitoring terminal collects data in each grid in turn to ensure coverage of the entire planting area.

[0014] The preset time interval is flexibly adjusted according to the crop growth cycle and monitoring needs, shortening the time interval during critical periods of crop growth and extending the time interval during periods of relatively stable growth.

[0015] As a further description of the present invention, the working process of step S2 includes:

[0016] The image data processing procedure includes: using a median filtering algorithm to remove salt-and-pepper noise from the image; by setting an appropriate filter window size, noise is effectively removed while preserving the image details to the greatest extent; then, image enhancement processing is performed, using a histogram equalization algorithm to enhance the image contrast, making the details of the crops clearer and facilitating subsequent feature extraction; finally, image segmentation is performed, using a method combining threshold segmentation and region growing to separate the crops from the background, obtaining image regions containing only the crops, providing accurate image data for subsequent growth status analysis.

[0017] The sensor data processing process includes: filtering the data, using the Kalman filter algorithm to remove noise from the data and improve the accuracy of the data, and then normalizing all the data to bring different types of data to the same standard.

[0018] As a further description of the present invention, the working process of step S3 includes:

[0019] The characteristic parameters of crops include: shape characteristic parameters, color characteristic parameters, and pest and disease characteristics, such as flies;

[0020] The shape characteristic parameters include: stem height, leaf area index, canopy coverage, and stem diameter;

[0021] The color characteristic parameters include: the proportion of leaf browning, spots, and withered parts;

[0022] The pest and disease characteristic parameters include: the proportion of leaf boreholes and notches.

[0023] As a further description of the present invention, the working process of step S4 includes:

[0024] Obtain the average stem height of crops in the i-th grid planting area. Average leaf area index Average canopy coverage and average stem diameter ;

[0025] The crop shape coefficient calculation model for the i-th grid planting area is constructed, and the expression is:

[0026] ;

[0027] In the formula, Let be the crop shape coefficient of the i-th grid planting area. , and These are the weighting coefficients.

[0028] As a further description of the present invention, the working process of step S4 also includes:

[0029] Obtain the average proportions of browning, spotting, and wilting on the leaves of crops in the i-th grid planting area. and ;

[0030] Construct a crop color coefficient calculation model for the i-th grid planting area, with the following expression:

[0031] ;

[0032] In the formula, Let be the crop color coefficient for the i-th grid planting area. , c and These are the weighting coefficients.

[0033] As a further description of the present invention, the working process of step S4 also includes:

[0034] Obtain the proportion of borer holes and notches on the leaves of crops in the i-th grid planting area. and ;

[0035] Construct a pest and disease coefficient calculation model for the i-th grid planting area, with the following expression:

[0036]

[0037] In the formula, Let be the pest and disease coefficient of the i-th grid planting area. , , and These are the weighting coefficients.

[0038] As a further description of the present invention, the working process of step S4 also includes:

[0039] Compare the shape coefficient, color coefficient, and pest and disease coefficient of the crop in the i-th grid seed region with the corresponding threshold range or threshold set by the system. If If it does not fall within the corresponding threshold range, it indicates that the crop's morphological structure is unhealthy; if If the value is greater than or equal to the corresponding threshold, it indicates that the crop is lacking nutrients; if If the value is greater than or equal to the corresponding threshold, it indicates that crop diseases and pests are serious.

[0040] like It belongs to the corresponding threshold range. and If all values ​​are less than the corresponding threshold, then a model for calculating the overall state coefficient of crops is constructed, expressed as follows:

[0041] ;

[0042] In the formula, Let be the overall crop condition coefficient for the i-th grid planting area. , and These are the weighting coefficients;

[0043] Will Compared with different overall state threshold ranges set by the system, according to The corresponding overall status threshold range divides the crop growth status into: qualified, good, and excellent.

[0044] As a further description of the present invention, the working process of step S5 includes:

[0045] Then, the normalized environmental data are compared and analyzed with the suitable environmental parameter range for crop growth set by the system to determine whether the current environmental conditions are suitable for crop growth. When the environmental parameters exceed the suitable range, corresponding early warning information is issued.

[0046] By correlating environmental data with crop growth and health status, when any abnormal situation occurs, such as unhealthy crop morphology and structure, lack of nutrition, or severe crop diseases and pests, the system acquires data on the changes of various environmental data over a set historical period and constructs function curves for these changes. The area enclosed by each curve and the x-axis is then calculated and compared with the corresponding standard area interval set by the system. This allows for the rapid identification of significantly related environmental factors, i.e., environmental data that does not conform to the corresponding standard area interval is the relevant environmental factor causing the current abnormal situation.

[0047] A crop growth status and environmental monitoring system based on image processing, the system comprising:

[0048] The data acquisition module is used to collect parameters of crop growth status and growth environment.

[0049] The data processing module is used to process the collected parameters;

[0050] The data analysis module is used to analyze the processed parameters to determine the current growth status of crops and the current environmental status of crops.

[0051] The beneficial effects of this invention are:

[0052] This invention extracts crop growth status features based on acquired image parameters, analyzes crops from three aspects: shape, color, and pests and diseases, and determines the crop growth status based on the analysis results. It also determines whether the current environmental conditions are suitable for crop growth based on sensor data, and combines the crop growth status and environmental parameters to quickly identify environmental factors that are significantly related to various growth status issues. This not only improves the accuracy of crop growth status analysis, but also enables a comprehensive understanding of the relationship between crop growth and the environment, providing a more scientific and reasonable decision-making basis for agricultural production management. Attached Figure Description

[0053] The invention will now be further described with reference to the accompanying drawings.

[0054] Figure 1 This is a partial flowchart of the crop growth status and environmental monitoring method based on image processing provided by the present invention. Detailed Implementation

[0055] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0056] Please see Figure 1 As shown, this invention is a method for monitoring crop growth status and the environment based on image processing. The method includes the following steps:

[0057] Step S1: Deploy multiple mobile monitoring terminals in the crop planting area. Each monitoring terminal is equipped with a high-definition camera and various environmental monitoring sensors. The high-definition camera captures images of the crops in real time, and the various environmental monitoring sensors collect crop growth environment parameters synchronously.

[0058] Step S2: Process the image data and sensor data;

[0059] Step S3: Extract features from the processed crop images to extract various feature parameters of the crops;

[0060] Step S4: Normalize the extracted characteristic parameters of crops, and analyze the growth and health status of crops based on the normalized characteristic parameters.

[0061] Step S5: Analyze the processed sensor data to determine whether the current environmental conditions are suitable for crop growth.

[0062] The above describes the solution. This invention provides a method for monitoring crop growth status and environment based on image processing, addressing the problems of low efficiency, poor accuracy, and incomplete monitoring in existing methods. It uses a high-definition camera to capture real-time images of crops, while various environmental monitoring sensors simultaneously collect crop growth environment parameters. Based on the acquired image parameters, it extracts crop growth status characteristics, analyzing crops from three aspects: shape, color, and pests and diseases. The analysis results determine the crop's growth status, and sensor data assesses whether current environmental conditions are suitable for crop growth. By combining the crop's growth status and environmental parameters, it quickly identifies environmental factors significantly related to various growth status issues. This not only improves the accuracy of crop growth status analysis but also provides a comprehensive understanding of the relationship between crop growth and the environment, offering a more scientific and rational basis for agricultural production management.

[0063] As a further description of the present invention, the working process of step S1 includes:

[0064] The monitoring terminal moves within the planting area according to a preset time interval and movement path, and transmits the collected images and environmental data to the data processing center via a wireless network.

[0065] The preset movement path is determined by dividing the planting area into a grid. The planting area is divided into multiple grids of equal size, and the monitoring terminal collects data in each grid in turn to ensure coverage of the entire planting area.

[0066] The preset time interval is flexibly adjusted according to the crop growth cycle and monitoring needs, shortening the time interval during critical periods of crop growth and extending the time interval during periods of relatively stable growth.

[0067] As a further description of the present invention, the working process of step S2 includes:

[0068] The image data processing procedure includes: using a median filtering algorithm to remove salt-and-pepper noise from the image; by setting an appropriate filter window size, noise is effectively removed while preserving the image details to the greatest extent; then, image enhancement processing is performed, using a histogram equalization algorithm to enhance the image contrast, making the details of the crops clearer and facilitating subsequent feature extraction; finally, image segmentation is performed, using a method combining threshold segmentation and region growing to separate the crops from the background, obtaining image regions containing only the crops, providing accurate image data for subsequent growth status analysis.

[0069] The sensor data processing process includes: filtering the data, using the Kalman filter algorithm to remove noise from the data and improve the accuracy of the data, and then normalizing all the data to bring different types of data to the same standard.

[0070] As a further description of the present invention, the working process of step S3 includes:

[0071] The characteristic parameters of crops include: shape characteristic parameters, color characteristic parameters, and pest and disease characteristics, such as flies;

[0072] The shape characteristic parameters include: stem height, leaf area index, canopy coverage, and stem diameter;

[0073] The color characteristic parameters include: the proportion of leaf browning, spots, and withered parts;

[0074] The pest and disease characteristic parameters include: the proportion of leaf boreholes and notches.

[0075] As a further description of the present invention, the working process of step S4 includes:

[0076] Obtain the average stem height of crops in the i-th grid planting area. Average leaf area index Average canopy coverage and average stem diameter ;

[0077] The crop shape coefficient calculation model for the i-th grid planting area is constructed, and the expression is:

[0078] ;

[0079] In the formula, Let be the crop shape coefficient of the i-th grid planting area. , and These are the weighting coefficients.

[0080] Through the above technical solution, this embodiment provides a method for calculating crop shape coefficients based on crop shape feature parameters. First, the average stem height of the crop in the i-th grid planting area is obtained. Average leaf area index Average canopy coverage and average stem diameter Then through the formula Calculate the crop shape coefficient for the i-th grid planting area, where, The ratio of stem height to stem diameter reflects the synergy between plant morphology and canopy structure. Reflects the plant's health. Reflects canopy density, It reflects the combined effect of plant support strength and height (such as lodging resistance). The uniformity of the leaf distribution is important; excessive height may indicate severe shading.

[0081] As a further description of the present invention, the working process of step S4 also includes:

[0082] Obtain the average proportions of browning, spotting, and wilting on the leaves of crops in the i-th grid planting area. and ;

[0083] Construct a crop color coefficient calculation model for the i-th grid planting area, with the following expression:

[0084] ;

[0085] In the formula, Let be the crop color coefficient for the i-th grid planting area. , c and These are the weighting coefficients.

[0086] Through the above technical solution, the present invention provides a method for obtaining crop color coefficients based on crop color feature parameters, and obtains the average proportions of browning, spots, and withered parts of crop leaves in the i-th grid planting area. and Then through the formula Calculate the crop color coefficient for the i-th grid planting area, where, This indicates a synergistic effect between browning and wilt, which together accelerate color deterioration. This indicates that spots and browning have a synergistic effect, and that spots and browning have a competitive influence.

[0087] It should be noted that spots and withering have different physiological mechanisms and usually do not directly synergize or inhibit each other.

[0088] As a further description of the present invention, the working process of step S4 also includes:

[0089] Obtain the proportion of borer holes and notches on the leaves of crops in the i-th grid planting area. and ;

[0090] Construct a pest and disease coefficient calculation model for the i-th grid planting area, with the following expression:

[0091]

[0092] In the formula, Let be the pest and disease coefficient of the i-th grid planting area. , , and These are the weighting coefficients.

[0093] Through the above technical solution, this embodiment provides a method for obtaining crop disease and pest coefficients based on crop disease and pest characteristic parameters, and obtains the proportion of boreholes and notches on crop leaves in the i-th grid planting area. and Substitute into the formula Calculate the pest and disease coefficient for the i-th grid planting area, where, As interactive elements, wormholes represent internal damage, and notches represent edge damage. The actual destructive force of internal damage to the blade increases superlinearly.

[0094] As a further description of the present invention, the working process of step S4 also includes:

[0095] Compare the shape coefficient, color coefficient, and pest and disease coefficient of the crop in the i-th grid seed region with the corresponding threshold range or threshold set by the system. If If it does not fall within the corresponding threshold range, it indicates that the crop's morphological structure is unhealthy; if If the value is greater than or equal to the corresponding threshold, it indicates that the crop is lacking nutrients; if If the value is greater than or equal to the corresponding threshold, it indicates that crop diseases and pests are serious.

[0096] like It belongs to the corresponding threshold range. and If all values ​​are less than the corresponding threshold, then a model for calculating the overall state coefficient of crops is constructed, expressed as follows:

[0097] ;

[0098] In the formula, Let be the overall crop condition coefficient for the i-th grid planting area. , and These are the weighting coefficients;

[0099] Will Compared with different overall state threshold ranges set by the system, according to The corresponding overall status threshold range divides the crop growth status into: qualified, good, and excellent.

[0100] As a further description of the present invention, the working process of step S5 includes:

[0101] Then, the normalized environmental data are compared and analyzed with the suitable environmental parameter range for crop growth set by the system to determine whether the current environmental conditions are suitable for crop growth. When the environmental parameters exceed the suitable range, corresponding early warning information is issued.

[0102] By correlating environmental data with crop growth and health status, when any abnormal situation occurs, such as unhealthy crop morphology and structure, lack of nutrition, or severe crop diseases and pests, the system acquires data on the changes of various environmental data over a set historical period and constructs function curves for these changes. The area enclosed by each curve and the x-axis is then calculated and compared with the corresponding standard area interval set by the system. This allows for the rapid identification of significantly related environmental factors, i.e., environmental data that does not conform to the corresponding standard area interval is the relevant environmental factor causing the current abnormal situation.

[0103] It should be noted that all weight coefficients, thresholds, threshold intervals and standard curves in this invention are empirical values ​​and can be modified in combination with the crop growth stage. In addition, all parameters in this application have been normalized.

[0104] The foregoing has provided a detailed description of one embodiment of the present invention, but this description is merely a preferred embodiment and should not be construed as limiting the scope of the invention. All equivalent variations and modifications made within the scope of the claims of this invention should still fall within the patent coverage of this invention.

Claims

1. A method for monitoring crop growth status and environment based on image processing, characterized in that, The method includes the following steps: Step S1: Deploy multiple mobile monitoring terminals in the crop planting area. Each monitoring terminal is equipped with a high-definition camera and various environmental monitoring sensors. The high-definition camera captures images of the crops in real time, and the various environmental monitoring sensors collect crop growth environment parameters synchronously. Step S2: Process the image data and sensor data; Step S3: Extract features from the processed crop images to extract various feature parameters of the crops; Step S4: Normalize the extracted characteristic parameters of crops, and analyze the growth and health status of crops based on the normalized characteristic parameters. Step S5: Analyze the processed sensor data to determine whether the current environmental conditions are suitable for crop growth.

2. The method for monitoring crop growth status and environment based on image processing according to claim 1, characterized in that, The working process of step S1 includes: The monitoring terminal moves within the planting area according to a preset time interval and movement path, and transmits the collected images and environmental data to the data processing center via a wireless network. The preset movement path is determined by dividing the planting area into a grid. The planting area is divided into multiple grids of equal size, and the monitoring terminal collects data in each grid in turn to ensure coverage of the entire planting area. The preset time interval is flexibly adjusted according to the crop growth cycle and monitoring needs, shortening the time interval during critical periods of crop growth and extending the time interval during periods of relatively stable growth.

3. The method for monitoring crop growth status and environment based on image processing according to claim 2, characterized in that, The working process of step S2 includes: The image data processing procedure includes: using a median filtering algorithm to remove salt-and-pepper noise from the image; by setting an appropriate filter window size, noise is effectively removed while preserving the image details to the greatest extent; then, image enhancement processing is performed, using a histogram equalization algorithm to enhance the image contrast, making the details of the crops clearer and facilitating subsequent feature extraction; finally, image segmentation is performed, using a method combining threshold segmentation and region growing to separate the crops from the background, obtaining image regions containing only the crops, providing accurate image data for subsequent growth status analysis. The sensor data processing process includes: filtering the data, using the Kalman filter algorithm to remove noise from the data and improve the accuracy of the data, and then normalizing all the data to bring different types of data to the same standard.

4. The method for monitoring crop growth status and environment based on image processing according to claim 2, characterized in that, The working process of step S3 includes: The characteristic parameters of crops include: shape characteristic parameters, color characteristic parameters, and pest and disease characteristics, such as flies; The shape characteristic parameters include: stem height, leaf area index, canopy coverage, and stem diameter; The color characteristic parameters include: the proportion of leaf browning, spots, and withered parts; The pest and disease characteristic parameters include: the proportion of leaf boreholes and notches.

5. The method for monitoring crop growth status and environment based on image processing according to claim 2, characterized in that, The working process of step S4 includes: Obtain the average stem height of crops in the i-th grid planting area. Average leaf area index Average canopy coverage and average stem diameter ; The crop shape coefficient calculation model for the i-th grid planting area is constructed, and the expression is: ； In the formula, Let be the crop shape coefficient of the i-th grid planting area. , and These are the weighting coefficients.

6. The method for monitoring crop growth status and environment based on image processing according to claim 5, characterized in that, The working process of step S4 also includes: Obtain the average proportions of browning, spotting, and wilting on the leaves of crops in the i-th grid planting area. and ; Construct a crop color coefficient calculation model for the i-th grid planting area, with the following expression: ； In the formula, Let be the crop color coefficient for the i-th grid planting area. , c and These are the weighting coefficients.

7. The method for monitoring crop growth status and environment based on image processing according to claim 6, characterized in that, The working process of step S4 also includes: Obtain the proportion of borer holes and notches on the leaves of crops in the i-th grid planting area. and ; Construct a pest and disease coefficient calculation model for the i-th grid planting area, with the following expression: In the formula, Let be the pest and disease coefficient of the i-th grid planting area. , , and These are the weighting coefficients.

8. The method for monitoring crop growth status and environment based on image processing according to claim 6, characterized in that, The working process of step S4 also includes: Compare the shape coefficient, color coefficient, and pest and disease coefficient of the crop in the i-th grid seed region with the corresponding threshold range or threshold set by the system. If If it does not fall within the corresponding threshold range, it indicates that the crop's morphological structure is unhealthy; if If the value is greater than or equal to the corresponding threshold, it indicates that the crop is lacking nutrients; if If the value is greater than or equal to the corresponding threshold, it indicates that crop diseases and pests are serious. like It belongs to the corresponding threshold range. and If all values ​​are less than the corresponding threshold, then a model for calculating the overall state coefficient of crops is constructed, expressed as follows: ; In the formula, Let be the overall crop condition coefficient for the i-th grid planting area. , and These are the weighting coefficients; Will Compared with different overall state threshold ranges set by the system, according to The corresponding overall status threshold range divides the crop growth status into: qualified, good, and excellent.

9. The method for monitoring crop growth status and environment based on image processing according to claim 1, characterized in that, The working process of step S5 includes: Then, the normalized environmental data are compared and analyzed with the suitable environmental parameter range for crop growth set by the system to determine whether the current environmental conditions are suitable for crop growth. When the environmental parameters exceed the suitable range, corresponding early warning information is issued. By correlating environmental data with crop growth and health status, when any abnormal situation occurs, such as unhealthy crop morphology and structure, lack of nutrition, or severe crop diseases and pests, the system acquires data on the changes of various environmental data over a set historical period and constructs function curves for these changes. The area enclosed by each curve and the x-axis is then calculated and compared with the corresponding standard area interval set by the system. This allows for the rapid identification of significantly related environmental factors, i.e., environmental data that does not conform to the corresponding standard area interval is the relevant environmental factor causing the current abnormal situation.

10. A crop growth status and environmental monitoring system based on image processing, the system being used to implement the crop growth status and environmental monitoring method based on image processing as described in any one of claims 1-9, characterized in that, The system includes: The data acquisition module is used to collect parameters of crop growth status and growth environment. The data processing module is used to process the collected parameters; The data analysis module is used to analyze the processed parameters to determine the current growth status of crops and the current environmental status of crops.

Images