Method for predicting maize hybrid expression based on multi-environment data

Abstract

The invention relates to the technical field of general image data processing or generation, in particular to a method for predicting maize hybrid expression based on multi-environment data, and the method comprises the steps: collecting an environment scene image of a growth region of a target crop and a canopy image of the target crop, and obtaining a scene image set and a canopy image set; obtaining a scene state based on the scene image set; obtaining a type image set and a shape image set based on the canopy image set; according to the type image set and the shape image set, determining a target crop hybridization abnormal state; and in response to the abnormal state, performing abnormal result prediction. According to the method, the abnormal hybridization expression state of the target crop is determined through the type image set and the shape image set, rapid prediction of the hybridization expression state of the corn crop is realized, the method is different from the prior art which needs to be realized through complicated manual monitoring, and timely and accurate judgment of the corn crop field with the abnormal hybridization expression state is realized.

Description

Technical Field

[0001] The present application relates to the general field of image data processing or generation technology, and in particular to a method for predicting corn hybrid performance based on multi-environment data. Background Art

[0002] Crop canopy information can comprehensively reflect the dynamic changes of crops during their growth period and characterize the growth status of crops. At present, dynamic monitoring of crop growth has been highly valued as an important direction for multi-environment data prediction. With the development of computer vision and graphics and image processing technology, digital image acquisition has gradually been applied to the monitoring of crop growth process, and a large number of attempts have been made from multiple angles, multiple levels, and multiple crops.

[0003] In the existing technology, the hybrid performance of crops such as corn needs to be monitored manually at various stages in order to obtain the hybrid performance results in a timely manner and make responses. However, this method is complicated and requires a lot of manpower and financial resources. It does not have good economic value and cannot be quickly combined in multiple scenarios. Summary of the invention

[0004] The inventors discovered through research that Ji Shouwen and others used digital image processing technology to study weeds in the corn seedling stage, identified weeds based on projection area, leaf width and leaf length, and further determined weed density based on the projection area of ​​the weeds. Based on this, the inventors optimized and adapted it to solve the prediction of hybrid performance of corn crops, thereby achieving rapid prediction of hybrid performance of corn crops.

[0005] The purpose of this application is to provide a method for predicting corn hybrid performance based on multi-environmental data to solve the technical problem that the prior art cannot provide a method for predicting corn hybrid performance based on canopy information.

[0006] According to one aspect of the present application, a method for predicting corn hybrid performance based on multi-environment data is provided, the method being executed by a processor, comprising: Collect environmental scene images of the target crop growth area and canopy images of the target crop to obtain scene atlas and canopy atlas; Based on the scenario atlas, the scenario status is obtained; Based on the canopy atlas, we obtain the species atlas and shape atlas; Determine the abnormal state of hybrid performance of target crops based on the species atlas and shape atlas; In response to the performance abnormality, an abnormal outcome prediction is performed.

[0007] In some embodiments, the target crops include at least a corn crop. In some embodiments, the scenario atlas includes at least soil moisture, soil temperature, air temperature and humidity, and light intensity.

[0008] In some embodiments, the canopy atlas includes at least an atlas obtained based on an acquisition distance and an acquisition frequency.

[0009] In some embodiments, the species atlas includes at least canopy size and height of the target crop.

[0010] In some embodiments, the shape atlas includes at least a canopy shape of a target crop.

[0011] In some embodiments, the determination of abnormal hybrid performance of target crops based on the species atlas and the shape atlas is specifically as follows: Perform preprocessing based on the category atlas and the shape atlas; Perform edge detection on the preprocessed image to obtain an edge image; Perform curve intersection point detection on the edge image to obtain the curve intersection points in the canopy area; fitting in response to the curve intersection points to obtain a curvature characterizing a target crop; Calculate the target crop anomaly based on the curvature.

[0012] In some embodiments, the curvature is calculated as: in, is the curvature ratio; is the curvature of the target crop; is the standard curvature; is the curvature difference.

[0013] In some embodiments, when Less than or equal to When , the curvature of the target crop is normal; when Greater than When , the curvature of the target crop is abnormal.

[0014] In some embodiments, the abnormal result prediction includes at least the hybridization showing normal results, the hybridization showing abnormal results, and the hybridization showing a tendency toward abnormal results.

[0015] Compared with the prior art, the present application has the following advantages and beneficial effects: the method of the present application determines the abnormal hybrid performance of the target crop through a species atlas and a shape atlas, thereby realizing rapid prediction of the hybrid performance of corn crops, which is different from the prior art that requires complicated manual monitoring; at the same time, the present application intuitively realizes timely and accurate judgment of corn crops with abnormal hybrid performance by calculating the curvature value in the canopy information. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 It is a flow chart of the prediction method of this application. DETAILED DESCRIPTION

[0018] The following will be combined with the attached examples of the present application Figure 1 The technical solutions in the embodiments of the present application are described clearly and completely. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0019] Application Overview Digital agriculture research and application have been booming. As an important direction in the field of digital agriculture, dynamic monitoring of crop growth has been highly valued by researchers. With the development of computer vision and graphic image processing technology, digital image acquisition products have been gradually applied to crop growth process monitoring. Researchers have conducted a lot of attempts from multiple angles, multiple levels, and multiple crops. This application is based on the inconvenience of existing hybridization monitoring and prediction, and performs rapid prediction of corn crop hybridization anomalies based on the canopy and growth environment.

[0020] Exemplary Methods The present embodiment provides a method for predicting corn hybrid performance based on multi-environment data, which is performed by a processor. The processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0021] The method specifically includes collecting environmental scene images of the target crop growth area and canopy images of the target crop to obtain scene atlases and canopy atlases; based on the scene atlases, obtaining scene states; based on the canopy atlases, obtaining species atlases and shape atlases; determining the abnormal hybrid performance of the target crop according to the species atlases and shape atlases; and predicting abnormal results in response to the abnormal performance. This method focuses on the canopy information of corn crops, which is different from the prior art that gives priority to overall considerations when observing and predicting hybrid performance, and can more accurately and quickly predict the results of corn hybrid performance. At the same time, this method combines the curvature of the fitting curve of the target corn crop in the prediction to achieve the prediction and judgment of the abnormal hybrid performance.

[0022] Based on this, the following describes each step in detail: In some embodiments, the target crops include at least corn crops.

[0023] In some embodiments, the scenario atlas includes at least soil moisture, soil temperature, air temperature and humidity, and light intensity. In some embodiments, the canopy atlas includes at least an atlas obtained based on an acquisition distance and an acquisition frequency.

[0024] In some embodiments, the species atlas includes at least the canopy size and height of the target crop, and the shape atlas includes at least the canopy shape of the target crop.

[0025] In some embodiments, the abnormal state of hybridization performance of the target crop is determined based on the species atlas and the shape atlas, specifically: preprocessing is performed based on the species atlas and the shape atlas; edge detection is performed on the preprocessed image to obtain an edge image; curve intersection point detection is performed on the edge image to obtain curve intersection points within the canopy area; fitting is performed in response to the curve intersection points to obtain a curvature that characterizes the target crop; and the abnormal state of the target crop is calculated based on the curvature.

[0026] In detail, the curvature is calculated as: in, is the curvature ratio; is the curvature of the target crop; is the standard curvature; is the curvature difference, where Less than or equal to When , the curvature of the target crop is normal; when Greater than When , the curvature of the target crop is abnormal.

[0027] In some embodiments, the abnormal result prediction includes at least the hybridization showing normal results, the hybridization showing abnormal results, and the hybridization showing a tendency toward abnormal results.

[0028] The above shows and describes the basic principles, main features and advantages of the present application. For those skilled in the art, it is obvious that the present application is not limited to the details of the above-mentioned exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or basic features of the present application.

[0029] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present application is limited by the appended claims rather than the above description, so it is intended to include all changes within the meaning and scope of the equivalent elements of the claims in the present application. Any reference sign in the claims should not be regarded as limiting the claims involved.

[0030] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. A method for predicting corn hybrid performance based on multi-environment data, the method being executed by a processor, characterized in that: include: Collect environmental scene images of the target crop growth area and canopy images of the target crop to obtain scene atlas and canopy atlas; Based on the scenario atlas, the scenario status is obtained; Based on the canopy atlas, we obtain the species atlas and shape atlas; Determine the abnormal state of hybrid performance of target crops based on the species atlas and shape atlas; In response to the performance abnormality, an abnormal outcome prediction is performed.

2. The method according to claim 1, characterized in that Target crops include at least corn crops.

3. The method according to claim 1, characterized in that The scenario atlas includes at least soil moisture, soil temperature, air temperature and humidity, and light intensity.

4. The method according to claim 1, characterized in that: The canopy atlas at least includes an atlas obtained based on a collection distance and a collection frequency.

5. The method according to claim 1, characterized in that The species atlas includes at least the canopy size and height of the target crops.

6. The method according to claim 5, characterized in that The shape atlas includes at least the canopy shape of the target crop.

7. The method according to claim 1, characterized in that The method of determining the abnormal state of hybrid performance of target crops according to the species atlas and the shape atlas is specifically as follows: Perform preprocessing based on the category atlas and the shape atlas; Perform edge detection on the preprocessed image to obtain an edge image; Perform curve intersection point detection on the edge image to obtain the curve intersection points in the canopy area; fitting in response to the curve intersection points to obtain a curvature characterizing a target crop; Calculate the target crop anomaly based on the curvature.

8. The method according to claim 7, characterized in that The curvature is calculated as: in, is the curvature ratio; is the curvature of the target crop; is the standard curvature; is the curvature difference.

9. The method according to claim 8, characterized in that when Less than or equal to When , the curvature of the target crop is normal; when Greater than When , the curvature of the target crop is abnormal.

10. The method according to claim 1, characterized in that The prediction of abnormal results at least includes the hybridization showing normal results, the hybridization showing abnormal results, and the hybridization showing a tendency toward abnormal results.

Images