Method and device for breeding crop varieties resistant to high planting density based on time-series images of unmanned aerial vehicles

Abstract

The present invention provides a method and device for breeding crop varieties tolerant to high planting density based on drone time-series images, which relates to the technical field of agricultural informatization, and includes: acquiring time-series images collected by a drone for a crop planting area, where multiple varieties of crops are planted at different densities in the crop planting area; based on the time-series images, extracting the canopy development stage corresponding to each variety of crop and the intermediate features corresponding to the canopy development stage, so as to quantify the difference index of the canopy development rate of each variety of crop at different densities by using the intermediate features; according to the correlation between the high-planting-density tolerance index corresponding to each variety of crop and the difference index of the canopy development rate at different densities, screening out the target intermediate features, so as to realize the breeding of crop varieties tolerant to high planting density by using the target intermediate features. The present invention effectively quantifies the difference index of the canopy development rate of crop varieties under different planting densities, and significantly improves the efficiency and reliability of breeding crop varieties tolerant to high planting density.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural informatization, and particularly to a method and device for breeding crop varieties tolerant to high planting density based on UAV time-series images. Background Art

[0002] The development rate of the crop canopy largely determines its light absorption efficiency, thereby affecting the yield. When breeding varieties tolerant to high planting density, it is crucial to understand the growth dynamics of crops under high-density planting conditions. Therefore, quickly and accurately quantifying the development rate of crops at critical periods, defining the phenotypes of their early vigor, mid-term vigor, and maturity, and analyzing the influence mechanism of these phenotypic characteristics on the high-density tolerance ability are of great significance for optimizing breeding strategies and breeding ideal varieties tolerant to high planting density.

[0003] Traditional methods for breeding varieties tolerant to high planting density mainly rely on manual field statistics of crop development parameters such as plant height, yield, and pod number at different densities. This method is inefficient, has large subjective errors, and is difficult to effectively quantify the growth rate. Especially when there are many breeding materials, it becomes more difficult to statistically analyze growth information in real time, posing a severe challenge to high-throughput variety breeding. UAV phenotyping technology uses UAVs equipped with various sensors for plant monitoring. Previous studies mainly focused on collecting data once at each growth stage and constructing an inversion model in combination with machine learning, but it cannot reflect the growth and development dynamics of crop varieties under different planting densities, affecting the reliability of breeding crop varieties tolerant to high planting density. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a method and device for breeding crop varieties tolerant to high planting density based on UAV time-series images, which effectively quantify the canopy development rate difference index of crop varieties under different planting densities, and significantly improve the efficiency and reliability of breeding crop varieties tolerant to high planting density.

[0005] In the first aspect, an embodiment of the present invention provides a method for breeding crop varieties tolerant to high planting density based on UAV time-series images, including:

[0006] Obtain time-series images collected by a UAV for a crop planting area, where multiple varieties of crops are planted at different densities in the crop planting area, and the time-series images include RGB images, multispectral orthoimages, and elevation images corresponding to each variety of crop;

[0007] Based on the time-series images, extract the canopy development stage and intermediate features corresponding to the canopy development stage for each variety of crop, so as to use the intermediate features to quantify the canopy development rate difference index of each variety of crop under different densities;

[0008] According to the correlation between the density tolerance index corresponding to each variety of crop and the difference index of canopy development rate at different densities, target intermediate features are screened to realize the breeding of crop varieties with high density tolerance by using the target intermediate features.

[0009] In one implementation, based on time-series images, the canopy development stage corresponding to each variety of crop and the intermediate features corresponding to the canopy development stage are extracted, including:

[0010] Segment the time-series images to obtain the RGB sub-images, multi-spectral ortho-images, and elevation sub-images of each variety of crop;

[0011] For each variety of crop, based on the RGB sub-image, multi-spectral ortho-image, and elevation sub-image of the crop of this variety, the canopy coverage, plant height, and leaf area index of the crop of this variety are extracted to fit the time-series curve of canopy development of the crop of this variety;

[0012] According to the time-series curve of canopy development of the crop of this variety, the canopy development stage corresponding to the crop of this variety and the intermediate features corresponding to the canopy development stage are extracted.

[0013] In one implementation, based on the RGB sub-image, multi-spectral ortho-image, and elevation sub-image of the crop of this variety, the canopy coverage, plant height, and leaf area index of the crop of this variety are extracted to fit the time-series curve of canopy development of the crop of this variety, including:

[0014] Extract the canopy coverage of the crop of this variety based on the RGB sub-image;

[0015] And, extract the plant height of the crop of this variety based on the elevation sub-image;

[0016] And, extract the texture features of the crop of this variety based on the RGB sub-image, extract the vegetation index of the crop of this variety based on the RGB sub-image and the multi-spectral ortho-image, and output the leaf area index of the crop of this variety based on the vegetation index and the texture features through a pre-trained leaf area index estimation model;

[0017] For the canopy coverage, plant height, and leaf area index of the crop of this variety, P-splines are respectively fitted to obtain the time-series curve of canopy coverage, the time-series curve of plant height, and the time-series curve of leaf area index as the time-series curve of canopy development of the crop of this variety.

[0018] In one implementation, the training steps of the leaf area index estimation model include:

[0019] Taking the measured leaf area index value at a specified sub-region within the crop planting area as the training label, and taking the texture features and vegetation indices of the crops of this variety planted within the specified sub-region as the model inputs, training a Bi-LSTM model based on bidirectional hidden states to obtain a leaf area index estimation model;

[0020] Among them, the bidirectional hidden states include a forward hidden state and a backward hidden state. The forward hidden state represents the leaf area index from the past to the present, and the backward hidden state represents the leaf area index from the future to the present.

[0021] In one implementation, according to the canopy development time series curve of the crops of this variety, extracting the corresponding canopy development stage of the crops of this variety and the intermediate features corresponding to the canopy development stage, including:

[0022] Based on the plant height change characterized by the plant height time series curve of the crops of this variety, dividing the corresponding canopy development stage of the crops of this variety into an early stage, a middle stage, and a mature stage;

[0023] For each stage, respectively extracting the intermediate features characterizing the canopy development rate in this stage from the canopy coverage time series curve, the plant height time series curve, and the leaf area index time series curve.

[0024] In one implementation, using the intermediate features to quantify the canopy development rate difference index of the crops of each variety under different densities, including:

[0025] For each intermediate feature, determining the ratio between the intermediate features of the crops of this variety under different densities to obtain an intermediate feature ratio;

[0026] Taking each intermediate feature ratio as the canopy development rate difference index of the crops of this variety.

[0027] In one implementation, according to the correlation between the density tolerance index corresponding to the crops of each variety and the canopy development rate difference index of the crops of each variety under different densities, screening out the target intermediate features, including:

[0028] For the crops of each variety, determining the Pearson correlation coefficient between the density tolerance index corresponding to the crops of this variety and the intermediate feature ratio of the crops of this variety, and screening out the target intermediate features from the intermediate features in descending order of the Pearson correlation coefficient.

[0029] In a second aspect, an embodiment of the present invention further provides a device for breeding density-tolerant crop varieties based on UAV time-series images, including:

[0030] An image acquisition module, configured to acquire time-series images collected by a drone for a crop planting area, where multiple varieties of crops are planted at different densities in the crop planting area, and the time-series images include RGB images, multispectral orthophotos, and elevation images corresponding to each variety of crop;

[0031] A development rate difference quantification module, configured to extract the canopy development stage corresponding to each variety of crop and intermediate features corresponding to the canopy development stage based on the time-series images, so as to quantify the canopy development rate difference index of each variety of crop at different densities by using the intermediate features;

[0032] A variety breeding module, configured to screen out target intermediate features according to the correlation between the density tolerance index corresponding to each variety of crop and the canopy development rate difference index of the variety at different densities, so as to realize the breeding of crop varieties tolerant to close planting by using the target intermediate features.

[0033] In a third aspect, an embodiment of the present invention further provides an electronic device, including a processor and a memory, where the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the method according to any one of the first aspect.

[0034] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are called and executed by a processor, the computer-executable instructions cause the processor to implement the method according to any one of the first aspect.

[0035] A method and device for breeding crop varieties tolerant to close planting based on drone time-series images provided by an embodiment of the present invention first acquire time-series images collected by a drone for a crop planting area, where multiple varieties of crops are planted at different densities in the crop planting area, and the time-series images include RGB images, multispectral orthophotos, and elevation images corresponding to each variety of crop; then extract the canopy development stage corresponding to each variety of crop and intermediate features corresponding to the canopy development stage based on the time-series images, so as to quantify the canopy development rate difference index of each variety of crop at different densities by using the intermediate features; finally, screen out target intermediate features according to the correlation between the density tolerance index corresponding to each variety of crop and the canopy development rate difference index of the variety at different densities, so as to realize the breeding of crop varieties tolerant to close planting by using the target intermediate features. The above method extracts the canopy development stage of crops and its corresponding intermediate features from the time-series data collected by drones, quantifies the canopy development rate difference index of crops at different planting densities, and combines the density tolerance index corresponding to the crops and its correlation with the canopy development rate difference index at different densities to realize the breeding of crop varieties tolerant to close planting, thereby significantly improving the efficiency and reliability of breeding crop varieties tolerant to close planting.

[0036] Other features and advantages of the present invention will be set forth in the following description, and in part will be obvious from the description, or may be learned by practice of the present invention. The objectives and other advantages of the present invention are realized and attained by the structure particularly pointed out in the specification, claims as well as the drawings.

[0037] To make the above objectives, features and advantages of the present invention more comprehensible, preferred embodiments accompanied by the appended drawings are described in detail as follows. Description of the Drawings

[0038] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0039] Figure 1 Schematic flowchart of a method for breeding crop varieties tolerant to high planting density based on UAV time-series images provided by an embodiment of the present invention;

[0040] Figure 2 Overall flowchart of a method for breeding crop varieties tolerant to high planting density based on UAV time-series images provided by an embodiment of the present invention;

[0041] Figure 3 Schematic flowchart of a high-density tolerance analysis based on a dynamic model provided by an embodiment of the present invention;

[0042] Figure 4 Schematic diagram of a time series curve provided by an embodiment of the present invention;

[0043] Figure 5 Correlation between canopy rate difference and high-density tolerance index provided by an embodiment of the present invention;

[0044] Figure 6 Schematic diagram of breeding high-density tolerant crop varieties based on intermediate characteristics provided by an embodiment of the present invention;

[0045] Figure 7 Schematic structural diagram of a device for breeding crop varieties tolerant to high planting density based on UAV time-series images provided by an embodiment of the present invention;

[0046] Figure 8 Schematic structural diagram of an electronic device provided by an embodiment of the present invention. Detailed Embodiments

[0047] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0048] Currently, the traditional method for breeding high-density tolerant varieties mainly relies on manual counting of crop development parameters in the field. This method is inefficient, has large subjective errors, and there is little research on the acquisition of continuous crop images and the construction of dynamic models by combining time series algorithms. It is difficult to effectively quantify the growth rate and the differences of crops under different densities, which poses a severe challenge to high-throughput variety breeding. Based on this, the embodiments of the present invention provide a method and device for breeding high-density tolerant crop varieties based on UAV time series images, which effectively quantify the canopy development rate difference index of crop varieties under different planting densities and significantly improve the efficiency and reliability of breeding high-density tolerant crop varieties.

[0049] To facilitate the understanding of this embodiment, first, a method for breeding high-density tolerant crop varieties based on UAV time series images disclosed in the embodiments of the present invention will be introduced in detail. Refer to Figure 1 the flowchart of a method for breeding high-density tolerant crop varieties based on UAV time series images shown in

[0050] Step S102: Obtain the time series images collected by the UAV for the crop planting area.

[0051] Among them, multiple varieties of crops are planted at different densities in the crop planting area, and the time series images include the RGB images, multispectral orthophotos, and elevation images corresponding to each variety of crops. In one example, the UAV is equipped with a digital camera and a multispectral camera, and the images of the crop planting area are taken in a vertical photography manner. Starting from the emergence of the crops, a flight is carried out every N (such as 5) days, and the taken images are stitched to generate time series RGB images, multispectral orthophotos, and elevation images respectively.

[0052] Step S104: Based on the time series images, extract the canopy development stage and the intermediate features corresponding to the canopy development stage for each variety of crops, so as to quantify the canopy development rate difference index of each variety of crops under different densities by using the intermediate features.

[0053] Among them, the canopy development stage is divided into an early stage, a middle stage, and a mature stage. The early stage refers to the stage from crop emergence to the height of the first plant. The middle stage refers to the stage when the crop grows from the height of the first plant to the height of the second plant. The mature stage refers to the stage after the crop reaches the height of the second plant. The height of the first plant is related to the height of the second plant. For example, if the height of the second plant is the maximum plant height, then the height of the first plant is 25% of the maximum plant height. The intermediate characteristics of the early stage include: the time point when the maximum plant height reaches 25%, the canopy coverage and leaf area index at this time point, and the average change rates of the early plant height, canopy coverage, and leaf area index; the intermediate characteristics of the middle stage include: the maximum values of the plant height, canopy coverage, and leaf area index, and the average change rates of these three in the middle stage; the intermediate characteristics of the mature stage include: the average change rates of the plant height, canopy coverage, and leaf area index during the mature period. The canopy development rate difference index is the ratio of the intermediate characteristics of the early, middle, and mature stages of each variety at different densities.

[0054] In one example, first, the canopy coverage, plant height, and leaf area index of the crops of each variety are extracted based on the time-series images to fit the canopy development time-series curve of the crops of each variety. Then, the canopy development stage corresponding to the crops of each variety and the intermediate characteristics corresponding to the canopy development stage are further extracted using the canopy development time-series curve. Finally, by calculating the ratio of the intermediate characteristics of the early, middle, and mature stages of each variety at different densities, the canopy development rate difference index of the crops of each variety at different densities is quantified.

[0055] Step S106, according to the correlation between the density tolerance index corresponding to the crops of each variety and the canopy development rate difference index at different densities, the target intermediate characteristics are screened to realize the breeding of crop varieties tolerant to high planting density using the target intermediate characteristics.

[0056] In one example, the correlation between the density tolerance index and the canopy development rate difference index can be characterized by the Pearson correlation coefficient. The higher the value of the Pearson correlation coefficient, the higher the possibility that the corresponding intermediate characteristic is used as the target intermediate characteristic required for the breeding of crop varieties tolerant to high planting density.

[0057] The method for breeding crop varieties tolerant to high planting density based on UAV time-series images provided by the embodiments of the present invention extracts the canopy development stage of the crops and its corresponding intermediate characteristics from the time-series data collected by the UAV, quantifies the canopy development rate difference index of the crops under different planting densities, and combines the density tolerance index corresponding to the crops with the correlation between the canopy development rate difference index at different densities to realize the breeding of crop varieties tolerant to high planting density, thereby significantly improving the efficiency and reliability of the breeding of crop varieties tolerant to high planting density.

[0058] In specific implementation, the embodiments of the present invention utilize the UAV phenotyping technology, combine time series prediction and dynamic models, analyze the influence mechanism of canopy development rate on the density tolerance ability, and realize the breeding of high-throughput crop varieties with high density tolerance. Through the high-throughput advantage of UAVs, record the growth and development dynamics of crop varieties under different planting densities, accurately quantify the canopy development rate, and combine statistical analysis methods to conduct correlation analysis on the density tolerance ability of crop varieties, providing a technical basis for the high-throughput breeding of density-tolerant breeding materials.

[0059] See Figure 2 The overall flowchart of a method for breeding crop varieties with high density tolerance based on UAV time series images shown in Figure 2 It is shown that the method includes: time series data acquisition, including UAV digital image acquisition, UAV multispectral image acquisition, and measurement of leaf area index of some varieties; image processing, including image stitching, segmentation, and removal of ground background; feature extraction, including extraction of plant height, canopy coverage, vegetation index, texture features, etc., and extraction of leaf area index based on vegetation index and texture features using Bi-LSTM (Bidirectional Long Short Term Memory); construction of dynamic models and extraction of intermediate features, including early vigor features (i.e., intermediate features in the early stage), middle vigor features (i.e., intermediate features in the middle stage), and maturity features (i.e., intermediate features in the maturity stage); correlation relationship of density tolerance index, including correlation coefficient and SHAP (SHapley Additive exPlanations) algorithm. Further, see Figure 3 The flowchart of density tolerance analysis based on a dynamic model shown in

[0060] In Figure 2 and Figure 3 On the basis of, the embodiments of the present invention propose a method for breeding crop varieties with high density tolerance based on UAV time series images, which can extract crop phenotypic parameters through time series images and algorithms with high throughput, and quantify the crop development rate under different densities, aiming to improve the efficiency and reliability of breeding crop varieties with high density tolerance. Specifically, the embodiments of the present invention provide a specific implementation manner of a method for breeding crop varieties with high density tolerance based on UAV time series images.

[0061] For the aforementioned step S102, the embodiments of the present invention provide an implementation manner for obtaining time series images collected by the UAV for the crop planting area. Specifically:

[0062] The acquired data includes time-series images and ground data at a specified sub-region within the crop planting area, which is the measured value of the leaf area index. In one example, a drone is equipped with a digital camera and a multispectral camera to capture images of the crop planting area in a vertical photography manner. Starting from the emergence of the crop, flights are conducted every 5 days, and the captured images are stitched to generate time-series RGB images, multispectral orthoimages, and elevation images respectively. The ground data measures the actual leaf area index value of the specified sub-region through LAI-2200C.

[0063] For the aforementioned step S104, the embodiment of the present invention also provides an implementation manner of extracting the canopy development stage corresponding to each variety of crop and the intermediate features corresponding to the canopy development stage based on time-series images, as shown in the following steps 1A to 1C:

[0064] Step 1A: Segment the time-series images to obtain the RGB sub-images, multispectral ortho-sub-images, and elevation sub-images of each variety of crop.

[0065] In one example, use QGIS to generate a vector file containing geographical location information for each variety, and segment the stitched time-series images to obtain the RGB sub-images, multispectral ortho-sub-images, and elevation sub-images of each variety of crop.

[0066] Step 1B: For each variety of crop, based on the RGB sub-images, multispectral ortho-sub-images, and elevation sub-images of the variety, extract the canopy coverage, plant height, and leaf area index of the variety to fit the time-series curve of the canopy development of the variety. In specific implementation, it includes:

[0067] (1) Extract the canopy coverage of the variety based on the RGB sub-images. In one example, based on the segmented RGB sub-images, use the threshold method to remove the soil background, and calculate the canopy coverage of each variety on the date of the flying drone by dividing the number of vegetation pixel points by the total number of pixel points.

[0068] (2) Extract the plant height of the variety based on the elevation sub-images. In one example, based on the segmented elevation sub-images, use the percentile method to extract the plant height, with the ninety-ninth percentile as the upper boundary and the first percentile as the lower boundary, to obtain the plant height of each variety on all dates of the flying drone.

[0069] (3) Extract the texture features of the crops of this variety based on the RGB sub-images, extract the vegetation indices of the crops of this variety based on the RGB sub-images and the multispectral ortho-images, and output the leaf area index of the crops of this variety based on the vegetation indices and texture features through a pre-trained leaf area index estimation model. Among them, the texture features include mean (MEA), variance (VAR), homogeneity (HOM), contrast (CON), dissimilarity (DIS), entropy (ENT), second moment (SEC), and correlation (COR). In one example, the texture features are extracted from the RGB sub-images using the gray-level co-occurrence matrix method in Python; and the average DN (Digital Number) of each band in the RGB sub-images and the multispectral ortho-images is extracted, and then the vegetation indices are calculated; the characteristic data such as the time-series vegetation indices of each variety are input into the leaf area index estimation model, and the model will output the corresponding predicted leaf area index value. Finally, the leaf area index of each variety on all the flight drone dates is obtained.

[0070] Before performing (3), it is necessary to pre-construct a leaf area index estimation model. In specific implementation, the measured leaf area index value at a specified sub-region within the crop planting area can be used as the training label, and the texture features and vegetation indices of the crops of this variety planted within the specified sub-region can be used as the model input to train a Bi-LSTM model based on bidirectional hidden states to obtain the leaf area index estimation model; among them, the bidirectional hidden states include the forward hidden state and the backward hidden state. The forward hidden state represents the leaf area index from the past to the present, and the backward hidden state represents the leaf area index from the future to the present. In one example, a part of the soybean plots with measured leaf area index values is used as the training set, and an improved Bi-LSTM algorithm is used to establish the estimation model. The model input includes the time-series vegetation indices, texture features, etc. extracted from the RGB sub-images and the multispectral ortho-images. A bidirectional hidden state is added to the existing unidirectional LSTM model, where the forward hidden state represents the leaf area index information from the past to the present, and the backward hidden state represents the leaf area index information from the future to the present. Bi-LSTM selectively remembers and forgets information through the mechanisms of memory cells, input gates, forget gates, and output gates under the bidirectional processing method, so as to capture the dynamic relationship between features such as vegetation indices and the leaf area index.

[0071] (4) For the canopy coverage, plant height, and leaf area index of the crops of this variety, P-splines are respectively fitted to obtain the time series curves of canopy coverage, plant height, and leaf area index, which serve as the time series curves of canopy development for the crops of this variety. This step can also be referred to as dynamic model construction. Among them, P-spline is a semi-parametric model used to fit the measurement of traits at regular time intervals. Based on the plant height, canopy coverage, and leaf area index data of all flight drone dates respectively, Python is used to fit the P-spline to obtain the time series curves in days within the growth period of each variety, which are used to characterize the dynamic canopy development of the crops. Such as Figure 4 As shown in the schematic diagram of a time series curve, the time series curve includes the time series curve of canopy coverage, the time series curve of plant height, and the time series curve of leaf area index.

[0072] Step 1C: According to the time series curve of canopy development of the crops of this variety, extract the corresponding canopy development stage of the crops of this variety and the intermediate features corresponding to the canopy development stage.

[0073] In specific implementation, based on the change in plant height characterized by the time series curve of plant height of the crops of this variety, the corresponding canopy development stage of the crops of this variety can be divided into an early stage, a middle stage, and a mature stage; then for each stage, the intermediate features characterizing the canopy development rate are respectively extracted from the time series curves of canopy coverage, plant height, and leaf area index.

[0074] First, extract the growth vitality of the crops at different stages. It includes: Plant height is an intuitive indicator to measure the growth and development of crops. According to the change in plant height, the canopy development of crops can be divided into three stages: early, middle, and mature. The early stage refers to the period from emergence to reaching 25% of the maximum plant height; the middle stage is from this point to reaching the maximum plant height; the mature stage refers to the period after reaching the maximum plant height.

[0075] Then, extract intermediate features to characterize the crop development status at different stages. It includes: Plant height, canopy coverage, and leaf area index are key indicators reflecting the horizontal and vertical growth rates and photosynthesis efficiency of crops within a certain period of time. By analyzing the time series curves of plant height, canopy coverage, and leaf area index of each variety, the intermediate features characterizing the crop development rate at each stage can be extracted. The features of the early stage include: the time point of reaching 25% of the maximum plant height, the canopy coverage and leaf area index at this time point, and the average change rates of early plant height, canopy coverage, and leaf area index. The features of the middle stage include: the maximum values of plant height, canopy coverage, and leaf area index, and the average change rates of these three during the middle stage. The features of the mature stage include: the average change rates of plant height, canopy coverage, and leaf area index during the mature stage. Specifically, refer to the definition of intermediate features at different stages shown in Table 1:

[0076] Table 1 Definition of intermediate features at different stages

[0077]

[0078]

[0079] For the foregoing step S104, the embodiment of the present invention further provides an implementation manner of using intermediate features to quantify the canopy development rate difference index of crops of each variety at different densities. For each intermediate feature, the ratio between the intermediate features of the crops of this variety at different densities can be determined to obtain an intermediate feature ratio; then each intermediate feature ratio is used as the canopy development rate difference index of the crops of this variety.

[0080] In one example, after increasing the planting density of the crops, conditions such as radiation interception and nutrient competition have changed significantly, thereby affecting the growth rate. To quantify the difference in canopy development rate of each variety at high and low densities, the intermediate features of each variety at different densities in the early, middle, and mature stages are calculated for their ratios. The calculation formula is as follows:

[0081] Traits Variation(TV)=Trait high density / Trait low density ;

[0082] where Traits Variation(TV) represents the canopy development rate, Trait high density represents the intermediate feature at high planting density, and Trait low density represents the intermediate feature at low planting density.

[0083] For the foregoing step S106, the embodiment of the present invention provides a specific implementation manner of screening target intermediate features according to the correlation between the density tolerance index corresponding to the crops of each variety and the canopy development rate difference index at different densities, including: for the crops of each variety, determining the Pearson correlation coefficient between the density tolerance index corresponding to the crops of this variety and the intermediate feature ratio of the crops of this variety, and screening out the target intermediate features from the intermediate features in descending order of the Pearson correlation coefficient.

[0084] Among them, the yield per unit area after increasing the planting area is a direct index to measure the density tolerance performance of crop varieties. Therefore, the ratio of the yield per unit area of each variety at high and low planting densities is used as the density tolerance index of this variety. The calculation formula of the density tolerance index is as follows:

[0085] Density tolerance(DT) = Yield high density / Yield low density ;

[0086] Among them, Density tolerance(DT) represents the density tolerance index, and Yield high density represents the yield per unit area under high planting density, and Yield low density represents the yield per unit area under low planting density.

[0087] First, conduct a correlation analysis between the canopy development rate and the density tolerance index. It includes: The development rates of crop varieties often vary under high and low densities, which ultimately leads to different yields per unit area under high and low densities. The DT and TV calculated in the previous steps define the differences in growth rate and yield per unit area. To better understand the relationship between them, by calculating the Pearson correlation coefficient, measure the linear relationship between the intermediate characteristic ratio and the density tolerance index, and at the same time evaluate the importance of these intermediate characteristic differences, and explore how changes in intermediate characteristics after increasing the planting density will result in increased yield, which will provide guidance for analyzing the relationship between the development rate and the density tolerance index at different stages, such as Figure 5 the correlation between a canopy rate difference and the density tolerance index shown.

[0088] Then, through the correlation coefficient, the target intermediate characteristics highly correlated with the density tolerance coefficient (DT) at each stage can be obtained. See Figure 6 the schematic diagram of breeding density-tolerant crop varieties based on intermediate characteristics shown, Figure 6 in which the effects of breeding density-tolerant varieties by combining LAI tPH25 , LAI-mid, and CC-mature in pairs are given. The performance of combining LAI-mid and LAI tPH25 to breed density-tolerant varieties is the strongest. As the planting density increases, almost all soybean varieties with a rapid increase in LAI in the early stage and a high LAI growth rate in the middle stage can ultimately obtain a higher yield per unit area, confirming that the increase in yield depends on the increase in LAI in the early and middle stages. At the mature stage, there is no general linear relationship between the intermediate characteristic CC-mature and DT. However, when combined with LAI tPH25 and LAI-mid, a similar pattern appears: those varieties with an increase in LAI in the early and middle stages and a higher CC-mature at maturity significantly increase the yield per unit area. On the contrary, if a variety increases LAI in the early stage but has a lower CC-mature at maturity, its yield increase will be very limited.

[0089] In summary, the method for breeding crop varieties with high tolerance to planting density based on UAV time-series images provided by the embodiments of the present invention quantifies the differences in crop development rates under different densities based on time-series images to achieve efficient breeding of varieties with high tolerance to planting density. Specifically, as an emerging intelligent breeding method, UAV phenotyping can quickly cover large areas of farmland and capture subtle crop growth states. The embodiments of the present invention utilize the high-throughput advantage of UAV phenotyping to realize the construction of a dynamic model based on image-derived features, effectively quantify the differences in growth rates of different varieties under high and low densities, and analyze the relationship between growth rate and density tolerance by combining statistical means, providing new ideas and methods for breeding crop varieties with high tolerance to planting density.

[0090] Based on the foregoing embodiments, the embodiments of the present invention provide a device for breeding crop varieties with high tolerance to planting density based on UAV time-series images. Refer to Figure 7 the structural schematic diagram of a device for breeding crop varieties with high tolerance to planting density based on UAV time-series images shown below. The device mainly includes the following parts:

[0091] An image acquisition module 702, configured to acquire time-series images collected by a UAV for a crop planting area, where multiple varieties of crops are planted at different densities in the crop planting area, and the time-series images include RGB images, multispectral orthophotos, and elevation images corresponding to the crops of each variety;

[0092] A development rate difference quantification module 704, configured to extract the canopy development stage and intermediate features corresponding to the canopy development stage for the crops of each variety based on the time-series images, so as to quantify the canopy development rate difference index of the crops of each variety under different densities by using the intermediate features;

[0093] A variety breeding module 706, configured to screen out target intermediate features according to the correlation between the density tolerance index corresponding to the crops of each variety and the canopy development rate difference index of the crops of each variety under different densities, so as to realize the breeding of crop varieties with high tolerance to planting density by using the target intermediate features.

[0094] The device for breeding crop varieties with high tolerance to planting density based on UAV time-series images provided by the embodiments of the present invention extracts the canopy development stage and corresponding intermediate features of the crops from the time-series data collected by the UAV, quantifies the canopy development rate difference index of the crops under different planting densities, and combines the density tolerance index corresponding to the crops and the correlation between the density tolerance index and the canopy development rate difference index of the crops under different densities to realize the breeding of crop varieties with high tolerance to planting density, thereby significantly improving the efficiency and reliability of breeding crop varieties with high tolerance to planting density.

[0095] In one implementation manner, the development rate difference quantification module 704 is specifically configured to:

[0096] Segment the time-series images to obtain the RGB sub-images, multi-spectral ortho-images, and elevation sub-images of the crops of each variety.

[0097] For the crops of each variety, based on the RGB sub-images, multi-spectral ortho-images, and elevation sub-images of the crops of this variety, extract the canopy cover, plant height, and leaf area index of the crops of this variety to fit the canopy development time-series curve of the crops of this variety.

[0098] According to the canopy development time-series curve of the crops of this variety, extract the corresponding canopy development stage and the intermediate features corresponding to the canopy development stage of the crops of this variety.

[0099] In one implementation, the development rate difference quantification module 704 is specifically used for:

[0100] Extract the canopy cover of the crops of this variety based on the RGB sub-images.

[0101] And, extract the plant height of the crops of this variety based on the elevation sub-images.

[0102] And, extract the texture features of the crops of this variety based on the RGB sub-images, extract the vegetation index of the crops of this variety based on the RGB sub-images and multi-spectral ortho-images, and output the leaf area index of the crops of this variety based on the vegetation index and texture features through a pre-trained leaf area index estimation model.

[0103] For the canopy cover, plant height, and leaf area index of the crops of this variety, fit P-splines respectively to obtain the canopy cover time-series curve, plant height time-series curve, and leaf area index time-series curve as the canopy development time-series curve of the crops of this variety.

[0104] In one implementation, it further includes a model training module for:

[0105] Use the measured value of the leaf area index at a specified sub-region within the crop planting area as the training label, and use the texture features and vegetation index of the crops of this variety planted within the specified sub-region as the model input to train the Bi-LSTM model based on bidirectional hidden states to obtain the leaf area index estimation model.

[0106] Among them, the bidirectional hidden states include the forward hidden state and the backward hidden state. The forward hidden state represents the leaf area index from the past to the present, and the backward hidden state represents the leaf area index from the future to the present.

[0107] In one implementation, the development rate difference quantification module 704 is specifically used for:

[0108] Based on the plant height changes characterized by the time series curve of the plant height of the crops of this variety, the canopy development stages corresponding to the crops of this variety are divided into an early stage, a middle stage, and a mature stage;

[0109] For each stage, intermediate features characterizing the canopy development rate in this stage are respectively extracted from the time series curve of canopy coverage, the time series curve of plant height, and the time series curve of leaf area index.

[0110] In one implementation manner, the development rate difference quantification module 704 is specifically configured to:

[0111] For each intermediate feature, determine the ratio between the intermediate features of the crops of this variety under different densities to obtain an intermediate feature ratio;

[0112] Take each intermediate feature ratio as the canopy development rate difference index of the crops of this variety.

[0113] In one implementation manner, the variety breeding module 706 is specifically configured to:

[0114] For the crops of each variety, determine the Pearson correlation coefficient between the density tolerance index corresponding to the crops of this variety and the intermediate feature ratio of the crops of this variety, and screen out the target intermediate features from the intermediate features in descending order of the Pearson correlation coefficient.

[0115] The device provided in the embodiments of the present invention has the same implementation principle and the same technical effects as those of the foregoing method embodiments. For a brief description, for the parts not mentioned in the device embodiments, reference may be made to the corresponding contents in the foregoing method embodiments.

[0116] The embodiments of the present invention provide an electronic device. Specifically, the electronic device includes a processor and a storage device; a computer program is stored on the storage device, and the computer program executes the method according to any one of the foregoing implementation manners when being run by the processor.

[0117] Figure 8 FIG. 28 is a schematic structural diagram of an electronic device provided in an embodiment of the present invention. The electronic device 100 includes: a processor 80, a memory 81, a bus 82, and a communication interface 83. The processor 80, the communication interface 83, and the memory 81 are connected through the bus 82; the processor 80 is configured to execute an executable module stored in the memory 81, such as a computer program.

[0118] Among them, the memory 81 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between this system network element and at least one other network element is realized through at least one communication interface 83 (which can be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. can be used.

[0119] The bus 82 can be an ISA bus, a PCI bus, an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, Figure 8 only a bidirectional arrow is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0120] Among them, the memory 81 is used to store a program. After receiving an execution instruction, the processor 80 executes the program. The method executed by the device defined by the flow process disclosed in any embodiment of the foregoing embodiments of the present invention can be applied to the processor 80 or implemented by the processor 80.

[0121] The processor 80 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in the processor 80 or the instructions in the form of software. The above-mentioned processor 80 may be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it may also be a digital signal processor (DSP for short), an application specific integrated circuit (ASIC for short), a field-programmable gate array (FPGA for short), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present invention can be directly embodied as being executed and completed by a hardware decoding processor, or executed and completed by a combination of the hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory 81, and the processor 80 reads the information in the memory 81 and combines its hardware to complete the steps of the above method.

[0122] The computer program product of the readable storage medium provided by the embodiments of the present invention includes a computer-readable storage medium storing program code, and the instructions included in the program code can be used to execute the methods described in the foregoing method embodiments. For specific implementation, reference can be made to the foregoing method embodiments and will not be elaborated herein.

[0123] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The foregoing storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs.

[0124] Finally, it should be noted that the above-mentioned embodiments are only specific embodiments of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: any person skilled in the art within the technical scope disclosed by the present invention can still modify the technical solutions described in the foregoing embodiments, or can easily think of changes, or make equivalent replacements for some of the technical features; and these modifications, changes, or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A method for breeding crop varieties resistant to dense planting based on UAV time-series images, characterized in that: include: Acquire time-series images collected by a drone for a crop planting area, wherein multiple varieties of crops are planted at different densities in the crop planting area, and the time-series images include RGB images, multispectral orthophoto images, and elevation images corresponding to each variety of crops; Based on the time series images, extracting the canopy development stage corresponding to each of the varieties of crops and the intermediate features corresponding to the canopy development stage, so as to quantify the canopy development rate difference index of each of the varieties of crops at different densities using the intermediate features; According to the correlation between the density tolerance index corresponding to each variety of the crop and the canopy development rate difference index under different densities, the target intermediate characteristics are screened out, so as to realize the breeding of crop varieties resistant to dense planting by using the target intermediate characteristics; Extracting the canopy development stage corresponding to each crop variety and the intermediate features corresponding to the canopy development stage, including: Segmenting the time series images to obtain RGB sub-images, multispectral orthophoto sub-images, and elevation sub-images of each crop variety; For each of the varieties of crops, based on the RGB sub-image, the multispectral orthophoto sub-image and the elevation sub-image of the variety of crops, the canopy coverage, plant height and leaf area index of the variety of crops are extracted to fit the canopy development time series curve of the variety of crops, including: extracting the canopy coverage of the variety of crops based on the RGB sub-image; and, extracting the plant height of the variety of crops based on the elevation sub-image; and, extracting the texture features of the variety of crops based on the RGB sub-image, extracting the vegetation index of the variety of crops based on the RGB sub-image and the multispectral orthophoto sub-image, and outputting the leaf area index of the variety of crops based on the vegetation index and the texture features through a pre-trained leaf area index estimation model; fitting P-splines for the canopy coverage, the plant height and the leaf area index of the variety of crops, respectively, to obtain a canopy coverage time series curve, a plant height time series curve and a leaf area index time series curve as the canopy development time series curve of the variety of crops; According to the canopy development time series curve of the crop variety, the canopy development stage corresponding to the crop variety and the intermediate features corresponding to the canopy development stage are extracted, including: based on the plant height changes characterized by the plant height time series curve of the crop variety, the canopy development stage corresponding to the crop variety is divided into an early stage, a middle stage and a mature stage; for each stage, the intermediate features characterizing the canopy development rate in that stage are respectively extracted from the canopy coverage time series curve, the plant height time series curve and the leaf area index time series curve.

2. The method for selecting crop varieties resistant to dense planting based on UAV time-series images according to claim 1, characterized in that: The training step of the leaf area index estimation model comprises: Taking the measured value of the leaf area index at the designated sub-region within the crop planting area as a training label, and taking the texture features and the vegetation index of the crop of the variety planted in the designated sub-region as model inputs, training a Bi-LSTM model based on a bidirectional hidden state, and obtaining a leaf area index estimation model; The bidirectional hidden state includes a forward hidden state and a backward hidden state, the forward hidden state represents the leaf area index from the past to the present, and the backward hidden state represents the leaf area index from the future to the present.

3. The method for selecting crop varieties resistant to dense planting based on UAV time-series images according to claim 1, characterized in that: The intermediate features are used to quantify the canopy development rate difference index of each crop variety at different densities, including: For each of the intermediate characteristics, determining the ratio of the intermediate characteristics of the crop of the variety at different densities to obtain an intermediate characteristic ratio; Each of the intermediate characteristic ratios is used as a canopy development rate difference index for the crop variety.

4. The method for selecting crop varieties resistant to dense planting based on UAV time-series images according to claim 3 is characterized in that: According to the correlation between the density tolerance index corresponding to each variety of crops and the canopy development rate difference index under different densities, the target intermediate features are screened out, including: For each variety of crops, the Pearson correlation coefficient between the density tolerance index corresponding to the variety of crops and the ratio of the intermediate characteristics of the variety of crops is determined, and the target intermediate characteristics are screened out from the intermediate characteristics in descending order of the Pearson correlation coefficients.

5. A device for selecting and breeding crop varieties resistant to dense planting based on time-series images from unmanned aerial vehicles, characterized in that: The device is used to implement the method for selecting crop varieties resistant to dense planting based on UAV time-series images as described in claim 1, and the device comprises: An image acquisition module is used to acquire time-series images collected by a drone for a crop planting area, wherein multiple varieties of crops are planted at different densities in the crop planting area, and the time-series images include RGB images, multispectral orthophoto images, and elevation images corresponding to each variety of crops; A development rate difference quantification module is used to extract the canopy development stage corresponding to each of the crop varieties and the intermediate features corresponding to the canopy development stage based on the time series images, so as to quantify the canopy development rate difference index of each of the crop varieties at different densities using the intermediate features; The variety breeding module is used to screen out target intermediate characteristics based on the correlation between the density tolerance index corresponding to each variety of crops and the canopy development rate difference index under different densities, so as to use the target intermediate characteristics to realize the breeding of crop varieties that are resistant to dense planting.

6. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the method according to any one of claims 1 to 4.

Images