Sugarcane plant pollen fertility determination method based on neural network model

Abstract

The invention provides a sugarcane plant pollen fertility determination method based on a neural network model, and relates to the technical field of plant cultivation. According to the method provided by the invention, the pollen image data and the environment data of the target sugarcane plant are acquired, and then the feature extraction and the feature fusion are performed on the pollen image data and the environment data through the trained neural network model, so that the fusion feature vector is obtained. And then the pollen fertility detection result of the target sugarcane plant is determined according to the fusion feature vector, so that rapid and accurate detection of the pollen fertility of the sugarcane plant can be realized, and compared with a manual detection mode, the detection time can be effectively saved, the detection efficiency can be improved, and the use requirement of large-scale detection of the pollen fertility of the sugarcane can be met.

Description

Technical Field

[0001] The present invention relates to the technical field of plant cultivation, and in particular to a method for determining the pollen fertility of sugarcane plants based on a neural network model. Background Art

[0002] In the process of cultivating sugarcane plants, the accurate detection of pollen fertility is of crucial significance for aspects such as crop breeding and seed quality assessment. Traditional methods for detecting pollen fertility mainly rely on manual observation and microscopic analysis. This manual detection method has some problems. Since the manual observation method not only requires professionals to have rich experience, but also has a cumbersome detection process, low efficiency, and consumes a large amount of time, it is difficult to meet the needs of large-scale detection. At the same time, manual judgment is easily affected by subjective factors, resulting in uneven accuracy and reliability of the detection results.

[0003] Therefore, there is an urgent need for a method for determining the pollen fertility of sugarcane plants based on a neural network model to achieve rapid and accurate detection of the pollen fertility of sugarcane, save detection time, improve detection efficiency, and meet the needs of large-scale detection. Summary of the Invention

[0004] The embodiments of the present invention provide a method for determining the pollen fertility of sugarcane plants based on a neural network model, which can quickly and accurately determine the pollen fertility of sugarcane plants, and then realize crop breeding and seed quality assessment of sugarcane based on the pollen fertility of sugarcane plants, thereby effectively improving agricultural production efficiency.

[0005] To achieve the above object, the embodiments of the present invention adopt the following technical solutions:

[0006] First aspect, a method for determining the pollen fertility of sugarcane plants based on a neural network model is provided. The method includes: obtaining a first training sample set, which includes multiple first training samples. Each first training sample includes a pollen image of a sugarcane plant, environmental data, and a pollen fertility detection result. The environmental data includes temperature, humidity, and light intensity when the pollen image is obtained. The pollen fertility detection result includes high fertility, low fertility, or sterility; performing an image augmentation operation on the pollen images included in the multiple first training samples to obtain a second training sample set. Among them, the image augmentation operation includes image rotation, image flipping, image scaling, or image noise addition operations. The second training sample set includes multiple second training samples. Each second training sample includes the pollen image of the sugarcane plant obtained by the image augmentation operation, environmental data, and a pollen fertility detection result. The pollen fertility detection result includes high fertility, low fertility, or sterility; training the neural network model according to the first training sample set and the second training sample set to obtain a trained neural network model; obtaining data to be detected, which includes a pollen image of a target sugarcane plant and environmental data; inputting the data to be detected into the trained neural network model and outputting a pollen fertility detection result of the target sugarcane plant. The pollen fertility detection result includes high fertility, low fertility, or sterility.

[0007] In a possible implementation manner of the first aspect, training the neural network model according to the first training sample set and the second training sample set to obtain a trained neural network model includes: establishing a target loss function with temperature, humidity, and light intensity as constraint conditions; based on the target loss function, training the neural network model according to the first training sample set and the second training sample set to obtain a trained neural network model;

[0008] The target loss function L is:

[0009] L = L1 + λ1L 温度 + λ2L 湿度 + λ3L 光照强度 ;

[0010]

[0011] L1 is the cross - entropy loss function, L 温度 is the temperature constraint term, L 湿度 is the humidity constraint term, L 光照强度 is the light intensity constraint term, λ1, λ2, λ3 are weight coefficients, N is the number of training samples, T i is the temperature value of the i - th training sample, H i is the humidity value of the i - th training sample, L i is the light intensity value of the i - th training sample.

[0012] In a possible implementation of the first aspect, a neural network model includes: an image data processing module, an environmental data processing module, a feature vector fusion module, and a detection module; the image data processing module and the environmental data processing module are respectively connected to the feature vector fusion module, and the feature vector fusion module is connected to the detection module; the image data processing module is configured to extract features from the pollen image included in the data to be detected, and obtain a first feature vector corresponding to the pollen image; the environmental data processing module is configured to extract features from the environmental data included in the data to be detected, and obtain a second feature vector corresponding to the environmental data; the feature vector fusion module is configured to perform feature fusion on the first feature vector and the second feature vector to obtain a fused feature vector; the detection module is configured to determine a pollen fertility detection result of the target sugarcane plant according to the fused feature vector, and the pollen fertility detection result includes high fertility, low fertility, or sterility.

[0013] In a possible implementation of the first aspect, the above neural network model further includes: an attention mechanism layer, and the attention mechanism layer is respectively connected to the feature vector fusion module and the detection module; the attention mechanism layer is configured to perform weighted summation on the fused feature vector based on the attention mechanism to obtain a weighted feature vector and an attention weight corresponding to each feature included in the data to be detected, and the features include pollen image, temperature, humidity, or light intensity; the detection module is further configured to determine a pollen fertility detection result of the target sugarcane plant according to the weighted feature vector.

[0014] In a possible implementation of the first aspect, the pollen fertility detection result further includes a contribution score for each feature included in the data to be detected, and the contribution score is used to measure the contribution degree of the standard feature to the pollen fertility detection result; the above method further includes: determining the attention weight corresponding to each feature as the contribution score for each feature.

[0015] In a possible implementation of the first aspect, obtaining the data to be detected includes: acquiring a pollen image of the target sugarcane plant at a target time through an image acquisition device; acquiring the temperature, humidity, and light intensity corresponding to each of multiple times of the target sugarcane plant through a sensor; and determining the temperature, humidity, and light intensity corresponding to the target sugarcane plant at the target time as the environmental data of the target sugarcane plant.

[0016] The beneficial effects of the present invention are as follows: The method provided by the present invention obtains multimodal data of the target sugarcane plant, that is, obtains pollen image data and environmental data of the target sugarcane plant, and then extracts and fuses features of the pollen image data and environmental data through a neural network model, and determines the pollen fertility detection result of the target sugarcane plant according to the obtained fused feature vector. Therefore, it can realize the rapid and accurate detection of the pollen fertility of sugarcane plants. Compared with the manual detection method, it can effectively save the detection time, improve the detection efficiency, and meet the use requirements for large-scale detection of the pollen fertility of sugarcane. Moreover, the method provided by the present invention can realize the training of the neural network model under the condition of limited training sample quantity by performing augmentation operations on the training samples included in the first training sample set, so as to realize the rapid and accurate detection of pollen fertility.

[0017] In a second aspect, the present invention provides a pollen fertility determination system for sugarcane plants based on a neural network model. The system includes: an acquisition unit, configured to acquire a first training sample set, the first training sample set includes a plurality of first training samples, each first training sample includes a pollen image of a sugarcane plant, environmental data, and a pollen fertility detection result, the environmental data includes temperature, humidity, and light intensity when the pollen image is acquired, and the pollen fertility detection result includes high fertility, low fertility, or sterility; an augmentation unit, configured to perform image augmentation operations on the pollen images included in the plurality of first training samples to obtain a second training sample set, wherein the image augmentation operations include image rotation, image flipping, image scaling, or image noise addition operations, the second training sample set includes a plurality of second training samples, each second training sample includes a pollen image of a sugarcane plant obtained by the image augmentation operation, environmental data, and a pollen fertility detection result, and the pollen fertility detection result includes high fertility, low fertility, or sterility; a training unit, configured to train the neural network model according to the first training sample set and the second training sample set to obtain a trained neural network model; the acquisition unit is further configured to acquire data to be detected, the data to be detected includes a pollen image and environmental data of a target sugarcane plant; a detection unit, configured to input the data to be detected into the trained neural network model and output a pollen fertility detection result of the target sugarcane plant, and the pollen fertility detection result includes high fertility, low fertility, or sterility.

[0018] In a possible implementation manner of the second aspect, the training unit is specifically configured to: establish a target loss function with temperature, humidity, and light intensity as constraint conditions; based on the target loss function, train the neural network model according to the first training sample set and the second training sample set to obtain a trained neural network model;

[0019] The target loss function L is:

[0020] L = L1 + λ1L 温度 + λ2L湿度 +λ3L 光照强度

[0021]

[0022] L1 is the cross-entropy loss function, L 温度 is the temperature constraint term, L 湿度 is the humidity constraint term, L 光照强度 is the light intensity constraint term, λ1, λ2, λ3 are weight coefficients, N is the number of training samples, T i is the temperature value of the i-th training sample, H i is the humidity value of the i-th training sample, L i is the light intensity value of the i-th training sample.

[0023] In a possible implementation of the second aspect, the neural network model includes: an image data processing module, an environmental data processing module, a feature vector fusion module, and a detection module; the image data processing module and the environmental data processing module are respectively connected to the feature vector fusion module, and the feature vector fusion module is connected to the detection module; the image data processing module is used to extract features from the pollen image included in the data to be detected, and obtain a first feature vector corresponding to the pollen image; the environmental data processing module is used to extract features from the environmental data included in the data to be detected, and obtain a second feature vector corresponding to the environmental data;

[0024] The feature vector fusion module is used to perform feature fusion on the first feature vector and the second feature vector to obtain a fused feature vector; the detection module is used to determine the pollen fertility detection result of the target sugarcane plant according to the fused feature vector, and the pollen fertility detection result includes high fertility, low fertility or sterility;

[0025] The neural network model further includes: an attention mechanism layer, and the attention mechanism layer is respectively connected to the feature vector fusion module and the detection module; the attention mechanism layer is used to perform weighted summation on the fused feature vector based on the attention mechanism to obtain a weighted feature vector and the attention weight corresponding to each feature included in the data to be detected, and the features include pollen image, temperature, humidity or light intensity; the detection module is further used to determine the pollen fertility detection result of the target sugarcane plant according to the weighted feature vector.

[0026] In the third aspect, an electronic device is provided. The electronic device includes a memory and one or more processors; the memory is coupled to the processor; wherein, computer program code is stored in the memory, and the computer program code includes computer instructions. When the computer instructions are executed by the processor, the electronic device is caused to execute the method in any implementation manner of the first aspect.

[0027] Fourthly, a computer-readable storage medium is provided, including computer instructions. When the computer instructions run on an electronic device, the electronic device is caused to execute the method in any implementation manner of the first aspect.

[0028] Fifthly, a computer program product is provided. When the computer program product runs on a computer, the computer is caused to execute the method in any implementation manner of the first aspect.

[0029] It can be understood that for the beneficial effects that can be achieved by the system of the second aspect, the electronic device of the third aspect, the computer-readable storage medium of the fourth aspect, and the computer program product of the fifth aspect provided above, reference can be made to the beneficial effects in the first aspect and any possible design manner thereof, which will not be elaborated herein. Description of the Drawings

[0030] Figure 1 It is a schematic diagram of the hardware structure of an electronic device shown in an embodiment of the present invention;

[0031] Figure 2 It is a flowchart of a method for determining the pollen fertility of sugarcane plants based on a neural network model shown in an embodiment of the present invention;

[0032] Figure 3 It is a schematic diagram of the hardware structure of a neural network model shown in an embodiment of the present invention;

[0033] Figure 4 It is a schematic diagram of the hardware structure of another neural network model shown in an embodiment of the present invention;

[0034] Figure 5 It is a schematic diagram of the hardware structure of a determination system shown in an embodiment of the present invention. Detailed Embodiments

[0035] Next, the technical solutions in the embodiments of the present invention will be described with reference to the drawings in the embodiments of the present invention. Among them, in the description of the present invention, unless otherwise specified, " / " means that the objects associated before and after are in an "or" relationship. For example, A / B may represent A or B; the "or" in the present invention is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. Among them, A and B can be singular or plural. And, in the description of the present invention, unless otherwise specified, "a plurality of" means two or more than two. "At least one (item)" or its similar expression means any combination of these items, including any combination of single item (item) or plural items (items).

[0036] In addition, for the convenience of clearly describing the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, terms such as "first" and "second" are used to distinguish identical or similar items with basically the same functions and roles. Those skilled in the art can understand that terms such as "first" and "second" do not limit the quantity and execution order, and "first", "second", etc. do not necessarily mean different.

[0037] Meanwhile, in the embodiments of the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of the present invention should not be construed as being superior or more advantageous than other embodiments or design solutions. Rather, the use of words such as "exemplary" or "for example" is intended to present relevant concepts in a specific way for easy understanding.

[0038] In the process of cultivating sugarcane plants, the accurate detection of pollen fertility is of crucial significance for aspects such as crop breeding and seed quality assessment. Traditional pollen fertility detection methods mainly rely on manual observation and microscopic analysis. There are some problems with this manual detection method. Since the manual observation method not only requires professionals to have rich experience, but also the detection process is cumbersome, inefficient, and consumes a large amount of time, it is difficult to meet the needs of large-scale detection. At the same time, manual judgment is easily affected by subjective factors, resulting in uneven accuracy and reliability of the detection results.

[0039] Therefore, there is an urgent need for a method for determining the pollen fertility of sugarcane plants based on a neural network model to achieve rapid and accurate detection of the pollen fertility of sugarcane, save detection time, improve detection efficiency, and meet the needs of large-scale detection.

[0040] In view of this, an embodiment of the present invention provides a method for determining the pollen fertility of sugarcane plants based on a neural network model. The above method includes: obtaining a first training sample set, the first training sample set includes a plurality of first training samples, each first training sample includes a pollen image of a sugarcane plant, environmental data, and a pollen fertility detection result, the environmental data includes temperature, humidity, and light intensity when the pollen image is obtained, and the pollen fertility detection result includes high fertility, low fertility, or sterility; performing an image augmentation operation on the pollen images included in the plurality of first training samples to obtain a second training sample set, wherein the image augmentation operation includes image rotation, image flipping, image scaling, or image noise addition operations, the second training sample set includes a plurality of second training samples, each second training sample includes a pollen image of a sugarcane plant obtained by the image augmentation operation, environmental data, and a pollen fertility detection result, and the pollen fertility detection result includes high fertility, low fertility, or sterility; training the neural network model according to the first training sample set and the second training sample set to obtain a trained neural network model; obtaining data to be detected, the data to be detected includes a pollen image and environmental data of a target sugarcane plant; inputting the data to be detected into the trained neural network model, and outputting a pollen fertility detection result of the target sugarcane plant, and the pollen fertility detection result includes high fertility, low fertility, or sterility.

[0041] The method provided by the present invention can realize rapid and accurate detection of the pollen fertility of sugarcane plants by obtaining multi-modal data of the target sugarcane plant, that is, obtaining pollen image data and environmental data of the target sugarcane plant, and then performing feature extraction and feature fusion on the pollen image data and environmental data through a neural network model, and determining the pollen fertility detection result of the target sugarcane plant according to the obtained fusion feature vector. Therefore, it can effectively save the detection time, improve the detection efficiency, and meet the usage requirements for large-scale detection of the pollen fertility of sugarcane compared with the manual detection method.

[0042] In some embodiments, a method for determining the pollen fertility of sugarcane plants based on a neural network model provided by an embodiment of the present invention can be executed by a system 100 for determining the pollen fertility of sugarcane plants based on a neural network model (hereinafter referred to as the determination system 100). As an example, the determination system 100 can be any electronic device 200 with data processing capabilities, such as a general computer, a personal computer, a laptop computer, a switch, or a tablet computer, etc. The specific implementation manner of the determination system 100 is not limited herein.

[0043] Figure 1 The hardware structure diagram of the electronic device provided by the embodiment of the present invention is shown. The electronic device 200 includes a processor 210, a memory 220, and a communication interface 230.

[0044] The processor 210 may include one or more processing cores. The processor 210 connects various parts within the electronic device 200 through various interfaces and circuits, and executes various functions of the electronic device 200 and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 220, and by invoking data stored in the memory 220. Optionally, the processor 210 may be implemented in at least one hardware form of a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processing (DSP), a field-programmable gate array (FPGA), or a programmable logic array (PLA).

[0045] The memory 220 may include a random access memory (RAM), or may also include a read-only memory (ROM). Optionally, the memory 220 includes a non-transitory computer-readable storage medium. The memory 220 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 220 may include a storage program area. Among them, the storage program area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a data acquisition function, a model training function, etc.), instructions for implementing the above various method embodiments, and the like.

[0046] The communication interface 230 is used to communicate with other devices, equipment, or communication networks, such as data storage devices, image processing devices, or Ethernet, a radio access network (RAN), wireless local area networks (WLAN), etc.

[0047] In terms of physical implementation, the above-mentioned various devices (such as the processor 210, the memory 220, and the communication interface 230) may respectively be devices in the same device (such as a laptop computer). Or, at least two of them may be provided in the same device, that is, as different devices in a device, such as a deployment method similar to that of devices or components in a distributed system.

[0048] It can be understood that the structure illustrated in this embodiment does not constitute a specific limitation on the electronic device 200. In other embodiments of the present invention, the electronic device 200 may include more or fewer components than those shown in the figure, or combine certain components, or split certain components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0049] The following will describe a method for determining the pollen fertility of sugarcane plants based on a neural network model provided by an embodiment of the present invention with reference to the accompanying drawings of the specification.

[0050] Figure 2 It is a flowchart of a method for determining the pollen fertility of sugarcane plants based on a neural network model provided by an embodiment of the present invention. Optionally, this method can be Figure 1 executed by the illustrated electronic device 200, that is, executed by the determination system 100. This method may include the following steps:

[0051] S1. Obtain a first training sample set, and the first training sample set includes a plurality of first training samples.

[0052] Specifically, each first training sample includes a pollen image of a sugarcane plant, environmental data, and a pollen fertility detection result. Among them, the pollen image of the sugarcane plant is an image obtained by a high-resolution microscope, and each pollen image includes a plurality of pollen grains of the sugarcane plant.

[0053] Among them, the environmental data includes the temperature, humidity, and light intensity when the pollen image is obtained. The determination system obtains the temperature through a temperature sensor arranged within a preset range of the sugarcane plant, obtains the humidity through a humidity sensor arranged within a preset range of the sugarcane plant, and obtains the light intensity through a light intensity sensor arranged within a preset range of the sugarcane plant.

[0054] The pollen fertility detection result includes high fertility, low fertility, or sterility. It should be noted that the fertility of a sugarcane plant refers to the ability of the sugarcane plant to reproduce sexually, that is, the ability to produce fertile seeds or offspring through sexual reproduction. High fertility is used to indicate that the sugarcane plant has a high ability to reproduce sexually, low fertility is used to indicate that the sugarcane plant has a low ability to reproduce sexually, and sterility is used to indicate that the sugarcane plant does not have the ability to reproduce sexually.

[0055] S2. Perform an image augmentation operation on the pollen images included in the plurality of first training samples to obtain a second training sample set.

[0056] Among them, the image augmentation operations include image rotation, image flipping, image scaling, or image noise addition operations. The second training sample set includes multiple second training samples. Each second training sample includes a pollen image of a sugarcane plant obtained by an image augmentation operation, environmental data, and a pollen fertility detection result. The pollen fertility detection result includes high fertility, low fertility, or sterility.

[0057] Specifically, each second training sample corresponds to a first training sample. The pollen image of each second training sample is obtained by performing an image augmentation operation on the pollen image of the corresponding first training sample. The environmental data and pollen fertility detection result of each second training sample are the same as those of the first training sample corresponding to this second training sample.

[0058] The following uses an example to explain the determination process of the second training sample set. The first training sample includes pollen image a, environmental data a, and pollen fertility detection result a. The determination system performs an image augmentation operation on pollen image a to obtain pollen image b, pollen image c, and pollen image d. Then, the determination system obtains the second training sample b according to pollen image b, environmental data a, and pollen fertility detection result a, obtains the second training sample c according to pollen image c, environmental data a, and pollen fertility detection result a, obtains the second training sample d according to pollen image d, environmental data a, and pollen fertility detection result a. Finally, the second training sample set is obtained according to the second training sample b, the second training sample c, and the second training sample d.

[0059] It should be understood that the above image augmentation operations are only for illustrative purposes. The embodiments of the present invention do not particularly limit the specific implementation manner of the image augmentation operations. The determination system can obtain more second training samples corresponding to the first training sample through any operation, and then obtain the second training sample set.

[0060] S3. Train the neural network model according to the first training sample set and the second training sample set to obtain a trained neural network model;

[0061] In some embodiments, training the neural network model according to the first training sample set and the second training sample set to obtain a trained neural network model includes:

[0062] Establish a target loss function with temperature, humidity, and light intensity as constraint conditions;

[0063] Based on the target loss function, train the neural network model according to the first training sample set and the second training sample set to obtain a trained neural network model;

[0064] The target loss function L is:

[0065] L = L1 + λ1L 温度 + λ2L 湿度 + λ3L 光照强度

[0066]

[0067] L1 is the cross - entropy loss function, L 温度 is the temperature constraint term, L 湿度 is the humidity constraint term, L 光照强度 is the light intensity constraint term, λ1, λ2, λ3 are weight coefficients, N is the number of training samples, T i is the temperature value of the i - th training sample, H i is the humidity value of the i - th training sample, L i is the light intensity value of the i - th training sample.

[0068] It should be understood that the actual values of the weight coefficients λ1, λ2, λ3 can be flexibly set according to the actual usage scenarios of users, and the embodiments of the present invention do not particularly limit the specific implementation manners of the weight coefficients λ1, λ2, λ3.

[0069] Specifically, in the temperature constraint term, 35 and 10 are the upper and lower threshold values of the temperature respectively, with the unit of degree Celsius, and the temperature constraint term is used to constrain the temperature range. During the growth process of sugarcane plants, high temperature will cause pollen inactivation or abnormal development, reducing fertility. Low temperature will slow down the physiological activities of pollen and even cause frost damage, which will also reduce fertility. Therefore, when the temperature is greater than 35 degrees Celsius, it is necessary to increase the loss penalty. Similarly, when the temperature is less than 10 degrees Celsius, it is also necessary to increase the loss penalty.

[0070] In an example, the temperature values of the environmental data of 5 training samples are 36, 25, 8, 12, and 40 respectively. Among them, when the temperature value is 36 degrees Celsius, max(36 - 35, 0) = 1, max(10 - 36, 0) = 0; when the temperature value is 8 degrees Celsius, max(8 - 35, 0) = 0, max(10 - 8, 0) = 2, L 温度 = 1 + 0 + 2 + 0 + 5 / 5 = 1.6.

[0071] Specifically, in the humidity constraint term, 80 and 30 are the upper and lower threshold values of the humidity respectively, with the unit of %, and are used to constrain the humidity range. During the growth process of sugarcane plants, high humidity will cause pollen to absorb water and expand or even burst, affecting its activity and fertilization ability. Low humidity will cause pollen to dehydrate and inactivate, also reducing fertility. Therefore, when the humidity is greater than 80%, it is necessary to increase the loss penalty. Similarly, when the humidity is less than 30%, it is also necessary to increase the loss penalty.

[0072] In one example, the humidity values of the environmental data of 5 training samples are 85, 25, 40, 90, and 30 respectively, L 湿度 = (5 + 5 + 10 + 0 + 0) / 5 = 4.

[0073] Specifically, in the light intensity constraint term, 1000 is the lower threshold of temperature, with the unit of l ux , which is used to constrain the light intensity range. During the growth process of sugarcane plants, light is a key factor for plants to carry out photosynthesis, affecting the development and fertility of pollen. Insufficient light will lead to poor pollen development, reducing its activity and fertilization ability. Therefore, when the light intensity is less than 1000, it is also necessary to increase the loss penalty.

[0074] In one example, the light intensity values of the environmental data of 5 training samples are 1200, 800, 1500, 500, and 1000 respectively, L 光照强度 = (0 + 200 + 0 + 500 + 0) / 5 = 140.

[0075] It should be noted that the above objective loss function is only for illustrative purposes. The method provided by the embodiments of the present invention can also establish an objective loss function based on more or fewer parameters as constraints. For example, the expression mode of the target gene of sugarcane plants can be used as a constraint condition.

[0076] The method provided by the embodiments of the present invention can make the neural network model pay more attention to key biological influencing factors during the training process by establishing constraint terms according to temperature, humidity, and light intensity, thereby improving the scientificity and accuracy of its prediction.

[0077] S4. Obtain the data to be detected, where the data to be detected includes the pollen image and environmental data of the target sugarcane plant.

[0078] In some embodiments, obtaining the data to be detected includes: obtaining the pollen image of the target sugarcane plant at the target moment through an image acquisition device; obtaining the temperature, humidity, and light intensity corresponding to each moment of the target sugarcane plant at multiple moments through sensors; and determining the temperature, humidity, and light intensity corresponding to the target sugarcane plant at the target moment as the environmental data of the target sugarcane plant.

[0079] S5. Input the data to be detected into the trained neural network model, and output the pollen fertility detection result of the target sugarcane plant. The pollen fertility detection result includes high fertility, low fertility, or sterility.

[0080] In one possible implementation, see Figure 3, a neural network model 300, comprising: an image data processing module 310, an environmental data processing module 320, a feature vector fusion module 330, and a detection module 340; the image data processing module 310 and the environmental data processing module 320 are respectively connected to the feature vector fusion module 330, and the feature vector fusion module 330 is connected to the detection module 340; the image data processing module 310 is configured to extract features from the pollen image included in the data to be detected, and obtain a first feature vector corresponding to the pollen image; the environmental data processing module 320 is configured to extract features from the environmental data included in the data to be detected, and obtain a second feature vector corresponding to the environmental data; the feature vector fusion module 330 is configured to perform feature fusion on the first feature vector and the second feature vector to obtain a fused feature vector; the detection module 340 is configured to determine a pollen fertility detection result of the target sugarcane plant according to the fused feature vector, and the pollen fertility detection result includes high fertility, low fertility, or sterility;

[0081] In some embodiments, referring to Figure 4 , the neural network model 300 further includes: an attention mechanism layer 350, and the attention mechanism layer 350 is respectively connected to the feature vector fusion module 330 and the detection module 340; the attention mechanism layer 350 is configured to perform weighted summation on the fused feature vector based on the attention mechanism to obtain a weighted feature vector and an attention weight corresponding to each feature included in the data to be detected, and the features include pollen image, temperature, humidity, or light intensity; the detection module 340 is further configured to determine a pollen fertility detection result of the target sugarcane plant according to the weighted feature vector.

[0082] As can be seen from the above, the attention mechanism performs weighted summation on the fused feature vector according to the weight matrix, can accurately capture the importance between each feature, effectively improve the performance of the neural network model, and moreover, through the attention mechanism, the importance of each feature (image, temperature, humidity, and light intensity) for the pollen fertility detection result can be accurately distinguished, meeting the usage requirements of the neural network model in different usage scenarios.

[0083] As can be seen from the above S1 - S5, the method provided by the present invention obtains multimodal data of the target sugarcane plant, that is, obtains pollen image data and environmental data of the target sugarcane plant, and then extracts and fuses features from the pollen image data and environmental data through a neural network model, and determines the pollen fertility detection result of the target sugarcane plant according to the obtained fused feature vector. Therefore, it can achieve fast and accurate detection of the pollen fertility of sugarcane plants. Compared with the manual detection method, it can effectively save the detection time, improve the detection efficiency, and meet the usage requirements for large - scale detection of the pollen fertility of sugarcane. Moreover, the method provided by the present invention can train the neural network model by performing augmentation operations on the training samples included in the first training sample set, so as to achieve fast and accurate detection of pollen fertility even when the number of training samples is limited.

[0084] In a possible implementation manner, the pollen fertility detection result further includes the contribution score of each feature included in the data to be detected, and the contribution score is used to measure the contribution degree of the standard feature to the pollen fertility detection result.

[0085] The method provided by the embodiments of the present invention further includes:

[0086] Determine the attention weight corresponding to each feature as the contribution score of each feature.

[0087] In this way, the method provided by the embodiments of the present invention can determine the contribution score of each feature, and the user can determine the contribution degree of each feature to the pollen fertility detection result of the target sugarcane plant based on the contribution score of each feature, thereby increasing the interpretability of the pollen fertility detection result output by the neural network model and meeting the usage requirements of the user in different usage scenarios.

[0088] The above mainly introduces the solution of the embodiments of the present invention from the perspective of the method. It can be understood that to implement the above functions, the system 100 includes at least one of the corresponding hardware structures and software modules for executing each function. Those skilled in the art should easily realize that, combining the units and algorithm steps of each example described in the embodiments disclosed herein, the embodiments of the present invention can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the way of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the embodiments of the present invention.

[0089] In the embodiments of the present invention, the determination system 100 can be divided into functional units according to the above method examples. For example, the determination system 100 can be corresponding to each function and divided into respective functional units, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. It should be noted that the division of units in the embodiments of the present invention is illustrative, only a logical function division, and there can be other division methods in actual implementation.

[0090] Exemplarily, Figure 5 FIG. shows a schematic hardware structure diagram of a determination system provided by an embodiment of the present invention. The determination system 100 includes: an acquisition unit 110, configured to acquire a first training sample set, the first training sample set including a plurality of first training samples, each first training sample including a pollen image of a sugarcane plant, environmental data, and a pollen fertility detection result, the environmental data including temperature, humidity, and light intensity when the pollen image is acquired, and the pollen fertility detection result including high fertility, low fertility, or sterility; an augmentation unit 120, configured to perform an image augmentation operation on the pollen images included in the plurality of first training samples to obtain a second training sample set, where the image augmentation operation includes image rotation, image flipping, image scaling, or image noise addition operations, the second training sample set including a plurality of second training samples, each second training sample including a pollen image of a sugarcane plant obtained by the image augmentation operation, environmental data, and a pollen fertility detection result, the pollen fertility detection result including high fertility, low fertility, or sterility; a training unit 130, configured to train a neural network model according to the first training sample set and the second training sample set to obtain a trained neural network model; the acquisition unit 110 is further configured to acquire data to be detected, the data to be detected including a pollen image of a target sugarcane plant and environmental data; a detection unit 140, configured to input the data to be detected into the trained neural network model and output a pollen fertility detection result of the target sugarcane plant, the pollen fertility detection result including high fertility, low fertility, or sterility.

[0091] Optionally, the training unit 130 is specifically configured to: establish a target loss function with temperature, humidity, and light intensity as constraint conditions; based on the target loss function, train the neural network model according to the first training sample set and the second training sample set to obtain a trained neural network model;

[0092] The target loss function L is:

[0093] L = L1 + λ1L 温度 + λ2L 湿度 + λ3L 光照强度

[0094]

[0095] L1 is the cross-entropy loss function, L 温度 is the temperature constraint term, L 湿度 is the humidity constraint term, L 光照强度 is the light intensity constraint term, λ1, λ2, and λ3 are weight coefficients, N is the number of training samples, and T i is the temperature value of the i-th training sample, H i is the humidity value of the i-th training sample, L i is the light intensity value of the i-th training sample.

[0096] It should be understood that for the specific descriptions of the above optional methods, reference can be made to the foregoing method embodiments, which will not be elaborated herein. In addition, for the explanations and beneficial effects descriptions of any of the above-provided determinations of the system 100, reference can be made to the corresponding method embodiments above, which will not be elaborated.

[0097] The embodiments of the present invention further provide a computer-readable storage medium, in which at least one computer instruction is stored, and the at least one computer instruction is loaded and executed by a processor to implement the methods of the above various embodiments. For the explanations and beneficial effects descriptions of any of the above-provided computer-readable storage media, reference can be made to the corresponding embodiments above, which will not be elaborated herein.

[0098] The embodiments of the present invention further provide a chip. The chip integrates a control circuit for implementing the functions of the above determination system 100 and one or more ports. Optionally, the functions supported by the chip can be referred to above, which will not be elaborated herein.

[0099] Those of ordinary skill in the art can understand that all or part of the steps for implementing the above embodiments can be completed by a program instructing relevant hardware. The program can be stored in a computer-readable storage medium. The above-mentioned storage medium can be a read-only memory, a random access memory, etc. The above-mentioned processing unit or processor can be a central processing unit, a general-purpose processor, an application specific integrated circuit (ASIC), a digital signal processor (DSP), a field programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof.

[0100] An embodiment of the present invention further provides a computer program product containing instructions. When the instructions run on a computer, the computer is caused to execute any one of the methods in the above embodiments. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions according to the embodiments of the present invention are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from a website, a computer, a server, or a data center to another website, computer, server, or data center in a wired manner (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or a wireless manner (such as infrared, wireless, microwave, etc.). The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or a data center integrating one or more available media. The available medium may be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as an SSD), etc.

[0101] It should be noted that the devices for storing computer instructions or computer programs provided in the embodiments of the present invention, such as but not limited to, the above-mentioned memory, computer-readable storage medium, and communication chip, etc., are all non-transitory. Those skilled in the art should be able to realize that in the above one or more examples, the functions described in the embodiments of the present invention can be implemented by hardware, software, firmware, or any combination thereof. When implemented using software, these functions may be stored in a computer-readable storage medium or transmitted as one or more instructions or codes on a computer-readable storage medium. The computer-readable storage medium includes a computer storage medium and a communication medium, where the communication medium includes any medium facilitating the transmission of a computer program from one place to another. The storage medium may be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0102] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for determining the pollen fertility of sugarcane plants based on a neural network model, characterized in that, The method includes: Obtaining a first training sample set, the first training sample set including a plurality of first training samples, each first training sample including a pollen image of a sugarcane plant, environmental data, and a pollen fertility detection result, the environmental data including temperature, humidity, and light intensity when the pollen image is obtained, and the pollen fertility detection result including high fertility, low fertility, or sterility; Performing an image augmentation operation on the pollen images included in the plurality of first training samples to obtain a second training sample set, wherein the image augmentation operation includes image rotation, image flipping, image scaling, or image noise addition operations, the second training sample set including a plurality of second training samples, each second training sample including a pollen image of a sugarcane plant obtained by the image augmentation operation, environmental data, and a pollen fertility detection result, the pollen fertility detection result including high fertility, low fertility, or sterility; Training a neural network model according to the first training sample set and the second training sample set to obtain a trained neural network model; Obtaining data to be detected, the data to be detected including a pollen image and environmental data of a target sugarcane plant; Inputting the data to be detected into the trained neural network model and outputting a pollen fertility detection result of the target sugarcane plant, the pollen fertility detection result including high fertility, low fertility, or sterility.

2. The method according to claim 1, characterized in that The training the neural network model according to the first training sample set and the second training sample set to obtain a trained neural network model includes: Establishing a target loss function with temperature, humidity, and light intensity as constraint conditions; Based on the target loss function, training the neural network model according to the first training sample set and the second training sample set to obtain a trained neural network model; The target loss function L is: L = L1 + λ1L 温度 + λ2L 湿度 + λ3L 光照强度 ; L1 is the cross-entropy loss function, L 温度 is the temperature constraint term, L 湿度 is the humidity constraint term, L 光照强度 is the light intensity constraint term, λ1, λ2, λ3 are the weight coefficients, N is the number of training samples, T i is the temperature value of the i-th training sample, H i is the humidity value of the i-th training sample, L i is the light intensity value of the i-th training sample.

3. The method according to claim 2, wherein The neural network model includes: an image data processing module, an environmental data processing module, a feature vector fusion module, and a detection module; the image data processing module and the environmental data processing module are respectively connected to the feature vector fusion module, and the feature vector fusion module is connected to the detection module; The image data processing module is configured to extract features from the pollen image included in the data to be detected to obtain a first feature vector corresponding to the pollen image; The environmental data processing module is configured to extract features from the environmental data included in the data to be detected to obtain a second feature vector corresponding to the environmental data; The feature vector fusion module is configured to perform feature fusion on the first feature vector and the second feature vector to obtain a fused feature vector; The detection module is configured to determine a pollen fertility detection result of the target sugarcane plant according to the fused feature vector, the pollen fertility detection result including high fertility, low fertility, or sterility.

4. The method according to claim 3, wherein The neural network model further includes: an attention mechanism layer, and the attention mechanism layer is respectively connected to the feature vector fusion module and the detection module; The attention mechanism layer is used to perform weighted summation on the fused feature vectors based on the attention mechanism to obtain weighted feature vectors and the attention weights corresponding to each feature included in the data to be detected, where the features include pollen images, temperature, humidity, or light intensity; The detection module is further used to determine the pollen fertility detection result of the target sugarcane plant according to the weighted feature vectors.

5. The method according to claim 4, wherein The pollen fertility detection result further includes the contribution score of each feature included in the data to be detected, and the contribution score is used to represent the contribution degree of the standard feature to the pollen fertility detection result; The method further includes: Determining the attention weight corresponding to each feature as the contribution score of each feature.

6. The method according to claim 5, wherein The obtaining of the data to be detected includes: Obtaining a pollen image of a target sugarcane plant at a target time through an image acquisition device; Obtaining the temperature, humidity, and light intensity corresponding to each of multiple times of the target sugarcane plant through sensors; Determining the temperature, humidity, and light intensity corresponding to the target sugarcane plant at the target time as the environmental data of the target sugarcane plant.

7. A pollen fertility determination system for sugarcane plants based on a neural network model, characterized in that, The system includes: An acquisition unit, configured to acquire a first training sample set, where the first training sample set includes multiple first training samples, and each first training sample includes a pollen image of a sugarcane plant, environmental data, and a pollen fertility detection result. The environmental data includes the temperature, humidity, and light intensity when the pollen image is acquired, and the pollen fertility detection result includes high fertility, low fertility, or sterility; An augmentation unit, configured to perform image augmentation operations on the pollen images included in the multiple first training samples to obtain a second training sample set. Among them, the image augmentation operations include image rotation, image flipping, image scaling, or image noise addition operations. The second training sample set includes multiple second training samples, and each second training sample includes a pollen image of a sugarcane plant obtained by the image augmentation operation, environmental data, and a pollen fertility detection result. The pollen fertility detection result includes high fertility, low fertility, or sterility; A training unit, configured to train a neural network model according to the first training sample set and the second training sample set to obtain a trained neural network model; The acquisition unit is further configured to acquire data to be detected, where the data to be detected includes a pollen image and environmental data of a target sugarcane plant; A detection unit, configured to input the data to be detected into the trained neural network model and output the pollen fertility detection result of the target sugarcane plant. The pollen fertility detection result includes high fertility, low fertility, or sterility.

8. The system according to claim 7, wherein, The training unit is specifically configured to: Establish a target loss function with temperature, humidity, and light intensity as constraint conditions; Based on the target loss function, train a neural network model according to the first training sample set and the second training sample set to obtain a trained neural network model; The target loss function L is: L = L1 + λ1L 温度 + λ2L 湿度 + λ3L 光照强度 ; L1 is the cross-entropy loss function, L 温度 is the temperature constraint term, L 湿度 is the humidity constraint term, L 光照强度 is the light intensity constraint term, λ1, λ2, λ3 are weight coefficients, N is the number of training samples, T i is the temperature value of the i-th training sample, H i is the humidity value of the i-th training sample, L i is the light intensity value of the i-th training sample.

9. The system according to claim 8, wherein The neural network model includes: an image data processing module, an environmental data processing module, a feature vector fusion module, and a detection module; the image data processing module and the environmental data processing module are respectively connected to the feature vector fusion module, and the feature vector fusion module is connected to the detection module; The image data processing module is configured to extract features from the pollen image included in the data to be detected, and obtain a first feature vector corresponding to the pollen image; The environmental data processing module is configured to extract features from the environmental data included in the data to be detected, and obtain a second feature vector corresponding to the environmental data; The feature vector fusion module is configured to perform feature fusion on the first feature vector and the second feature vector to obtain a fused feature vector; The detection module is configured to determine a pollen fertility detection result of the target sugarcane plant according to the fused feature vector, and the pollen fertility detection result includes high fertility, low fertility or sterility; The neural network model further includes: an attention mechanism layer, and the attention mechanism layer is respectively connected to the feature vector fusion module and the detection module; The attention mechanism layer is configured to perform weighted summation on the fused feature vector based on the attention mechanism, and obtain a weighted feature vector and an attention weight corresponding to each feature included in the data to be detected, and the features include pollen image, temperature, humidity or light intensity; The detection module is further configured to determine a pollen fertility detection result of the target sugarcane plant according to the weighted feature vector.

10. An electronic device, characterized in that, It includes: A processor; A memory for storing instructions executable by the processor; Wherein, the processor is configured to execute the instructions to implement the method for determining the pollen fertility of a sugarcane plant based on a neural network model according to any one of claims 1-6.

Images