Method and device for determining growth period of crops and storage medium

Abstract

The embodiment of the invention provides a method and device for determining the growth period of crops and a storage medium. The method comprises the following steps: inputting an obtained to-be-identified image of a crop into a crop classification model to obtain a crop type of the crop; determining a first acquisition date of the to-be-identified image, and acquiring a second acquisition date of the initial image of the crop and a historical growth period of the crop at the second acquisition date; determining the effective accumulated temperature of the crop in the date interval according to the crop type and the meteorological data of each date between the first acquisition date and the second acquisition date; determining at least one candidate growth period of the crop in the first acquisition date according to the effective accumulated temperature and the historical growth period; inputting the to-be-recognized image into a growth period recognition model corresponding to the crop type to obtain a prediction probability of each growth period of the crop; and determining the growth period of the crop at the first acquisition date according to the at least one candidate growth period and the prediction probability of each growth period of the crop, so that the determined growth period of the crop is more accurate.

Description

Technical Field

[0001] The present application relates to the field of agricultural production technology, and in particular to a method, device and storage medium for determining the growth period of crops. Background Art

[0002] In the process of crop production, more accurate judgment of the growth period of crops is the basis for timely management, improving work efficiency and benefits, and determining planting plans such as crop rotation arrangements.

[0003] When existing technologies use field sensors to identify the growth period of rice, most of them build models after training with a large amount of labeled image data, or add more phenotypic characteristics of rice to increase more information, thereby realizing the judgment of the current growth period of rice.

[0004] However, the recognition difficulty is low in the seedling stage of early crops, and the coverage of crops in the later stage gradually increases. Considering only the image information of a single time, the recognition difficulty is higher, the recognition results are inconsistent with the actual situation, and the recognition error in the growth period is large. Summary of the invention

[0005] The purpose of the embodiments of the present application is to provide a method, device and storage medium for determining the growth period of crops, so as to solve the problem of inaccurate identification of the growth period of crops in the prior art.

[0006] In order to achieve the above-mentioned object, the first aspect of the present application provides a method for determining the growth period of a crop, comprising:

[0007] Acquire an image of a crop to be identified, and input the image to be identified into a crop classification model so that the crop classification model outputs the crop type of the crop;

[0008] Determine a first acquisition date of the image to be identified, and acquire a second acquisition date of the initial image of the crop, and the historical growth period of the crop on the second acquisition date, wherein the second acquisition date is earlier than the first acquisition date;

[0009] Determine the effective accumulated temperature of the crop in the date interval according to the crop type and the meteorological data of each date in the date interval between the first acquisition date and the second acquisition date;

[0010] Determine at least one candidate growth period of the crop on the first acquisition date according to the effective accumulated temperature and the historical growth period;

[0011] Inputting the image to be identified into a growth period identification model corresponding to the crop type, so that the growth period identification model outputs the predicted probability of each growth period of the crop, and the growth period identification model characterizes the relationship between the image of the crop and the growth period of the crop;

[0012] The growth stage of the crop at the first acquisition date is determined according to at least one candidate growth stage and the predicted probability of each growth stage of the crop.

[0013] In an embodiment of the present application, determining at least one candidate growth period in which the crop is located on a first acquisition date based on the effective accumulated temperature and the historical growth period includes: determining the minimum effective accumulated temperature that the crop needs to reach from the historical growth period to each growth period after the historical growth period; constructing a plurality of effective accumulated temperature intervals based on all the minimum effective accumulated temperatures; determining a target effective accumulated temperature interval in which the effective accumulated temperature is located from the plurality of effective accumulated temperature intervals, and determining at least one growth period corresponding to the target effective accumulated temperature interval as at least one candidate growth period.

[0014] In an embodiment of the present application, determining the effective accumulated temperature of the crop in the date interval based on the crop type and the meteorological data of each date in the date interval between the first acquisition date and the second acquisition date includes: acquiring the average daily temperature of each date in the date interval from the meteorological data; acquiring the lower limit temperature of the crop based on the crop type, and determining the temperature difference between each daily average temperature and the lower limit temperature; and determining the sum of the temperature differences of all dates as the effective accumulated temperature of the crop in the date interval.

[0015] In an embodiment of the present application, a crop classification model is constructed by the following steps: obtaining first training images of different types of crops, wherein the first training image of each crop carries a first characterization attribute of each crop; inputting the first training image of each crop into the first model so that the first model outputs the crop type of each crop to train the first model; and determining that the training of the first model is completed when the first model meets the corresponding training completion conditions, and the trained first model is a crop classification model.

[0016] In an embodiment of the present application, a growth period recognition model for each crop is constructed by the following steps: for any one crop, a plurality of second training images of the crop are obtained, each second training image is marked with a second characterization attribute of the crop in any historical growth period; the plurality of second training images are input into the second model, so that the second model outputs the historical growth period corresponding to each second training image, so as to train the second model; when the second model meets the corresponding training completion conditions, it is determined that the training of the second model is completed, and the trained second model is the growth period recognition model corresponding to the crop.

[0017] In an embodiment of the present application, determining the growing period of a crop based on at least one candidate growing period and the predicted probability of each growing period of the crop includes: screening the growing period corresponding to each predicted probability based on at least one candidate growing period to obtain the remaining growing periods; and selecting the growing period with the largest predicted probability from the remaining growing periods as the growing period of the crop on the first acquisition date.

[0018] In an embodiment of the present application, the reproductive period corresponding to each predicted probability is screened based on at least one candidate reproductive period to obtain the remaining reproductive periods including: for each reproductive period corresponding to the predicted probability, if the reproductive period is not included in at least one candidate reproductive period, the reproductive period is eliminated; for each reproductive period corresponding to the predicted probability, if the reproductive period is included in at least one candidate reproductive period, the reproductive period is determined as the remaining reproductive period.

[0019] In the embodiment of the present application, the crop is rice.

[0020] A second aspect of the present application provides a device for determining a crop growth period, comprising:

[0021] a memory configured to store instructions;

[0022] The processor is configured to call instructions from the memory and implement the above method for determining the growth period of crops when executing the instructions.

[0023] A third aspect of the present application provides a machine-readable storage medium having instructions stored thereon, which, when executed by a processor, configure the processor to execute the above-mentioned method for determining the growth period of crops.

[0024] Through the above technical scheme, the crop type of the crop is determined based on the crop classification model, the growing period is predicted based on the growing period identification model corresponding to the crop type, and the results predicted by the growing period identification model are screened in combination with the crop's time-series growth information and meteorological data to obtain the crop's growing period, making the determined growing period of the crop more accurate.

[0025] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings:

[0027] Figure 1 The flowchart of the method for determining the growth period of crops according to the embodiment of the present application is schematically shown;

[0028] Figure 2 A schematic diagram of a process for determining a crop growth period according to another embodiment of the present application is shown;

[0029] Figure 3 The internal structure diagram of a computer device according to an embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0031] It should be noted that if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0032] Figure 1 The flowchart of the method for determining the crop growth period according to the embodiment of the present application is schematically shown. Figure 1 As shown, in one embodiment of the present application, a method for determining a crop growth period is provided, comprising the following steps:

[0033] Step 101: Acquire an image of a crop to be identified, and input the image to be identified into a crop classification model so that the crop classification model outputs the crop type of the crop.

[0034] Crops may refer to various plants cultivated in agriculture. For example, crops may refer to wheat, corn, soybeans, rice, rapeseed, etc. In the embodiment of the present application, the crop is rice. There are many types of rice, for example, conventional indica rice, hybrid indica rice, conventional japonica rice, and hybrid japonica rice. The planting patterns adopted by different types of rice may be different, for example, double-season early rice, mid-season rice, double-season late rice, and single-season late rice.

[0035] When determining the growth period of the crop, the processor may obtain an image of the crop to be identified and input the image to be identified into a crop classification model so that the crop classification model outputs the crop type of the crop. The crop types may include conventional indica rice, hybrid indica rice, conventional japonica rice, and hybrid japonica rice, wherein the crop classification model may be used to identify the type of the crop, which may be constructed before determining the growth period of the crop or before identifying the crop type of the crop. When constructing the crop classification model, historical images of each crop may be obtained and obtained based on large model training.

[0036] In an embodiment of the present application, a crop classification model is constructed by the following steps: obtaining first training images of different types of crops, wherein the first training image of each crop carries a first characterization attribute of each crop; inputting the first training image of each crop into the first model so that the first model outputs the crop type of each crop to train the first model; and determining that the training of the first model is completed when the first model meets the corresponding training completion conditions, and the trained first model is a crop classification model.

[0037] When constructing a crop classification model, first training images of different types of crops may be obtained, wherein the first training image of each crop carries a first characterization attribute of each crop. For example, if the crop is rice, images of conventional indica rice, hybrid indica rice, conventional japonica rice, and hybrid japonica rice may be obtained as training images. The first characterization attribute includes the difference features in the appearance of the crop image, for example, the plant height, dry weight, leaf width, ear length, and color of the crop. After the first training image is obtained, it may be input into the first model so that the first model outputs the crop type of each crop to train the first model.

[0038] The first model may be an image recognition model, such as CNN, LeNet, AlexNet, VGG, GoogLeNet, and ResNet. When the first model meets the corresponding training completion conditions, it can be determined that the training of the first model is completed, and the trained first model is a crop classification model. The training completion conditions may include that the number of training iterations reaches a preset number, and / or the prediction accuracy reaches a preset accuracy, and / or the preset error is less than a preset value.

[0039] Step 102: Determine a first acquisition date of the image to be identified, and acquire a second acquisition date of the initial image of the crop, and the historical growth period of the crop on the second acquisition date, wherein the second acquisition date is earlier than the first acquisition date.

[0040] The processor can determine the first acquisition date of the image to be identified, and obtain the second acquisition date of the initial image of the crop, and the historical growth stage of the crop on the second acquisition date. The second acquisition date is earlier than the first acquisition date, that is, the initial image is collected and acquired before the image to be identified. The initial image refers to the image that is first collected after the growth of the crop. The growth stage of the crop at this time can be any one of the tillering stage, booting stage, heading stage, filling stage and maturity stage. In order to better understand the subsequent growth of the crop, the image of the crop can be obtained as early as possible. For example, when the initial image is obtained on the second acquisition date, the historical growth stage of the crop is preferably the early tillering stage.

[0041] Step 103: Determine the effective accumulated temperature of the crop in the date interval according to the crop type and the meteorological data of each date in the date interval between the first acquisition date and the second acquisition date.

[0042] The processor can determine the effective accumulated temperature of the crop in the date interval according to the crop type and the meteorological data of each date in the date interval between the first acquisition date and the second acquisition date. The meteorological data of each date includes the highest temperature, the lowest temperature, the average daily temperature and the air humidity of the planting area where the crop is located on the corresponding date.

[0043] In an embodiment of the present application, determining the effective accumulated temperature of the crop in the date interval based on the crop type and the meteorological data of each date in the date interval between the first acquisition date and the second acquisition date includes: acquiring the average daily temperature of each date in the date interval from the meteorological data; acquiring the lower limit temperature of the crop based on the crop type, and determining the temperature difference between each daily average temperature and the lower limit temperature; and determining the sum of the temperature differences of all dates as the effective accumulated temperature of the crop in the date interval.

[0044] The processor can obtain the average daily temperature of the corresponding date from the meteorological data of each date in the date interval. The processor can obtain the lower limit temperature of the crop based on the crop type, and determine the temperature difference between each daily average temperature and the lower limit temperature. That is, different crop types have different corresponding lower limit temperatures. For example, when the crop is conventional indica rice and hybrid indica rice, the corresponding lower limit temperature can be set to 12°C. When it is conventional japonica rice and hybrid japonica rice, the corresponding lower limit temperature can be set to 10°C. The processor can determine the sum of the temperature differences of all dates, and determine the sum of the temperature differences of all dates as the effective accumulated temperature of the crop in the date interval.

[0045] Step 104: Determine at least one candidate growth period of the crop on the first acquisition date according to the effective accumulated temperature and the historical growth period.

[0046] The processor may determine at least one candidate growth stage of the crop on the first acquisition date based on the effective accumulated temperature and the historical growth stages.

[0047] In an embodiment of the present application, determining at least one candidate growth period in which the crop is located on a first acquisition date based on the effective accumulated temperature and the historical growth period includes: determining the minimum effective accumulated temperature that the crop needs to reach from the historical growth period to each growth period after the historical growth period; constructing a plurality of effective accumulated temperature intervals based on all the minimum effective accumulated temperatures; determining a target effective accumulated temperature interval in which the effective accumulated temperature is located from the plurality of effective accumulated temperature intervals, and determining at least one growth period corresponding to the target effective accumulated temperature interval as at least one candidate growth period.

[0048] The processor can determine the minimum effective accumulated temperature that the crop needs to reach in each growth period after entering the historical growth period from the historical growth period, and construct multiple effective accumulated temperature intervals based on all the minimum effective accumulated temperatures. The processor can determine a target effective accumulated temperature interval in which the effective accumulated temperature is located from the multiple effective accumulated temperature intervals, and determine at least one growth period corresponding to the target effective accumulated temperature interval as at least one candidate growth period.

[0049] For example, the historical growth period of the crop on the second acquisition date is the tillering period. At this time, the minimum effective accumulated temperature from the tillering period to the booting period is G2, the minimum effective accumulated temperature from the tillering period to the heading period is G2+G3, the minimum effective accumulated temperature from the tillering period to the filling period is G2+G3+G4, and the minimum effective accumulated temperature from the tillering period to the maturity period is G2+G3+G4+G5. The following effective accumulated temperature intervals can be constructed: (-∞, G2]; (G2, G2+G3]; (G2+G3, G2+G3+G4]; (G2+G3+G4, G2+G3+G4+G5], (G2+G3+G4+G5, +∞). At this time, if the effective accumulated temperature is in the interval of (-∞, G2), the candidate growth period includes the tillering period or the booting period; if the effective accumulated temperature is in the interval of (G2, G2+G3], the candidate growth period includes the booting period or the heading period; if the effective accumulated temperature is in the interval of (G2+G3, G2+G3+G4], the candidate growth period includes the heading period or the filling period; if the effective accumulated temperature is in the interval of (G2+G3+G4, G2+G3+G4+G5], the candidate growth period includes the filling period or the maturity period; if the effective accumulated temperature is in the interval of (G2+G3+G4+G5, +∞), the candidate growth period includes the maturity period.

[0050] For another example, the historical growth period of the crop on the second acquisition date is the booting stage. At this time, the effective accumulated temperature intervals are as follows: (-∞, G3]; (G3, G3+G4]; (G3+G4, G3+G4+G5], (G3+G4+G5, +∞). At this time, the minimum effective accumulated temperature from the booting stage to the heading stage is G3, the minimum effective accumulated temperature from the booting stage to the filling stage is G3+G4, and the minimum effective accumulated temperature from the booting stage to the maturity stage is G3+G4. +G5, at this time, if the effective accumulated temperature is in the interval of (-∞, G3], the candidate growth period includes the booting stage or the heading stage; if the effective accumulated temperature is in the interval of (G3, G3+G4], the candidate growth period includes the heading stage or the filling stage; if the effective accumulated temperature is in the interval of (G3+G4, G3+G4+G5], the candidate growth period includes the filling stage or the maturity stage; if the effective accumulated temperature is in the interval of (G3+G4+G5, +∞), the candidate growth period includes the maturity stage.

[0051] Step 105: Input the image to be identified into a growth period identification model corresponding to the crop type, so that the growth period identification model outputs the predicted probability of each growth period of the crop. The growth period identification model characterizes the relationship between the image of the crop and the growth period of the crop.

[0052] The processor can input the image to be identified into the growth period identification model corresponding to the crop type, so that the growth period identification model outputs the predicted probability of each growth period of the crop, and the growth period identification model characterizes the relationship between the image of the crop and the growth period of the crop. Among them, the growth period identification model can be used to identify the growth period of the crop, which can be constructed before determining the growth period of the crop or identifying the crop type of the crop. The growth period identification model can be obtained based on the training of the large model.

[0053] In an embodiment of the present application, a growth period recognition model for each crop is constructed by the following steps: for any one crop, a plurality of second training images of the crop are obtained, each second training image is marked with a second characterization attribute of the crop in any historical growth period; the plurality of second training images are input into the second model, so that the second model outputs the historical growth period corresponding to each second training image, so as to train the second model; when the second model meets the corresponding training completion conditions, it is determined that the training of the second model is completed, and the trained second model is the growth period recognition model corresponding to the crop.

[0054] When constructing a growth period recognition model for each crop, multiple second training images of the crop are obtained, each of which is marked with a second characterization attribute of the crop in any historical growth period. The second characterization attribute may include leaf features, plant height, whether the crop is in ear form, etc. After obtaining the second training image, the multiple second training images may be input into the second model so that the second model outputs the historical growth period corresponding to each second training image to train the second model.

[0055] The second model may also be an image recognition model, such as CNN, LeNet, AlexNet, VGG, GoogLeNet, and ResNet. When the second model meets the corresponding training completion conditions, it can be determined that the second model training is completed, and the trained second model is a growth period recognition model for the corresponding crop. The training completion conditions may include that the number of training iterations reaches a preset number, and / or the prediction accuracy reaches a preset accuracy, and / or the preset error is less than a preset value.

[0056] Step 106: Determine the growth stage of the crop at the first acquisition date based on at least one candidate growth stage and the predicted probability of each growth stage of the crop.

[0057] The processor may determine the growth period of the crop at the first acquisition date based on at least one candidate growth period and the predicted probability of each growth period of the crop. For example, the growth period of each predicted probability may be compared with at least one candidate growth period, and one growth period may be selected as the growth period of the crop.

[0058] In an embodiment of the present application, determining the growing period of a crop based on at least one candidate growing period and the predicted probability of each growing period of the crop includes: screening the growing period corresponding to each predicted probability based on at least one candidate growing period to obtain the remaining growing periods; and selecting the growing period with the largest predicted probability from the remaining growing periods as the growing period of the crop on the first acquisition date.

[0059] The processor may filter the growth period corresponding to each predicted probability based on at least one candidate growth period to obtain the remaining growth periods. For example, the processor may perform intersection processing on at least one candidate growth period and the growth period corresponding to each predicted probability to obtain the remaining growth periods, or may obtain the remaining growth periods based on traversing whether the growth period exists in at least one candidate growth period. The processor may select the growth period with the largest predicted probability from the remaining growth periods as the growth period of the crop at the first acquisition date.

[0060] In an embodiment of the present application, the reproductive period corresponding to each predicted probability is screened based on at least one candidate reproductive period to obtain the remaining reproductive periods including: for each reproductive period corresponding to the predicted probability, if the reproductive period is not included in at least one candidate reproductive period, the reproductive period is eliminated; for each reproductive period corresponding to the predicted probability, if the reproductive period is included in at least one candidate reproductive period, the reproductive period is determined as the remaining reproductive period.

[0061] For each growing period corresponding to the predicted probability, it is possible to traverse whether the growing period exists in at least one candidate growing period. If the growing period does not exist in at least one candidate growing period, that is, the growing period is not included in at least one candidate growing period, then the credibility or reliability of the growing period identification model may be low. At this time, the processor can eliminate the growing period, that is, no longer consider the growing period when subsequently determining the growing period of the crop on the first acquisition date.

[0062] For each growing period corresponding to the predicted probability, it is possible to traverse whether the growing period exists in at least one candidate growing period. If the growing period exists in at least one candidate growing period, that is, the growing period is included in at least one candidate growing period, then the credibility or reliability of the growing period identification model may be higher. At this time, the processor may not eliminate the growing period, that is, the growing period may be considered in the subsequent determination of the growing period of the crop on the first acquisition date, and the processor may determine the growing period as the remaining growing period.

[0063] like Figure 2 As shown, taking rice as an example, a flow chart of another method for determining the growth period of a crop is provided.

[0064] Taking rice as an example, rice pictures can be collected, and the rice pictures can be used to train the rice category recognition model M1 and the rice image recognition model M2. Specifically, multiple pictures of whole rice plants at different growth stages are taken, and the existing pictures are classified. The rice categories are divided into four categories: conventional indica rice, conventional japonica rice, hybrid indica rice, and hybrid japonica rice. Multiple characterization attributes of different types of rice are selected to train the model, and the trained rice category recognition model M1 is obtained. The rice category recognition model M1 is used to determine the rice category. According to the rice category, multiple characterization attributes of rice at different growth stages are selected to train the model, and the trained rice image recognition model M2 is obtained. The rice image recognition model M2 is used to determine what growth stage the rice is in.

[0065] When determining the growth period TN of rice, each real-time acquired picture can be input into the rice category recognition model M1 to obtain the rice category, and the rice image recognition model M2 of the corresponding category can be matched based on the rice category. For example, if the rice category is conventional indica rice, the corresponding rice image recognition model M2 is conventional indica rice M2, which can be used to identify each growth period of conventional indica rice. If the rice category is conventional japonica rice, the corresponding rice image recognition model M2 is conventional japonica rice M2, which can be used to identify each growth period of conventional japonica rice. If the rice category is hybrid indica rice, the corresponding rice image recognition model M2 is hybrid indica rice M2, which can be used to identify each growth period of hybrid indica rice. If the rice category is hybrid japonica rice, the corresponding rice image recognition model M2 is hybrid japonica rice M2, which can be used to identify each growth period of hybrid japonica rice.

[0066] After matching the rice image recognition model M2 of the corresponding category, the real-time acquired picture can be input into the model to predict the current possible growth period of the rice. At the same time, the accumulated temperature of the crop in the time interval can be determined based on the meteorological data of each date between the time of the real-time acquired picture and the time of the first acquisition of the rice image, and based on the meteorological data of all dates, and a preliminary growth period judgment can be made based on the accumulated temperature to obtain the preliminary judged growth period. Afterwards, the growth period of the rice currently predicted by the above model can be filtered or screened based on the preliminary judged growth period to obtain the growth period TN of the rice.

[0067] Through the above technical scheme, the crop type is determined based on the crop classification model, the growing period is predicted based on the growing period identification model corresponding to the crop type, and the results predicted by the growing period identification model are screened in combination with the crop's time-series growth information and meteorological data to obtain the crop's growing period, making the determined growing period of the crop more accurate.

[0068] Figure 1 and Figure 2 FIG. 1 is a flow chart of a method for determining the growth period of crops in one embodiment. Figure 1 and Figure 2 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1 and Figure 2At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0069] In one embodiment, a device for determining a crop growth period is provided, comprising:

[0070] a memory configured to store instructions;

[0071] The processor is configured to call instructions from the memory and implement the above method for determining the growth period of crops when executing the instructions.

[0072] In one embodiment, a storage medium is provided, on which a program is stored, and when the program is executed by a processor, the method for determining the growth period of crops is implemented.

[0073] In one embodiment, a processor is provided, and the processor is used to run a program, wherein the program executes the above method for determining the growth period of crops when it is run.

[0074] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor A01, a network interface A02, a memory (not shown in the figure) and a database (not shown in the figure) connected through a system bus. Among them, the processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02 and a database (not shown in the figure). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 in the non-volatile storage medium A04. The database of the computer device is used to store data such as the growth period of crops. The network interface A02 of the computer device is used to communicate with an external terminal through a network connection. When the computer program B02 is executed by the processor A01, a method for determining the growth period of crops is implemented.

[0075] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0076] The embodiment of the present application provides a device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the following steps are implemented:

[0077] Acquire an image of a crop to be identified, and input the image to be identified into a crop classification model so that the crop classification model outputs the crop type of the crop;

[0078] Determine a first acquisition date of the image to be identified, and acquire a second acquisition date of the initial image of the crop, and the historical growth period of the crop on the second acquisition date, wherein the second acquisition date is earlier than the first acquisition date;

[0079] Determine the effective accumulated temperature of the crop in the date interval according to the crop type and the meteorological data of each date in the date interval between the first acquisition date and the second acquisition date;

[0080] Determine at least one candidate growth period of the crop on the first acquisition date according to the effective accumulated temperature and the historical growth period;

[0081] Inputting the image to be identified into a growth period identification model corresponding to the crop type, so that the growth period identification model outputs the predicted probability of each growth period of the crop, and the growth period identification model characterizes the relationship between the image of the crop and the growth period of the crop;

[0082] The growth stage of the crop at the first acquisition date is determined according to at least one candidate growth stage and the predicted probability of each growth stage of the crop.

[0083] In one embodiment, determining at least one candidate growth period of a crop on a first acquisition date based on the effective accumulated temperature and the historical growth period includes: determining the minimum effective accumulated temperature that the crop needs to reach for each growth period after entering the historical growth period from the historical growth period; constructing a plurality of effective accumulated temperature intervals based on all the minimum effective accumulated temperatures; determining a target effective accumulated temperature interval in which the effective accumulated temperature is located from the plurality of effective accumulated temperature intervals, and determining at least one growth period corresponding to the target effective accumulated temperature interval as at least one candidate growth period.

[0084] In one embodiment, determining the effective accumulated temperature of the crop in the date interval based on the crop type and the meteorological data of each date in the date interval between the first acquisition date and the second acquisition date includes: obtaining the average daily temperature of each date in the date interval from the meteorological data; obtaining the lower limit temperature of the crop based on the crop type, and determining the temperature difference between each daily average temperature and the lower limit temperature; and determining the sum of the temperature differences of all dates as the effective accumulated temperature of the crop in the date interval.

[0085] In one embodiment, a crop classification model is constructed by the following steps: obtaining first training images of different types of crops, wherein the first training image of each crop carries a first characterization attribute of each crop; inputting the first training image of each crop into a first model so that the first model outputs the crop type of each crop to train the first model; and determining that the training of the first model is completed when the first model meets the corresponding training completion conditions, and the trained first model is a crop classification model.

[0086] In one embodiment, a growth period recognition model for each crop is constructed by the following steps: for any crop, a plurality of second training images of the crop are obtained, each second training image is marked with a second characterization attribute of the crop in any historical growth period; the plurality of second training images are input into the second model, so that the second model outputs the historical growth period corresponding to each second training image, so as to train the second model; when the second model meets the corresponding training completion conditions, it is determined that the training of the second model is completed, and the trained second model is the growth period recognition model corresponding to the crop.

[0087] In one embodiment, determining the growing period of a crop based on at least one candidate growing period and the predicted probability of each growing period of the crop includes: screening the growing period corresponding to each predicted probability based on at least one candidate growing period to obtain the remaining growing periods; and selecting the growing period with the largest predicted probability from the remaining growing periods as the growing period of the crop on the first acquisition date.

[0088] In one embodiment, the reproductive period corresponding to each predicted probability is screened based on at least one candidate reproductive period to obtain the remaining reproductive periods, including: for each reproductive period corresponding to the predicted probability, if the reproductive period is not included in at least one candidate reproductive period, the reproductive period is eliminated; for each reproductive period corresponding to the predicted probability, if the reproductive period is included in at least one candidate reproductive period, the reproductive period is determined as the remaining reproductive period.

[0089] In one embodiment, the crop is rice.

[0090] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that initializes the method steps for determining the growth period of crops.

[0091] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0092] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0093] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0094] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0095] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0096] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0097] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0098] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0099] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for determining the growth period of crops, characterized in that: The method comprises: Acquire an image of a crop to be identified, and input the image to be identified into a crop classification model so that the crop classification model outputs the crop type of the crop; Determine a first acquisition date of the image to be identified, and acquire a second acquisition date of the initial image of the crop, and a historical growth period of the crop on the second acquisition date, wherein the second acquisition date is earlier than the first acquisition date; Determine the effective accumulated temperature of the crop in the date interval according to the crop type and the meteorological data of each date in the date interval between the first acquisition date and the second acquisition date; Determine at least one candidate growth period of the crop at the first acquisition date according to the effective accumulated temperature and the historical growth period; Inputting the image to be identified into a growth period identification model corresponding to the crop type, so that the growth period identification model outputs a predicted probability of each growth period of the crop, wherein the growth period identification model characterizes a relationship between the image of the crop and the growth period of the crop; The growth stage of the crop at the first acquisition date is determined according to the at least one candidate growth stage and the predicted probability of each growth stage of the crop.

2. The method for determining the growth period of crops according to claim 1, characterized in that: Determining at least one candidate growth period of the crop on the first acquisition date according to the effective accumulated temperature and the historical growth period includes: Determining the minimum effective accumulated temperature that the crop needs to reach in each growth period after the historical growth period from the historical growth period; Construct multiple effective accumulated temperature intervals based on all minimum effective accumulated temperatures; A target effective accumulated temperature interval in which the effective accumulated temperature is located is determined from a plurality of effective accumulated temperature intervals, and at least one growth period corresponding to the target effective accumulated temperature interval is determined as the at least one candidate growth period.

3. The method for determining the crop growth period according to claim 1, characterized in that: The step of determining the effective accumulated temperature of the crop in the date interval according to the crop type and the meteorological data of each date in the date interval between the first acquisition date and the second acquisition date comprises: Obtaining the average daily temperature of each date in the date interval from the meteorological data; Acquire a lower limit temperature of the crop based on the crop type, and determine a temperature difference between each daily average temperature and the lower limit temperature; The sum of the temperature differences of all dates is determined as the effective accumulated temperature of the crop in the date interval.

4. The method for determining the crop growth period according to claim 1, characterized in that: The crop classification model is constructed by the following steps: Acquire first training images of different types of crops, wherein the first training image of each crop carries a first representative attribute of each crop; Inputting a first training image of each crop into a first model so that the first model outputs a crop type of each crop to train the first model; When the first model meets the corresponding training completion condition, it is determined that the training of the first model is completed, and the trained first model is the crop classification model.

5. The method for determining the growth period of crops according to claim 1, characterized in that: The growth period identification model for each crop is constructed through the following steps: For any crop, a plurality of second training images of the crop are obtained, each second training image being marked with a second characteristic attribute of the crop in any historical growth period; Inputting the plurality of second training images into a second model so that the second model outputs a historical growth period corresponding to each second training image, so as to train the second model; When the second model meets the corresponding training completion condition, it is determined that the training of the second model is completed, and the trained second model is a growth period recognition model corresponding to the crop.

6. The method for determining the crop growth period according to claim 1, characterized in that: Determining the growth period of the crop according to the at least one candidate growth period and the predicted probability of each growth period of the crop comprises: Based on the at least one candidate reproductive period, the reproductive period corresponding to each predicted probability is screened to obtain the remaining reproductive periods; The growth period with the largest predicted probability is selected from the remaining growth periods as the growth period of the crop on the first acquisition date.

7. The method for determining the growth period of crops according to claim 6, characterized in that: The step of screening the growth period corresponding to each predicted probability based on the at least one candidate growth period to obtain the remaining growth periods includes: For each reproductive period corresponding to the predicted probability, if the reproductive period is not included in the at least one candidate reproductive period, excluding the reproductive period; For each growth period corresponding to the predicted probability, if the growth period is included in the at least one candidate growth period, the growth period is determined as a remaining growth period.

8. The method for determining the growth period of crops according to any one of claims 1 to 7, characterized in that: The crop is rice.

9. A device for determining the growth period of crops, characterized in that: The device comprises: a memory configured to store instructions; A processor is configured to call the instructions from the memory and implement the method for determining the growth period of crops according to any one of claims 1 to 8 when executing the instructions.

10. A machine-readable storage medium having instructions stored thereon, characterized in that: When the instruction is executed by a processor, the processor is configured to execute the method for determining the growth period of a crop according to any one of claims 1 to 8.

Images