CN113408374A - Yield estimation method, device and equipment based on artificial intelligence and storage medium - Google Patents
Yield estimation method, device and equipment based on artificial intelligence and storage medium Download PDFInfo
- Publication number
- CN113408374A CN113408374A CN202110616657.0A CN202110616657A CN113408374A CN 113408374 A CN113408374 A CN 113408374A CN 202110616657 A CN202110616657 A CN 202110616657A CN 113408374 A CN113408374 A CN 113408374A
- Authority
- CN
- China
- Prior art keywords
- target
- information
- yield
- image information
- artificial intelligence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000003860 storage Methods 0.000 title claims abstract description 13
- 238000003062 neural network model Methods 0.000 claims abstract description 28
- 230000007613 environmental effect Effects 0.000 claims abstract description 19
- 238000012549 training Methods 0.000 claims description 30
- 238000011156 evaluation Methods 0.000 claims description 15
- 239000000284 extract Substances 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 5
- 238000004519 manufacturing process Methods 0.000 claims 1
- 230000006870 function Effects 0.000 abstract description 6
- 230000008569 process Effects 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 5
- 238000013527 convolutional neural network Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 239000002689 soil Substances 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000003306 harvesting Methods 0.000 description 3
- 241000209140 Triticum Species 0.000 description 2
- 235000021307 Triticum Nutrition 0.000 description 2
- 238000012271 agricultural production Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Business, Economics & Management (AREA)
- Agronomy & Crop Science (AREA)
- General Health & Medical Sciences (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Probability & Statistics with Applications (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Animal Husbandry (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
Abstract
本发明涉及农业技术领域，公开了一种基于人工智能的产量预估方法、装置、设备及存储介质，所述方法包括：获取目标农作物的当前生长图像信息，提取所述当前生长图像信息的目标特征信息；根据所述目标特征信息在大数据平台查找对应的历史生长信息；获取预设神经网络模型，根据所述预设神经网络模型和所述历史生长信息得到目标产量预估模型；获取所述目标农作物的环境图像信息，根据所述当前生长图像信息和所述环境图像信息通过所述目标产量预估模型进行产量预测，得到所述目标农作物的预估产量，相较于现有技术通过不同功能的传感器测得的单一数据对农作物产量的推测，能够有效提高预估农作物产量的正确率，以及降低预估成本。
The invention relates to the technical field of agriculture, and discloses an artificial intelligence-based yield estimation method, device, equipment and storage medium. The method includes: acquiring current growth image information of a target crop, and extracting a target of the current growth image information. feature information; search for corresponding historical growth information on the big data platform according to the target feature information; obtain a preset neural network model, and obtain a target yield prediction model according to the preset neural network model and the historical growth information; Describe the environmental image information of the target crop, carry out yield prediction through the target yield estimation model according to the current growth image information and the environmental image information, and obtain the estimated yield of the target crop, compared to the prior art by The prediction of crop yield from a single data measured by sensors with different functions can effectively improve the accuracy of crop yield estimation and reduce the estimated cost.
Description
Technical Field
The invention relates to the technical field of agriculture, in particular to a yield estimation method, a device, equipment and a storage medium based on artificial intelligence.
Background
With the rapid development of artificial intelligence, smart agriculture is already an important component of smart economy, and China is used as a big agricultural country rather than a strong agricultural country, so that high-level facility agricultural production and optimized facility biological environment control are realized, agricultural related information acquisition and analysis technology is one of the most critical technologies in agricultural production, the most applied places of analysis technology are estimation of the yield of different crops, and currently, the commonly used estimation technology is to obtain corresponding environmental factors through sensor probes with different functions, such as: the yield of the crops during harvesting is comprehensively estimated through the environmental factors, such as temperature, humidity, illuminance, air, soil components, wind power information and the like, but any single sensor data has the limitation of a certain application range and cannot comprehensively reflect the physiological and biochemical characteristics of the crops, so that the predicted yield and the final actual yield have larger errors.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
The invention mainly aims to provide a yield estimation method, a yield estimation device, yield estimation equipment and a storage medium based on artificial intelligence, and aims to solve the technical problem that the accuracy of the estimated crop yield cannot be effectively improved in the prior art.
In order to achieve the above object, the present invention provides an artificial intelligence based yield estimation method, which comprises the following steps:
acquiring current growth image information of a target crop, and extracting target characteristic information of the current growth image information;
searching corresponding historical growth information on a big data platform according to the target characteristic information;
acquiring a preset neural network model, and acquiring a target yield estimation model according to the preset neural network model and the historical growth information;
and obtaining environment image information of the target crop, and predicting the yield through the target yield prediction model according to the current growth image information and the environment image information to obtain the predicted yield of the target crop.
Optionally, before obtaining the current growth image information of the target crop and extracting the target feature information of the current growth image information, the method further includes:
selecting a target area from the areas where the target crops are planted;
acquiring a preset adjustment strategy, and adjusting the camera equipment arranged in the target area in real time according to the preset adjustment strategy;
shooting the target crop according to the adjusted camera equipment to obtain current growth image information of the target crop.
Optionally, the acquiring current growth image information of the target crop, and extracting target feature information of the current growth image information include:
acquiring current growth image information of a target crop, and analyzing the current growth image information to obtain corresponding pixel vector information;
acquiring a target clustering center, and calculating corresponding pixel block information according to the target clustering center and the pixel vector information;
and extracting the target characteristic information of the current growth image information according to the pixel block information.
Optionally, the searching for corresponding historical growth information on a big data platform according to the target feature information includes:
acquiring structural information of the target crops, and dividing the target characteristic information according to the structural information;
respectively searching corresponding current growth information on a big data platform according to the divided target characteristic information;
and matching the current growth information, and obtaining corresponding historical growth information according to a matching result.
Optionally, the matching the current growth information and obtaining corresponding historical growth information according to a matching result includes:
matching the current growth information to obtain a corresponding matching result;
screening the successfully matched current growth information in the matching result according to the structural information of the target crop to obtain target growth information;
and traversing and combining the target growth information to obtain corresponding historical growth information.
Optionally, the obtaining environmental image information of the target crop, and performing yield prediction according to the current growth image information and the environmental image information through the target yield prediction model to obtain the predicted yield of the target crop includes:
acquiring environmental image information of the target crop, and generating a current training data set according to the current growth image information and the environmental image information;
and acquiring a preset yield evaluation index, and if the index of the current training data set is larger than the preset yield evaluation index, predicting the yield through the target yield prediction model according to the current training data to obtain the predicted yield of the target crops.
Optionally, the obtaining a preset yield evaluation index, if the index of the current training data set is greater than the preset yield evaluation index, performing yield prediction according to the current training data through the target yield prediction model, and after obtaining the predicted yield of the target crop, further includes:
acquiring the actual yield of the target crop, and calculating the fault tolerance of the target yield estimation model according to the actual yield and the estimated yield;
and if the fault tolerance rate is within a preset range, estimating the yield of the target crops according to the target yield estimation model.
In addition, in order to achieve the above object, the present invention further provides an artificial intelligence based yield estimation apparatus, including:
the extraction module is used for acquiring current growth image information of a target crop and extracting target characteristic information of the current growth image information;
the searching module is used for searching corresponding historical growth information on a big data platform according to the target characteristic information;
the acquisition module is used for acquiring a preset neural network model and obtaining a target yield estimation model according to the preset neural network model and the historical growth information;
and the yield prediction module is used for acquiring the environment image information of the target crop, and predicting the yield through the target yield prediction model according to the current growth image information and the environment image information to obtain the predicted yield of the target crop.
In addition, in order to achieve the above object, the present invention further provides an artificial intelligence based yield estimation apparatus, including: a memory, a processor, and an artificial intelligence based yield prediction program stored on the memory and executable on the processor, the artificial intelligence based yield prediction program configured to implement the artificial intelligence based yield prediction method as described above.
In addition, to achieve the above object, the present invention further provides a storage medium having an artificial intelligence based yield estimation program stored thereon, wherein the artificial intelligence based yield estimation program, when executed by a processor, implements the artificial intelligence based yield estimation method as described above.
According to the yield estimation method based on artificial intelligence, the target characteristic information of the current growth image information is extracted by acquiring the current growth image information of a target crop; searching corresponding historical growth information on a big data platform according to the target characteristic information; acquiring a preset neural network model, and acquiring a target yield estimation model according to the preset neural network model and the historical growth information; the method comprises the steps of obtaining environment image information of the target crop, predicting the yield through a target yield prediction model according to the current growth image information and the environment image information, obtaining the predicted yield of the target crop, and compared with the prior art that the yield of the crop is predicted through single data measured by sensors with different functions, the method can effectively improve the accuracy of the predicted crop yield and reduce the prediction cost.
Drawings
FIG. 1 is a schematic diagram of an artificial intelligence-based yield estimation device for a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart illustrating a first embodiment of the artificial intelligence based yield estimation method according to the present invention;
FIG. 3 is a schematic flow chart illustrating a second embodiment of the artificial intelligence based yield estimation method according to the present invention;
FIG. 4 is a schematic flow chart illustrating a third embodiment of the artificial intelligence based yield estimation method according to the present invention;
FIG. 5 is a functional block diagram of a first embodiment of an artificial intelligence based yield estimation apparatus according to the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of an artificial intelligence-based yield prediction apparatus of a hardware operating environment according to an embodiment of the present invention.
As shown in FIG. 1, the artificial intelligence based yield prediction apparatus may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a Random Access Memory (RAM) Memory, or may be a Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the configuration shown in FIG. 1 does not constitute a limitation of an artificial intelligence based yield prediction apparatus and may include more or less components than those shown, or some components in combination, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a storage medium, may include therein an operating system, a network communication module, a user interface module, and an artificial intelligence based yield estimator.
In the artificial intelligence based yield prediction apparatus shown in FIG. 1, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 of the yield estimation device based on artificial intelligence of the present invention may be disposed in the yield estimation device based on artificial intelligence, and the yield estimation device based on artificial intelligence invokes the yield estimation program based on artificial intelligence stored in the memory 1005 through the processor 1001, and executes the yield estimation method based on artificial intelligence provided by the embodiment of the present invention.
Based on the hardware structure, the embodiment of the yield estimation method based on artificial intelligence is provided.
Referring to FIG. 2, FIG. 2 is a flowchart illustrating a first embodiment of a yield estimation method based on artificial intelligence according to the present invention.
In a first embodiment, the artificial intelligence based yield prediction method comprises the steps of:
and step S10, acquiring current growth image information of the target crop, and extracting target characteristic information of the current growth image information.
It should be noted that, the execution subject of the embodiment is an artificial intelligence-based yield estimation device, and may also be other devices that can achieve the same or similar functions, such as a yield estimation controller, and the like.
It should be understood that the current growth image information refers to image information of a target crop at a specific time during the growth process, the growth condition of the target crop can be visually observed through the current growth image information, after the current growth image information of the target crop is obtained, the most representative feature information in the current growth image information is extracted as target feature information, for example, three feature information, namely a feature information, B feature information and C feature information, are obtained by analyzing the current growth image information, where a is the feature information most representative of the target crop, and at this time, the a feature information is taken as the target feature information.
Further, in order to effectively reduce the estimated cost, before acquiring the current growth image information of the target crop and extracting the target feature information of the current growth image information, the method further includes:
selecting a target area from the areas where the target crops are planted; acquiring a preset adjustment strategy, and adjusting the camera equipment arranged in the target area in real time according to the preset adjustment strategy; shooting the target crop according to the adjusted camera equipment to obtain current growth image information of the target crop.
It can be understood that the preset adjustment strategy refers to a strategy for adjusting a lens of the camera device, and the preset adjustment strategy can be used for shooting the target crop in multiple directions to obtain current growth image information of the target crop.
In specific implementation, the yield estimation controller acquires current growth image information of a target crop and extracts target characteristic information of the current growth image information.
And step S20, searching corresponding historical growth information on a big data platform according to the target characteristic information.
It should be understood that, after the target characteristic information is obtained, the target characteristic information is divided according to the structural information of the target crop, since the target characteristic information is the characteristic information which can represent the target crop most, and the structure information refers to the structure information of each part of the target crop, for example, if the target crop is wheat, the structural information is root structural information, stem structural information, and ear structural information, searching corresponding current growth information on the big data platform according to the divided target characteristic information, wherein the current growth information at the moment is the growth information corresponding to the target characteristic information of different structure positions, and the current growth information may not be collected in the same target crop, it is necessary to match the current growth information, and screening the current growth information according to the matching result to obtain the complete historical growth information of the target crop.
In specific implementation, the yield pre-estimation controller searches corresponding historical growth information on a big data platform according to the target characteristic information.
And step S30, acquiring a preset neural network model, and acquiring a target yield estimation model according to the preset neural network model and the historical growth information.
It should be understood that the preset Neural network model refers to a Convolutional Neural network model (CNN) that includes convolution calculation and has a deep structure, and may also be other Neural network models having the same structure.
In specific implementation, the yield estimation controller obtains a preset neural network model, and obtains a target yield estimation model according to the preset neural network model and the historical growth information.
And step S40, obtaining environment image information of the target crop, and predicting the yield through the target yield prediction model according to the current growth image information and the environment image information to obtain the predicted yield of the target crop.
It should be understood that the environmental image information refers to the surrounding environment information of the target crop during the growth process, including soil information, CO2The environment image information and the current growth image information are input into a target yield estimation model after the environment image information and the current growth image information are obtained, and the target yield estimation model predicts the yield of the target crops according to the environment image information and the current growth image information to obtain the estimated yield of the target crops.
In specific implementation, the yield estimation controller obtains environment image information of the target crop, and performs yield estimation through the target yield estimation model according to the current growth image information and the environment image information to obtain the estimated yield of the target crop.
Further, in order to verify the accuracy of the target yield estimation model, after the yield estimation is performed through the target yield estimation model according to the current training data to obtain the estimated yield of the target crop, the method further includes:
acquiring the actual yield of the target crop, and calculating the fault tolerance of the target yield estimation model according to the actual yield and the estimated yield; and if the fault tolerance rate is within a preset range, estimating the yield of the target crops according to the target yield estimation model.
It can be understood that the actual yield refers to the net yield of the target crop after harvesting, and after the estimated yield and the actual yield are obtained, the fault tolerance of the target yield estimation model is calculated according to the estimated yield and the actual yield, and the specific calculation formula is as follows: the fault tolerance rate is | estimated yield-actual yield |/estimated yield 100%, the preset range refers to 0-2%, when the calculated fault tolerance rate is less than or equal to 2%, the estimation of the target crop through the target yield estimation model is qualified, and when the calculated fault tolerance rate is greater than 2%, the obtained historical growth data or the selected target area is in a problem and needs to be searched or selected again.
In the embodiment, target characteristic information of current growth image information is extracted by acquiring the current growth image information of a target crop; searching corresponding historical growth information on a big data platform according to the target characteristic information; acquiring a preset neural network model, and acquiring a target yield estimation model according to the preset neural network model and the historical growth information; the method comprises the steps of obtaining environment image information of the target crop, predicting the yield through a target yield prediction model according to the current growth image information and the environment image information, obtaining the predicted yield of the target crop, and compared with the prior art that the yield of the crop is predicted through single data measured by sensors with different functions, the method can effectively improve the accuracy of the predicted crop yield and reduce the prediction cost.
In an embodiment, as shown in fig. 3, a second embodiment of the yield prediction method based on artificial intelligence according to the present invention is proposed based on the first embodiment, and the step S10 includes:
step S101, obtaining current growth image information of a target crop, and analyzing the current growth image information to obtain corresponding pixel vector information.
It should be understood that after obtaining the current growth image information of the target crop, the pixel point and the pixel size in the current sound field image information are analyzed, and the pixel vector information is calculated according to the pixel point and the pixel size, for example, the position coordinate of the pixel point is (x, y), the pixel size is B, and the specific calculation formula is:
wherein m is the abscissa of the center point, n is the ordinate of the center point, and C is the pixel vector.
In specific implementation, the yield estimation controller acquires current growth image information of a target crop, and analyzes the current growth image information to obtain corresponding pixel vector information.
And step S102, acquiring a target clustering center, and calculating corresponding pixel block information according to the target clustering center and the pixel vector information.
It will be appreciated that the distance of adjacent pixel regions is calculated from the total number of pixels and the number of pixel regions of the currently grown image information, i.e. the distance of adjacent pixel regions
And calculating pixel block information including the size and position information of the pixel block according to the target clustering center and the pixel vector information.
In specific implementation, the yield estimation controller acquires a target clustering center, and calculates corresponding pixel block information according to the target clustering center and the pixel vector information.
And step S103, extracting target characteristic information of the current growth image information according to the pixel block information.
It should be understood that after obtaining the pixel block information, the current image information is classified to obtain pixel block information of different structure positions, and since the pixel block information of each structure position corresponds to different feature information, the feature extraction is performed on the current growth image information according to the pixel block information to obtain corresponding target feature information.
In specific implementation, the yield estimation controller extracts the target characteristic information of the current growth image information according to the pixel block information.
In the embodiment, current growth image information of a target crop is acquired and analyzed to obtain corresponding pixel vector information; acquiring a target clustering center, and calculating corresponding pixel block information according to the target clustering center and the pixel vector information; and extracting target characteristic information of the current growing image information according to the pixel block information, calculating the pixel block information through the analyzed pixel vector information and a target clustering center, and performing characteristic extraction on the current growing image information based on the pixel block information to obtain the target characteristic information, so that the accuracy of obtaining the target characteristic information can be effectively improved.
In an embodiment, as shown in fig. 4, a third embodiment of the yield prediction method based on artificial intelligence according to the present invention is proposed based on the first embodiment, and the step S40 includes:
step S401, obtaining environment image information of the target crop, and generating a current training data set according to the current growth image information and the environment image information.
It is understood that the environmental image information refers to the surrounding environment information of the target crop during the growth process, including soil information, CO2The content information, the illuminance information, the temperature information and the like of the target crop are obtained, the current growth image information and the environment image information are sorted according to a preset rule, and the sorted image information is used as a current training data set, wherein the preset rule refers to a rule of influence degrees on the growth of the target crop, and the larger the influence degree is, the closer the sorting is.
In specific implementation, the yield estimation controller acquires environment image information of the target crop, and generates a current training data set according to the current growth image information and the environment image information.
Step S402, obtaining a preset yield evaluation index, and if the index of the current training data set is larger than the preset yield evaluation index, predicting the yield through the target yield prediction model according to the current training data to obtain the predicted yield of the target crop.
It can be understood that the preset yield estimation index refers to an estimation index of the lowest yield of the target crop, after the current training data set, the index of the current training data set needs to be compared with the preset yield estimation index, if the index of the current training data set is smaller than or equal to the preset yield estimation index, the yield of the target crop is directly estimated to be a fixed value, and if the index of the current training data set is larger than the preset yield estimation index, the yield of the target crop is predicted through the target yield estimation model to obtain the corresponding estimated yield.
In specific implementation, the yield estimation controller obtains a preset yield estimation index, and if the index of the current training data set is greater than the preset yield estimation index, the yield estimation controller predicts the yield through the target yield estimation model according to the current training data to obtain the estimated yield of the target crop.
In the embodiment, a current training data set is generated according to the current growth image information and the environment image information by acquiring the environment image information of the target crop; obtaining a preset yield evaluation index, if the index of the current training data set is larger than the preset yield evaluation index, predicting the yield through the target yield prediction model according to the current training data to obtain the predicted yield of the target crop, comparing the index of the current training data set with the preset yield evaluation index, and predicting the yield of the target crop according to the comparison result, so that the accuracy of the yield of the predicted crop can be effectively improved.
In addition, an embodiment of the present invention further provides a storage medium, where an artificial intelligence based yield estimation program is stored, and when executed by a processor, the artificial intelligence based yield estimation program implements the steps of the artificial intelligence based yield estimation method described above.
Since the storage medium adopts all technical solutions of all the embodiments, at least all the beneficial effects brought by the technical solutions of the embodiments are achieved, and no further description is given here.
In addition, referring to fig. 5, an embodiment of the present invention further provides an artificial intelligence based yield estimation apparatus, where the artificial intelligence based yield estimation apparatus includes:
the extraction module 10 is configured to acquire current growth image information of a target crop, and extract target feature information of the current growth image information.
It should be understood that the current growth image information refers to image information of a target crop at a specific time during the growth process, the growth condition of the target crop can be visually observed through the current growth image information, after the current growth image information of the target crop is obtained, the most representative feature information in the current growth image information is extracted as target feature information, for example, three feature information, namely a feature information, B feature information and C feature information, are obtained by analyzing the current growth image information, where a is the feature information most representative of the target crop, and at this time, the a feature information is taken as the target feature information.
Further, in order to effectively reduce the estimated cost, before acquiring the current growth image information of the target crop and extracting the target feature information of the current growth image information, the method further includes:
selecting a target area from the areas where the target crops are planted; acquiring a preset adjustment strategy, and adjusting the camera equipment arranged in the target area in real time according to the preset adjustment strategy; shooting the target crop according to the adjusted camera equipment to obtain current growth image information of the target crop.
It can be understood that the preset adjustment strategy refers to a strategy for adjusting a lens of the camera device, and the preset adjustment strategy can be used for shooting the target crop in multiple directions to obtain current growth image information of the target crop.
In specific implementation, the yield estimation controller acquires current growth image information of a target crop and extracts target characteristic information of the current growth image information.
And the searching module 20 is configured to search corresponding historical growth information on the big data platform according to the target feature information.
It should be understood that, after the target characteristic information is obtained, the target characteristic information is divided according to the structural information of the target crop, since the target characteristic information is the characteristic information which can represent the target crop most, and the structure information refers to the structure information of each part of the target crop, for example, if the target crop is wheat, the structural information is root structural information, stem structural information, and ear structural information, searching corresponding current growth information on the big data platform according to the divided target characteristic information, wherein the current growth information at the moment is the growth information corresponding to the target characteristic information of different structure positions, and the current growth information may not be collected in the same target crop, it is necessary to match the current growth information, and screening the current growth information according to the matching result to obtain the complete historical growth information of the target crop.
In specific implementation, the yield pre-estimation controller searches corresponding historical growth information on a big data platform according to the target characteristic information.
The obtaining module 30 is configured to obtain a preset neural network model, and obtain a target yield estimation model according to the preset neural network model and the historical growth information.
It should be understood that the preset Neural network model refers to a Convolutional Neural network model (CNN) that includes convolution calculation and has a deep structure, and may also be other Neural network models having the same structure.
In specific implementation, the yield estimation controller obtains a preset neural network model, and obtains a target yield estimation model according to the preset neural network model and the historical growth information.
And the yield prediction module 40 is configured to obtain environment image information of the target crop, and perform yield prediction according to the current growth image information and the environment image information through the target yield prediction model to obtain a predicted yield of the target crop.
It should be understood that the environmental image information refers to the surrounding environment information of the target crop during the growth process, including soil information, CO2The environment image information and the current growth image information are input into a target yield estimation model after the environment image information and the current growth image information are obtained, and the target yield estimation model predicts the yield of the target crops according to the environment image information and the current growth image information to obtain the estimated yield of the target crops.
In specific implementation, the yield estimation controller obtains environment image information of the target crop, and performs yield estimation through the target yield estimation model according to the current growth image information and the environment image information to obtain the estimated yield of the target crop.
Further, in order to verify the accuracy of the target yield estimation model, after the yield estimation is performed through the target yield estimation model according to the current training data to obtain the estimated yield of the target crop, the method further includes:
acquiring the actual yield of the target crop, and calculating the fault tolerance of the target yield estimation model according to the actual yield and the estimated yield; and if the fault tolerance rate is within a preset range, estimating the yield of the target crops according to the target yield estimation model.
It can be understood that the actual yield refers to the net yield of the target crop after harvesting, and after the estimated yield and the actual yield are obtained, the fault tolerance of the target yield estimation model is calculated according to the estimated yield and the actual yield, and the specific calculation formula is as follows: the fault tolerance rate is | estimated yield-actual yield |/estimated yield 100%, the preset range refers to 0-2%, when the calculated fault tolerance rate is less than or equal to 2%, the estimation of the target crop through the target yield estimation model is qualified, and when the calculated fault tolerance rate is greater than 2%, the obtained historical growth data or the selected target area is in a problem and needs to be searched or selected again.
In the embodiment, target characteristic information of current growth image information is extracted by acquiring the current growth image information of a target crop; searching corresponding historical growth information on a big data platform according to the target characteristic information; acquiring a preset neural network model, and acquiring a target yield estimation model according to the preset neural network model and the historical growth information; the method comprises the steps of obtaining environment image information of the target crop, predicting the yield through a target yield prediction model according to the current growth image information and the environment image information, obtaining the predicted yield of the target crop, and compared with the prior art that the yield of the crop is predicted through single data measured by sensors with different functions, the method can effectively improve the accuracy of the predicted crop yield and reduce the prediction cost.
It should be noted that the above-described work flows are only exemplary, and do not limit the scope of the present invention, and in practical applications, a person skilled in the art may select some or all of them to achieve the purpose of the solution of the embodiment according to actual needs, and the present invention is not limited herein.
In addition, the technical details that are not described in detail in this embodiment can be referred to the yield estimation method based on artificial intelligence provided in any embodiment of the present invention, and are not described herein again.
In an embodiment, the extraction module 10 is further configured to select a target area from the areas where the target crop is planted; acquiring a preset adjustment strategy, and adjusting the camera equipment arranged in the target area in real time according to the preset adjustment strategy; shooting the target crop according to the adjusted camera equipment to obtain current growth image information of the target crop.
In an embodiment, the extraction module 10 is further configured to obtain current growth image information of a target crop, and analyze the current growth image information to obtain corresponding pixel vector information; acquiring a target clustering center, and calculating corresponding pixel block information according to the target clustering center and the pixel vector information; and extracting the target characteristic information of the current growth image information according to the pixel block information.
In an embodiment, the search module 20 is further configured to obtain structural information of the target crop, and divide the target characteristic information according to the structural information; respectively searching corresponding current growth information on a big data platform according to the divided target characteristic information; and matching the current growth information, and obtaining corresponding historical growth information according to a matching result.
In an embodiment, the searching module 20 is further configured to match the current growth information to obtain a corresponding matching result; screening the successfully matched current growth information in the matching result according to the structural information of the target crop to obtain target growth information; and traversing and combining the target growth information to obtain corresponding historical growth information.
In an embodiment, the yield prediction module 40 is further configured to obtain environment image information of the target crop, and generate a current training data set according to the current growth image information and the environment image information; and acquiring a preset yield evaluation index, and if the index of the current training data set is larger than the preset yield evaluation index, predicting the yield through the target yield prediction model according to the current training data to obtain the predicted yield of the target crops.
In an embodiment, the yield prediction module 40 is further configured to obtain an actual yield of the target crop, and calculate a fault tolerance of the target yield prediction model according to the actual yield and the predicted yield; and if the fault tolerance rate is within a preset range, estimating the yield of the target crops according to the target yield estimation model.
Other embodiments or implementations of the artificial intelligence based yield estimation apparatus of the present invention are described with reference to the above method embodiments, and are not intended to be exhaustive.
Further, it is to be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention or portions thereof that contribute to the prior art may be embodied in the form of a software product, where the computer software product is stored in a storage medium (e.g. Read Only Memory (ROM)/RAM, magnetic disk, optical disk), and includes several instructions for enabling a terminal device (e.g. a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110616657.0A CN113408374B (en) | 2021-06-02 | 2021-06-02 | Yield estimation method, device, equipment and storage medium based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110616657.0A CN113408374B (en) | 2021-06-02 | 2021-06-02 | Yield estimation method, device, equipment and storage medium based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113408374A true CN113408374A (en) | 2021-09-17 |
| CN113408374B CN113408374B (en) | 2022-09-23 |
Family
ID=77676020
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110616657.0A Active CN113408374B (en) | 2021-06-02 | 2021-06-02 | Yield estimation method, device, equipment and storage medium based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113408374B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114723744A (en) * | 2022-05-16 | 2022-07-08 | 安徽国祯生态科技有限公司 | Straw intelligent storage system based on image recognition |
| CN115965161A (en) * | 2023-02-14 | 2023-04-14 | 联通(四川)产业互联网有限公司 | Crop yield prediction method based on artificial intelligence and historical data |
| CN118246606A (en) * | 2024-05-21 | 2024-06-25 | 北京佳格天地科技有限公司 | Crop yield prediction method, system and storage medium based on artificial intelligence |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101968780A (en) * | 2010-09-28 | 2011-02-09 | 天津大学 | Nonparametric regression method |
| US20160171680A1 (en) * | 2014-12-16 | 2016-06-16 | The Board of Trustees of the Land Stanford Junior University | Systems and Methods for Satellite Image Processing to Estimate Crop Yield |
| CN109508824A (en) * | 2018-11-07 | 2019-03-22 | 西京学院 | A kind of detection of crop growth situation and yield predictor method |
| CN109583301A (en) * | 2018-10-29 | 2019-04-05 | 广东奥博信息产业股份有限公司 | A kind of optimal external planting conditions prediction technique of plant growing process and device |
| CN111191791A (en) * | 2019-12-02 | 2020-05-22 | 腾讯云计算（北京）有限责任公司 | Application method, training method, device, equipment and medium of machine learning model |
| CN111260496A (en) * | 2020-02-03 | 2020-06-09 | 中国农业大学 | Livestock and poultry monitoring method and system |
| WO2020132092A1 (en) * | 2018-12-19 | 2020-06-25 | The Board Of Trustees Of The University Of Illinois | Apparatus and method for crop yield prediction |
| CN111461435A (en) * | 2020-04-01 | 2020-07-28 | 中国农业科学院农业信息研究所 | Crop yield prediction method and system |
| CN111985724A (en) * | 2020-08-28 | 2020-11-24 | 深圳前海微众银行股份有限公司 | A method, device, equipment and storage medium for crop yield estimation |
| CN112418473A (en) * | 2019-08-20 | 2021-02-26 | 阿里巴巴集团控股有限公司 | Crop information processing method, device, equipment and computer storage medium |
| CN112489049A (en) * | 2020-12-04 | 2021-03-12 | 山东大学 | Mature tomato fruit segmentation method and system based on superpixels and SVM |
-
2021
- 2021-06-02 CN CN202110616657.0A patent/CN113408374B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101968780A (en) * | 2010-09-28 | 2011-02-09 | 天津大学 | Nonparametric regression method |
| US20160171680A1 (en) * | 2014-12-16 | 2016-06-16 | The Board of Trustees of the Land Stanford Junior University | Systems and Methods for Satellite Image Processing to Estimate Crop Yield |
| CN109583301A (en) * | 2018-10-29 | 2019-04-05 | 广东奥博信息产业股份有限公司 | A kind of optimal external planting conditions prediction technique of plant growing process and device |
| CN109508824A (en) * | 2018-11-07 | 2019-03-22 | 西京学院 | A kind of detection of crop growth situation and yield predictor method |
| WO2020132092A1 (en) * | 2018-12-19 | 2020-06-25 | The Board Of Trustees Of The University Of Illinois | Apparatus and method for crop yield prediction |
| CN112418473A (en) * | 2019-08-20 | 2021-02-26 | 阿里巴巴集团控股有限公司 | Crop information processing method, device, equipment and computer storage medium |
| CN111191791A (en) * | 2019-12-02 | 2020-05-22 | 腾讯云计算（北京）有限责任公司 | Application method, training method, device, equipment and medium of machine learning model |
| CN111260496A (en) * | 2020-02-03 | 2020-06-09 | 中国农业大学 | Livestock and poultry monitoring method and system |
| CN111461435A (en) * | 2020-04-01 | 2020-07-28 | 中国农业科学院农业信息研究所 | Crop yield prediction method and system |
| CN111985724A (en) * | 2020-08-28 | 2020-11-24 | 深圳前海微众银行股份有限公司 | A method, device, equipment and storage medium for crop yield estimation |
| CN112489049A (en) * | 2020-12-04 | 2021-03-12 | 山东大学 | Mature tomato fruit segmentation method and system based on superpixels and SVM |
Non-Patent Citations (3)
| Title |
|---|
| MAITINIYAZI MAIMAITIJIANG等: "Soybean yield prediction from UAV using multimodal data fusion and deep learning", 《REMOTE SENSING OF ENVIRONMENT》 * |
| 周元琦等: "基于无人机RGB图像颜色及纹理特征指数的小麦产量预测", 《扬州大学学报（农业与生命科学版）》 * |
| 王有宁等: "HJ-1星CCD数据多次分类反演夏收作物油菜与小麦的空间分布", 《江苏农业科学》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114723744A (en) * | 2022-05-16 | 2022-07-08 | 安徽国祯生态科技有限公司 | Straw intelligent storage system based on image recognition |
| CN115965161A (en) * | 2023-02-14 | 2023-04-14 | 联通(四川)产业互联网有限公司 | Crop yield prediction method based on artificial intelligence and historical data |
| CN115965161B (en) * | 2023-02-14 | 2023-06-13 | 联通(四川)产业互联网有限公司 | Crop yield prediction method based on artificial intelligence and historical data |
| CN118246606A (en) * | 2024-05-21 | 2024-06-25 | 北京佳格天地科技有限公司 | Crop yield prediction method, system and storage medium based on artificial intelligence |
| CN118246606B (en) * | 2024-05-21 | 2024-08-06 | 北京佳格天地科技有限公司 | Crop yield prediction method, system and storage medium based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113408374B (en) | 2022-09-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tetila et al. | A deep-learning approach for automatic counting of soybean insect pests | |
| CN112257603B (en) | Hyperspectral image classification method and related equipment | |
| CN113408374A (en) | Yield estimation method, device and equipment based on artificial intelligence and storage medium | |
| CN112560876A (en) | Single-stage small sample target detection method for decoupling measurement | |
| JP2023504624A (en) | Systems and methods for identifying crop damage | |
| CN110765882B (en) | Video tag determination method, device, server and storage medium | |
| CN111325381A (en) | A multi-source heterogeneous farmland big data yield prediction method, system and device | |
| Patel et al. | Deep learning-based plant organ segmentation and phenotyping of sorghum plants using LiDAR point cloud | |
| Kini et al. | Early stage black pepper leaf disease prediction based on transfer learning using ConvNets | |
| CN107180245A (en) | A kind of indoor and outdoor scene recognition method and device | |
| CN113361194A (en) | Sensor drift calibration method based on deep learning, electronic equipment and storage medium | |
| CN117710833A (en) | Mapping geographic information data acquisition method and related device based on cloud computing | |
| Nakajima et al. | Biomass estimation of World rice (Oryza sativa L.) core collection based on the convolutional neural network and digital images of canopy | |
| Megalingam et al. | Coconut trees classification based on height, inclination, and orientation using MIN-SVM algorithm | |
| Banoth et al. | Soil image classification using transfer learning approach: MobileNetV2 with CNN | |
| Prashar et al. | Plant disease detection using deep learning (convolutional neural networks) | |
| CN117058498B (en) | Training method of segmentation map evaluation model, and segmentation map evaluation method and device | |
| CN117475477A (en) | Insect identification methods, electronic devices and storage media | |
| Xie et al. | Multi-Scale and Multi-Factor ViT Attention Model for Classification and Detection of Pest and Disease in Agriculture. | |
| CN116952853A (en) | Agricultural monitoring system for monitoring pasture quality | |
| CN116484193A (en) | Crop yield prediction method, system, equipment and medium | |
| Chakravarty et al. | Deep Learning Approach to Sugarcane Disease Identification: From Image Analysis to Mobile Application | |
| Singh et al. | 3D-CTM: Unsupervised crop type mapping based on 3D convolutional autoencoder and satellite image time series | |
| Stanski et al. | Flower detection using object analysis: new ways to quantify plant phenology in a warming tundra biome | |
| Pawar et al. | Detection of leaf diseases for multiple plants using convolutional neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |