CN110751035A - Seed corn production identification method and device - Google Patents
Seed corn production identification method and device Download PDFInfo
- Publication number
- CN110751035A CN110751035A CN201910872912.0A CN201910872912A CN110751035A CN 110751035 A CN110751035 A CN 110751035A CN 201910872912 A CN201910872912 A CN 201910872912A CN 110751035 A CN110751035 A CN 110751035A
- Authority
- CN
- China
- Prior art keywords
- sample
- seed production
- vegetation index
- corn
- information
- 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.)
- Pending
Links
- 240000008042 Zea mays Species 0.000 title claims abstract description 134
- 235000002017 Zea mays subsp mays Nutrition 0.000 title claims abstract description 134
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 title claims abstract description 123
- 235000005822 corn Nutrition 0.000 title claims abstract description 123
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 115
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000013526 transfer learning Methods 0.000 claims abstract description 46
- 238000013145 classification model Methods 0.000 claims abstract description 42
- 238000012549 training Methods 0.000 claims abstract description 29
- 238000005070 sampling Methods 0.000 claims description 13
- 235000016383 Zea mays subsp huehuetenangensis Nutrition 0.000 claims description 11
- 235000009973 maize Nutrition 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000007637 random forest analysis Methods 0.000 claims description 6
- 230000003595 spectral effect Effects 0.000 claims description 6
- 230000015572 biosynthetic process Effects 0.000 claims description 5
- 238000003786 synthesis reaction Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 4
- 230000005855 radiation Effects 0.000 claims description 4
- 238000001228 spectrum Methods 0.000 claims description 3
- 239000000463 material Substances 0.000 abstract description 5
- 238000004891 communication Methods 0.000 description 5
- 238000011835 investigation Methods 0.000 description 5
- 238000013508 migration Methods 0.000 description 4
- 230000005012 migration Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000003066 decision tree Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000010219 correlation analysis Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 208000003643 Callosities Diseases 0.000 description 1
- 206010020649 Hyperkeratosis Diseases 0.000 description 1
- 208000027066 STING-associated vasculopathy with onset in infancy Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013138 pruning Methods 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
-
- 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
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention provides a method and a device for identifying seed corn, wherein the method comprises the following steps: acquiring a vegetation index characteristic set of the corn to be inspected; inputting the vegetation index characteristic set of the seed production corn to be inspected into a preset seed production corn identification classification model based on transfer learning to obtain identification result information; the preset seed production corn identification classification model based on the transfer learning is obtained based on sample seed production corn vegetation index feature set and sample ground reference data set training. The method has the advantages that the seed production corn vegetation index of the to-be-inspected land is directly identified through the preset seed production corn identification classification model based on the transfer learning, the seed production corn vegetation index characteristic set to be inspected can be effectively classified through the preset seed production corn identification classification model based on the transfer learning in the transfer learning idea, the sample utilization efficiency is improved, and the consumption of manpower and material resources is effectively reduced.
Description
Technical Field
The invention relates to the technical field of crop identification, in particular to a seed corn identification method and device.
Background
With the development of modern agriculture, the accurate supervision on crop seed production is very important, the seed production area of crops is accurately mastered, and the seed production area which is abused in private and numerous is found in time, so that the method is a requirement for the development of modern agriculture and is also a foundation for ensuring the seed supply safety.
In the prior art, for the identification of seed production corns, crop remote sensing data is obtained for crops in an investigation place through remote sensing images, crop sample data is physically investigated, crop classification results are judged manually, then manual investigation and step-by-step reporting are carried out, only the identification of the crops in the investigation place can be realized, and the crop classification results of non-investigation places cannot be obtained.
At present, how to realize classification and identification of non-investigated crops has become an urgent problem to be solved in the industry.
Disclosure of Invention
The embodiment of the invention provides a method and a device for identifying seed corn, which are used for solving the technical problems in the background art or at least partially solving the technical problems in the background art.
In a first aspect, an embodiment of the present invention provides a method for identifying seed corn, including:
acquiring a vegetation index characteristic set of the corn to be inspected;
inputting the vegetation index characteristic set of the seed production corn to be inspected into a preset seed production corn identification classification model based on transfer learning to obtain identification result information;
the preset seed production corn identification classification model based on the transfer learning is obtained based on sample seed production corn vegetation index feature set and sample ground reference data set training.
More specifically, before the step of inputting the vegetation index feature set of the seed production corn to be examined into a preset seed production corn identification and classification model based on transfer learning, the method further comprises the following steps:
acquiring a sample seed production corn vegetation index feature set and a sample ground reference data set;
sampling the corn vegetation index characteristic set row of the sample seed production in a replaced random sampling mode, and sampling the ground reference data set column of the sample to obtain a sample training set;
and inputting the sample training set into a preset random forest network for model training, and obtaining a preset seed production corn identification classification model based on transfer learning when a preset condition is met.
Prior to the step of obtaining a sample seed corn vegetation index signature set and a sample ground reference data set, the method further comprises:
acquiring multi-time-phase remote sensing image information of a first sample area and multi-time-phase remote sensing image information of an area to be inspected, and determining second sample multi-time-phase remote sensing image information according to the first sample area multi-time-phase remote sensing image information and the area to be inspected multi-time-phase remote sensing image information;
extracting a time sequence spectrum characteristic curve of each time phase sample according to the second sample multi-time phase remote sensing image information;
obtaining vegetation index information of each sample of each time phase according to the time sequence spectral characteristic curve of each time phase sample, and determining vegetation index correlation information of each time phase according to the vegetation index information of each sample of each time phase;
selecting target vegetation index information of each time phase according to the vegetation index correlation information of each time phase;
and carrying out wave band synthesis according to the target vegetation index information of a plurality of time phases to obtain a sample seed production corn vegetation index characteristic set.
More specifically, the step of obtaining the multi-temporal remote sensing image information of the first sample area and the multi-temporal remote sensing image information of the area to be observed specifically includes:
acquiring multi-time-phase initial remote sensing image information of a sample area and multi-time-phase initial remote sensing image information of an area to be inspected;
respectively carrying out information preprocessing on the multi-temporal initial remote sensing image information of the sample area and the multi-temporal initial remote sensing image information of the area to be inspected to obtain the multi-temporal remote sensing image information of the first sample area and the multi-temporal remote sensing image information of the area to be inspected;
the information preprocessing specifically comprises radiation correction processing, orthorectification processing and image registration processing.
More specifically, the sample ground reference dataset specifically includes: crop type information, crop growth condition information, crop seed production castration time information, sample plot area information and sample geographic coordinate information.
More specifically, the determining the vegetation index correlation information of each time phase according to the sample vegetation index information of each time phase specifically includes:
wherein r isxyIs the correlation information between the x and y features,
and
are the mean of the x and y features, xiAnd yiX and y, respectively, of the ith feature, n being the number of samples.
In a second aspect, an embodiment of the present invention provides an identification apparatus for seed corn, including:
the acquisition module is used for acquiring a seed production corn vegetation index characteristic set to be examined;
the identification module is used for inputting the vegetation index characteristic set of the seed production corn to be examined into a preset seed production corn identification classification model based on transfer learning to obtain identification result information;
the preset seed production corn identification classification model based on the transfer learning is obtained based on sample seed production corn vegetation index feature set and sample ground reference data set training.
In a third aspect, an embodiment of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, the steps of the method for identifying corn seeds according to the first aspect are implemented.
In a fourth aspect, the present invention provides a non-transitory computer readable storage medium, on which a computer program is stored, the computer program, when executed by a processor, implementing the steps of the identification method for producing corn according to the first aspect.
According to the seed corn identification method and device provided by the embodiment of the invention, the seed corn vegetation index of a to-be-inspected land is directly identified through the preset seed corn identification classification model based on the transfer learning to obtain the identification classification result, the preset seed corn identification classification model based on the transfer learning is obtained by inputting the sample seed corn vegetation index feature set of a sample area and the sample ground reference data set into a random forest algorithm, and the seed corn vegetation index feature set of the to-be-inspected land can be effectively classified through the preset seed corn identification classification model based on the transfer learning in the transfer learning idea, so that the sample utilization efficiency is improved, and the consumption of manpower and material resources is effectively reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for identifying maize seeds of the invention according to an embodiment of the invention;
FIG. 2 is a schematic structural diagram of an apparatus for identifying corn seeds according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The vegetation index described in the embodiment of the invention specifically refers to an index which quantitatively reflects the conditions of vegetation soil background, growth and development and the like under a certain condition according to the spectral reflection characteristic of vegetation, and the vegetation index is widely used for qualitative and quantitative evaluation of vegetation coverage and growth vigor in the field of remote sensing technology application.
Fig. 1 is a schematic flow chart of a method for identifying maize for seed production described in an embodiment of the present invention, as shown in fig. 1, including:
s1, acquiring a seed production corn vegetation index feature set to be inspected;
step S2, inputting the vegetation index feature set of the seed production corn to be inspected into a preset seed production corn identification classification model based on transfer learning to obtain identification result information;
the preset seed production corn identification classification model based on the transfer learning is obtained based on sample seed production corn vegetation index feature set and sample ground reference data set training.
Step 1 is that the step of obtaining a seed production corn vegetation index feature set to be examined described in the embodiments of the present invention specifically means obtaining initial remote sensing image information of a region to be examined and performing information preprocessing on the initial remote sensing image information to obtain multi-temporal remote sensing image information of the region to be examined; determining the sum of the multi-temporal remote sensing image information of the area to be inspected and the date of the multi-temporal remote sensing image information of the sample area, and calculating the multi-temporal remote sensing image information corresponding to the date of the sum;
extracting time sequence spectral characteristic curve of each time phase sample according to multi-time phase remote sensing image information corresponding to the merging date, obtaining vegetation index information of each time phase sample according to the time sequence spectral characteristic curve of each time phase sample, determining vegetation index correlation information of each time phase according to the vegetation index information of each time phase sample,
the correlation coefficient is calculated using the following formula:
wherein r isxyIs the correlation information between the x and y features,
and
are the mean of the x and y features, xiAnd yiX and y for the ith feature, respectively, and n is the number of samples. Wherein the value range of the correlation coefficient is [ -1,1],rxyThe larger the absolute value of (a), the stronger the correlation between x and y, and screening k vegetation indexes according to the correlation, wherein the screening principle is that if the absolute value of a correlation coefficient between two different vegetation indexes is 1, only one vegetation index is selected.
The method comprises the steps of selecting target vegetation index information of each time phase according to the vegetation index correlation information of each time phase, creating a multiband time sequence grid data set through single-waveband images of the time phases according to the target vegetation index information of the time phases, and obtaining a sample seed production corn vegetation index characteristic set according to the grid data set.
The step S2 specifically is that the preset seed production corn identification classification model based on transfer learning described in the embodiment of the present invention uses a sample seed production corn vegetation index feature set and a sample ground reference data set as training samples, performs line sampling on the sample seed production corn vegetation index feature set in a replaced random sampling manner, and performs column sampling on the sample ground reference data set to obtain a sample training set.
Based on a sample training set, a plurality of weak classifier CART decision trees are constructed, when elements are sampled randomly, the square root of the total number of features is taken as the feature number, the maximum depth represents that the CART decision trees are not separable, and when the nodes only have the same ground object type, the splitting is finished, and the value is 0. The random seed is the minimum sample number of a leaf node, is used for judging whether the weak classifier CART decision tree needs pruning, and is usually selected to be 1. And training the seed production corn identification classification model, and obtaining the preset seed production corn identification classification model based on transfer learning when the preset conditions are met.
The preset condition described in the embodiment of the present invention may be a preset number of times of training or a preset training time.
The migration learning described in the embodiment of the invention refers to the application of learned knowledge or trained models to other related problems to be solved, existing samples are migrated to a similar ecological area for crop mapping, the features learned from a reference area are migrated to a target area, direct push migration with the same source task and target task but different domains is realized, and the identification of the corn for seed production in an unexplored area is realized.
The method and the device have the advantages that the vegetation index of the corn for seed production to be inspected is directly identified through the preset corn for seed production identification classification model based on the transfer learning, so that the identification classification result is obtained, the preset corn for seed production identification classification model based on the transfer learning is obtained by inputting the corn for seed production vegetation index characteristic set of the sample area and the ground reference data set of the sample into a random forest algorithm, the corn for seed production vegetation index characteristic set to be inspected can be effectively classified through the preset corn for seed production identification classification model based on the transfer learning through the transfer learning idea, the sample utilization efficiency is improved, and the consumption of manpower and material resources is effectively reduced.
On the basis of the embodiment, before the step of inputting the vegetation index feature set of the seed production corn to be examined into a preset seed production corn identification and classification model based on transfer learning, the method further comprises the following steps:
acquiring a sample seed production corn vegetation index feature set and a sample ground reference data set;
sampling the corn vegetation index characteristic set row of the sample seed production in a replaced random sampling mode, and sampling the ground reference data set column of the sample to obtain a sample training set;
and inputting the sample training set into a preset random forest network for model training, and obtaining a preset seed production corn identification classification model based on transfer learning when a preset condition is met.
The replaced random sampling mode described in the embodiment of the invention refers to a collection mode in which a collected sample is replaced to the original position after the sample is collected.
The training samples collected in the embodiment of the invention are all data in the input sample seed production corn vegetation index feature set.
The preset condition described in the embodiment of the present invention may be a preset number of times of training or a preset training time.
The preset seed production corn identification classification model based on the transfer learning described in the embodiment of the invention specifically refers to the preset seed production corn identification classification model after the training is completed, the existing samples are transferred to a similar ecological region for crop mapping based on the transfer learning mode, the characteristics learned from a reference region are transferred to a target region, and the direct push type transfer with the same source task and the target task but different domains is realized.
The method for seed production of corn is discovered based on sample cross-space transfer learning, accurate seed production of corn identification can be carried out on a seed production corn field without an investigation place, and an effective method is provided for discovering the private reproduction and the abusing of the seed production of corn. The method for producing the corn based on the sample cross-space migration learning discovery can effectively expand the space utilization range of the sample, improve the utilization efficiency of the sample and reduce the consumption of manpower and material resources.
On the basis of the above embodiment, before the step of obtaining the sample seed production corn vegetation index feature set and the sample ground reference data set, the method further comprises:
acquiring multi-temporal remote sensing image information of a first sample area and multi-temporal remote sensing image information of an area to be inspected, and determining multi-temporal remote sensing image information of a second sample according to the multi-temporal remote sensing image information of the sample area and the multi-temporal remote sensing image information of the area to be inspected;
extracting a time sequence spectrum characteristic curve of each time phase sample according to the second sample multi-time phase remote sensing image information;
obtaining vegetation index information of each sample of each time phase according to the time sequence spectral characteristic curve of each time phase sample, and determining vegetation index correlation information of each time phase according to the vegetation index information of each sample of each time phase;
selecting target vegetation index information of each time phase according to the vegetation index correlation information of each time phase;
and carrying out wave band synthesis according to the target vegetation index information of a plurality of time phases to obtain a sample seed production corn vegetation index characteristic set.
The vegetation index information of each sample described in the embodiment of the invention specifically includes n vegetation indexes such as NDVI, EVI, TVI, RVI, NDWI, DVI, GNDVI, SAVI and the like.
The selecting of the target vegetation index information of each time phase according to the vegetation index correlation information of each time phase described in the embodiment of the invention specifically comprises sorting the vegetation index correlation information of each time phase, and selecting k pieces of target vegetation index information from the vegetation indexes in n of each time phase according to a sorting result; if the absolute value of the correlation coefficient between two different vegetation indexes is 1, only one vegetation index is selected.
The band synthesis of the target vegetation index information of multiple time phases described in the embodiment of the invention specifically means that a multiband time sequence grid data set is created from the target vegetation index information of multiple time phases, namely single-band images of multiple time phases, and the band synthesis is carried out to obtain a sample seed production corn vegetation index feature set.
According to the embodiment of the invention, the calculation efficiency is improved by reducing data redundancy, and the appropriate target vegetation index is screened out according to the correlation analysis. Meanwhile, according to the migration learning method principle, when the remote sensing image date is selected, a union of the regional multi-temporal remote sensing image information and the regional multi-temporal remote sensing image information to be examined is obtained, and then sample image features corresponding to the union date are calculated, so that the subsequent steps can be favorably carried out.
On the basis of the above embodiment, the step of obtaining the multi-temporal remote sensing image information of the first sample area and the multi-temporal remote sensing image information of the area to be observed specifically includes:
acquiring multi-time-phase initial remote sensing image information of a sample area and multi-time-phase initial remote sensing image information of an area to be inspected;
respectively carrying out information preprocessing on the multi-temporal initial remote sensing image information of the sample area and the multi-temporal initial remote sensing image information of the area to be inspected to obtain the multi-temporal remote sensing image information of the first sample area and the multi-temporal remote sensing image information of the area to be inspected;
the information preprocessing specifically comprises radiation correction processing, orthorectification processing and image registration processing.
The sample region multi-temporal initial remote sensing image information described in the embodiment of the invention can be acquired through an internet remote sensing data sharing website.
The radiation correction process, the orthorectification process, and the image registration process described in the embodiments of the present invention may be implemented by the ENVI platform.
The embodiment of the invention effectively eliminates the influence of sunlight, atmosphere and other environments received by the remote sensing image in the imaging process by respectively carrying out information preprocessing on the multi-time-phase initial remote sensing image information of the sample area and the multi-time-phase initial remote sensing image information of the area to be observed, ensures the reliability of the remote sensing image and is beneficial to the implementation of subsequent steps.
On the basis of the above embodiment, the sample ground reference data set specifically includes: crop type information, crop growth condition information, crop seed production castration time information, sample plot area information and sample geographic coordinate information.
On the basis of the above embodiment, the determining vegetation index correlation information of each time phase according to the sample vegetation index information of each time phase specifically includes:
wherein r isxyIs the correlation information between the x and y features,
and
are the mean of the x and y features, xiAnd yiX and y, respectively, of the ith feature, n being the number of samples.
Specifically, in the embodiment of the present invention, vegetation index correlation information of each time phase is determined, and the correlation information is sorted, where a value range of the correlation information is [ -1,1 [ ]],rxyThe larger the absolute value of the index is, the stronger the correlation between x and y is, and k vegetation indexes are screened out according to the correlation sorting; if the absolute value of the correlation coefficient between two different vegetation indexes is 1, only one vegetation index is selected.
According to the embodiment of the invention, the data redundancy is reduced, the calculation efficiency is improved, and the proper target vegetation index is screened out according to the correlation analysis, so that the subsequent steps can be favorably carried out.
FIG. 2 is a schematic view of a corn seed production identification device according to an embodiment of the present invention, e.g.
Shown in fig. 2, includes: an acquisition module 210 and an identification module 220; the obtaining module 210 is configured to obtain a seed production corn vegetation index feature set to be examined; the identification module 220 is configured to input the seed production corn vegetation index feature set to be examined into a preset seed production corn identification classification model based on transfer learning to obtain identification result information;
the preset seed production corn identification classification model based on the transfer learning is obtained based on sample seed production corn vegetation index feature set and sample ground reference data set training.
The apparatus provided in the embodiment of the present invention is used for executing the above method embodiments, and for details of the process and the details, reference is made to the above embodiments, which are not described herein again.
The method and the device have the advantages that the vegetation index of the corn for seed production to be inspected is directly identified through the preset corn for seed production identification classification model based on the transfer learning, so that the identification classification result is obtained, the preset corn for seed production identification classification model based on the transfer learning is obtained by inputting the corn for seed production vegetation index characteristic set of the sample area and the ground reference data set of the sample into a random forest algorithm, the corn for seed production vegetation index characteristic set to be inspected can be effectively classified through the preset corn for seed production identification classification model based on the transfer learning through the transfer learning idea, the sample utilization efficiency is improved, and the consumption of manpower and material resources is effectively reduced.
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 3, the electronic device may include: a processor (processor)310, a communication Interface (communication Interface)320, a memory (memory)330 and a communication bus 340, wherein the processor 310, the communication Interface 320 and the memory 330 communicate with each other via the communication bus 340. The processor 310 may call logic instructions in the memory 330 to perform the following method: acquiring a vegetation index characteristic set of the corn to be inspected; inputting the vegetation index characteristic set of the seed production corn to be inspected into a preset seed production corn identification classification model based on transfer learning to obtain identification result information; the preset seed production corn identification classification model based on the transfer learning is obtained based on sample seed production corn vegetation index feature set and sample ground reference data set training.
In addition, the logic instructions in the memory 330 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
An embodiment of the present invention discloses a computer program product, which includes a computer program stored on a non-transitory computer readable storage medium, the computer program including program instructions, when the program instructions are executed by a computer, the computer can execute the methods provided by the above method embodiments, for example, the method includes: acquiring a vegetation index characteristic set of the corn to be inspected; inputting the vegetation index characteristic set of the seed production corn to be inspected into a preset seed production corn identification classification model based on transfer learning to obtain identification result information; the preset seed production corn identification classification model based on the transfer learning is obtained based on sample seed production corn vegetation index feature set and sample ground reference data set training.
Embodiments of the present invention provide a non-transitory computer-readable storage medium storing server instructions, where the server instructions cause a computer to execute the method provided in the foregoing embodiments, for example, the method includes: acquiring a vegetation index characteristic set of the corn to be inspected; inputting the vegetation index characteristic set of the seed production corn to be inspected into a preset seed production corn identification classification model based on transfer learning to obtain identification result information; the preset seed production corn identification classification model based on the transfer learning is obtained based on sample seed production corn vegetation index feature set and sample ground reference data set training.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (9)
1. A method for identifying seed corn, comprising:
acquiring a vegetation index characteristic set of the corn to be inspected;
inputting the vegetation index characteristic set of the seed production corn to be inspected into a preset seed production corn identification classification model based on transfer learning to obtain identification result information;
the preset seed production corn identification classification model based on the transfer learning is obtained based on sample seed production corn vegetation index feature set and sample ground reference data set training.
2. The method for identifying maize for seed production according to claim 1, wherein before the step of inputting the vegetation index feature set of the maize for seed production to be examined into a preset maize for seed production identification classification model based on transfer learning, the method further comprises:
acquiring a sample seed production corn vegetation index feature set and a sample ground reference data set;
sampling the corn vegetation index characteristic set row of the sample seed production in a replaced random sampling mode, and sampling the ground reference data set column of the sample to obtain a sample training set;
and inputting the sample training set into a preset random forest network for model training, and obtaining a preset seed production corn identification classification model based on transfer learning when a preset condition is met.
3. The method for identifying maize as seed production according to claim 2, wherein prior to the step of obtaining the sample maize seed production vegetation index signature set and the sample ground reference data set, the method further comprises:
acquiring multi-time-phase remote sensing image information of a first sample area and multi-time-phase remote sensing image information of an area to be inspected, and determining second sample multi-time-phase remote sensing image information according to the first sample area multi-time-phase remote sensing image information and the area to be inspected multi-time-phase remote sensing image information;
extracting a time sequence spectrum characteristic curve of each time phase sample according to the second sample multi-time phase remote sensing image information;
obtaining vegetation index information of each sample of each time phase according to the time sequence spectral characteristic curve of each time phase sample, and determining vegetation index correlation information of each time phase according to the vegetation index information of each sample of each time phase;
selecting target vegetation index information of each time phase according to the vegetation index correlation information of each time phase;
and carrying out wave band synthesis according to the target vegetation index information of a plurality of time phases to obtain a sample seed production corn vegetation index characteristic set.
4. The method for identifying corn seeds production according to claim 3, wherein the step of obtaining the multi-temporal remote sensing image information of the first sample area and the multi-temporal remote sensing image information of the area to be inspected specifically comprises:
acquiring multi-time-phase initial remote sensing image information of a sample area and multi-time-phase initial remote sensing image information of an area to be inspected;
respectively carrying out information preprocessing on the multi-temporal initial remote sensing image information of the sample area and the multi-temporal initial remote sensing image information of the area to be inspected to obtain the multi-temporal remote sensing image information of the first sample area and the multi-temporal remote sensing image information of the area to be inspected;
the information preprocessing specifically comprises radiation correction processing, orthorectification processing and image registration processing.
5. The method for identifying maize for seed production according to claim 2, wherein the sample ground reference dataset specifically comprises: crop type information, crop growth condition information, crop seed production castration time information, sample plot area information and sample geographic coordinate information.
6. The method for identifying maize for seed production according to claim 3, wherein the determining the vegetation index correlation information of each time phase according to the sample vegetation index information of each time phase specifically comprises:
wherein r isxyIs the correlation information between the x and y features,
andare the mean of the x and y features, xiAnd yiX and y, respectively, of the ith feature, n being the number of samples.
7. An identification device for corn production, comprising:
the acquisition module is used for acquiring a seed production corn vegetation index characteristic set to be examined;
the identification module is used for inputting the vegetation index characteristic set of the seed production corn to be examined into a preset seed production corn identification classification model based on transfer learning to obtain identification result information;
the preset seed production corn identification classification model based on the transfer learning is obtained based on sample seed production corn vegetation index feature set and sample ground reference data set training.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program performs the steps of the method for identifying maize as claimed in any one of claims 1 to 6.
9. A non-transitory computer readable storage medium, having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method for identifying maize as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910872912.0A CN110751035A (en) | 2019-09-16 | 2019-09-16 | Seed corn production identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910872912.0A CN110751035A (en) | 2019-09-16 | 2019-09-16 | Seed corn production identification method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110751035A true CN110751035A (en) | 2020-02-04 |
Family
ID=69276507
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910872912.0A Pending CN110751035A (en) | 2019-09-16 | 2019-09-16 | Seed corn production identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110751035A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111414863A (en) * | 2020-03-23 | 2020-07-14 | 国家海洋信息中心 | Enhanced integrated remote sensing image classification method |
| CN113807219A (en) * | 2021-09-06 | 2021-12-17 | 苏州中科蓝迪软件技术有限公司 | Method for identifying types of grain and oil crops in planting land by steps |
| CN114202691A (en) * | 2021-12-09 | 2022-03-18 | 广东省科学院广州地理研究所 | Rice identification method, device and equipment based on remote sensing image |
| CN114743112A (en) * | 2022-04-18 | 2022-07-12 | 农业农村部大数据发展中心 | Seed production corn field identification method and device based on big data and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107480706A (en) * | 2017-07-24 | 2017-12-15 | 中国农业大学 | A kind of seed production corn field remote sensing recognition method and device |
| EP3340130A1 (en) * | 2016-12-23 | 2018-06-27 | Hexagon Technology Center GmbH | Method for prediction of soil and/or plant condition |
| US20180189564A1 (en) * | 2016-12-30 | 2018-07-05 | International Business Machines Corporation | Method and system for crop type identification using satellite observation and weather data |
-
2019
- 2019-09-16 CN CN201910872912.0A patent/CN110751035A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3340130A1 (en) * | 2016-12-23 | 2018-06-27 | Hexagon Technology Center GmbH | Method for prediction of soil and/or plant condition |
| US20180189564A1 (en) * | 2016-12-30 | 2018-07-05 | International Business Machines Corporation | Method and system for crop type identification using satellite observation and weather data |
| CN107480706A (en) * | 2017-07-24 | 2017-12-15 | 中国农业大学 | A kind of seed production corn field remote sensing recognition method and device |
Non-Patent Citations (3)
| Title |
|---|
| 张超等: "基于多时相GF-1 WFV和高分纹理的制种玉米田识别", 《农业机械学报》 * |
| 温忠麟: "心理与教育统计", 《广东高等教育出版社》 * |
| 潘晓霞: "虚拟现实与人工智能技术的综合应用", 《中国原子能出版社》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111414863A (en) * | 2020-03-23 | 2020-07-14 | 国家海洋信息中心 | Enhanced integrated remote sensing image classification method |
| CN111414863B (en) * | 2020-03-23 | 2023-01-17 | 国家海洋信息中心 | Enhanced integrated remote sensing image classification method |
| CN113807219A (en) * | 2021-09-06 | 2021-12-17 | 苏州中科蓝迪软件技术有限公司 | Method for identifying types of grain and oil crops in planting land by steps |
| CN114202691A (en) * | 2021-12-09 | 2022-03-18 | 广东省科学院广州地理研究所 | Rice identification method, device and equipment based on remote sensing image |
| CN114743112A (en) * | 2022-04-18 | 2022-07-12 | 农业农村部大数据发展中心 | Seed production corn field identification method and device based on big data and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110751035A (en) | Seed corn production identification method and device | |
| Khoury et al. | Distributions, ex situ conservation priorities, and genetic resource potential of crop wild relatives of sweetpotato [Ipomoea batatas (L.) Lam., I. series Batatas] | |
| Sun et al. | Monitoring maize lodging grades via unmanned aerial vehicle multispectral image | |
| Dhau et al. | Testing the capability of spectral resolution of the new multispectral sensors on detecting the severity of grey leaf spot disease in maize crop | |
| CN107480706A (en) | A kind of seed production corn field remote sensing recognition method and device | |
| Sverdrup-Thygeson et al. | Can airborne laser scanning assist in mapping and monitoring natural forests? | |
| Ortega-Huerta et al. | Mapping coffee plantations with Landsat imagery: an example from El Salvador | |
| Ninomiya | High-throughput field crop phenotyping: current status and challenges | |
| Wang et al. | Classification of rice yield using UAV-based hyperspectral imagery and lodging feature | |
| CN109063660B (en) | Crop identification method based on multispectral satellite image | |
| Ayrey et al. | Ecologically-based metrics for assessing structure in developing area-based, enhanced forest inventories from LiDAR | |
| CN113657158A (en) | Google Earth Engine-based large-scale soybean planting region extraction algorithm | |
| CN116543316A (en) | Method for identifying turf in paddy field by utilizing multi-time-phase high-resolution satellite image | |
| Tamiminia et al. | comparison of machine and deep learning methods to estimate shrub willow biomass from UAS imagery | |
| Chellasamy et al. | A multievidence approach for crop discrimination using multitemporal worldview-2 imagery | |
| Schindler et al. | Method for national mapping spatial extent of southern beech forest using temporal spectral signatures | |
| Mendigoria et al. | Seed architectural phenes prediction and variety classification of dry beans (phaseolus vulgaris) using machine learning algorithms | |
| Carlier et al. | Wheat ear segmentation based on a multisensor system and superpixel classification | |
| Chen et al. | CropQuant-Air: an AI-powered system to enable phenotypic analysis of yield-and performance-related traits using wheat canopy imagery collected by low-cost drones | |
| Bhadra et al. | End-to-end 3D CNN for plot-scale soybean yield prediction using multitemporal UAV-based RGB images | |
| Kumar | Research Paper On Sugarcane Diseaese Detection Model | |
| CN114782835B (en) | Crop lodging area proportion detection method and device | |
| Verma et al. | [Retracted] Plantosphere: Next Generation Adaptive and Smart Agriculture System | |
| Yigezu et al. | Early ginger disease detection using deep learning approach | |
| Rocha IV et al. | Philippine carabao mango pest identification 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200204 |
|
| RJ01 | Rejection of invention patent application after publication |