CN109523509B - Method and device for detecting heading stage of wheat and electronic equipment - Google Patents

Method and device for detecting heading stage of wheat and electronic equipment Download PDF

Info

Publication number
CN109523509B
CN109523509B CN201811145965.4A CN201811145965A CN109523509B CN 109523509 B CN109523509 B CN 109523509B CN 201811145965 A CN201811145965 A CN 201811145965A CN 109523509 B CN109523509 B CN 109523509B
Authority
CN
China
Prior art keywords
image
wheat
heading
detected
feature
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.)
Active
Application number
CN201811145965.4A
Other languages
Chinese (zh)
Other versions
CN109523509A (en
Inventor
韩冰
周望
徐爱国
金红伟
朱平
席建辉
刘伯远
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Aerospace new weather Technology Co.,Ltd.
Original Assignee
Aerospace New Weather Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Aerospace New Weather Technology Co ltd filed Critical Aerospace New Weather Technology Co ltd
Priority to CN201811145965.4A priority Critical patent/CN109523509B/en
Publication of CN109523509A publication Critical patent/CN109523509A/en
Application granted granted Critical
Publication of CN109523509B publication Critical patent/CN109523509B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30181—Earth observation
    • G06T2207/30188—Vegetation; Agriculture

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Quality & Reliability (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Analysis (AREA)

Abstract

The invention discloses a method and a device for detecting a heading stage of wheat and electronic equipment, wherein the method comprises the following steps: acquiring an image to be detected; inputting an image to be detected into a wheat characteristic detection model to obtain a characteristic labeling image; the wheat characteristic detection model is obtained by training a sample image of the heading stage of wheat by utilizing a neural network architecture; a plurality of characteristic frames are marked on the characteristic marking image; and determining whether the image to be detected is a wheat image in the heading stage or not by using the characteristic frame marked on the characteristic marking image. The method is based on a detection model obtained by training a sample image of the wheat heading stage through a neural network architecture, and the wheat heading characteristic detection is carried out on an input field wheat image. The method does not need to comprehensively analyze a plurality of pictures of continuous growth sequences, can realize the ear identification based on a single wheat crop image, can effectively identify the heading stage of the wheat under the environment condition of changeable field light, and has high identification accuracy.

Description

Method and device for detecting heading stage of wheat and electronic equipment
Technical Field
The invention relates to the technical field of image processing and agricultural meteorological observation intersection, in particular to a method and a device for detecting a heading date of wheat and electronic equipment.
Background
Wheat is one of the main grain crops in China, and has a wide planting area nationwide. Wheat is one of the three grains and can be almost completely eaten. For a long time, the wheat development period observation is mainly recorded in a manual field observation mode, the manual observation result is easily influenced by subjective factors and skill level differences of observers, and the manual observation is time-consuming, labor-consuming and long in period. Therefore, the productivity can be greatly liberated by carrying out real-time and automatic observation on the development period of the wheat by using a series of crop images obtained in the field and an image processing technology, and the development of agricultural automatic observation business has important significance.
The heading stage of the wheat marks that the wheat is shifted from vegetative growth (growth of roots, stems, leaves and the like) to reproductive growth (flowering and fruiting), and is also a progressive stage of vegetative growth and vigorous reproductive growth, which is the most important key stage for determining the yield of crops, so the accurate observation of the heading stage of the wheat is particularly important.
In the prior art, the detection of the heading stage of wheat is generally based on the color characteristics of wheat ears in an image as a segmentation basis, and the wheat ears in the image are identified by obtaining the color characteristics of the wheat ears. However, in the method, the ear is identified by using an outdoor digital image, and a shot picture is easily influenced by sunlight, and the flag leaves of the wheat are easily reflected when the light is strong, so that the false detection of the flag leaves of the wheat as the ear is easily caused.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method and an apparatus for detecting a heading date of wheat, and an electronic device, so as to solve the problem of low detection accuracy of the heading date of wheat.
According to a first aspect, the embodiment of the present invention provides a method for detecting a heading date of wheat, including:
acquiring an image to be detected;
inputting the image to be detected into a wheat characteristic detection model to obtain a characteristic labeling image; the wheat characteristic detection model is obtained by training a sample image of the heading stage of wheat by utilizing a neural network architecture; a plurality of feature frames are marked on the feature marking image;
and determining whether the image to be detected is a wheat image in the heading stage or not by using the characteristic frame marked on the characteristic marking image.
The detection method for the heading stage of the wheat provided by the embodiment of the invention is characterized in that a detection model obtained by training a sample image of the heading stage of the wheat based on a neural network architecture is used for detecting the characteristics of the wheat ear of an input field wheat image. The method does not need to comprehensively analyze a plurality of pictures of continuous growth sequences, can realize the ear identification based on a single wheat crop image, can effectively identify the ear sprouting period of the wheat under the environment condition of changeable field light, and has high identification accuracy and strong practicability.
With reference to the first aspect, in a first embodiment of the first aspect, all the feature boxes are divided into a plurality of feature categories, and the feature categories are features of various stages of the growth period of wheat;
wherein, the determining whether the image to be detected is the wheat image in the heading stage by using the characteristic frame marked on the characteristic marking image comprises the following steps:
calculating the proportion of the heading feature frame in all the feature frames; wherein the heading feature box is the feature box of which the feature category is heading period;
judging whether the ratio is less than or equal to a first threshold value;
and when the proportion is less than or equal to a first threshold value, determining that the image to be detected is not the wheat image in the heading stage.
According to the wheat heading detection method provided by the embodiment of the invention, whether the image to be detected is the wheat image in the heading stage is determined according to the size relation between the ratio of the heading stage feature frames in all the feature frames and the first threshold; namely, a statistical method is utilized to carry out secondary judgment on the feature frame detected by the wheat feature detection model, so that the detection accuracy is improved.
With reference to the first embodiment of the first aspect, in a second embodiment of the first aspect, each feature box is further labeled with a confidence level; further comprising:
when the percentage is larger than a first threshold, counting the number of the heading feature frames with the confidence degrees larger than a second threshold;
judging whether the counted number of the heading feature frames is larger than a third threshold value or not;
and when the counted number of the heading feature frames is larger than a third threshold value, determining that the image to be detected is a wheat image in the heading stage.
The detection method for the heading stage of the wheat provided by the embodiment of the invention detects whether the image to be detected is the heading stage by using the confidence coefficient of the heading feature frame again, so that the detection accuracy is further improved.
With reference to the second embodiment of the first aspect, in a third embodiment of the first aspect, the method further includes:
when the counted number of the heading feature frames is smaller than or equal to a third threshold value, acquiring the shooting date of the image to be detected;
constructing a regression model according to the shooting date; wherein the regression model is used to predict the remaining days of a growth period prior to the heading period;
and determining whether the image to be detected is a wheat image in the heading stage or not based on the remaining days predicted by the regression model.
In the method for detecting the heading date of the wheat provided by the embodiment of the invention, in the process of determining whether the image to be detected is the heading date or not, a regression model is constructed by combining other types of variables corresponding to the shooting date; namely, the image characteristics are combined with other characteristics to determine the detection result of the image to be detected, so that the detection result has higher reliability.
With reference to the third embodiment of the first aspect, in the fourth embodiment of the first aspect, the determining whether the image to be detected is a wheat image in heading date based on the remaining days predicted by the regression model includes:
judging whether the remaining days are less than or equal to a fourth threshold value;
and when the remaining days are less than or equal to the fourth threshold, determining that the image to be detected is a wheat image in the heading stage.
With reference to the third implementation manner of the first aspect, in a fifth implementation manner of the first aspect, the constructing a linear prediction model according to the shooting date includes:
extracting microclimate data based on the shooting date; wherein the microclimate data includes at least one of daily average temperature, diurnal temperature difference, daily rainfall, and soil water content per unit volume;
selecting an explanation variable for the microclimate data, wherein the explanation variable is one or more of the microclimate data;
and constructing the regression model by using the explanation variables.
The method for detecting the heading date of the wheat, provided by the embodiment of the invention, combines the image characteristics with the microclimate data, is used for the subsequent comprehensive detection of the heading date of the image to be detected, and improves the detection accuracy.
With reference to the fifth embodiment of the first aspect, in the sixth embodiment of the first aspect, the selection of the microclimate data is performed by using the following formula:
Figure BDA0001815681760000041
wherein, yiIs the ith microclimate data; xiIs the ith interpretation variable; beta is a minimum two-component estimation value; λ is not less than 0 and is a penalty function.
With reference to the fifth implementation manner of the first aspect, in the seventh implementation manner of the first aspect, the regression model is represented by the following formula:
Figure BDA0001815681760000042
wherein, D is the number of remaining days; k is a constant; n is the number of said explanatory variables; xiIs the ith interpretation variable; alpha is alphaiIs the coefficient corresponding to the ith interpretation variable.
With reference to the first aspect, or any one implementation manner of the first aspect, in an eighth implementation manner of the first aspect, before the step of detecting the image to be detected based on the wheat feature detection model, the method further includes:
segmenting the image to be detected to obtain a plurality of sub-images to be detected;
wherein, based on wheat characteristic detection model, it is right wait to detect the image, include:
and detecting the subgraph to be detected based on the wheat feature detection model.
According to the detection method for the heading stage of the wheat provided by the embodiment of the invention, the image to be detected is segmented, so that each subgraph can effectively cover the characteristic to be detected, conditions are provided for subsequent detection, and the detection accuracy is improved.
According to a second aspect, the embodiment of the present invention further provides a device for detecting a heading date of wheat, including:
the acquisition module is used for acquiring an image to be detected;
the detection module is used for inputting the image to be detected into a wheat characteristic detection model to obtain a characteristic labeling image; the wheat characteristic detection model is obtained by training a sample image of the heading stage of wheat by utilizing a neural network architecture; a plurality of feature frames are marked on the feature marking image;
and the determining module is used for determining whether the image to be detected is a wheat image in the heading stage by using the characteristic frame marked on the characteristic marking image.
The detection device for the heading stage of the wheat provided by the embodiment of the invention is a detection model obtained by training a sample image of the heading stage of the wheat based on a neural network architecture, and is used for detecting the characteristics of the wheat ear of the input field wheat image. The method does not need to comprehensively analyze a plurality of pictures of continuous growth sequences, can realize the ear identification based on a single wheat crop image, can effectively identify the ear sprouting period of the wheat under the environment condition of changeable field light, and has high identification accuracy and strong practicability.
According to a third aspect, an embodiment of the present invention further provides an electronic device, including:
a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing therein computer instructions, and the processor executing the computer instructions to perform the method for detecting heading date of wheat as described in the first aspect or any embodiment of the first aspect.
According to a fourth aspect, the present invention further provides a computer-readable storage medium, which stores computer instructions for causing a computer to execute the method for detecting a heading date of wheat according to the first aspect or any embodiment of the first aspect.
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 other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a method for detecting heading date of wheat according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method for detecting heading date of wheat according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a feature labeled image according to an embodiment of the invention;
FIG. 4 is a partial flow chart of a method for detecting heading date of wheat according to an embodiment of the present invention;
FIG. 5 is a flowchart of a method for detecting heading date of wheat according to an embodiment of the present invention;
fig. 6 is a schematic diagram of a to-be-detected subgraph segmentation according to an embodiment of the invention;
FIG. 7 is a flow chart of the construction of a wheat heading feature model according to an embodiment of the invention;
FIG. 8 is a block diagram of a wheat heading stage detecting apparatus according to an embodiment of the present invention;
FIG. 9 is a schematic structural diagram of a wheat heading stage detection device according to an embodiment of the present invention;
fig. 10 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present 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.
In accordance with an embodiment of the present invention, there is provided an embodiment of a method for detecting heading date of wheat, it is noted that the steps illustrated in the flowchart of the accompanying drawings may be executed in a computer system such as a set of computer executable instructions, and that while a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be executed in an order different than that illustrated herein.
In this embodiment, a method for detecting a heading date of wheat is provided, which can be used in the above-mentioned electronic device, and fig. 1 is a flowchart of the method for detecting a heading date of wheat according to an embodiment of the present invention, as shown in fig. 1, the flowchart includes the following steps:
and S11, acquiring an image to be detected.
The image to be detected can be the image to be detected which is acquired in real time by image acquisition equipment erected in the farmland and is transmitted back to the electronic equipment for subsequent detection; if the wheat in the farmland does not need to be confirmed in real time whether to enter the heading stage, the image to be detected can be stored in the electronic equipment or acquired from the outside, and the like; only by ensuring that the electronic equipment can acquire the image to be detected according to the detection requirement.
And S12, inputting the image to be detected into the wheat characteristic detection model to obtain a characteristic labeling image.
The wheat characteristic detection model is obtained by training a sample image of the heading stage of wheat by utilizing a neural network architecture; and the characteristic labeling image is labeled with a plurality of characteristic frames.
Specifically, the wheat characteristic detection model can be obtained by training a sample image in the heading stage of wheat in advance, or can be obtained by training the sample image in the heading stage of wheat when the image to be detected needs to be detected; or obtained in other ways. Only when the image to be detected is detected, the electronic equipment can detect the image to be detected by utilizing the wheat characteristic detection model; the wheat feature detection model is obtained by training a sample image of the wheat heading stage by utilizing a neural network architecture, for example, the neural network architecture can be a Convolutional Neural Network (CNN), a Faster-RCNN and the like. Wherein, the sample images of the heading stage of the wheat can be obtained under different growing environments, different wheat varieties and different field environments; or only including the sample image of the heading stage, or performing visual interpretation on the wheat image collected from the field, and performing frame marking on the wheat in the heading stage in the wheat image.
In addition, after the electronic device detects the image to be detected by using the wheat feature detection model, the obtained feature labeled image can be labeled with wheat of each feature, that is, after the image to be detected passes through the wheat feature detection model, the obtained feature labeled image is labeled with a plurality of feature frames.
And S13, determining whether the image to be detected is the wheat image in the heading stage by using the characteristic frame marked on the characteristic marking image.
The electronic equipment can determine whether the image to be detected is a wheat image in the heading stage or not by utilizing the number of the characteristic frames marked on the characteristic marking image; or determining whether the image to be detected is a wheat image in the heading stage by using the ratio of the characteristic frame for showing the heading stage; or other methods, or with other characteristics, to determine images of the heading wheat.
The detection method for the heading stage of wheat provided by this embodiment is based on a detection model obtained by training a sample image of the heading stage of wheat based on a neural network architecture, and performs ear characteristic detection on an input field wheat image. The method does not need to comprehensively analyze a plurality of pictures of continuous growth sequences, can realize the ear identification based on a single wheat crop image, can effectively identify the ear sprouting period of the wheat under the environment condition of changeable field light, and has high identification accuracy and strong practicability.
An embodiment of the present invention further provides a method for detecting a heading date of wheat, which can be used in the electronic device, and fig. 2 is a flowchart of the method for detecting a heading date of wheat according to an embodiment of the present invention, and as shown in fig. 2, the flow includes the following steps:
and S21, acquiring an image to be detected. Please refer to S11 in fig. 1, which is not described herein again.
And S22, inputting the image to be detected into the wheat characteristic detection model to obtain a characteristic labeling image.
The wheat characteristic detection model is obtained by training a sample image of the heading stage of wheat by utilizing a neural network architecture; and the characteristic labeling image is labeled with a plurality of characteristic frames.
For example, the resulting feature labeling image is shown in fig. 3. Please refer to S12 in fig. 1, which is not described herein again.
And S23, determining whether the image to be detected is the wheat image in the heading stage by using the characteristic frame marked on the characteristic marking image.
Wherein, all the characteristic frames are divided into a plurality of characteristic categories, and the characteristic categories are the characteristics of each stage of the growth period of the wheat. Specifically, the whole growth period of wheat goes through: seedling stage, tillering stage, overwintering stage, body-raising stage, jointing stage, booting stage, heading stage, flowering stage, filling stage and maturation stage.
For example, after the wheat feature detection model is used to detect the image to be detected, the output result may be the statistics of the number of feature frames in each breeding period, and the following table may be adopted:
growth period Number of
Stage of emergence 0
Tillering stage 0
Winter season 0
Rising period 0
…
Heading period 12
Flowering period 2
Grouting period 1
Wherein, a characteristic frame of each growth period of the wheat can be shown, or only a few growth periods thereof can be shown; the specific setting can be carried out according to the actual situation.
Furthermore, the determination of the birth duration using the labeling box comprises the steps of:
and S231, calculating the ratio of the heading feature frame in all the feature frames.
Wherein, the heading characteristic frame is a characteristic frame with the characteristic category of heading period.
And calculating the number of all the feature frames, and then calculating the proportion of the heading feature frames in all the feature frames by using the number of all the feature frames and the number of the heading feature frames. For example, as shown in the above table, the number of all feature boxes is 12+2+1 — 15; the number of heading date feature boxes was 12, and the calculated percentage was 80%.
S232, judging whether the occupation ratio is less than or equal to a first threshold value.
After calculating the ratio of the heading period feature frames in all the feature frames, the electronic device determines whether the calculated ratio is less than or equal to a first threshold, and if the ratio is less than or equal to the first threshold, S233 is executed; otherwise, S234 is executed.
The value of the first threshold is between 0 and 1, the specific value is related to hardware parameters of an image sensor in the image acquisition equipment for acquiring the image to be detected, the erection angle of the image acquisition equipment and other factors, and the specific value can be specifically set according to actual conditions.
And S233, determining that the image to be detected is not the wheat image in the heading stage.
And when the calculated ratio is less than or equal to the first threshold value, determining that the wheat in the image to be detected is not in the heading stage.
And S234, counting the number of the heading feature boxes with the confidence degrees larger than the second threshold value.
After the wheat feature detection model is used for detecting the image to be detected, the output result is also marked with the confidence degree corresponding to each feature frame, and the electronic equipment counts the number of the heading feature frames with the confidence degrees larger than the second threshold value.
And S235, judging whether the counted number of the heading feature frames is larger than a third threshold value.
After counting the number of the heading feature frames with the confidence degree larger than the second threshold, the electronic device determines whether the counted number of the heading feature frames is larger than a third threshold, and executes S236 when the counted number of the heading feature frames is larger than the third threshold; otherwise, determining that the wheat in the image to be detected is not in the heading stage, namely determining that the image to be detected is not the wheat image in the heading stage.
And S236, determining the image to be detected as a wheat image in the heading stage.
And when the electronic equipment judges that the counted number of the heading feature frames is larger than a third threshold value, determining that the wheat in the image to be detected is in the heading stage, namely determining that the image to be detected is the wheat image in the heading stage.
Compared with the embodiment shown in fig. 1, in the detection method for the heading date of wheat provided by the embodiment, whether the image to be detected is the wheat image in the heading date is determined according to the magnitude relation between the percentage of the heading date feature frame in all the feature frames and the first threshold and the confidence; namely, a statistical method is utilized to carry out secondary judgment on the feature frame detected by the wheat feature detection model, so that the detection accuracy is improved.
As an optional implementation manner of this embodiment, when it is determined that the counted number of heading feature frames is less than or equal to the third threshold, the electronic device determines again whether the image to be detected is the heading-stage wheat image by using the microclimate data corresponding to the shooting date of the image to be detected. The method is characterized in that the direct characteristic information acquired by the wheat heading characteristic model and indirect crop information such as field microclimate data are comprehensively judged corresponding to the amount judgment of the wheat heading stage, and the temperature, the humidity, the soil moisture and the like have direct influence on the duration of the growth cycle of crops, so that the residual days of a previous growth period (namely the jointing stage) of the wheat heading stage are predicted by using the direct characteristic information and the field microclimate data, and the initial date of the heading stage is indirectly acquired. Specifically, as shown in fig. 4, S23 further includes:
and S237, when the counted number of the heading feature frames is less than or equal to a third threshold value, acquiring the shooting date of the image to be detected.
And after the electronic equipment determines that the counted number of the heading feature frames is smaller than or equal to a third threshold, acquiring the shooting date of the image to be detected so as to acquire microclimate data by using the shooting date.
And S238, constructing a regression model according to the shooting date.
Wherein the regression model is used to predict the remaining days of a growth phase preceding the heading phase.
The electronic equipment extracts microclimate data by utilizing the shooting date of the image to be detected, and constructs a regression model for predicting the remaining days of a growth period before the heading period. Specifically, the method comprises the following steps:
(1) microclimate data is extracted based on the shooting date.
Wherein the microclimate data includes at least one of daily average temperature, day-night temperature difference, daily rainfall and soil water content per unit volume.
For example, historical artificial observation data and historical microclimate data of the growth period of the wheat can be obtained, the field microclimate data are recorded once every hour, and all variables such as the average temperature, the day-night temperature difference, the daily rainfall, the water content of 5cm soil in unit volume and the like can be calculated through the observation value of each hour.
(2) The choice of interpretation variables is made for the microclimate data.
Wherein the explanatory variables are one or more of the microclimate data. That is, a variable (explanatory variable) closely related to the number of days from the start of heading date was obtained by analyzing microclimate data.
The selection of the interpretation variables for the microclimate data is made using the following formula:
Figure BDA0001815681760000101
wherein, yiIs the ith microclimate data; xiIs the ith interpretation variable; beta is a minimum two-component estimation value; λ is not less than 0 and is a penalty function.
The selection model of the interpretation variables can compress a part of the coefficients to 0, and the variables with the remaining coefficients not being 0 are variables closely related to the interpreted variables. The selection model may be a LASSO model or other selection models.
(3) A regression model is constructed using the explanatory variables.
The electronics fit a linear model to the days remaining to the end of the last growth phase (i.e., the jointing phase) of the heading phase using the selected interpretation variables. Specifically, the regression model is represented by the following formula:
Figure BDA0001815681760000111
wherein, D is the number of remaining days; k is a constant; n is the number of said explanatory variables; xiIs the ith interpretation variable; alpha is alphaiIs the coefficient corresponding to the ith interpretation variable.
For example, the interpretive variable selected in step (2) is 3, i.e., the average daily temperature X1Earth temperature X2And the water content of the soil X3Then the remaining days can be expressed as: d is K + alpha1×X1+α2×X2+α3×X3(ii) a Wherein alpha is1～α3Is a constant.
And S239, determining whether the image to be detected is the wheat image in the heading stage or not based on the residual days predicted by the regression model.
And after the remaining days are obtained based on the regression model, the electronic equipment determines whether the image to be detected is the wheat image in the heading stage or not by comparing the remaining days with a fourth threshold value. In particular, the amount of the solvent to be used,
and judging whether the remaining days are less than or equal to a fourth threshold value. And when the remaining days are less than or equal to a fourth threshold value, determining that the image to be detected is a wheat image in the heading stage. Otherwise, determining that the image to be detected is not the wheat image in the heading stage.
In the embodiment, in the process of determining whether the image to be detected is in the heading stage, a regression model is constructed by combining other types of variables corresponding to the shooting date; namely, the image characteristics are combined with other characteristics to determine the detection result of the image to be detected, so that the detection result has higher reliability.
In this embodiment, a method for detecting a heading date of wheat is provided, which can be used in the above-mentioned electronic device, and fig. 5 is a flowchart of the method for detecting a heading date of wheat according to the embodiment of the present invention, as shown in fig. 5, the flowchart includes the following steps:
and S31, acquiring an image to be detected. Please refer to S21 in fig. 2 for details, which are not described herein.
And S32, segmenting the image to be detected to obtain a plurality of subgraphs to be detected.
As shown in fig. 6, the image to be detected is subjected to sub-image segmentation, that is, the original image is subjected to sub-image segmentation according to specific parameters of the adopted image sensor, such as observation height resolution, field angle, shooting depression angle, and the like, so as to ensure that the obtained sub-images can effectively cover the features to be detected.
For example, as shown in fig. 6, the division effect map has M × N pixels of the image to be detected, the number of pixels per divided image is limited to 300 × 300, and if the number of pixels of the divided image is less than 300 × 300, the image is subjected to 0 interpolation.
And S33, inputting the image to be detected into the wheat characteristic detection model to obtain a characteristic labeling image.
The wheat characteristic detection model is obtained by training a sample image of the heading stage of wheat by utilizing a neural network architecture; and the characteristic labeling image is labeled with a plurality of characteristic frames.
Specifically, as shown in fig. 7, the wheat feature detection model can be constructed by the following steps:
(1) a sample image is acquired.
The method comprises the steps of recording a high-definition digital image of the growth state of the wheat based on the images collected by image sensors in automatic wheat observation equipment installed in different regions, and carrying out primary preprocessing on the obtained crop image, namely, removing the crop image which is taken as an object picture and contains foreign matters such as unclear crops or water drops on a camera lens, so as to ensure that the obtained crop image can meet the subsequent processing requirement. And (3) screening images of the wheat heading stage on the basis of the judgment standard of the heading stage in agricultural meteorological observation standards on the preprocessed crop images to form a wheat heading stage image data set.
(2) And manually marking the characteristics.
Visually interpreting the wheat heading stage picture data set, carrying out frame marking on the wheat heading features in the image, wherein the recorded information of the marked frame can be expressed as (X)p,Yp,Lp,Wp) Wherein (X)p,Yp) The coordinate information of the pixel of the upper left corner of the characteristic frame in the wheat heading stage image in the whole wheat heading stage image is represented by (L)p,Wp) The length and width of the pixel occupied for this feature are recorded in the form of an xml file.
(3) The PRN network acquires ear characteristics.
And (4) taking the marked ear Feature image as input data, and performing convolution processing to obtain a Feature map (Feature map) of the original image.
(4) Ear characterization pooling to fixed size.
And (3) simultaneously inputting the output feature map and the feature candidate box output in the step (2) into the ROI pooling layer, and extracting the features of the corresponding feature candidate box. The pooling mode adopts maximum value 2 multiplied by 2 pooling; and obtaining the candidate frame characteristics.
(5) Bbox regression and Softmax classification.
After passing through the full connection layer, the classification score (Softmax classification) of the candidate frame and the regression bounding box are output. In specific implementation, the model is evaluated by adopting K-fold cross validation (K-fold cross validation), K is 10, the learning rate of random gradient descent (SGD) is set to be 0.001, and the iteration number is set to be 50000; for the Bbox regressor, a detection evaluation function (interaction _ over _ unit) is adopted, wherein GroudTruth is calculated according to four parameters of a target labeling area of a training sample, and DetectionResult is calculated according to four predicted parameters (x, y, l, w). And continuously adjusting related parameters in the algorithm iteration process, and storing the network model and the parameters after training is finished to obtain the wheat heading stage characteristic model.
And after obtaining the wheat heading stage characteristic model, the electronic equipment sequentially inputs the subgraphs to be detected into the wheat characteristic detection model so as to label the characteristic frame.
And S34, determining whether the image to be detected is the wheat image in the heading stage by using the characteristic frame marked on the characteristic marking image.
Each sub-image to be detected can be regarded as an independent image to be detected, and when it is determined whether the image to be detected is a wheat image in the heading stage, statistical analysis is performed on feature frames of all the sub-images to be detected, for details, see S24 in the embodiment shown in fig. 2, which is not described herein again.
Compared with the embodiment shown in fig. 2, the detection method for the heading date of wheat provided by the embodiment can ensure that each subgraph can effectively cover the features to be detected by segmenting the image to be detected, thereby providing conditions for subsequent detection and improving the detection accuracy.
It should be noted that the method for detecting the heading stage of wheat provided in the embodiment of the present invention may also be applied to detection of other growth stages of wheat, or detection of growth stages of other crops, and the like.
In this embodiment, a device for detecting the heading date of wheat is also provided, and the device is used to implement the above embodiments and preferred embodiments, which have already been described and will not be described again. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
This embodiment provides a detection apparatus for wheat heading stage, as shown in fig. 8, including:
an obtaining module 41, configured to obtain an image to be detected;
the detection module 42 is configured to input the image to be detected into a wheat feature detection model to obtain a feature labeling image; the wheat characteristic detection model is obtained by training a sample image of the heading stage of wheat by utilizing a neural network architecture; a plurality of feature frames are marked on the feature marking image;
a determining module 43, configured to determine whether the image to be detected is a wheat image in the heading period by using the feature frame marked on the feature marking image.
The detection device for the heading stage of wheat provided by this embodiment trains a sample image of the heading stage of wheat based on a neural network architecture to obtain a detection model, and performs ear feature detection on an input field wheat image. The method does not need to comprehensively analyze a plurality of pictures of continuous growth sequences, can realize the ear identification based on a single wheat crop image, can effectively identify the ear sprouting period of the wheat under the environment condition of changeable field light, and has high identification accuracy and strong practicability.
As an optional implementation manner of this embodiment, as shown in fig. 9, wherein the determining module 43 includes:
a calculating unit 431, configured to calculate a ratio of the heading feature frame in all the feature frames; wherein the heading feature box is the feature box of which the feature category is heading period.
A first judging unit 432, configured to judge whether the ratio is less than or equal to a first threshold.
A first determining unit 433, configured to determine that the image to be detected is not a wheat image in the heading period when the ratio is less than or equal to a first threshold.
A counting unit 434, configured to count the number of the heading feature boxes with the confidence level being greater than a second threshold when the percentage is greater than a first threshold.
A second determining unit 435, configured to determine whether the counted number of the heading feature frames is greater than a third threshold.
A second determining unit 436, configured to determine that the image to be detected is a wheat image in a heading stage when the counted number of heading feature frames is greater than a third threshold.
As an optional implementation manner of this embodiment, as shown in fig. 9, the determining module 43 further includes:
the obtaining unit 437 is configured to obtain a shooting date of the image to be detected when the counted number of the heading feature frames is less than or equal to a third threshold.
A construction unit 438, configured to construct a regression model according to the shooting date; wherein the regression model is used to predict the number of days remaining in a growth phase prior to the heading phase.
The third determining unit 439 is configured to determine whether the image to be detected is a wheat image in the heading date based on the remaining days predicted by the regression model.
The wheat heading date detection device in this embodiment is in the form of a functional unit, where the unit refers to an ASIC circuit, a processor and memory executing one or more software or fixed programs, and/or other devices that can provide the above-mentioned functions.
Further functional descriptions of the modules are the same as those of the corresponding embodiments, and are not repeated herein.
The embodiment of the invention also provides electronic equipment which is provided with the device for detecting the heading date of wheat shown in the figure 10.
Referring to fig. 10, fig. 10 is a schematic structural diagram of an electronic device according to an alternative embodiment of the present invention, as shown in fig. 10, the electronic device may include: at least one processor 51, such as a CPU (Central Processing Unit), at least one communication interface 53, memory 54, at least one communication bus 52. Wherein a communication bus 52 is used to enable the connection communication between these components. The communication interface 53 may include a Display (Display) and a Keyboard (Keyboard), and the optional communication interface 53 may also include a standard wired interface and a standard wireless interface. The Memory 54 may be a high-speed RAM Memory (volatile Random Access Memory) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. The memory 54 may alternatively be at least one memory device located remotely from the processor 51. Wherein the processor 51 may be in connection with the apparatus described in fig. 5, the memory 54 stores an application program, and the processor 51 calls the program code stored in the memory 54 for performing any of the above-mentioned method steps.
The communication bus 52 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The communication bus 52 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in FIG. 10, but this is not intended to represent only one bus or type of bus.
The memory 54 may include a volatile memory (RAM), such as a random-access memory (RAM); the memory may also include a non-volatile memory (english: non-volatile memory), such as a flash memory (english: flash memory), a hard disk (english: hard disk drive, abbreviation: HDD), or a solid-state drive (english: SSD); the memory 54 may also comprise a combination of the above types of memories.
The processor 51 may be a Central Processing Unit (CPU), a Network Processor (NP), or a combination of a CPU and an NP.
The processor 51 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a Programmable Logic Device (PLD), or a combination thereof. The PLD may be a Complex Programmable Logic Device (CPLD), a field-programmable gate array (FPGA), a General Array Logic (GAL), or any combination thereof.
Optionally, the memory 54 is also used to store program instructions. The processor 51 may call program instructions to implement the method for detecting heading date of wheat as shown in the embodiments described in fig. 1, fig. 2 or fig. 5 of the present application.
Embodiments of the present invention further provide a non-transitory computer storage medium, where the computer storage medium stores computer-executable instructions, and the computer-executable instructions may execute the XXX processing method in any of the above method embodiments. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk (Hard Disk Drive, abbreviated as HDD), a Solid State Drive (SSD), or the like; the storage medium may also comprise a combination of memories of the kind described above.
Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope defined by the appended claims.

Claims (11)

1. A method for detecting the heading stage of wheat is characterized by comprising the following steps:
acquiring an image to be detected;
inputting the image to be detected into a wheat characteristic detection model to obtain a characteristic labeling image; the wheat characteristic detection model is obtained by training a sample image of the heading stage of wheat by utilizing a neural network architecture; a plurality of feature frames are marked on the feature marking image;
determining whether the image to be detected is a wheat image in the heading stage or not by using the characteristic frame marked on the characteristic marking image; all the feature frames are divided into a plurality of feature categories, each feature frame is also marked with confidence, and the feature categories are features of each stage of the growth period of the wheat;
wherein, the determining whether the image to be detected is the wheat image in the heading stage by using the characteristic frame marked on the characteristic marking image comprises the following steps:
calculating the proportion of the heading feature frame in all the feature frames; wherein the heading feature box is the feature box of which the feature category is heading period;
judging whether the ratio is less than or equal to a first threshold value;
when the percentage is larger than a first threshold, counting the number of the heading feature frames with the confidence degrees larger than a second threshold;
judging whether the counted number of the heading feature frames is larger than a third threshold value or not;
when the counted number of the heading feature frames is smaller than or equal to a third threshold value, acquiring the shooting date of the image to be detected;
constructing a regression model according to the shooting date; wherein the regression model is used to predict the remaining days of a growth period prior to the heading period;
and determining whether the image to be detected is a wheat image in the heading stage or not based on the remaining days predicted by the regression model.
2. The method of claim 1,
the determining whether the image to be detected is the wheat image in the heading stage by using the characteristic frame marked on the characteristic marking image comprises the following steps:
and when the proportion is less than or equal to a first threshold value, determining that the image to be detected is not the wheat image in the heading stage.
3. The method according to claim 2, wherein the determining whether the image to be detected is a wheat image in heading date by using the feature frame marked on the feature marking image further comprises:
and when the counted number of the heading feature frames is larger than a third threshold value, determining that the image to be detected is a wheat image in the heading stage.
4. The method according to claim 1, wherein the determining whether the image to be detected is a wheat image of heading date based on the remaining days predicted by the regression model comprises:
judging whether the remaining days are less than or equal to a fourth threshold value;
and when the remaining days are less than or equal to the fourth threshold, determining that the image to be detected is a wheat image in the heading stage.
5. The method of claim 1, wherein constructing a regression model based on the capture date comprises:
extracting microclimate data based on the shooting date; wherein the microclimate data includes at least one of daily average temperature, diurnal temperature difference, daily rainfall, and soil water content per unit volume;
selecting an explanation variable for the microclimate data, wherein the explanation variable is one or more of the microclimate data;
and constructing the regression model by using the explanation variables.
6. The method of claim 5, wherein the selection of the interpretation variables is made using the following formula:
Figure FDA0003011465430000021
wherein, yiIs the ith microclimate data; n is the number of the microclimate data; xiIs the ith interpretation variable; p is the number of the corresponding explanation variables of the ith microclimate data; beta is least squares estimationEvaluating; λ is not less than 0 and is a penalty function.
7. The method of claim 5, wherein the regression model is represented by the following formula:
Figure FDA0003011465430000031
wherein, D is the number of remaining days; k is a constant; n is the number of said explanatory variables; xiIs the ith interpretation variable; alpha is alphaiIs the coefficient corresponding to the ith interpretation variable.
8. The method according to any one of claims 1 to 7, wherein the step of detecting the image to be detected based on the wheat feature detection model further comprises:
segmenting the image to be detected to obtain a plurality of sub-images to be detected;
wherein, will wait to detect the image input wheat characteristic detection model to obtain the characteristic mark image, include:
and inputting the subgraphs to be detected into the wheat characteristic detection model in sequence.
9. A wheat heading stage detection device is characterized by comprising:
the acquisition module is used for acquiring an image to be detected;
the detection module is used for inputting the image to be detected into a wheat characteristic detection model to obtain a characteristic labeling image; the wheat characteristic detection model is obtained by training a sample image of the heading stage of wheat by utilizing a neural network architecture; a plurality of feature frames are marked on the feature marking image;
the determining module is used for determining whether the image to be detected is a wheat image in the heading stage by using the characteristic frame marked on the characteristic marking image; all the feature frames are divided into a plurality of feature categories, each feature frame is also marked with confidence, and the feature categories are features of each stage of the growth period of the wheat;
wherein, the determining whether the image to be detected is the wheat image in the heading stage by using the characteristic frame marked on the characteristic marking image comprises the following steps:
calculating the proportion of the heading feature frame in all the feature frames; wherein the heading feature box is the feature box of which the feature category is heading period;
judging whether the ratio is less than or equal to a first threshold value;
when the percentage is larger than a first threshold, counting the number of the heading feature frames with the confidence degrees larger than a second threshold;
judging whether the counted number of the heading feature frames is larger than a third threshold value or not;
when the counted number of the heading feature frames is smaller than or equal to a third threshold value, acquiring the shooting date of the image to be detected;
constructing a regression model according to the shooting date; wherein the regression model is used to predict the remaining days of a growth period prior to the heading period;
and determining whether the image to be detected is a wheat image in the heading stage or not based on the remaining days predicted by the regression model.
10. An electronic device, comprising:
a memory and a processor, the memory and the processor being communicatively connected to each other, the memory having stored therein computer instructions, and the processor executing the computer instructions to perform the method for detecting heading date of wheat according to any one of claims 1 to 8.
11. A computer-readable storage medium storing computer instructions for causing a computer to perform the method for detecting heading date of wheat according to any one of claims 1 to 8.
CN201811145965.4A 2018-09-28 2018-09-28 Method and device for detecting heading stage of wheat and electronic equipment Active CN109523509B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811145965.4A CN109523509B (en) 2018-09-28 2018-09-28 Method and device for detecting heading stage of wheat and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811145965.4A CN109523509B (en) 2018-09-28 2018-09-28 Method and device for detecting heading stage of wheat and electronic equipment

Publications (2)

Publication Number Publication Date
CN109523509A CN109523509A (en) 2019-03-26
CN109523509B true CN109523509B (en) 2021-08-13

Family

ID=65771852

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811145965.4A Active CN109523509B (en) 2018-09-28 2018-09-28 Method and device for detecting heading stage of wheat and electronic equipment

Country Status (1)

Country Link
CN (1) CN109523509B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113011220A (en) * 2019-12-19 2021-06-22 广州极飞科技股份有限公司 Spike number identification method and device, storage medium and processor
CN113139552A (en) * 2021-04-29 2021-07-20 航天新气象科技有限公司 Wheat heading period identification method and device, electronic equipment and storage medium

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH09271246A (en) * 1996-04-08 1997-10-21 Kubota Corp Combine
CN102621075A (en) * 2012-03-09 2012-08-01 华中科技大学 Method for automatically detecting rice heading stage
CN102663397A (en) * 2012-03-21 2012-09-12 华中科技大学 Automatic detection method of wheat seedling emergence
CN102855485A (en) * 2012-08-07 2013-01-02 华中科技大学 Automatic wheat earing detection method
CN102948282A (en) * 2012-10-31 2013-03-06 北京农业信息技术研究中心 Wheatear germination degree detection method
CN107316289A (en) * 2017-06-08 2017-11-03 华中农业大学 Crop field spike of rice dividing method based on deep learning and super-pixel segmentation
CN107392223A (en) * 2017-06-09 2017-11-24 中国科学院合肥物质科学研究院 A kind of Adaboost is the same as the NCC complete wheat head recognition methods being combined and system
CN108416353A (en) * 2018-02-03 2018-08-17 华中农业大学 Crop field spike of rice fast partition method based on the full convolutional neural networks of depth

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100216225A1 (en) * 2009-02-25 2010-08-26 Ag-Defense Systems, Inc. Portable microorganism detection unit

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH09271246A (en) * 1996-04-08 1997-10-21 Kubota Corp Combine
CN102621075A (en) * 2012-03-09 2012-08-01 华中科技大学 Method for automatically detecting rice heading stage
CN102663397A (en) * 2012-03-21 2012-09-12 华中科技大学 Automatic detection method of wheat seedling emergence
CN102855485A (en) * 2012-08-07 2013-01-02 华中科技大学 Automatic wheat earing detection method
CN102948282A (en) * 2012-10-31 2013-03-06 北京农业信息技术研究中心 Wheatear germination degree detection method
CN107316289A (en) * 2017-06-08 2017-11-03 华中农业大学 Crop field spike of rice dividing method based on deep learning and super-pixel segmentation
CN107392223A (en) * 2017-06-09 2017-11-24 中国科学院合肥物质科学研究院 A kind of Adaboost is the same as the NCC complete wheat head recognition methods being combined and system
CN108416353A (en) * 2018-02-03 2018-08-17 华中农业大学 Crop field spike of rice fast partition method based on the full convolutional neural networks of depth

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
BP神经网络在小麦赤霉病气象预测中的应用;刘志红等;《云南农业大学学报(自然科学版)》;20100531(第5期);第680-685页 *
Detecting spikes of wheat plants using neural networks with laws texture energy;Li Qiongyan et al;《Plant Methods》;20171031;第1-10页 *
基于图像的水稻关键发育期自动观测技术研究;白晓东;《中国博士学位论文全文数据库信息科技辑》;20150715(第7期);第88-89、96-100页 *

Also Published As

Publication number Publication date
CN109523509A (en) 2019-03-26

Similar Documents

Publication Publication Date Title
CN109785337B (en) In-column mammal counting method based on example segmentation algorithm
US20230316555A1 (en) System and Method for Image-Based Remote Sensing of Crop Plants
Liu et al. A computer vision system for early stage grape yield estimation based on shoot detection
CN113392775B (en) Sugarcane seedling automatic identification and counting method based on deep neural network
CN109522899B (en) Detection method and device for ripe coffee fruits and electronic equipment
CN109492665A (en) Detection method, device and the electronic equipment of growth period duration of rice
CN110414738B (en) Crop yield prediction method and system
CN110991222B (en) Object state monitoring and sow oestrus monitoring method, device and system
Solvin et al. Use of UAV photogrammetric data in forest genetic trials: measuring tree height, growth, and phenology in Norway spruce (Picea abies L. Karst.)
CN113658192B (en) Multi-target pedestrian track acquisition method, system, device and medium
CN112419202B (en) Automatic wild animal image recognition system based on big data and deep learning
CN109523509B (en) Method and device for detecting heading stage of wheat and electronic equipment
CN115439654B (en) Method and system for finely dividing weakly supervised farmland plots under dynamic constraint
CN114494909B (en) Method and system for generating spatial distribution diagram of soybean growing season
CN115527130A (en) Grassland pest mouse density investigation method and intelligent evaluation system
CN116579521B (en) Yield prediction time window determining method, device, equipment and readable storage medium
CN115331124A (en) Invasive plant biomass estimation method based on unmanned aerial vehicle remote sensing
CN113011220A (en) Spike number identification method and device, storage medium and processor
CN115620119A (en) Weather type image detection and foggy day image processing method and device
CN112488230A (en) Crop water stress degree judging method and device based on machine learning
CN113436193A (en) Urban black and odorous water body monitoring method and device
CN113807129A (en) Crop area identification method and device, computer equipment and storage medium
CN116052141B (en) Crop growth period identification method, device, equipment and medium
CN115690585B (en) Method and system for extracting wheat tillering number based on digital photo
CN109544505A (en) Detection method, device and the electronic equipment in coffee florescence

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
TA01 Transfer of patent application right
TA01 Transfer of patent application right

Effective date of registration: 20210705

Address after: No. 28, Weiming Road, Binhu District, Wuxi City, Jiangsu Province

Applicant after: Aerospace new weather Technology Co.,Ltd.

Address before: No. 100, Jinxi Road, Binhu District, Wuxi City, Jiangsu Province

Applicant before: JIANGSU PROVINCE RADIO SCIENTIFIC RESEARCH INSTITUTE Co.,Ltd.

GR01 Patent grant
GR01 Patent grant