CN111985849A - Overground biomass generation method and device for cotton field - Google Patents

Overground biomass generation method and device for cotton field Download PDF

Info

Publication number
CN111985849A
CN111985849A CN202010916168.2A CN202010916168A CN111985849A CN 111985849 A CN111985849 A CN 111985849A CN 202010916168 A CN202010916168 A CN 202010916168A CN 111985849 A CN111985849 A CN 111985849A
Authority
CN
China
Prior art keywords
gray level
pixel
set search
band
index
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202010916168.2A
Other languages
Chinese (zh)
Other versions
CN111985849B (en
Inventor
陈鹏飞
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.)
Institute of Geographic Sciences and Natural Resources of CAS
Original Assignee
Institute of Geographic Sciences and Natural Resources of CAS
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 Institute of Geographic Sciences and Natural Resources of CAS filed Critical Institute of Geographic Sciences and Natural Resources of CAS
Priority to CN202010916168.2A priority Critical patent/CN111985849B/en
Publication of CN111985849A publication Critical patent/CN111985849A/en
Application granted granted Critical
Publication of CN111985849B publication Critical patent/CN111985849B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/02—Agriculture; Fishing; Forestry; Mining
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/40—Analysis of texture
    • G06T7/41—Analysis of texture based on statistical description of texture
    • G06T7/45—Analysis of texture based on statistical description of texture using co-occurrence matrix computation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/90—Determination of colour characteristics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • 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)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Educational Administration (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Development Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Agronomy & Crop Science (AREA)
  • Marine Sciences & Fisheries (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mining & Mineral Resources (AREA)
  • General Health & Medical Sciences (AREA)
  • Animal Husbandry (AREA)
  • Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Investigating Or Analysing Materials By Optical Means (AREA)

Abstract

The embodiment of the invention provides an aboveground biomass generation method and device for a cotton field. Counting the number of times that a plurality of pixels with gray level i and pixels with gray level j of a green band corresponding to a set search direction in an acquired spectrum band image appear simultaneously; constructing a co-occurrence matrix corresponding to each set search direction according to the number of times that the pixel with the gray level i and the pixel with the gray level j corresponding to each set search direction appear simultaneously; calculating a texture index according to the co-occurrence matrix corresponding to each set search direction; calculating a triangular spectral index according to the near infrared band reflectivity, the green band reflectivity and the red band reflectivity in the spectral band image; and generating the aboveground biomass according to the texture index and the triangular spectral index. According to the technical scheme provided by the embodiment of the invention, the aboveground biomass can be generated according to the texture index and the triangular spectral index calculated by the spectral band image, and the accuracy of generating the aboveground biomass of the cotton field is improved.

Description

Overground biomass generation method and device for cotton field
[ technical field ] A method for producing a semiconductor device
The invention relates to the technical field of remote sensing inversion, in particular to a method and a device for generating aboveground biomass of a cotton field.
[ background of the invention ]
The aboveground biomass of the cotton field is the dry matter weight of the upper part of the cotton field in unit land area, and is an important index for indicating the growth vigor of cotton. The method realizes the rapid and nondestructive detection of the aboveground biomass of the cotton field, and has important significance for timely dividing field management units, developing accurate operation management, saving chemical fertilizers, saving pesticide application amount, protecting the environment and improving the economic benefits of farmers. However, no technical scheme for estimating the aboveground biomass of the cotton field based on image spectrum and texture information exists at present, so that the accuracy of calculating the aboveground biomass of the cotton field is reduced.
[ summary of the invention ]
In view of the above, the embodiments of the present invention provide an aboveground biomass generation method and apparatus for a cotton field, so as to improve the accuracy of calculating aboveground biomass of the cotton field.
In one aspect, an embodiment of the present invention provides an aboveground biomass generation method for a cotton field, including:
counting the number of times that a plurality of pixels with gray level i and pixels with gray level j of a green waveband corresponding to a set search direction in the acquired spectrum waveband image according to the set window size;
constructing a co-occurrence matrix corresponding to each set search direction according to the number of times that the pixel with the gray level i and the pixel with the gray level j corresponding to each set search direction appear simultaneously;
calculating a texture index according to the co-occurrence matrix corresponding to each set search direction;
calculating a triangular spectral index according to the near infrared band reflectivity, the green band reflectivity and the red band reflectivity in the spectral band image;
and generating aboveground biomass according to the texture index and the triangular spectral index.
Optionally, the counting the number of times that a pixel with a gray level i and a pixel with a gray level j in a green band in the acquired spectrum band image occur simultaneously includes:
acquiring the spectrum band image shot by the unmanned aerial vehicle, wherein the spectrum band image comprises a target area;
setting the size of a calculated window according to the target area;
determining a set maximum gray value according to the maximum gray value of the green band in the spectrum band image;
determining a set minimum gray value according to the minimum gray value of the green band in the spectrum band image;
dividing the gray level of the green wave band in the spectrum wave band image into gray level setting levels;
and determining the gray level of each pixel of the green wave band corresponding to each set search direction in the spectrum wave band image according to the set gray maximum value, the set gray minimum value and the gray set level.
Optionally, the calculating a texture index according to the co-occurrence matrix corresponding to each set search direction includes:
calculating the probability of the simultaneous occurrence of the pixel with the gray level i and the pixel with the gray level j corresponding to each set search direction according to the number of times of the simultaneous occurrence of the pixel with the gray level i and the pixel with the gray level j in the co-occurrence matrix corresponding to each set search direction and the sum of elements in the co-occurrence matrix;
calculating the contrast of a green band according to the probability that the pixel with the gray level i and the pixel with the gray level j corresponding to each set search direction appear at the same time;
calculating the inverse difference moment of the green wave band according to the probability that the pixel with the gray level i and the pixel with the gray level j corresponding to each set search direction appear at the same time;
generating average contrast according to the contrasts corresponding to the plurality of set search directions;
generating an average inverse difference moment according to the inverse difference moment corresponding to each set search direction;
and generating a texture index according to the average contrast and the average inverse difference moment.
Optionally, the calculating the triangular spectral index according to the near infrared band reflectivity, the green band reflectivity and the red band reflectivity in the spectral band image includes:
by the formula TVI 0.5 × (120 × (R)nir-Rgreen)-200×(Rred-Rgreen) Reflectance of the near infrared band, the green waveCalculating the segment reflectivity and the red band reflectivity to generate the triangular spectral index, wherein TVI is the triangular spectral index, R is the triangular spectral indexnirIs the near infrared band reflectivity, RgreenIs the green band reflectivity, RredIs the red band reflectivity.
Optionally, the generating aboveground biomass from the texture index and the triangular spectral index comprises:
and calculating the texture index and the triangular spectral index by a formula of Biomass ═ a × BTI + b × TVI + c, and generating the above-ground Biomass, wherein Biomass is the above-ground Biomass, BTI is the texture index, TVI is the triangular spectral index, and a, b and c are model parameters.
Optionally, the generating a texture index according to the average contrast and the average inverse difference moment comprises:
by the formula
Figure BDA0002665090650000031
Calculating the average contrast and the average inverse difference moment to generate the texture index, wherein BTI is the texture index, CONgFor said average contrast, IDMgIs the average inverse difference moment.
Optionally, the generating an average contrast according to contrasts corresponding to a plurality of set search directions includes:
carrying out average calculation on the contrasts corresponding to a plurality of set search directions to generate the average contrast;
the generating the average inverse difference moment according to the inverse difference moments corresponding to the plurality of set search directions includes:
and carrying out average calculation on the adverse difference moments corresponding to a plurality of set search directions to generate the average adverse difference moment.
In another aspect, an embodiment of the present invention provides an above-ground biomass generation device for a cotton field, including:
the counting module is used for counting the number of times that a plurality of pixels with gray level i and pixels with gray level j corresponding to the set search direction appear simultaneously in the acquired spectrum band image according to the set window size;
the construction module is used for constructing a co-occurrence matrix corresponding to each set search direction according to the number of times that the pixel with the gray level i and the pixel with the gray level j corresponding to each set search direction appear simultaneously;
the first calculation module is used for calculating texture indexes according to the symbiotic matrix corresponding to each set search direction;
the second calculation module is used for calculating the triangular spectral index according to the near infrared band reflectivity, the green band reflectivity and the red band reflectivity in the spectral band image;
a first generation module for generating aboveground biomass from the texture index and the triangular spectral index.
In another aspect, an embodiment of the present invention provides a storage medium, including: the storage medium comprises a stored program, wherein when the program runs, the device where the storage medium is located is controlled to execute the aboveground biomass generation method of the cotton field.
In another aspect, an embodiment of the present invention provides a computer device comprising a memory for storing information including program instructions and a processor for controlling the execution of the program instructions, wherein the program instructions are loaded and executed by the processor to implement the above-ground biomass generation method for cotton fields.
According to the technical scheme of the aboveground biomass generation method of the cotton field, the number of times that a pixel with a gray level i and a pixel with a gray level j of a green wave band corresponding to a plurality of set search directions in an acquired spectrum wave band image appear at the same time is counted; constructing a co-occurrence matrix corresponding to each set search direction according to the number of times that the pixel with the gray level i and the pixel with the gray level j corresponding to each set search direction appear simultaneously; calculating a texture index according to the co-occurrence matrix corresponding to each set search direction; calculating a triangular spectral index according to the near infrared band reflectivity, the green band reflectivity and the red band reflectivity in the spectral band image; and generating the aboveground biomass according to the texture index and the triangular spectral index. According to the technical scheme provided by the embodiment of the invention, the aboveground biomass can be generated according to the texture index and the triangular spectral index calculated by the spectral band image, and the accuracy of generating the aboveground biomass of the cotton field is improved.
[ description of the drawings ]
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive labor.
FIG. 1 is a flow chart of a method for above-ground biomass generation of a cotton field according to an embodiment of the present invention;
FIG. 2 is a flow chart of another method for above-ground biomass production in a cotton field according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of another aboveground biomass production method for a cotton field according to an embodiment of the present invention;
fig. 4 is a schematic diagram of the number of times that a pixel with a gray level i and a pixel with a gray level j occur simultaneously according to an embodiment of the present invention;
FIG. 5 is a flow chart of the calculation of texture index of FIG. 2;
FIG. 6 is a schematic structural diagram of an aboveground biomass production device for a cotton field according to an embodiment of the present invention;
fig. 7 is a schematic diagram of a computer device according to an embodiment of the present invention.
[ detailed description ] embodiments
For better understanding of the technical solutions of the present invention, the following detailed descriptions of the embodiments of the present invention are provided with reference to the accompanying drawings.
It should be understood that the described embodiments are only some embodiments of the invention, and not all embodiments. 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 terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the examples of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be understood that the term "and/or" as used herein is merely one type of associative relationship that describes an associated object, meaning that three types of relationships may exist, e.g., A and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
The remote sensing technology can be used for realizing the rapid and nondestructive detection of the aboveground biomass of the cotton field, and a large amount of related researches are carried out by relying on remote sensing data obtained by three platforms, namely ground equipment, a man-machine platform and a satellite, so that the application of the remote sensing technology in the aboveground biomass monitoring of the cotton field is promoted. However, the remote sensing observation methods have certain defects, such as the defects of long revisit period and low time resolution of satellite remote sensing; the data acquired by the ground equipment has the problems of small observation range, large workload, narrow visual field and the like; the manned aircraft has the defects of high cost and long flight preparation time in remote sensing. In recent years, the unmanned aerial vehicle remote sensing technology is gradually applied to agricultural remote sensing monitoring by the characteristics of mobility, flexibility, strong timeliness, easy operation and low cost, and becomes an important supplement of the existing remote sensing data acquisition means. The unmanned aerial vehicle remote sensing can obtain images with high time and spatial resolution, and is particularly suitable for field scale remote sensing observation. Currently, there are related researches on aboveground biomass of cotton fields based on unmanned aerial vehicle remote sensing, but most of the researches only carry out estimation of aboveground biomass of cotton fields based on remote sensing image spectral information, and neglect the effect of texture information based on remote sensing images on cotton aboveground biomass estimation, and texture index is a way to reflect texture information.
In the related art, the remote sensing estimation method of the biomass on the ground of the cotton field is based on the spectral information of the image, and the spectral information of the image is insensitive to the biomass change on the ground under the condition of medium vegetation density or high vegetation density, so that the phenomenon of saturation occurs, and the estimation precision of the biomass on the ground is lowered. The cotton grows from small to big, and the soil pixels are gradually filled by the cotton pixels on the image. The texture information provides support for the above-ground biomass estimation of the cotton field, overcoming the phenomenon of "saturation" that occurs when the above-ground biomass is estimated based on the image spectral information only. However, no technical scheme for estimating the aboveground biomass of the cotton field based on the coupling of the spectral information and the texture information exists at present, and the spectral band image comprises the spectral information. Although a few studies have been made to estimate the biomass information of wheat and rice based on the coupling of spectral information and texture index, on one hand, the canopy structures of cotton, wheat and rice are different, and the methods for wheat and rice are difficult to apply to cotton, so that the accuracy of calculating the aboveground biomass of cotton fields is reduced. On the other hand, the texture index is calculated by firstly calculating a co-occurrence matrix from the spectral band image and then calculating the texture index from the co-occurrence matrix. The calculation of the co-occurrence matrix involves setting parameters such as setting gray level, setting maximum gray level, setting minimum gray level, setting window size, and setting search direction, and the setting of these parameters directly affects the calculation result of the co-occurrence matrix, and further affects the calculation of the texture index. In another related art, when setting parameters such as gray level, maximum gray level, minimum gray level, window size, and search direction, a fixed rule is not given, but these values are set randomly, so that the research result cannot be solidified into a model for popularization and application. In addition, in the related art, when the texture Index is constructed, the texture parameters are randomly combined according to the configuration of a Normalized Difference Vegetation Index (NDVI) to screen an optimal result, so that the constructed texture Index lacks a mechanism explanation, the result of estimating the aboveground biomass based on the texture Index often depends on a data set, and the accuracy of calculating the aboveground biomass of the cotton field is reduced.
In order to solve the technical problems in the related art, the embodiment of the invention provides an aboveground biomass generation method for a cotton field. Fig. 1 is a flowchart of an aboveground biomass generation method for a cotton field according to an embodiment of the present invention, as shown in fig. 1, the method includes:
and 102, counting the number of times that a plurality of pixels with gray level i and pixels with gray level j corresponding to the set search direction in the acquired spectrum band image according to the set window size.
In the embodiment of the invention, each step is executed by computer equipment.
In this step, the number of times that a pixel with a gray level i and a pixel with a gray level j of a green band corresponding to a plurality of set search directions in the acquired spectrum band image are adjacent is counted, wherein i and j can be the same or different.
And 104, constructing a co-occurrence matrix corresponding to each set search direction according to the number of times that the pixel with the gray level i and the pixel with the gray level j corresponding to each set search direction appear simultaneously.
As an alternative, the search direction is set to include 4 directions, for example, the search direction is set to include a 0 ° direction, a 45 ° direction, a 90 ° direction, or a 135 ° direction.
In particular, the co-occurrence matrix can be written as
Figure BDA0002665090650000071
Wherein, GLCM is symbiotic matrix, P (i, j) is the number of times that the pixel with gray level i and the pixel with gray level j appear at the same time. As an alternative, i has a value of 1 to NgJ has a value of 1 to Ng，NgThe maximum value of the gray scale is 15.
And 106, calculating texture indexes according to the co-occurrence matrixes corresponding to each set search direction.
And 108, calculating the triangular spectral index according to the near infrared band reflectivity, the green band reflectivity and the red band reflectivity in the spectral band image.
Specifically, by the formula TVI ═ 0.5 × (120 × (R)nir-Rgreen)-200×(Rred-Rgreen) Computing the near infrared band reflectivity, the green band reflectivity and the red band reflectivity to generate a Triangular spectral Index (TVI), wherein the TVI is the Triangular spectral Index, and R is the Triangular spectral IndexnirIs the reflectivity of the near infrared band, RgreenIs a green band reflectance, RredIs the red band reflectivity.
And 110, generating the aboveground biomass according to the texture index and the triangular spectral index.
Specifically, the texture index and the triangular spectral index are calculated by the formula Biomass ═ a × BTI + b × TVI + c, so as to generate the above-ground Biomass, wherein Biomass is the above-ground Biomass, BTI is the texture index, TVI is the triangular spectral index, and a, b, and c are model parameters. The a, the b and the c can be obtained through a mirror image regression algorithm, and the cotton in different regions, the cotton of different varieties or the cotton growing in different climates have different model parameters.
According to the technical scheme of the aboveground biomass generation method of the cotton field, the number of times that a pixel with a gray level i and a pixel with a gray level j of a green wave band corresponding to a plurality of set search directions in an acquired spectrum wave band image appear at the same time is counted; constructing a co-occurrence matrix corresponding to each set search direction according to the number of times that the pixel with the gray level i and the pixel with the gray level j corresponding to each set search direction appear simultaneously; calculating a texture index according to the co-occurrence matrix corresponding to each set search direction; calculating a triangular spectral index according to the near infrared band reflectivity, the green band reflectivity and the red band reflectivity in the spectral band image; and generating the aboveground biomass according to the texture index and the triangular spectral index. According to the technical scheme provided by the embodiment of the invention, the aboveground biomass can be generated according to the texture index and the triangular spectral index calculated by the spectral band image, and the accuracy of generating the aboveground biomass of the cotton field is improved.
The embodiment of the invention provides another aboveground biomass generation method for a cotton field. Fig. 2 is a flowchart illustrating another aboveground biomass production method for a cotton field according to an embodiment of the present invention, and fig. 3 is a schematic diagram illustrating another aboveground biomass production method for a cotton field according to an embodiment of the present invention, as shown in fig. 2 and 3, the method includes:
step 202, acquiring a spectrum band image shot by the unmanned aerial vehicle.
In the embodiment of the invention, each step is executed by computer equipment.
Step 202 is preceded by: the multispectral camera carried on the unmanned aerial vehicle shoots the spectrum wave band image of the cotton field. Alternatively, the multispectral camera mounted on the drone can capture the spectral band images within a set period of time, for example, the multispectral camera mounted on the drone captures the spectral band images when there is no cloud in the clear between 10:00-14: 00. The unmanned aerial vehicle needs to fly at a set height, and a multispectral camera carried on the unmanned aerial vehicle needs to shoot a spectral band image at a set course overlapping rate, a set side overlapping rate and a set ground resolution corresponding to an image, wherein the set height comprises 40m, the set course overlapping rate comprises 75%, the set side overlapping rate comprises 75%, and the set ground resolution corresponding to the image comprises 2.82 cm.
In the embodiment of the invention, the spectrum waveband image comprises a blue light waveband image, a green light waveband image, a red side waveband image and a near infrared waveband image. The green band image comprises green band reflectivity, the red band image comprises red band reflectivity, and the near infrared band image comprises near infrared band reflectivity.
As an alternative, the computer device receives the spectral band images captured by the drone.
And step 204, setting the calculated window size according to the target area.
In the embodiment of the invention, according to the size of the defined window, in order to estimate the aboveground biomass information of the cotton of each operation unit, the size of the window is set to be the same as that of the target area when each target area is calculated. The window size includes the accurate operation unit of cotton, and the target area includes the operation unit.
And step 206, taking the maximum value of the gray value of the green wave band in the spectrum wave band image as a set maximum value of gray value.
In the embodiment of the present invention, the set maximum value of the gray scale can be set according to the maximum value of the gray scale of the spectrum band image, and the set maximum value of the gray scale is used for indicating the upper limit of the gray scale value.
And step 208, taking the minimum value of the gray value of the green wave band in the spectrum wave band image as a set minimum value of gray value.
In the embodiment of the present invention, the minimum set gray value can be set according to the minimum gray value of the spectral band image, and the minimum set gray value is used to indicate the lower limit of the gray value.
And step 210, dividing the gray level of the green wave band in the spectrum wave band image into gray setting levels. In the embodiment of the present invention, the gray setting level includes 15 levels.
In the embodiment of the invention, the upper limit and the lower limit of the grading can be set according to the maximum value and the minimum value of the gray value of the green band image, and the gray level is divided into 15 levels.
And step 212, determining the gray level of each pixel of the green band corresponding to each set search direction in the spectrum band image according to the set gray maximum value, the set gray minimum value and the gray set level.
In the embodiment of the invention, the spectrum band image comprises a plurality of pixels, and each pixel has a gray value.
In this step, for example, 15 equal divisions are performed between the set maximum value and the set minimum value of the gray scale of the target region, and each part of the target region is named in the order from large to small, and the gray scale value of the pixel falls into which class, that is, which gray scale level.
And step 214, counting the number of times that a plurality of pixels with gray level i and gray level j of the green band corresponding to the set search direction appear simultaneously in the acquired spectrum band image.
In this step, the number of times that the pixel with the gray level i and the pixel with the gray level j appear simultaneously includes the number of times that the pixel with the gray level i and the pixel with the gray level j are adjacent to each other, where i and j may be the same or different.
Fig. 4 is a schematic diagram of the number of times that a pixel with a gray level i and a pixel with a gray level j simultaneously appear, as shown in fig. 4, in the 0 ° direction, when i is 1 and j is 1, the number of times that the pixel with a gray level 1 and the pixel with a gray level 1 are adjacent is 1, that is, the number of times that the pixel with a gray level 1 and the pixel with a gray level 1 simultaneously appear is 1; when i is 3 and j is 1, the number of times that the pixel with the gray level of 3 is adjacent to the pixel with the gray level of 1 is 1.
And step 216, constructing a co-occurrence matrix corresponding to each set search direction according to the number of times that the pixel with the gray level i and the pixel with the gray level j corresponding to each set search direction appear simultaneously.
In particular, the co-occurrence matrix can be written as
Figure BDA0002665090650000101
Wherein, GLCM is symbiotic matrix, P (i, j) is the number of times that the pixel with gray level i and the pixel with gray level j appear at the same time. As an alternative, i has a value of 1 to NgJ has a value of 1 to Ng，NgIs the maximum value of the gray level.
And step 218, calculating texture indexes according to the co-occurrence matrixes corresponding to the set search directions.
In an embodiment of the present invention, fig. 5 is a flowchart of calculating a texture index in fig. 2, and as shown in fig. 5, step 218 specifically includes:
and 2182, calculating the probability of simultaneous occurrence of the pixel with the gray level i and the pixel with the gray level j corresponding to each set search direction according to the number of times of simultaneous occurrence of the pixel with the gray level i and the pixel with the gray level j in the co-occurrence matrix corresponding to each set search direction and the sum of elements in the co-occurrence matrix.
Specifically, the number of times that a pixel with a gray level i and a pixel with a gray level j simultaneously appear in a co-occurrence matrix corresponding to each set search direction and the sum of elements in the co-occurrence matrix are calculated by a formula P (i, j) ═ P (i, j)/R, so as to generate the probability that the pixel with the gray level i and the pixel with the gray level j simultaneously appear, wherein P (i, j) is the probability that the pixel with the gray level i and the pixel with the gray level j simultaneously appear, P (i, j) is the number of times that the pixel with the gray level i and the pixel with the gray level j simultaneously appear, and R is the sum of elements in the gray level co-occurrence matrix.
And 2184, calculating the contrast of the green band according to the probability that the pixel with the gray level i and the pixel with the gray level j corresponding to each set search direction occur at the same time.
In particular, by the formula
Figure BDA0002665090650000111
Performing calculation to generate contrast of green band, wherein CONgIs the contrast of the green band, p (i, j) is the probability of the pixel with the gray level i and the pixel with the gray level j appearing simultaneously, and the value of i is 1 to NgJ has a value of 1 to Ng，NgIs the maximum value of the gray level.
And 2186, calculating the inverse difference moment of the green band according to the probability that the pixel with the gray level i and the pixel with the gray level j corresponding to each set search direction occur at the same time.
In particular, by the formula
Figure BDA0002665090650000112
Calculating to generate inverse difference moment of green band, wherein IDMgIs the inverse difference moment of the green band, p (i, j) is the probability of the simultaneous occurrence of the pixel with the gray level i and the pixel with the gray level j, and the value of i is 1 to NgJ has a value of 1 to Ng，NgIs the maximum value of the gray level.
Step 2188, generating an average contrast according to the contrasts corresponding to the plurality of set search directions. .
Specifically, the average contrast is generated by averaging the contrasts corresponding to the plurality of set search directions.
Step 2190 generates an average negative moment from the negative moments corresponding to the plurality of set search directions.
Specifically, the average inverse difference moments corresponding to a plurality of set search directions are averaged to generate an average inverse difference moment.
And 2192, generating a texture index according to the average contrast and the average inverse difference moment.
In particular toGround through the formula
Figure BDA0002665090650000121
Calculating to generate texture index, wherein BTI is texture index, CONgFor average contrast, IDMgThe mean moment of dissimilarity.
In the embodiment of the application, the cotton is usually planted in a mulching film mode, the pixels corresponding to each soil show uniform reflectivity due to the mulching film, the pixels corresponding to the cotton can be located at different parts of a plant, and the difference of the reflectivity between the pixels corresponding to the cotton is usually larger than the difference between the pixels corresponding to the soil along with the change of the proportion of the stems and the leaves of the plant. Therefore, as the cotton grows, the biomass is increased, the pixels corresponding to the soil are gradually replaced by the pixels corresponding to the vegetation, the contrast is increased, the adverse moment is reduced, and the texture index is increased.
And step 220, calculating the triangular spectral index according to the near infrared band reflectivity, the green band reflectivity and the red band reflectivity in the spectral band image.
In the embodiment of the present invention, please refer to step 108 for detailed description of step 220.
And step 222, generating the aboveground biomass according to the texture index and the triangular spectral index.
In the embodiment of the present invention, please refer to step 110 for a detailed description of step 222.
According to the technical scheme of the aboveground biomass generation method of the cotton field, the number of times that a pixel with a gray level i and a pixel with a gray level j of a green wave band corresponding to a plurality of set search directions in an acquired spectrum wave band image appear at the same time is counted; constructing a co-occurrence matrix corresponding to each set search direction according to the number of times that the pixel with the gray level i and the pixel with the gray level j corresponding to each set search direction appear simultaneously; calculating a texture index according to the co-occurrence matrix corresponding to each set search direction; calculating a triangular spectral index according to the near infrared band reflectivity, the green band reflectivity and the red band reflectivity in the spectral band image; and generating the aboveground biomass according to the texture index and the triangular spectral index. According to the technical scheme provided by the embodiment of the invention, the aboveground biomass can be generated according to the texture index and the triangular spectral index calculated by the spectral band image, and the accuracy of generating the aboveground biomass of the cotton field is improved.
According to the technical scheme provided by the embodiment of the invention, the texture index can be calculated based on the spectrum band image shot by the unmanned aerial vehicle so as to generate the aboveground biomass of the cotton field. According to the method, the spectrum image shot by the low-altitude unmanned aerial vehicle is fully utilized to have better texture information, and the aboveground biomass of the cotton field is inverted by calculating the texture index, so that the inversion error is weakened, and the inversion accuracy of the aboveground biomass of the cotton field is improved.
According to the technical scheme provided by the embodiment of the invention, the soil background in the spectral band image is not required to be removed in the process of generating the aboveground biomass of the cotton field, so that the efficiency of generating the aboveground biomass of the cotton field is improved.
The embodiment of the invention provides an overground biomass generation device for a cotton field. Fig. 6 is a schematic structural diagram of an above-ground biomass generation device for a cotton field according to an embodiment of the present invention, as shown in fig. 6, the device includes: a statistics module 11, a construction module 12, a first calculation module 13, a second calculation module 14 and a first generation module 15.
The counting module 11 is configured to count, according to the set window size, the number of times that a plurality of pixels with a gray level i and a gray level j in a green band corresponding to the set search direction appear simultaneously in the acquired spectrum band image.
The constructing module 12 is configured to construct a co-occurrence matrix corresponding to each set search direction according to the number of times that the pixel with the gray level i and the pixel with the gray level j corresponding to each set search direction appear simultaneously.
The first calculating module 13 is configured to calculate a texture index according to the co-occurrence matrix corresponding to each set search direction.
The second calculating module 14 is configured to calculate a triangular spectral index according to the near-infrared band reflectivity, the green band reflectivity, and the red band reflectivity in the spectral band image.
The first generation module 15 is used to generate aboveground biomass from the texture index and the triangular spectral index.
In the embodiment of the present invention, the apparatus further includes: the device comprises an acquisition module 16, a selection module 17, a second generation module 18, a third generation module 19 and a determination module 20.
The acquisition module 16 is configured to acquire a spectrum band image captured by the unmanned aerial vehicle, where the spectrum band image includes a target area.
The first setting module 17 is configured to set the calculated window size according to the target area.
The second setting module 18 is configured to use the maximum value of the gray scale value of the green band in the spectrum band image as a maximum value of a set gray scale.
The third setting module 19 is configured to use the minimum gray value of the green band in the spectrum band image as a set minimum gray value.
The dividing module 20 is configured to divide the gray level of the green band in the spectrum band image into gray setting levels.
The determining module 21 is configured to determine a gray level of each pixel of a green band corresponding to each set search direction in the spectrum band image according to the set gray maximum value, the set gray minimum value, and the gray setting level.
In the embodiment of the present invention, the first calculating module 13 specifically includes: a first computation submodule 131, a second computation submodule 132, a third computation submodule 133, a first generation submodule 134, a second generation submodule 135 and a third generation submodule 136.
The first calculating submodule 131 is configured to calculate a probability that a pixel with a gray level i and a pixel with a gray level j corresponding to each set search direction occur simultaneously according to the number of times that the pixel with a gray level i and the pixel with a gray level j occur simultaneously in the co-occurrence matrix corresponding to each set search direction and the sum of elements in the co-occurrence matrix.
The second calculating submodule 132 is configured to calculate the contrast of the green band according to the probability that the pixel with the gray level i and the pixel with the gray level j corresponding to each set search direction occur at the same time.
The third calculating submodule 133 is configured to calculate an inverse difference moment of the green band according to a probability that a pixel with a gray level i and a pixel with a gray level j corresponding to each set search direction occur at the same time.
The first generating submodule 134 is configured to generate an average contrast according to contrasts corresponding to a plurality of set search directions.
The second generating submodule 135 is configured to generate an average inverse difference moment according to the inverse difference moments corresponding to the plurality of set search directions.
The third generation submodule 136 is configured to generate a texture index based on the average contrast and the average inverse difference moment.
In the embodiment of the present invention, the second calculating module 14 is specifically configured to use the formula TVI ═ 0.5 × (120 × (R ×)nir-Rgreen)-200×(Rred-Rgreen) Computing the near infrared band reflectivity, the green band reflectivity and the red band reflectivity to generate a triangular spectral index, wherein TVI is the triangular spectral index, R is the triangular spectral indexnirIs the reflectivity of the near infrared band, RgreenIs a green band reflectance, RredIs the red band reflectivity.
In this embodiment of the present invention, the first generating module 15 is specifically configured to calculate the texture index and the triangular spectral index by using a formula, "a × BTI + b × TVI + c", to generate the above-ground Biomass, where the biological mass is the above-ground Biomass, the BTI is the texture index, the TVI is the triangular spectral index, and a, b, and c are model parameters.
In the embodiment of the present invention, the third generation submodule 136 is specifically configured to pass through a formula
Figure BDA0002665090650000151
Calculating average contrast and average inverse difference moment to generate texture index, wherein BTI is texture index, CON is texture indexgFor average contrast, IDMgThe mean moment of dissimilarity.
In this embodiment of the present invention, the first generating sub-module 134 is specifically configured to perform average calculation on the contrasts corresponding to the multiple set search directions, so as to generate an average contrast.
In this embodiment of the present invention, the second generating sub-module 135 is specifically configured to perform average calculation on the inverse difference moments corresponding to the plurality of set search directions to generate an average inverse difference moment. The above-ground biomass generation device of the cotton field provided by the embodiment can be used for realizing the above-ground biomass generation method of the cotton field in fig. 1 and fig. 2, and specific description can be referred to the above-ground biomass generation method of the cotton field, and the description is not repeated here.
According to the technical scheme of the aboveground biomass generation method of the cotton field, the number of times that a pixel with a gray level i and a pixel with a gray level j of a green wave band corresponding to a plurality of set search directions in an acquired spectrum wave band image appear at the same time is counted; constructing a co-occurrence matrix corresponding to each set search direction according to the number of times that the pixel with the gray level i and the pixel with the gray level j corresponding to each set search direction appear simultaneously; calculating a texture index according to the co-occurrence matrix corresponding to each set search direction; calculating a triangular spectral index according to the near infrared band reflectivity, the green band reflectivity and the red band reflectivity in the spectral band image; and generating the aboveground biomass according to the texture index and the triangular spectral index. According to the technical scheme provided by the embodiment of the invention, the aboveground biomass can be generated according to the texture index and the triangular spectral index calculated by the spectral band image, and the accuracy of generating the aboveground biomass of the cotton field is improved.
The embodiment of the invention provides a storage medium, which comprises a stored program, wherein when the program runs, the equipment where the storage medium is located is controlled to execute the steps of the above-ground biomass generation method of the cotton field, and the specific description can refer to the above-ground biomass generation method of the cotton field.
Embodiments of the present invention provide a computer apparatus comprising a memory for storing information including program instructions and a processor for controlling execution of the program instructions, the program instructions being loaded into and executed by the processor to perform the steps of the above-described embodiments of the above-ground biomass generation method for a cotton field, as described in detail with reference to the above-described embodiments of the above-ground biomass generation method for a cotton field.
Fig. 7 is a schematic diagram of a computer device according to an embodiment of the present invention. As shown in fig. 7, the computer device 30 of this embodiment includes: a processor 31, a memory 32 and a computer program 33 stored in the memory 32 and capable of running on the processor 31, wherein the computer program 33 when executed by the processor 31 implements the above-ground biomass generation method applied to the cotton field in the embodiment, and for avoiding repetition, the details are not repeated herein. Alternatively, the computer program is executed by the processor 31 to implement the functions of each model/unit in the above-ground biomass generation device applied to the cotton field in the embodiment, and in order to avoid repetition, the description is omitted here.
The computer device 30 includes, but is not limited to, a processor 31, a memory 32. Those skilled in the art will appreciate that fig. 7 is merely an example of a computer device 30 and is not intended to limit the computer device 30 and that it may include more or fewer components than shown, or some components may be combined, or different components, e.g., the computer device may also include input output devices, network access devices, buses, etc.
The Processor 31 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The storage 32 may be an internal storage unit of the computer device 30, such as a hard disk or a memory of the computer device 30. The memory 32 may also be an external storage device of the computer device 30, such as a plug-in hard disk provided on the computer device 30, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like. Further, the memory 32 may also include both internal and external storage units of the computer device 30. The memory 32 is used for storing computer programs and other programs and data required by the computer device. The memory 32 may also be used to temporarily store data that has been output or is to be output.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the embodiments provided in the present invention, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions in actual implementation, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
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 units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) or a Processor (Processor) to execute some steps of the methods according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.

Claims (10)

1. A method of aboveground biomass generation in a cotton field, comprising:
counting the number of times that a plurality of pixels with gray level i and pixels with gray level j of a green waveband corresponding to a set search direction in the acquired spectrum waveband image according to the set window size;
constructing a co-occurrence matrix corresponding to each set search direction according to the number of times that the pixel with the gray level i and the pixel with the gray level j corresponding to each set search direction appear simultaneously;
calculating a texture index according to the co-occurrence matrix corresponding to each set search direction;
calculating a triangular spectral index according to the near infrared band reflectivity, the green band reflectivity and the red band reflectivity in the spectral band image;
and generating aboveground biomass according to the texture index and the triangular spectral index.
2. The method of claim 1, wherein counting the number of times that a pixel with a gray level i and a pixel with a gray level j occur simultaneously in the acquired image of the spectral band comprises:
acquiring the spectrum band image shot by the unmanned aerial vehicle, wherein the spectrum band image comprises a target area;
setting the size of a calculated window according to the target area;
taking the maximum value of the gray value of the green wave band in the spectrum wave band image as a set maximum value of gray;
taking the minimum value of the gray value of the green wave band in the spectrum wave band image as a set minimum value of gray;
dividing the gray level of the green wave band in the spectrum wave band image into gray level setting levels;
and determining the gray level of each pixel of the green wave band corresponding to each set search direction in the spectrum wave band image according to the set gray maximum value, the set gray minimum value and the gray set level.
3. The method according to claim 1, wherein the calculating the texture index according to the co-occurrence matrix corresponding to each set search direction comprises:
calculating the probability of the simultaneous occurrence of the pixel with the gray level i and the pixel with the gray level j corresponding to each set search direction according to the number of times of the simultaneous occurrence of the pixel with the gray level i and the pixel with the gray level j in the co-occurrence matrix corresponding to each set search direction and the sum of elements in the co-occurrence matrix;
calculating the contrast of a green band according to the probability that the pixel with the gray level i and the pixel with the gray level j corresponding to each set search direction appear at the same time;
calculating the inverse difference moment of the green wave band according to the probability that the pixel with the gray level i and the pixel with the gray level j corresponding to each set search direction appear at the same time;
generating average contrast according to the contrasts corresponding to the plurality of set search directions;
generating an average inverse difference moment according to the inverse difference moment corresponding to each set search direction;
and generating a texture index according to the average contrast and the average inverse difference moment.
4. The method of claim 1, wherein calculating the triangular spectral index from the near infrared band reflectivity, the green band reflectivity, and the red band reflectivity in the spectral band image comprises:
by the formula TVI 0.5 × (120 × (R)nir-Rgreen)-200×(Rred-Rgreen) The near infrared band reflectivity, the green band reflectivity and the red band reflectivity are calculated to generate the triangular spectral index, wherein TVI is the triangular spectral index, R is the triangular spectral indexnirIs the near infrared band reflectivity, RgreenIs the green band reflectivity, RredIs the red band reflectivity.
5. The method of claim 1, wherein the generating aboveground biomass from the texture index and the triangular spectral index comprises:
and calculating the texture index and the triangular spectral index by a formula of Biomass ═ a × BTI + b × TVI + c, and generating the above-ground Biomass, wherein Biomass is the above-ground Biomass, BTI is the texture index, TVI is the triangular spectral index, and a, b and c are model parameters.
6. The method of claim 3, wherein generating the texture index from the average contrast and the average inverse difference moment comprises:
by the formula
Figure FDA0002665090640000021
Calculating the average contrast and the average inverse difference moment to generate the texture index, wherein BTI is the texture index, CONgFor said average contrast, IDMgIs the average inverse difference moment.
7. The method of claim 3, wherein generating the average contrast according to the contrasts corresponding to the plurality of set search directions comprises:
carrying out average calculation on the contrasts corresponding to a plurality of set search directions to generate the average contrast;
the generating the average inverse difference moment according to the inverse difference moments corresponding to the plurality of set search directions includes:
and carrying out average calculation on the adverse difference moments corresponding to a plurality of set search directions to generate the average adverse difference moment.
8. An above-ground biomass production device for a cotton field, comprising:
the counting module is used for counting the number of times that a plurality of pixels with gray level i and pixels with gray level j corresponding to the set search direction appear simultaneously in the acquired spectrum band image according to the set window size;
the construction module is used for constructing a co-occurrence matrix corresponding to each set search direction according to the number of times that the pixel with the gray level i and the pixel with the gray level j corresponding to each set search direction appear simultaneously;
the first calculation module is used for calculating texture indexes according to the symbiotic matrix corresponding to each set search direction;
the second calculation module is used for calculating the triangular spectral index according to the near infrared band reflectivity, the green band reflectivity and the red band reflectivity in the spectral band image;
a first generation module for generating aboveground biomass from the texture index and the triangular spectral index.
9. A storage medium, comprising: the storage medium includes a stored program, wherein the program, when executed, controls an apparatus in which the storage medium is located to perform the above-ground biomass generation method for a cotton field of any one of claims 1 to 7.
10. A computer device comprising a memory for storing information including program instructions and a processor for controlling the execution of the program instructions, wherein the program instructions are loaded and executed by the processor to implement the steps of the above-ground biomass generation method of a cotton field of any one of claims 1 to 7.
CN202010916168.2A 2020-09-03 2020-09-03 Method and device for generating aboveground biomass of cotton field Active CN111985849B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010916168.2A CN111985849B (en) 2020-09-03 2020-09-03 Method and device for generating aboveground biomass of cotton field

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010916168.2A CN111985849B (en) 2020-09-03 2020-09-03 Method and device for generating aboveground biomass of cotton field

Publications (2)

Publication Number Publication Date
CN111985849A true CN111985849A (en) 2020-11-24
CN111985849B CN111985849B (en) 2024-05-14

Family

ID=73447491

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010916168.2A Active CN111985849B (en) 2020-09-03 2020-09-03 Method and device for generating aboveground biomass of cotton field

Country Status (1)

Country Link
CN (1) CN111985849B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105608293A (en) * 2016-01-28 2016-05-25 武汉大学 Forest aboveground biomass inversion method and system fused with spectrum and texture features
CN108427862A (en) * 2018-03-02 2018-08-21 华中农业大学 Multi items time of infertility cotton biomass non-destructive measuring method based on image analysis
CN109459392A (en) * 2018-11-06 2019-03-12 南京农业大学 A kind of rice the upperground part biomass estimating and measuring method based on unmanned plane multispectral image
CN111242934A (en) * 2020-01-16 2020-06-05 中国科学院地理科学与资源研究所 Wheat nitrogen concentration inversion method based on unmanned aerial vehicle image spectrum and texture features

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105608293A (en) * 2016-01-28 2016-05-25 武汉大学 Forest aboveground biomass inversion method and system fused with spectrum and texture features
CN108427862A (en) * 2018-03-02 2018-08-21 华中农业大学 Multi items time of infertility cotton biomass non-destructive measuring method based on image analysis
CN109459392A (en) * 2018-11-06 2019-03-12 南京农业大学 A kind of rice the upperground part biomass estimating and measuring method based on unmanned plane multispectral image
CN111242934A (en) * 2020-01-16 2020-06-05 中国科学院地理科学与资源研究所 Wheat nitrogen concentration inversion method based on unmanned aerial vehicle image spectrum and texture features

Non-Patent Citations (33)

* Cited by examiner, † Cited by third party
Title
PENGFEI CHEN等: "New Textural Indicators for Assessing Above-Ground Cotton Biomass Extracted from Optical Imagery Obtained via Unmanned Aerial Vehicle", REMOTE SENSING, vol. 12, no. 24, 19 December 2020 (2020-12-19) *
冯雷;方慧;周伟军;黄敏;何勇;: "基于多光谱视觉传感技术的油菜氮含量诊断方法研究", 光谱学与光谱分析, no. 09, 28 September 2006 (2006-09-28) *
刘新华;舒宁;: "纹理特征在多光谱遥感影像分类中的应用", 测绘信息与工程, no. 03 *
刘新华;舒宁;: "纹理特征在多光谱遥感影像分类中的应用", 测绘信息与工程, no. 03, 30 June 2006 (2006-06-30) *
刘畅;杨贵军;李振海;汤伏全;王建雯;张春兰;张丽妍;: "融合无人机光谱信息与纹理信息的冬小麦生物量估测", 中国农业科学, no. 16 *
刘畅;杨贵军;李振海;汤伏全;王建雯;张春兰;张丽妍;: "融合无人机光谱信息与纹理信息的冬小麦生物量估测", 中国农业科学, no. 16, 20 August 2018 (2018-08-20) *
夏怀英;郭平;: "基于统计混合模型的遥感影像阴影检测", 遥感学报, no. 04 *
夏怀英;郭平;: "基于统计混合模型的遥感影像阴影检测", 遥感学报, no. 04, 15 July 2011 (2011-07-15) *
常利利;马俊;邓中民;蒋蕾;: "基于灰度共生矩阵的织物组织结构差异分析", 纺织学报, no. 10 *
常利利;马俊;邓中民;蒋蕾;: "基于灰度共生矩阵的织物组织结构差异分析", 纺织学报, no. 10, 15 October 2008 (2008-10-15) *
张学儒;刘林山;张镱锂;张继平;聂勇;张华;: "基于ENVI ZOOM面向对象的高海拔灌丛植被提取――以定日县为例", 地理与地理信息科学, no. 04 *
张学儒;刘林山;张镱锂;张继平;聂勇;张华;: "基于ENVI ZOOM面向对象的高海拔灌丛植被提取――以定日县为例", 地理与地理信息科学, no. 04, 15 July 2010 (2010-07-15) *
张爱武等: "Landsat８光谱衍生数据分类体系下的牧草生物量反演", 光谱学与光谱分析, vol. 40, no. 1, pages 240 *
彭光雄;李京;何宇华;胡德勇;: "利用纹理分析方法提取CBERS02星CCD图像土地覆盖信息", 遥感技术与应用, no. 01 *
彭光雄;李京;何宇华;胡德勇;: "利用纹理分析方法提取CBERS02星CCD图像土地覆盖信息", 遥感技术与应用, no. 01, 30 March 2007 (2007-03-30) *
曹庆先;徐大平;鞠洪波;: "北部湾沿海5种红树林群落生物量的遥感估算", 广西科学, no. 03 *
曹庆先;徐大平;鞠洪波;: "北部湾沿海5种红树林群落生物量的遥感估算", 广西科学, no. 03, 15 August 2011 (2011-08-15) *
李利红;张华国;厉冬玲;史爱琴;王小珍;: "基于多尺度纹理和光谱信息的海岛土地利用遥感分类方法研究", 海洋学研究, no. 02 *
李利红;张华国;厉冬玲;史爱琴;王小珍;: "基于多尺度纹理和光谱信息的海岛土地利用遥感分类方法研究", 海洋学研究, no. 02, 15 June 2013 (2013-06-15) *
李智峰;朱谷昌;董泰锋;: "基于灰度共生矩阵的图像纹理特征地物分类应用", 地质与勘探, no. 03 *
李智峰;朱谷昌;董泰锋;: "基于灰度共生矩阵的图像纹理特征地物分类应用", 地质与勘探, no. 03, 15 May 2011 (2011-05-15) *
杨俊;丁峰;陈晨;刘涛;孙成明;丁大伟;霍中洋;: "小麦生物量及产量与无人机图像特征参数的相关性", 农业工程学报, no. 23 *
杨俊;丁峰;陈晨;刘涛;孙成明;丁大伟;霍中洋;: "小麦生物量及产量与无人机图像特征参数的相关性", 农业工程学报, no. 23, 8 December 2019 (2019-12-08) *
王宏光;刘义范;: "基于灰度共生矩阵的影像纹理特征研究", 测绘通报, no. 02 *
王宏光;刘义范;: "基于灰度共生矩阵的影像纹理特征研究", 测绘通报, no. 02, 25 February 2013 (2013-02-25) *
王昆;张晓丽;王珊;焦志敏;宁亮亮;吴石磊;: "鹫峰地区QuickBird影像纹理特征与生物量估测关系初探", 地理与地理信息科学, no. 03 *
王昆;张晓丽;王珊;焦志敏;宁亮亮;吴石磊;: "鹫峰地区QuickBird影像纹理特征与生物量估测关系初探", 地理与地理信息科学, no. 03, 15 May 2013 (2013-05-15) *
白雪冰;王克奇;王辉;: "基于灰度共生矩阵的木材纹理分类方法的研究", 哈尔滨工业大学学报, no. 12 *
白雪冰;王克奇;王辉;: "基于灰度共生矩阵的木材纹理分类方法的研究", 哈尔滨工业大学学报, no. 12, 28 December 2005 (2005-12-28) *
陈鹏飞等: "估测作物冠层生物量的新植被指数的研究", 光谱学与光谱分析, vol. 30, no. 2, pages 513 *
陈鹏飞等: "基于低空无人机影像光谱和纹理特征的棉花氮素营养诊断研究", 中国农业科学, vol. 52, no. 13, 1 July 2019 (2019-07-01) *
高士忠;: "基于灰度共生矩阵的织物纹理分析", 计算机工程与设计, no. 16 *
高士忠;: "基于灰度共生矩阵的织物纹理分析", 计算机工程与设计, no. 16, 28 August 2008 (2008-08-28) *

Also Published As

Publication number Publication date
CN111985849B (en) 2024-05-14

Similar Documents

Publication Publication Date Title
Chen et al. Strawberry yield prediction based on a deep neural network using high-resolution aerial orthoimages
Ma et al. Estimating above ground biomass of winter wheat at early growth stages using digital images and deep convolutional neural network
CN111406261B (en) Computer-implemented method for detecting infected object from large-field-of-view image
US11521380B2 (en) Shadow and cloud masking for remote sensing images in agriculture applications using a multilayer perceptron
CN107389036A (en) A kind of large spatial scale vegetation coverage computational methods of combination unmanned plane image
Sharifi Estimation of biophysical parameters in wheat crops in Golestan province using ultra-high resolution images
CN111815014A (en) Crop yield prediction method and system based on unmanned aerial vehicle low-altitude remote sensing information
Xu et al. Classification method of cultivated land based on UAV visible light remote sensing
KR20220119645A (en) Estimation of crop type and/or sowing date
Bai et al. A fast and robust method for plant count in sunflower and maize at different seedling stages using high-resolution UAV RGB imagery
CN115861858B (en) Small sample learning crop canopy coverage calculating method based on background filtering
CN113052102A (en) Farmland management partitioning method and device based on multispectral image of unmanned aerial vehicle
Yang et al. Fraction vegetation cover extraction of winter wheat based on RGB image obtained by UAV
Din et al. Onion Crop Monitoring with Multispectral Imagery Using Deep Neural Network
CN110321774A (en) Crops evaluation methods for disaster condition, device, equipment and computer readable storage medium
CN117372503B (en) River and lake shore zone vegetation classification and coverage calculation method and system
CN112632796A (en) Nitrogen content determination method, operation method, device, electronic device and storage medium
CN116721344A (en) Vegetation detection method, device and equipment based on aerial photographing equipment
CN111610159A (en) Earth surface temperature downscaling estimation method and vegetation water stress monitoring method
CN111985849A (en) Overground biomass generation method and device for cotton field
JPWO2020070852A1 (en) Learning equipment, image processing equipment, learning methods and learning programs
CN115598071A (en) Plant growth distribution state detection method and device
CN114842360A (en) Pasturing area drought identification method, system and management platform
Yang et al. New method for cotton fractional vegetation cover extraction based on UAV RGB images
Zhang et al. Automatic identification of soil and water conservation measures from centimeter-resolution unmanned aerial vehicle imagery

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant