CN113063742A - Method and system for measuring vegetation biomass, storage medium and terminal - Google Patents
Method and system for measuring vegetation biomass, storage medium and terminal Download PDFInfo
- Publication number
- CN113063742A CN113063742A CN202110315601.1A CN202110315601A CN113063742A CN 113063742 A CN113063742 A CN 113063742A CN 202110315601 A CN202110315601 A CN 202110315601A CN 113063742 A CN113063742 A CN 113063742A
- Authority
- CN
- China
- Prior art keywords
- vegetation
- image
- visible light
- hyperspectral
- biomass
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000002028 Biomass Substances 0.000 title claims abstract description 87
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000003860 storage Methods 0.000 title claims abstract description 11
- 238000007637 random forest analysis Methods 0.000 claims abstract description 16
- 230000001419 dependent effect Effects 0.000 claims abstract description 9
- 238000012937 correction Methods 0.000 claims description 20
- 238000012360 testing method Methods 0.000 claims description 12
- 238000000691 measurement method Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 238000007689 inspection Methods 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 5
- 238000003379 elimination reaction Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000008030 elimination Effects 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 6
- 238000012544 monitoring process Methods 0.000 abstract description 3
- 235000002595 Solanum tuberosum Nutrition 0.000 description 51
- 244000061456 Solanum tuberosum Species 0.000 description 51
- 235000012015 potatoes Nutrition 0.000 description 23
- 241000196324 Embryophyta Species 0.000 description 7
- 238000011835 investigation Methods 0.000 description 4
- 238000005303 weighing Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000009406 nutrient management Methods 0.000 description 2
- 239000002689 soil Substances 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 238000012271 agricultural production Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000000280 densification Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 239000003337 fertilizer Substances 0.000 description 1
- 238000011545 laboratory measurement Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 235000015097 nutrients Nutrition 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000005416 organic matter Substances 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0098—Plants or trees
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/01—Satellite radio beacon positioning systems transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/13—Receivers
- G01S19/14—Receivers specially adapted for specific applications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N2021/1793—Remote sensing
- G01N2021/1797—Remote sensing in landscape, e.g. crops
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Radar, Positioning & Navigation (AREA)
- Immunology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Remote Sensing (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Biology (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Botany (AREA)
- Wood Science & Technology (AREA)
- Food Science & Technology (AREA)
- Medicinal Chemistry (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Computer Networks & Wireless Communication (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a vegetation biomass measuring method, a vegetation biomass measuring system, a storage medium and a terminal, which belong to the technical field of vegetation growth monitoring, and are used for collecting visible light images and hyperspectral images of vegetation; respectively correcting the visible light image and the hyperspectral image to obtain a visible light orthographic image and a hyperspectral orthographic image of each wave band; acquiring a digital earth surface model and a vegetation index based on a visible light orthophoto map and a hyperspectral orthophoto map, and calculating the vegetation height based on the digital earth surface model; collecting dry and wet biomass of vegetation in a region corresponding to the visible light image and the hyperspectral image; the vegetation index and the vegetation height are used as independent variables, the dry and wet biomass of the vegetation is used as continuous dependent variables, a random forest regression prediction model is established, the overground biomass prediction of the vegetation is realized based on the prediction model, the growth process of the vegetation is monitored, the working efficiency of the whole process is high, and the labor cost can be saved.
Description
Technical Field
The invention relates to the technical field of vegetation growth monitoring, in particular to a method and a system for measuring vegetation biomass, a storage medium and a terminal.
Background
Vegetation biomass can be defined as the total amount of organic matter accumulated by an organism or a community over a period of time, and is generally defined as the amount of dry or wet unknown or energy accumulated per unit time or per unit area planted. The biomass on the vegetation land is closely related to the nutrient management and the yield of the biomass, the vegetation yield can be effectively forecasted by accurately measuring the dynamic change of the biomass on the vegetation land, and the nutrient management can be effectively carried out on different land parcels according to the nutrient demand, so that the application of chemical fertilizers is reduced, the cost is reduced, and the influence on the environment is reduced. Taking crops as an example, on the premise of limited cultivated land area, the yield of the crops is improved, the negative influence on the ecological environment is reduced, and the method is of great importance for ensuring the global grain safety.
In the prior art, the sample plot survey and the modeling of satellite remote sensing images are common methods for estimating biomass on vegetation ground. The sample plot survey is to sample in a planting area and send the planting area to a laboratory for weighing and measuring the biomass, and although the laboratory measurement can ensure the precision, the randomly selected sample has great uncertainty and is difficult to represent the biomass of a planted community because the difference between crops and plants is large; meanwhile, the sample plot investigation is time-consuming and labor-consuming, and is difficult to popularize and use in large-scale crop planting. The satellite remote sensing technology has been developed rapidly and successfully applied to agricultural production in recent years, and although the problems that sample plot investigation is time-consuming and labor-consuming in sample plot investigation and the like can be solved to a certain extent, the satellite acquired image is affected by weather conditions, effective image information cannot be acquired particularly when cloud cover is covered, and vegetation biomass information cannot be accurately predicted. The laser radar is also applied to crop investigation, and can accurately measure the vegetation height and structure, however, the laser radar is high in cost and long in image acquisition time, and the use of the laser radar is influenced by the terrain and traffic, so that the laser radar is not suitable for large-scale use in agricultural practice production.
Disclosure of Invention
The invention aims to solve the problems of low accuracy and low working efficiency of a vegetation biomass measuring method in the prior art, and provides a vegetation biomass measuring method, a system, a storage medium and a terminal.
The purpose of the invention is realized by the following technical scheme: a method of measuring an amount of vegetation biomass, the method comprising the steps of:
collecting a visible light image and a hyperspectral image of vegetation;
respectively correcting the visible light image and the hyperspectral image to obtain a visible light orthographic image and a hyperspectral orthographic image of each wave band;
acquiring a digital earth surface model and a vegetation index based on a visible light orthophoto map and a hyperspectral orthophoto map, and calculating the vegetation height based on the digital earth surface model;
collecting dry and wet biomass of vegetation in a region corresponding to the visible light image and the hyperspectral image;
and (3) establishing a random forest regression prediction model by taking the vegetation index and the vegetation height as independent variables and taking the dry and wet biomass of the vegetation as continuous dependent variables, and realizing the aboveground biomass prediction of the vegetation based on the prediction model.
As an option, the step of creating a random forest regression prediction model further includes:
and inputting the collected part of visible light images and/or hyperspectral images as test samples into a prediction model, and calculating a decision coefficient of the prediction model, a correction error of a correction model and a cross test error so as to judge the prediction performance of the prediction model.
As an option, before performing correction processing on the visible light image and the hyperspectral image respectively, the method further includes:
extracting characteristic points of each image;
and according to the mutual matching of the characteristic points, matching with the GPS information of the top point of each sample area, and splicing the images of the same sample area and the same growth period.
As an option, the acquiring the digital terrain model and the vegetation index based on the visible light orthophoto map and the hyperspectral orthophoto map specifically includes:
calculating the ultragreen indexes of a visible light orthophoto map and a hyperspectral orthophoto map;
extracting pixels corresponding to the vegetation from the visible light image and the hyperspectral image according to the ultragreen indexes;
and calculating vegetation indexes CI1 and MSR based on the gray-scale values of the corresponding pixels of the vegetation.
As an option, the calculation formula for calculating the vegetation height based on the digital terrain model is as follows:
nDSM＝DSM-DEM
wherein nDSM is the actual height of the vegetation in the cell; DSM is the absolute elevation of vegetation and corresponds to the gray value of the vegetation pixel; the DEM is the absolute altitude of the ground, and is obtained by marking a reserved area around vegetation and estimating and calculating by adopting a linear interpolation method.
As an option, the vegetation height calculation further includes a noise pixel elimination step:
searching all pixel points with values larger than 8 neighborhood pixels, and storing the pixel points into an array M;
sequencing all values in the array M from high to low;
executing a flooding method by taking P as a seed point, wherein the principle is that the difference between the pixel value of the seed point P and the pixel value of the seed point P meets a threshold value, if the pixel value of other pixel points is greater than the seed point P or the pixel point is marked as a point of a local maximum value, taking the other pixel points with the pixel values greater than the seed point P as the local maximum value, and otherwise, marking the seed point P as the local maximum value;
and calculating the average value of all local maximum values to obtain the actual height of the vegetation in the region after the noise is removed.
It should be further noted that the technical features corresponding to the above-mentioned method options can be combined with each other or replaced to form a new technical solution.
The present invention also includes an vegetation biomass measurement system, comprising:
the image acquisition unit is used for acquiring visible light images and hyperspectral images of the vegetation;
the image processing unit is used for respectively correcting the visible light image and the hyperspectral image to obtain a visible light orthophoto map and a hyperspectral orthophoto map of each wave band;
the calculating unit is used for acquiring a digital earth surface model and a vegetation index based on the visible light orthophoto map and the hyperspectral orthophoto map and calculating the vegetation height based on the digital earth surface model;
the biomass acquisition unit is used for acquiring dry and wet biomass of vegetation in a region corresponding to the visible light image and the hyperspectral image;
and the model creating unit is used for creating a random forest regression prediction model by taking the vegetation index and the vegetation height as independent variables and taking the dry and wet biomass of the vegetation as continuous dependent variables, and realizing the aboveground biomass prediction of the vegetation based on the prediction model.
As an option, the system further comprises a checking unit for calculating a decision coefficient of the prediction model, a correction error of the correction model and a cross-check error through a check sample, thereby judging the prediction performance of the prediction model; the inspection sample is specifically a part of visible light image and/or hyperspectral image acquired by the image acquisition unit.
It should be further noted that the technical features corresponding to the above-mentioned system options can be combined with each other or replaced to form a new technical solution.
The present invention also includes a storage medium having stored thereon computer instructions which, when executed, perform the steps of the vegetation biomass measurement method described above.
The invention also includes a terminal comprising a memory and a processor, the memory having stored thereon computer instructions executable on the processor, the processor when executing the computer instructions performing the steps of the vegetation biomass measurement method as described above.
Compared with the prior art, the invention has the beneficial effects that:
(1) the hyperspectral image of the vegetation is collected, the hyperspectral image can contain more vegetation information, the vegetation index and the vegetation height calculated based on the visible light image and the hyperspectral image of the vegetation can be more accurate, a random forest regression prediction model is established based on the vegetation index, the vegetation height and the dry and wet biomass of the vegetation, the overground biomass of the vegetation can be accurately predicted based on the prediction model, the vegetation growth process is monitored, the work efficiency of the whole process is high, and the labor cost can be saved.
(2) According to the method, the check sample is input into the prediction model, and the decision coefficient of the prediction model, the correction error of the correction model and the cross inspection error are calculated, so that the prediction capability of the prediction model is inspected, the model with high accuracy is put into use, and the aboveground biomass of the vegetation is predicted.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention.
FIG. 1 is a flowchart of a method of example 1 of the present invention;
fig. 2 is a schematic diagram of a noise pixel elimination process in embodiment 1 of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood 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 the description of the present invention, it should be noted that directions or positional relationships indicated by "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", and the like are directions or positional relationships based on the drawings, and are only for convenience of description and simplification of description, and do not indicate or imply that the device or element referred to must have a specific orientation, be configured and operated in a specific orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should be noted that, unless otherwise explicitly stated or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
In addition, the technical features involved in the different embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
The invention aims to provide a method, a system, a storage medium and a device for measuring the aboveground biomass of potatoes based on unmanned aerial vehicle remote sensing and hyperspectral technology, which have the characteristics of quick and accurate measurement, strong operability and low cost, and take potatoes as an example to illustrate the inventive concept of the application.
Example 1
As shown in fig. 1, in example 1, a method for measuring potato biomass specifically comprises the following steps:
s01: collecting a visible light image and a hyperspectral image of the potato; the visible light images and the hyperspectral images of the potatoes have the spectral ranges of 400nm to 1000nm, and the collected images are the visible light images and the hyperspectral images of the potatoes in different growth periods.
S02: respectively correcting the visible light image and the hyperspectral image to obtain a visible light orthographic image and a hyperspectral orthographic image of each wave band;
s03: acquiring a digital earth surface model and a vegetation index based on a visible light orthophoto map and a hyperspectral orthophoto map, and calculating the height of the potatoes based on the digital earth surface model;
s04: collecting dry and wet biomass of vegetation in a region corresponding to the visible light image and the hyperspectral image;
s05: and (3) establishing a random forest regression prediction model by taking the vegetation index and the height of the potatoes as independent variables and the dry and wet biomass of the potatoes as continuous dependent variables, and realizing the aboveground biomass prediction of the potatoes based on the prediction model.
Further, in step S01, the visible light image and the hyperspectral image of the potato are obtained by using an unmanned aerial vehicle. Specifically, unmanned aerial vehicle carries on spectrum camera has the characteristics of flexible, time-efficient, and the imaging mode of unmanned aerial vehicle carried high spectrum equipment mainly is push away scanning formula scanning, and its key feature is that resolution ratio is high, small, light in weight. The airborne hyperspectral camera acquires reflected light information of a ground target object by utilizing forward flying motion of the unmanned aerial vehicle and line scanning perpendicular to the flying direction, so that a two-dimensional image is formed. And setting parameters of the unmanned aerial vehicle, including flight height, flight path and shooting interval, according to the image resolution and the size of the target object. In this embodiment, 60 uniformly distributed rectangular areas with an area of 8m × 5.3m are randomly selected as sample cells in a planting cell to construct an aboveground biomass prediction model, and 12 sample cells are randomly selected as test samples to obtain GPS positioning information of four vertexes of all the rectangular cells. 270 potato seeds are sown in each cell, visible light and hyperspectral images are obtained twice by using an unmanned aerial vehicle at the flying height of 30 meters in the sunny weather about 60 days and 90 days after the potatoes are sown, and a flight line covers all the cells, so that in the specific implementation, 120 cell samples are used for constructing an aboveground biomass prediction model, and 24 cell samples are used as inspection samples. The visible light image is obtained by an RGB (red, green and blue) three-color sensor carried by Phantom 4pro in Xinjiang, the picture pixel is 2000 ten thousand pixels, the ground resolution is 0.5cm, the course overlapping rate is set to be 80%, and the lateral overlapping rate is 60%. The hyperspectral image is obtained by a Headwall Nano-Hyperspec hyperspectral camera carried by a Xinjiang matrix 600Pro unmanned aerial vehicle. The hyperspectral image contains 272 wave bands in total between 400nm and 1000nm, the transverse resolution is 640 pixels, the lateral overlapping rate is 60%, and the ground resolution is 2.2 cm. After the image acquisition is finished, the image quality is checked, and the problems of deletion, blurring and serious distortion do not exist in the acquired image.
Further, the step S02 of correcting the visible light image and the hyperspectral image to obtain a visible light orthographic projection image and a hyperspectral orthographic projection image of each waveband respectively specifically includes:
s021: extracting characteristic points of each image;
s022: according to the mutual matching among the feature points and the GPS information of the four vertexes of each rectangular cell, feature point matching is carried out on the images of the same sample area and the same growth period, image splicing processing is carried out according to the matched feature points, and the generated point cloud images are subjected to densification processing; the hyperspectral image is spliced through a near neighbor searching response algorithm in ENVI software.
S023: and performing geometric correction on the encrypted image to obtain an orthophoto map.
Further, the step S03 of acquiring the digital terrain model and the vegetation index based on the visible light orthophoto map and the hyperspectral orthophoto map specifically includes:
s031: calculating a visible light positive projection image,The ultragreen index of the hyperspectral orthophotomap; for the visible light orthographic projection image, the calculation formula of the ultragreen index (ExG) is ExGVisible light2G-R-B, wherein R, G, B is the gray scale value corresponding to three channels of the light image; aiming at the hyperspectral image, the calculation formula of the ultragreen index ExG is ExGGao Guangpu＝2*R540–R465–R680Wherein R is465、R540And R680An orthographic image of three wave bands of 465nm, 540nm and 680nm respectively.
S032: extracting corresponding pixels of the potatoes from the visible light image and the hyperspectral image according to the ultragreen indexes; specifically, because the ultragreen index corresponding to the vegetation pixel is far higher than that of soil, the obtained grayscale image is subjected to binarization processing through an Otsu algorithm, and the pixel position corresponding to the potato vegetation is segmented from the soil background, that is, the potato image is segmented from the background.
S033: and calculating vegetation indexes CI1 and MSR based on the gray values of the corresponding pixels of the potatoes. Specifically, in all the hyperspectral images, selecting the hyperspectral images positioned in the 670nm, 740nm and 800nm wave bands, and calculating the vegetation index CI1 and MSR of each cell in each growth period according to the gray value of the pixel corresponding to the vegetation, wherein the calculation formula is as follows:
CI1＝R800nm/R740nm–1
MSR＝(R800nm–R670nm–1)/[(R800nm+R670nm)*0.5+1]
wherein R is800nmRepresenting the gray value, R, of the corresponding pixel in the 800nm band740nmRepresenting a grey value, R, of a corresponding pixel in the 740nm band670nmThe gray value of the pixel corresponding to the 670nm wave band is represented, the step is realized by image processing software which is independently developed in a Matlab environment, and the vegetation index of the cell is defined as the average value of the vegetation indexes corresponding to all the pixels.
Further, step S03 further includes:
s034: calculating the height of the potatoes based on the digital earth surface model; specifically, in the DSM image, the grayscale value of a pixel corresponds to the absolute elevation of vegetation, and the actual height (nsmd) corresponding to all vegetation pixels is obtained by subtracting the absolute elevation (DEM) of the ground, and the specific calculation formula is:
nDSM＝DSM-DEM
wherein nDSM is the actual height of the cell potatoes; DSM is potato absolute altitude, corresponding to the gray value of the potato pixel; DEM is the absolute altitude of the ground, and is obtained by marking a reserved area around the potatoes and then estimating and calculating by adopting a linear interpolation method.
Further, since the nsmd represents the vegetation height corresponding to all pixel positions of the whole cell, the height of each plant cannot be represented, and the height of a single plant of a plant is usually represented as the local maximum height, the step S034 further includes a noise pixel removing step:
S034A: searching all pixel points with values larger than 8 neighborhood pixels, and storing the pixel points into an array M;
S034B: sequencing all values in the array M from high to low;
S034C: executing a flooding method by taking P as a seed point, wherein the principle is that the difference between the pixel value of the seed point P and the pixel value of the seed point P meets a threshold value, if the pixel value of other pixel points is greater than the seed point P or the pixel point is marked as a point of a local maximum value, taking the other pixel points with the pixel values greater than the seed point P as the local maximum value, and otherwise, marking the seed point P as the local maximum value;
S034D: and calculating the average value of all local maximum values to obtain the actual height of the potatoes in the subdistrict after the noise is eliminated. Fig. 2 is a schematic diagram of the above noise pixel elimination process, where fig. 2a is an original cell image, fig. 2b is an nsmd image, and fig. 2c is an nsmd image marking a local maximum point.
Further, the step S04 of collecting the dry and wet biomass of the vegetation in the region corresponding to the visible light image and the hyperspectral image specifically includes:
randomly selecting three plants in a planting district according to a traditional method, and weighing in a laboratory to obtain the amount of overground wet organisms; and (5) placing the mixture in an oven for 48 hours, drying and weighing the mixture to obtain dry biomass. Given that each cell consists of 270 plants, the dry and wet biomass per cell area can be estimated as shown in attribute table 1:
TABLE 1 Dry and Wet biomass tables for vegetation
It should be noted that the correction model samples in table 1 are used as continuous dependent variables of the random forest regression prediction model, and the samples to be detected are different from the samples used for model construction, and can be used for detecting the accuracy and robustness of the model.
Further, step S05 specifically includes:
s051: determining a modeling sample and a detection sample; specifically, in a total of 120 cell samples for constructing the above-ground biomass of the potatoes, the vegetation index and the height in 70% of the sample areas and the corresponding manually-detected dry and wet biomass are randomly selected to be used for constructing a model, namely, the sample is used as a modeling sample, and the vegetation index and the height in the remaining 30% of the sample cells and the corresponding manually-detected dry and wet biomass are used as samples to be detected.
S052: and respectively constructing dry and wet biomass prediction models of the ground by utilizing modules of a random forest regression model in Matlab software.
S053: inputting the collected part of visible light images and/or hyperspectral images as test samples into a dry and wet biomass prediction model of the ground, and calculating a decision coefficient of the prediction model, a correction error of a correction model and a cross test error so as to judge the prediction performance of the prediction model; specifically, the random forest regression model parameters are determined such that rc 2And rv 2Nearest 1, RMSEC and RESACCV nearest 0, and rc 2And rv 2As close as possible to prevent the overfitting condition from occurring. Determining the coefficient r2The ratio of the regression sum of squares to the sum of the total mean squared differences reflects the degree of interpretation of the regression model for the variation of the dependent variable. RMSEC and RMSECV reflect the difference between the predicted value and the actual value of the model, and the calculation formula is as follows:
wherein, yactMeasured value of aboveground biomass, ycalAs measured values, y, in the correction modelpredIs the measured value of the test sample in the cross test, and n is the number of samples.
S054: and (4) realizing aboveground biomass prediction of the potatoes based on the prediction model. Specifically, when biomass prediction on the actual ground is carried out, independent variable data of the biomass prediction model on the potato ground needs to be determined, namely visible light and hyperspectral images of the unmanned aerial vehicle of the area to be detected need to be collected, CI1, MSR vegetation index and vegetation height of potato vegetation in the area to be detected are calculated, and the independent variables are input into the biomass prediction model on the potato ground to obtain a predicted value. The accuracy of the prediction model for the detected samples is determined by the Root Mean Square Error of Prediction (RMSEP), which is expressed as follows:
wherein, ytestTo detect the predicted value of a sample, yactTo detect the manual measurement value of the sample, and to ensure the accuracy of the prediction model, the determination coefficient (r) of the model calibration set of the prediction model in this embodiment isc 2) Correction error (RMSEC) of correction model, cross-check decision coefficient (r)v 2) Cross test error (RMSECV), correlation degree r of predicted value and actual value of sample to be testedp 2And the value of the error RMSEP between the predicted value and the actual value of the sample to be detected is shown in Table 2.
TABLE 2 parameter reference table for prediction model
| Aboveground biomass | rc 2 | RMSEC (ton/mu) | rv 2 | RMSECV (ton/mu) | rp 2 | RMSEP (ton/mu) |
| Wet biomass | 0.85 | 0.32 | 0.78 | 0.40 | 0.83 | 0.36 |
| Dry biomass | 0.88 | 0.05 | 0.82 | 0.06 | 0.88 | 0.06 |
According to the method, the hyperspectral image of the potato is collected, the hyperspectral image can contain more potato information, the vegetation index and the potato height calculated based on the visible light image and the hyperspectral image of the potato can be more accurate, a random forest regression prediction model is established based on the vegetation index, the potato height and the dry and wet biomass of the potato, accurate prediction on the aboveground biomass of the potato can be realized based on the prediction model, the growth process of the potato is further monitored, the work efficiency of the whole process is high, and the labor cost can be saved.
Example 2
The embodiment provides a potato biomass measuring system, which has the same inventive concept as embodiment 1, and specifically comprises:
the image acquisition unit is used for acquiring a visible light image and a hyperspectral image of the potato; the visible light images and the hyperspectral images of the potatoes have the spectral ranges of 400nm to 1000nm, and the collected images are the visible light images and the hyperspectral images of the potatoes in different growth periods.
The image processing unit is used for respectively correcting the visible light image and the hyperspectral image to obtain a visible light orthophoto map and a hyperspectral orthophoto map of each wave band;
the calculation unit is used for acquiring a digital earth surface model and a vegetation index based on the visible light orthophoto map and the hyperspectral orthophoto map and calculating the height of the potatoes based on the digital earth surface model;
the biomass acquisition unit is used for acquiring dry and wet biomass of vegetation in a region corresponding to the visible light image and the hyperspectral image; in this embodiment, the dry and wet biomass of vegetation is collected manually.
And the model creating unit is used for creating a random forest regression prediction model by taking the vegetation index and the potato height as independent variables and taking the dry and wet biomass of the potatoes as continuous dependent variables, and realizing the aboveground biomass prediction of the potatoes based on the prediction model. In the implementation, the model creating unit is specifically Matlab, and dry and wet biomass prediction models of the ground are respectively constructed through modules of a random forest regression model in Matlab software.
In this embodiment, the image acquisition unit is specifically an RGB three-primary-color sensor carried by Xinntom 4Pro in Xinjiang and a Headwall Nano-Hyperspec hyperspectral camera carried by an unmanned aerial vehicle matrix 600Pro in Xinjiang. The image acquisition unit randomly acquires 60 uniformly distributed rectangular areas with the area of 8m by 5.3m in the planting cell as sample cells to construct a ground biomass prediction model, randomly selects 12 sample cells as test samples, and acquires GPS positioning information of four vertexes of all the rectangular cells. 270 potato seeds are sown in each cell, visible light and hyperspectral images are obtained twice by using an unmanned aerial vehicle at the flying height of 30 meters in the sunny weather about 60 days and 90 days after the potatoes are sown, and a flight line covers all the cells, so that in the specific implementation, 120 cell samples are used for constructing an aboveground biomass prediction model, and 24 cell samples are used as inspection samples.
In this embodiment, the image processing unit is an Agisoft Photoscan software and an ENVI software, or a device integrated with the Agisoft Photoscan software and the ENVI software, the visible light and the orthoimages of the hyperspectral bands are spliced based on the Agisoft Photoscan software, and the hyperspectral images are spliced based on the ENVI software.
In this embodiment, the computing unit includes image processing software developed autonomously in Matlab environment, or a device integrated with image processing software developed autonomously in Matlab environment, and is configured to extract pixels corresponding to the potato vegetation from the visible light and hyperspectral images according to an ultragreen index (ExG), and further calculate vegetation indexes CI1 and MSR of each cell in each growth period; meanwhile, the image processing software is also used for eliminating noise pixels so as to accurately calculate the height of the plant. The computing unit also comprises ArcGis software or a device integrated with the ArcGis software, and is used for marking reserved areas around the potato cells and estimating the DEM of the potato cells by a linear interpolation method.
Furthermore, the system also comprises a checking unit, which is used for calculating the decision coefficient of the prediction model, the correction error of the correction model and the cross-checking error through the checking sample so as to judge the prediction performance of the prediction model; the inspection sample is specifically a part of visible light image and/or hyperspectral image acquired by the image acquisition unit.
The invention discloses a potato ground biomass prediction system based on unmanned aerial vehicle hyperspectral remote sensing, which is characterized in that an unmanned aerial vehicle imaging system is used for acquiring potato ground vegetation images in multiple growth periods, calculating vegetation indexes and vegetation heights in the growth periods, and establishing a prediction model of the dry and wet biomass of the ground through a random forest regression model. Compared with the traditional measuring method, the method and the system have the advantages of high accuracy, labor saving and capability of realizing real-time monitoring of multiple growth periods.
Example 3
The present embodiment provides a storage medium having the same inventive concept as embodiment 1, and having stored thereon computer instructions which, when executed, perform the steps of the vegetation biomass measurement method described in embodiment 1.
Based on such understanding, the technical solution of the present embodiment or parts of the technical solution may be essentially implemented in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: 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.
Example 4
The present embodiment also provides a terminal, which has the same inventive concept as embodiment 1, and includes a memory and a processor, wherein the memory stores computer instructions executable on the processor, and the processor executes the computer instructions to perform the steps of the vegetation biomass measurement method in embodiment 1. The processor may be a single or multi-core central processing unit or a specific integrated circuit, or one or more integrated circuits configured to implement the present invention.
Each functional unit in the embodiments provided by 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 above detailed description is for the purpose of describing the invention in detail, and it should not be construed that the detailed description is limited to the description, and it will be apparent to those skilled in the art that various modifications and substitutions can be made without departing from the spirit of the invention.
Claims (10)
1. A method for measuring an amount of an implantable organism, comprising: the method comprises the following steps:
collecting a visible light image and a hyperspectral image of vegetation;
respectively correcting the visible light image and the hyperspectral image to obtain a visible light orthographic image and a hyperspectral orthographic image of each wave band;
acquiring a digital earth surface model and a vegetation index based on a visible light orthophoto map and a hyperspectral orthophoto map, and calculating the vegetation height based on the digital earth surface model;
collecting dry and wet biomass of vegetation in a region corresponding to the visible light image and the hyperspectral image;
and (3) establishing a random forest regression prediction model by taking the vegetation index and the vegetation height as independent variables and taking the dry and wet biomass of the vegetation as continuous dependent variables, and realizing the aboveground biomass prediction of the vegetation based on the prediction model.
2. The vegetation biomass measurement method of claim 1, wherein: the step of creating the random forest regression prediction model further comprises the following steps:
and inputting the collected part of visible light images and/or hyperspectral images as test samples into a prediction model, and calculating a decision coefficient of the prediction model, a correction error of a correction model and a cross test error so as to judge the prediction performance of the prediction model.
3. The vegetation biomass measurement method of claim 1, wherein: the method further comprises the following steps of before respectively correcting the visible light image and the hyperspectral image:
extracting characteristic points of each image;
and according to the mutual matching of the characteristic points, matching with the GPS information of the top point of each sample area, and splicing the images of the same sample area and the same growth period.
4. The vegetation biomass measurement method of claim 1, wherein: the acquiring of the digital earth surface model and the vegetation index based on the visible light orthophoto map and the hyperspectral orthophoto map specifically comprises:
calculating the ultragreen indexes of a visible light orthophoto map and a hyperspectral orthophoto map;
extracting pixels corresponding to the vegetation from the visible light image and the hyperspectral image according to the ultragreen indexes;
and calculating vegetation indexes CI1 and MSR based on the gray-scale values of the corresponding pixels of the vegetation.
5. The vegetation biomass measurement method of claim 4, wherein: the calculation formula for calculating the vegetation height based on the digital earth surface model is as follows:
nDSM＝DSM-DEM
wherein nDSM is the actual height of the vegetation in the cell; DSM is the absolute elevation of vegetation and corresponds to the gray value of the vegetation pixel; the DEM is the absolute altitude of the ground, and is obtained by marking a reserved area around vegetation and estimating and calculating by adopting a linear interpolation method.
6. The vegetation biomass measurement method of claim 5, wherein: the vegetation height calculation further comprises a noise pixel elimination step:
searching all pixel points with values larger than 8 neighborhood pixels, and storing the pixel points into an array M;
sequencing all values in the array M from high to low;
executing a flooding method by taking P as a seed point, wherein the principle is that the difference between the pixel value of the seed point P and the pixel value of the seed point P meets a threshold value, if the pixel value of other pixel points is greater than the seed point P or the pixel point is marked as a point of a local maximum value, taking the other pixel points with the pixel values greater than the seed point P as the local maximum value, and otherwise, marking the seed point P as the local maximum value;
and calculating the average value of all local maximum values to obtain the actual height of the vegetation in the region after the noise is removed.
7. The vegetation biomass measurement system of any one of claims 1-6, wherein: the system comprises:
the image acquisition unit is used for acquiring visible light images and hyperspectral images of the vegetation;
the image processing unit is used for respectively correcting the visible light image and the hyperspectral image to obtain a visible light orthophoto map and a hyperspectral orthophoto map of each wave band;
the calculating unit is used for acquiring a digital earth surface model and a vegetation index based on the visible light orthophoto map and the hyperspectral orthophoto map and calculating the vegetation height based on the digital earth surface model;
the biomass acquisition unit is used for acquiring dry and wet biomass of vegetation in a region corresponding to the visible light image and the hyperspectral image;
and the model creating unit is used for creating a random forest regression prediction model by taking the vegetation index and the vegetation height as independent variables and taking the dry and wet biomass of the vegetation as continuous dependent variables, and realizing the aboveground biomass prediction of the vegetation based on the prediction model.
8. The vegetation biomass measurement system of claim 7, wherein: the system also comprises a checking unit, a judging unit and a judging unit, wherein the checking unit is used for calculating a decision coefficient of the prediction model, a correction error of the correction model and a cross-checking error through a checking sample so as to judge the prediction performance of the prediction model; the inspection sample is specifically a part of visible light image and/or hyperspectral image acquired by the image acquisition unit.
9. A storage medium having stored thereon computer instructions, characterized in that: the computer instructions when executed perform the steps of the vegetation biomass measurement method of any one of claims 1-6.
10. A terminal comprising a memory and a processor, the memory having stored thereon computer instructions executable on the processor, the terminal comprising: the processor, when executing the computer instructions, performs the steps of the vegetation biomass measurement method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110315601.1A CN113063742A (en) | 2021-03-24 | 2021-03-24 | Method and system for measuring vegetation biomass, storage medium and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110315601.1A CN113063742A (en) | 2021-03-24 | 2021-03-24 | Method and system for measuring vegetation biomass, storage medium and terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113063742A true CN113063742A (en) | 2021-07-02 |
Family
ID=76561981
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110315601.1A Pending CN113063742A (en) | 2021-03-24 | 2021-03-24 | Method and system for measuring vegetation biomass, storage medium and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113063742A (en) |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102565061A (en) * | 2012-01-16 | 2012-07-11 | 沈阳农业大学 | Crop biomass nondestructive testing image acquisition and processing device and testing method |
| CN103632361A (en) * | 2012-08-20 | 2014-03-12 | 阿里巴巴集团控股有限公司 | An image segmentation method and a system |
| CN105067802A (en) * | 2015-08-14 | 2015-11-18 | 北京林业大学 | Shrub biomass measuring method through cellphone shooting |
| 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 |
| CN108007438A (en) * | 2017-12-01 | 2018-05-08 | 云南大学 | The estimating and measuring method of unmanned plane aeroplane photography remote sensing wetland plant biomass |
| CN108020211A (en) * | 2017-12-01 | 2018-05-11 | 云南大学 | A kind of method of unmanned plane aeroplane photography estimation instruction plant biomass |
| 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 |
| CN110398466A (en) * | 2019-08-05 | 2019-11-01 | 北京绿土科技有限公司 | Crop growth state monitoring method based on remote-sensing inversion |
| CN111062251A (en) * | 2020-03-23 | 2020-04-24 | 乔红波 | Monitoring method of farmland cotton aphid pest grade model based on unmanned aerial vehicle imaging |
| CN111121725A (en) * | 2019-12-31 | 2020-05-08 | 杭州高谱成像技术有限公司 | Hyperspectral data and three-dimensional modeling data acquisition system based on unmanned aerial vehicle |
| CN111414867A (en) * | 2020-03-24 | 2020-07-14 | 北京大学深圳研究生院 | Method for measuring and calculating aboveground biomass of plants |
| CN111429356A (en) * | 2020-03-31 | 2020-07-17 | 北京建筑大学 | Geometric registration and cutting method for ground hyperspectral image |
| CN111767865A (en) * | 2020-06-30 | 2020-10-13 | 北部湾大学 | Method for inverting mangrove forest biomass by using aerial image and laser data |
| CN111798327A (en) * | 2020-06-24 | 2020-10-20 | 安徽大学 | Construction method and application of wheat yield calculation model based on hyperspectral image |
| US20200334458A1 (en) * | 2019-04-16 | 2020-10-22 | Precision Silver, LLC | Systems and methods for rating vegetation health and biomass from remotely sensed morphological and radiometric data |
| CN111899296A (en) * | 2020-06-24 | 2020-11-06 | 广西大学 | Method and device for detecting log volume based on computer vision |
| CN111899268A (en) * | 2020-08-17 | 2020-11-06 | 上海商汤智能科技有限公司 | Image segmentation method and device, electronic equipment and storage medium |
| CN112287892A (en) * | 2020-11-23 | 2021-01-29 | 中国电建集团成都勘测设计研究院有限公司 | Arbor biomass measurement and calculation method based on unmanned aerial vehicle hyperspectral and machine learning algorithm |
-
2021
- 2021-03-24 CN CN202110315601.1A patent/CN113063742A/en active Pending
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102565061A (en) * | 2012-01-16 | 2012-07-11 | 沈阳农业大学 | Crop biomass nondestructive testing image acquisition and processing device and testing method |
| CN103632361A (en) * | 2012-08-20 | 2014-03-12 | 阿里巴巴集团控股有限公司 | An image segmentation method and a system |
| CN105067802A (en) * | 2015-08-14 | 2015-11-18 | 北京林业大学 | Shrub biomass measuring method through cellphone shooting |
| 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 |
| CN108007438A (en) * | 2017-12-01 | 2018-05-08 | 云南大学 | The estimating and measuring method of unmanned plane aeroplane photography remote sensing wetland plant biomass |
| CN108020211A (en) * | 2017-12-01 | 2018-05-11 | 云南大学 | A kind of method of unmanned plane aeroplane photography estimation instruction plant biomass |
| 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 |
| US20200141877A1 (en) * | 2018-11-06 | 2020-05-07 | Nanjing Agricultural University | Method for estimating aboveground biomass of rice based on multi-spectral images of unmanned aerial vehicle |
| US20200334458A1 (en) * | 2019-04-16 | 2020-10-22 | Precision Silver, LLC | Systems and methods for rating vegetation health and biomass from remotely sensed morphological and radiometric data |
| CN110398466A (en) * | 2019-08-05 | 2019-11-01 | 北京绿土科技有限公司 | Crop growth state monitoring method based on remote-sensing inversion |
| CN111121725A (en) * | 2019-12-31 | 2020-05-08 | 杭州高谱成像技术有限公司 | Hyperspectral data and three-dimensional modeling data acquisition system based on unmanned aerial vehicle |
| CN111062251A (en) * | 2020-03-23 | 2020-04-24 | 乔红波 | Monitoring method of farmland cotton aphid pest grade model based on unmanned aerial vehicle imaging |
| CN111414867A (en) * | 2020-03-24 | 2020-07-14 | 北京大学深圳研究生院 | Method for measuring and calculating aboveground biomass of plants |
| CN111429356A (en) * | 2020-03-31 | 2020-07-17 | 北京建筑大学 | Geometric registration and cutting method for ground hyperspectral image |
| CN111798327A (en) * | 2020-06-24 | 2020-10-20 | 安徽大学 | Construction method and application of wheat yield calculation model based on hyperspectral image |
| CN111899296A (en) * | 2020-06-24 | 2020-11-06 | 广西大学 | Method and device for detecting log volume based on computer vision |
| CN111767865A (en) * | 2020-06-30 | 2020-10-13 | 北部湾大学 | Method for inverting mangrove forest biomass by using aerial image and laser data |
| CN111899268A (en) * | 2020-08-17 | 2020-11-06 | 上海商汤智能科技有限公司 | Image segmentation method and device, electronic equipment and storage medium |
| CN112287892A (en) * | 2020-11-23 | 2021-01-29 | 中国电建集团成都勘测设计研究院有限公司 | Arbor biomass measurement and calculation method based on unmanned aerial vehicle hyperspectral and machine learning algorithm |
Non-Patent Citations (5)
| Title |
|---|
| BO LI 等: "Above-ground biomass estimation and yield prediction in potato by using UAV-based RGB and hyperspectral imaging", 《ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING》, vol. 162, pages 162 - 169 * |
| GARRIDO, L 等: "《SIGNAL PROCESSING》", 30 April 1988, pages: 157 - 180 * |
| 李伟娜;韦玮;张怀清;刘华;: "基于多角度高光谱数据的高寒沼泽湿地植被生物量估算", 遥感技术与应用, vol. 32, no. 05, pages 809 - 817 * |
| 李凤秀;张柏;刘殿伟;宋开山;: "洪河自然保护区乌拉苔草生物量高光谱遥感估算模型", 湿地科学, vol. 6, no. 01, pages 51 - 59 * |
| 王红岩;高志海;王瑜;白黎娜;吴俊君;: "基于TM遥感影像丰宁县森林地上生物量估测研究", 安徽农业科学, no. 32, pages 18472 - 18474 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11454534B2 (en) | Method and system for optical and microwave synergistic retrieval of aboveground biomass | |
| Li et al. | Remote estimation of canopy height and aboveground biomass of maize using high-resolution stereo images from a low-cost unmanned aerial vehicle system | |
| CN109581372B (en) | Ecological environment remote sensing monitoring method | |
| Hoffmann et al. | Crop water stress maps for an entire growing season from visible and thermal UAV imagery | |
| CN111289441B (en) | Multispectral field crop water content determination method, system and equipment | |
| CN110567891B (en) | Winter wheat canopy chlorophyll estimation system and method | |
| CN113029971B (en) | Crop canopy nitrogen monitoring method and system | |
| CN110796001A (en) | Satellite image film-covering farmland identification and extraction method and system | |
| CN111832518A (en) | Space-time fusion-based TSA remote sensing image land utilization method | |
| Xu et al. | Classification method of cultivated land based on UAV visible light remote sensing | |
| CN114202675A (en) | Crop growth parameter determination method and system based on multispectral remote sensing image of unmanned aerial vehicle | |
| Song et al. | Estimating effective leaf area index of winter wheat using simulated observation on unmanned aerial vehicle-based point cloud data | |
| CN115015258B (en) | Crop growth vigor and soil moisture association determination method and related device | |
| CN113655003B (en) | Method for estimating soil moisture content of winter wheat in green-turning period by using unmanned aerial vehicle photo | |
| Becirevic et al. | On the derivation of crop heights from multitemporal UAV based imagery | |
| Ormeci et al. | Identification of crop areas Using SPOT–5 data | |
| CN116773516A (en) | Soil carbon content analysis system based on remote sensing data | |
| Rinnamang et al. | Estimation of aboveground biomass using aerial photogrammetry from unmanned aerial vehicle in teak (Tectona grandis) plantation in Thailand | |
| CN113063742A (en) | Method and system for measuring vegetation biomass, storage medium and terminal | |
| CN115931774A (en) | Method, storage medium and equipment for monitoring crop moisture condition based on unmanned aerial vehicle | |
| Dobbs et al. | Using structure-from-motion to estimate cover crop biomass and characterize canopy structure | |
| CN113514402B (en) | System and method for predicting chlorophyll content of winter wheat | |
| CN115641502A (en) | Winter wheat drought unmanned aerial vehicle rapid monitoring and distinguishing method based on leaf area index | |
| CN114782835A (en) | Crop lodging area proportion detection method and device | |
| Wang et al. | Scaling effects of chlorophyll content in walnut leaves estimations with coupling Boruta algorithm and machine learning model |
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 |
Effective date of registration: 20220825 Address after: Room 10-1026, 10th Floor, Building 6, No. 1366 Hongfeng Road, Huzhou City, Zhejiang Province 313000 Applicant after: Translate Technology (Zhejiang) Co.,Ltd. Address before: 1213-223, 12 / F, building 3, No. 1366, Hongfeng Road, Kangshan street, Huzhou City, Zhejiang Province, 313000 Applicant before: Heshu Technology (Zhejiang) Co.,Ltd. |
|
| TA01 | Transfer of patent application right |