CN110765977A - Method for extracting wheat lodging information based on multi-temporal remote sensing data of unmanned aerial vehicle - Google Patents

Method for extracting wheat lodging information based on multi-temporal remote sensing data of unmanned aerial vehicle Download PDF

Info

Publication number
CN110765977A
CN110765977A CN201911063822.3A CN201911063822A CN110765977A CN 110765977 A CN110765977 A CN 110765977A CN 201911063822 A CN201911063822 A CN 201911063822A CN 110765977 A CN110765977 A CN 110765977A
Authority
CN
China
Prior art keywords
wheat
lodging
image
lodging information
fen
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
Application number
CN201911063822.3A
Other languages
Chinese (zh)
Inventor
李广
韩文霆
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.)
Nanjing Hepu Aviation Technology Co Ltd
Original Assignee
Nanjing Hepu Aviation Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nanjing Hepu Aviation Technology Co Ltd filed Critical Nanjing Hepu Aviation Technology Co Ltd
Priority to CN201911063822.3A priority Critical patent/CN110765977A/en
Publication of CN110765977A publication Critical patent/CN110765977A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/188—Vegetation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Multimedia (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Probability & Statistics with Applications (AREA)
  • Image Processing (AREA)
  • Image Analysis (AREA)

Abstract

The invention provides a method and a system for extracting wheat lodging information by unmanned aerial vehicle multi-temporal remote sensing, which comprises the following steps: acquiring an unmanned aerial vehicle remote sensing image in a wheat filling stage in a 2 stage; carrying out secondary low-pass filtering processing on the image to enhance the spatial domain of the image; constructing a scatter diagram of normal and lodging wheat; selecting a secondary low-pass filtering red wave band and a secondary low-pass filtering green wave band by taking an obvious boundary existing in the scatter diagram as a judgment standard, fitting the boundary to construct lodging information extraction characteristic parameters Fen (1) and Fen (2), and processing lodging information in a corresponding period; synthesizing the spatial similarity of the two characteristic parameters, acquiring lodging information and extracting a comprehensive characteristic parameter Fen (3); the comprehensive characteristic parameters are combined with a K-Means algorithm to extract the lodging information of the wheat in two periods. The method extracts the wheat lodging information by using the unmanned aerial vehicle remote sensing and image processing technology, has higher automation and higher precision compared with a manual investigation method, can be widely applied to the field of crop lodging monitoring, and provides technical support for agricultural disaster assessment and insurance claims.

Description

Method for extracting wheat lodging information based on multi-temporal remote sensing data of unmanned aerial vehicle
Technical Field
The invention relates to the technical field of unmanned aerial vehicle remote sensing image processing, in particular to a method for extracting wheat lodging information based on multi-temporal remote sensing data of an unmanned aerial vehicle.
Background
Wheat is one of three major food crops planted in China, and is planted in most regions of China. Lodging, one of the most common natural disasters of wheat, can induce various plant diseases and insect pests and seriously affect the grain filling process, and finally affect the yield and quality of wheat. And the wheat is unfavorable for mechanized harvesting after lodging, more manpower and material resources are needed to be invested for harvesting, the harvesting cost is greatly increased, and the income loss of the farmland is aggravated. According to related reports, the yield of the lodging wheat is reduced by about 50KG per mu on average compared with the non-lodging wheat, and meanwhile, the mechanical harvesting cost is about 25 yuan per mu on average, so that the accurate and rapid acquisition of the lodging information of the wheat has important significance for disaster assessment, prevention and control guidance and loss estimation of agricultural departments and agricultural insurance departments.
At present, crop lodging monitoring methods can be mainly divided into a human engineering method and a remote sensing method. The manual method is used for counting the lodging information of the wheat by manpower, so that time and labor are wasted, and the efficiency is low; the remote sensing method extracts the lodging information of the wheat according to the specificity of each characteristic variable of the lodging and non-lodging plots in the remote sensing image. However, the satellite remote sensing technology has the disadvantages of high cost, susceptibility to weather, low spatial-temporal resolution and the like, and the near-field remote sensing technology has the disadvantages of time and labor waste, low efficiency and the like, so that the further application of the near-field remote sensing technology on the farmland scale is limited. In recent years, unmanned aerial vehicle remote sensing overcomes the defects of satellite remote sensing and near-ground remote sensing by virtue of the advantages of easy platform construction, low cost, simple operation, high space-time resolution and the like, becomes a main tool for rapidly and accurately acquiring crop information in agricultural quantitative remote sensing research, and is a hotspot and trend of current research. At present, crop lodging information extraction methods by means of unmanned aerial vehicle remote sensing mainly focus on research by means of single-time phase data, and few researches are conducted on crop lodging information extraction methods based on multi-phase unmanned aerial vehicle remote sensing data.
Disclosure of Invention
Aiming at the problems, the invention provides a method for extracting the wheat lodging information based on multi-temporal remote sensing data of an unmanned aerial vehicle, which is characterized in that an image space domain is enhanced by utilizing visible light of the unmanned aerial vehicle to carry out secondary low-pass filtering, scatter diagrams of ground features in different periods are respectively obtained according to the difference of textures of normal wheat and lodging wheat, scatter boundary lines are fitted, boundary functions Fen (1) and Fen (2) of the ground features in different periods are obtained, the spatial distribution feature similarity of the two boundary functions is integrated, a comprehensive feature parameter Fen (3) for extracting the winter wheat lodging information is obtained, and finally, the lodging wheat information is gradually extracted. Compared with the existing crop lodging information extraction method, the method is less influenced by training samples, simple in calculation and high in classification precision and universality.
The purpose of the invention is realized by the following technical scheme:
(1) acquiring a 2-phase unmanned aerial vehicle remote sensing image;
(2) carrying out low-pass filtering on the obtained unmanned aerial vehicle remote sensing image to obtain an image characteristic space;
(3) extracting feature sets of different ground features from the feature space image obtained by transformation;
(4) establishing a scatter diagram of the ground object in different characteristic parameter combination coordinate systems;
(5) and acquiring scattered point boundary lines of the ground objects in different periods in the characteristic parameter combination coordinates, and acquiring comprehensive characteristic parameters according to the spatial distribution similarity of the boundary lines.
(6) And extracting the lodging information of the wheat by utilizing the comprehensive characteristic parameters.
Furthermore, the extraction of the lodging information of the wheat needs image acquisition equipment, and conditions and image data meet certain requirements. The method specifically comprises the following steps: selecting 15 of weather in a clear day by using an unmanned aerial vehicle visible light image acquisition system based on Pixhawk flight control, a SonyA5100 visible light camera and a MOY brushless micro single tripod head automatic walking line: 00-16: 00, collecting visible light remote sensing data, wherein the data collection height is 40 m, the course and side direction overlapping degree is 80%, the image resolution is 6000 multiplied by 4000, and the ground resolution is 0.8 cm. To ensure consistency of the illumination conditions at the image acquisition time, the camera shutter time was set to 1/1250s, ISO was set to 200, respectively, and the white balance was set to clear days.
Further, the method for obtaining the feature space of the image comprises the following steps: and performing secondary low-pass filtering on the visible light image of the unmanned aerial vehicle by using image processing software to obtain a feature space of the image.
Further, the method for extracting feature sets of different feature categories comprises the following steps: extracting a plurality of interested areas of different ground objects in the RGB color space image; and selecting a texture feature set of the ground object at the corresponding position in the feature space according to the ground object interesting region extracted from the RGB color space image.
Further, the method for establishing the scatter diagram of the ground feature different characteristic parameter combination coordinate system comprises the following steps: constructing a characteristic parameter coordinate system by combining different characteristic parameters in a pairwise manner by using the characteristic parameters obtained in a secondary low-pass filtering manner; and selecting the interested areas of all the objects as scatter point main bodies, and establishing scatter point diagrams corresponding to different feature parameter combination coordinate systems constructed above all the objects.
Furthermore, boundary functions are respectively obtained according to scattered point boundaries of ground objects in a characteristic parameter combination coordinate system in different periods, and then comprehensive boundary functions are obtained according to spatial similarity of the boundaries to extract the lodging information of the wheat, and the specific method comprises the following steps: the feature parameters of the ground objects which can be distinguished are obtained by the fact that the ground objects in different periods have definite boundary lines in the feature parameter combination coordinate system; performing linear or nonlinear fitting on the boundary of the ground object in different periods by using the obtained characteristic parameters to obtain a specific boundary function of the ground object; and summarizing the comprehensive boundary function according to the spatial distribution similarity of the specific boundary function, and finally extracting the lodging information of the wheat by combining the comprehensive boundary function and a K-means algorithm.
The invention also provides a system for extracting the wheat lodging information based on the multi-temporal remote sensing data of the unmanned aerial vehicle, which comprises an image acquisition module, an image feature processing module, a ground object scattered point processing module and a wheat lodging information extraction module.
The image acquisition module is used for acquiring an unmanned aerial vehicle remote sensing image of the wheat experimental ground;
the image feature processing module is used for acquiring different feature spaces of the image, extracting an interested region and selecting a feature set of the ground object at a corresponding position in the feature space;
the ground feature scatter processing module is used for constructing a scatter diagram of the ground features in the characteristic parameter combination coordinate system, and determining the characteristic parameters, the boundary functions in different periods and the comprehensive boundary function according to boundary lines of the ground feature scatter diagram.
Specifically, the boundary functions Fen (1), Fen (2) and the comprehensive boundary function Fen (3) corresponding to the 2 periods are obtained in a linear fitting mode:
Fen(1)=B2-1.003B1-14.242；
Fen(2)=B2-0.8604B1-19.338；
Fen(3)=B2-0.8622B1-22.76；
in the formula B1、B2The red and green bands of the second order low pass filtering, respectively.
And the wheat lodging information extraction module is used for extracting the wheat lodging information according to the obtained characteristic parameters and the obtained boundary function.
Furthermore, the specific function of the wheat lodging information extraction module is to extract the wheat lodging information by combining a K-Means algorithm according to the result data calculated by the Fen (3) wave band.
The invention has the beneficial effects that: the wheat lodging information extraction method provided by the invention constructs a ground feature scatter diagram through different characteristics, fits a boundary function of each period of the ground feature to obtain a comprehensive boundary function, and then combines a K-means algorithm to achieve the purpose of extracting the wheat lodging information. Wherein, the characteristics select a red wave band B of secondary low-pass filtering1And green band B2Constructing a scattered point coordinate system, and respectively obtaining a specific boundary function Fen (1) = B of each period through linear fitting2-1.003B1-14.242，Fen(2)=B2-0.8604B1-19.338 and a comprehensive demarcation function Fen (3) = B2-0.8622B122.76, automatically extracting the lodging information of the wheat by combining a K-means algorithm according to the result obtained by calculating the wave band of the image data according to Fen (3). The method can effectively eliminate the interference of human factors, has strong calculation stability and high universality, and has higher recognition rate than the prior art.
Drawings
FIG. 1 is a flow chart of a wheat lodging information extraction method based on unmanned aerial vehicle multi-temporal remote sensing data;
FIG. 2 is a schematic diagram of a wheat lodging information extraction system based on unmanned aerial vehicle multi-temporal remote sensing data;
FIG. 3 is an original image shot by the comparative test unmanned aerial vehicle of the present invention, wherein (a) the original image is shot in 5 months and 4 days, and (b) the original image is shot in 5 months and 16 days;
FIG. 4 is a texture feature space obtained by performing a second low-pass filtering on an original RGB map according to the present invention, wherein (a) is a three-band combination result map, (b) is a second low-pass filtered red band map, (c) is a second low-pass filtered green band map, and (d) is a second low-pass filtered blue band map;
FIG. 5 is a result graph of a feature space feature set of wheat and lodging wheat obtained by the present invention;
FIG. 6 is a scatter distribution diagram of the secondary low-pass filtered red and green bands combined coordinate system of different features obtained by the present invention, wherein (a) is a 5-month-4-day scatter diagram, and (b) is a 5-month-16-day scatter diagram;
FIG. 7 is a plot of the scatter plot scaling function results of wheat and lodging wheat fitted in accordance with the present invention, wherein (a) is a 5/month 4/day scaling function plot and (b) is a 5/month 16/day scaling function plot;
FIG. 8 is a plot of the result of a synthetic cut function resulting from the synthesis of the commonality of the scatter-point cut functions of different periods of time of the present invention, wherein (a) is a plot of the result of a synthetic cut point and (b) is a plot of the result of a synthetic cut function;
FIG. 9 is a graph of the results of calculations on an image according to the synthesis function of the present invention, wherein (a) is a graph of the results of calculations on days 5/month and 4, and (b) is a graph of the results of calculations on days 5/month and 16;
FIG. 10 is a graph of visual interpretation results of comparative tests of the present invention, wherein (a) is a graph of visual interpretation results for 5 months and 4 days, and (b) is a graph of visual interpretation results for 5 months and 16 days;
FIG. 11 is a graph of the results of the comparative experiments of the present invention on the extraction of lodging information of wheat according to the method of the present invention, wherein (a) is a graph of the results of 5/month and 4/day extraction, and (b) is a graph of the results of 5/month and 16/day extraction;
FIG. 12 is a graph of the results of wheat lodging extractions using a support vector machine of the present invention, wherein (a) is a graph of 5/month and 4/day extractions, and (b) is a graph of 5/month and 16/day extractions;
FIG. 13 is a graph showing the results of extraction of lodging wheat by the neural network method in comparative experiments of the present invention, wherein (a) is a graph showing the results of extraction within 5 months and 4 days, and (b) is a graph showing the results of extraction within 5 months and 16 days;
FIG. 14 is a graph showing the results of extraction of lodging wheat by the maximum likelihood method in the comparative experiment of the present invention, wherein (a) is a graph showing the results of extraction within 5 months and 4 days, and (b) is a graph showing the results of extraction within 5 months and 16 days.
Detailed Description
Example 1
Referring to fig. 1, a method for extracting wheat lodging information based on multi-temporal remote sensing data of an unmanned aerial vehicle comprises the following steps:
(1) 15 on sunny days: 00-16: 00, the flying height is 40 meters, the course and side direction overlapping degree is 80 percent, the image resolution is 6000 multiplied by 4000, and the ground resolution is 0.8 cm. The camera shutter time was set to 1/1250s, ISO was set to 200, and white balance was set to sunny days. And after the acquisition of the visible light remote sensing image of the unmanned aerial vehicle is finished, image splicing processing is carried out by using Pix4DMapper software.
(2) And (3) carrying out secondary low-pass filtering on the obtained interesting region of the unmanned aerial vehicle remote sensing image by using image processing software ENVI, setting the sizes of convolution kernels to be 3, setting the addition values to be 0, and obtaining the characteristic space of the image.
(3) Extracting a plurality of interested areas of different ground objects in the RGB color space image; and selecting a feature set of the ground object at the corresponding position in the feature space according to the ground object interesting region extracted from the RGB color space image.
(4) Constructing a characteristic parameter coordinate system by combining different characteristic parameters in pairs; and selecting the interested areas of all the objects as scatter point main bodies, and establishing scatter point diagrams corresponding to different feature parameter combination coordinate systems constructed above all the objects.
(5) The feature parameters of the ground features which can be distinguished are obtained by the fact that each ground feature has a definite boundary in the feature parameter combination coordinate system; performing linear or nonlinear fitting on the boundary of the two-stage data by using the obtained characteristic parameters to obtain a boundary function Fen (1) = B of the ground feature2-1.003B1-14.242，Fen(2)=B2-0.8604B1-19.338; then establishing a comprehensive boundary function Fen (3) = B by utilizing the commonality of Fen (1) and Fen (2)2-0.8622B122.76, and extracting the wheat lodging information by combining Fen (3) with a K-means algorithm.
B above1、B2Are respectively twoA sub-low pass filtered red band and a green band.
Example 2
Referring to fig. 2, a system for extracting wheat lodging information based on multi-temporal remote sensing data of an unmanned aerial vehicle comprises an image acquisition module, an image feature processing module, a ground object scatter processing module and a wheat lodging information extraction module.
The image acquisition module is used for acquiring an unmanned aerial vehicle remote sensing image of the wheat experimental ground;
the image feature processing module is used for acquiring different feature spaces of the image, extracting an interested region and selecting a feature set of the ground object at a corresponding position in the feature space;
the ground feature scatter processing module is used for constructing a scatter diagram of the ground features in the characteristic parameter combination coordinate system, and determining the characteristic parameters, the boundary functions in different periods and the comprehensive boundary function according to boundary lines of the ground feature scatter diagram.
Specifically, the boundary functions Fen (1), Fen (2) and the comprehensive boundary function Fen (3) corresponding to the 2 periods are obtained in a linear fitting mode:
Fen(1)=B2-1.003B1-14.242；
Fen(2)=B2-0.8604B1-19.338；
Fen(3)=B2-0.8622B1-22.76；
in the formula B1、B2The red and green bands of the second order low pass filtering, respectively.
And the wheat lodging information extraction module is used for extracting the wheat lodging information according to the obtained characteristic parameters and the obtained boundary function.
Furthermore, the specific function of the wheat lodging information extraction module is to extract the wheat lodging information by combining a K-Means algorithm according to the result data calculated by the Fen (3) wave band.
Example 3
In order to verify the classification effect of the method, the unmanned aerial vehicle remote sensing image region-of-interest is visually interpreted, and the result of the visual interpretation is used as a true value image for verifying the accuracy of the method. Meanwhile, other methods (a support vector machine, a neural network and a maximum likelihood method) are used for carrying out wheat lodging extraction, and visual interpretation results are respectively used for carrying out precision comparison and verification.
Pure pixel regions of 3 types of normal wheat, lodging wheat and bare soil are respectively selected from the original image as learning samples of a classification algorithm. The support vector machine adopts a Sigmoid function as a kernel function, a kernel parameter Bias is 1, a kernel parameter delta is 0.333, and a penalty factor is 100. Maximum likelihood method, probability threshold "None" is selected. The neural network activation function adopts a Logistic function, the training contribution threshold value is 0.9, the weight adjusting speed is 0.2, the training stride is 0.9, the minimum value of the expected error is 0.1, the hidden layer is 1, and the training iteration number is 1000.
The verification results of the respective classification methods are shown in table 1. And performing precision evaluation on the wheat lodging information extraction results of different methods by adopting a confusion matrix. Based on the confusion matrix method, evaluation indexes such as producer Precision (PA), User precision (UA), Overall classification precision (OA), Kappa coefficient and the like can be calculated. OA and Kappa can be used for evaluating the overall classification accuracy, and F can be constructed by utilizing PA and UA and can be used for evaluating the classification accuracy of a specific class. The OA coefficient and the Kappa coefficient are used for evaluating the overall extraction precision of the wheat lodging information, and the F coefficient is used for evaluating the specific precision of the extraction of the wheat lodging information. The Kappa coefficient is used for evaluating image accuracy indexes, the result of the Kappa coefficient is generally-1 to 1, the Kappa coefficient is small when the difference between two images is large, and the Kappa coefficient is 1 when the two images are completely consistent. Generally, when Kappa is more than or equal to 0.75, the consistency is good; when Kappa is more than or equal to 0.4 and less than 0.75, the consistency is general; when Kappa is less than 0.4, the consistency is poor.
TABLE 1 verification results of the respective classification methods
Figure DEST_PATH_IMAGE001
The verification result shows that the method provided by the invention has the highest extraction precision of more than 90.10%, the Kappa coefficient of more than 0.75 and the lodging information of more than 81.11% in the extraction and classification of the lodging information of the wheat. Therefore, compared with the existing wheat lodging information extraction method, the method is less influenced by training samples, simple in calculation and higher in universality and classification accuracy.

Claims (3)

1. A wheat lodging information extraction method based on unmanned aerial vehicle multi-temporal remote sensing data is characterized by comprising the following steps:
acquiring an unmanned aerial vehicle remote sensing image of the wheat in the 2-stage filling period; carrying out secondary low-pass filtering processing on the image to enhance the spatial domain of the image; respectively constructing scatter diagrams of pairwise combined coordinate systems of normal wheat and lodging wheat in two-time low-pass filtering three wave bands; selecting a secondary low-pass filtering red wave band and a secondary low-pass filtering green wave band as a single feature for constructing the wheat lodging information extraction feature parameters by taking whether a scatter diagram has an obvious boundary as a judgment standard; obtaining red wave band B according to normal wheat and lodging wheat in secondary low-pass filtering1And green band B2Respectively constructing two period image boundary functions Fen (1) and Fen (2) as the lodging information extraction characteristic parameters of the winter wheat in the corresponding period; integrating the spatial distribution characteristic similarity of the two boundary lines to obtain a comprehensive characteristic parameter Fen (3) extracted from the lodging information of the winter wheat; and finally, extracting the lodging information of the winter wheat by using the characteristic parameter Fen (3) in combination with a K-Means algorithm.
2. A wheat lodging information extraction system based on multi-temporal remote sensing data of an unmanned aerial vehicle comprises;
the image acquisition module is used for acquiring an unmanned aerial vehicle remote sensing image of the wheat experimental ground;
the image texture feature processing module is used for carrying out texture filtering processing on the image;
the ground object scatter processing module is used for scatter analysis and boundary function construction;
and the wheat lodging information extraction module extracts the wheat lodging information by utilizing the characteristic parameter calculation result and combining a K-Means algorithm.
3. Wheat lodging based on unmanned aerial vehicle multi-temporal remote sensing data according to claim 2The information extraction system is characterized in that the ground feature scattered point processing module has the specific function of obtaining a red waveband B by secondary low-pass filtering1And green band B2Establishing a boundary function Fen (1) = B for two phases in each case for a feature2-1.003B1-14.242 and Fen (2) = B2-0.8604B1-19.338 extracting characteristic parameters as winter wheat lodging information in corresponding periods respectively, and integrating spatial distribution characteristic similarity of two boundary lines to obtain comprehensive characteristic parameter Fen (3) = B extracted from winter wheat lodging information2-0.8622B1-22.76 performing computational processing on the image pixels; the specific function of the wheat lodging information extraction module is to extract the wheat lodging information by combining the calculation result of the characteristic parameter Fen (3) with the K-Means algorithm.
CN201911063822.3A 2019-11-04 2019-11-04 Method for extracting wheat lodging information based on multi-temporal remote sensing data of unmanned aerial vehicle Pending CN110765977A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911063822.3A CN110765977A (en) 2019-11-04 2019-11-04 Method for extracting wheat lodging information based on multi-temporal remote sensing data of unmanned aerial vehicle

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911063822.3A CN110765977A (en) 2019-11-04 2019-11-04 Method for extracting wheat lodging information based on multi-temporal remote sensing data of unmanned aerial vehicle

Publications (1)

Publication Number Publication Date
CN110765977A true CN110765977A (en) 2020-02-07

Family

ID=69335448

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911063822.3A Pending CN110765977A (en) 2019-11-04 2019-11-04 Method for extracting wheat lodging information based on multi-temporal remote sensing data of unmanned aerial vehicle

Country Status (1)

Country Link
CN (1) CN110765977A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111652893A (en) * 2020-04-22 2020-09-11 中国科学院城市环境研究所 Method and equipment for evaluating loss of typhoon to urban tree ecosystem
CN112287876A (en) * 2020-11-18 2021-01-29 广东新禾道信息科技有限公司 Unmanned aerial vehicle environmental pollution remote measurement data processing method and system based on block chain
CN112924967A (en) * 2021-01-26 2021-06-08 中国农业大学 Remote sensing monitoring method for crop lodging based on radar and optical data combination characteristics and application
CN115641444A (en) * 2022-12-23 2023-01-24 中国科学院空天信息创新研究院 Wheat lodging detection method, device, equipment and medium

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111652893A (en) * 2020-04-22 2020-09-11 中国科学院城市环境研究所 Method and equipment for evaluating loss of typhoon to urban tree ecosystem
CN112287876A (en) * 2020-11-18 2021-01-29 广东新禾道信息科技有限公司 Unmanned aerial vehicle environmental pollution remote measurement data processing method and system based on block chain
CN112924967A (en) * 2021-01-26 2021-06-08 中国农业大学 Remote sensing monitoring method for crop lodging based on radar and optical data combination characteristics and application
CN112924967B (en) * 2021-01-26 2022-12-13 中国农业大学 Remote sensing monitoring method for crop lodging based on radar and optical data combination characteristics and application
CN115641444A (en) * 2022-12-23 2023-01-24 中国科学院空天信息创新研究院 Wheat lodging detection method, device, equipment and medium

Similar Documents

Publication Publication Date Title
Feng et al. Yield estimation in cotton using UAV-based multi-sensor imagery
Gašparović et al. An automatic method for weed mapping in oat fields based on UAV imagery
Chen et al. Mapping croplands, cropping patterns, and crop types using MODIS time-series data
US20230292647A1 (en) System and Method for Crop Monitoring
Solano et al. A methodology based on GEOBIA and WorldView-3 imagery to derive vegetation indices at tree crown detail in olive orchards
Lu et al. Linear mixture model applied to Amazonian vegetation classification
Farmonov et al. Crop type classification by DESIS hyperspectral imagery and machine learning algorithms
CN109325431B (en) Method and device for detecting vegetation coverage in feeding path of grassland grazing sheep
CN110765977A (en) Method for extracting wheat lodging information based on multi-temporal remote sensing data of unmanned aerial vehicle
CN111461052A (en) Migration learning-based method for identifying lodging regions of wheat in multiple growth periods
US11710232B2 (en) Image processing based advisory system and a method thereof
KR20200020209A (en) Applaratus for Monitoring Crop Growth through Multispectral Image Histogram Pattern Analysis of Plot Unit
CN116543316B (en) Method for identifying turf in paddy field by utilizing multi-time-phase high-resolution satellite image
Olenskyj et al. End-to-end deep learning for directly estimating grape yield from ground-based imagery
CN110647932B (en) Planting crop structure remote sensing image classification method and device
Zhang et al. Yield estimation of citrus fruit using rapid image processing in natural background
Ouyang et al. Assessment of canopy size using UAV-based point cloud analysis to detect the severity and spatial distribution of canopy decline
Meng et al. Fine hyperspectral classification of rice varieties based on attention module 3D-2DCNN
Yan et al. High-resolution mapping of paddy rice fields from unmanned airborne vehicle images using enhanced-TransUnet
Lee et al. Single-plant broccoli growth monitoring using deep learning with UAV imagery
Kim et al. Growth monitoring of field-grown onion and garlic by CIE L* a* b* color space and region-based crop segmentation of UAV RGB images
CN111832480B (en) Remote sensing identification method for rape planting area based on spectral characteristics
Silva et al. Mapping two competing grassland species from a low-altitude Helium balloon
Zhang et al. Large-scale apple orchard mapping from multi-source data using the semantic segmentation model with image-to-image translation and transfer learning
CN115035423B (en) Hybrid rice parent and parent identification extraction method based on unmanned aerial vehicle remote sensing image

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20200207

WD01 Invention patent application deemed withdrawn after publication