CN112364691A - Tobacco pest and disease damage identification method - Google Patents
Tobacco pest and disease damage identification method Download PDFInfo
- Publication number
- CN112364691A CN112364691A CN202011076981.XA CN202011076981A CN112364691A CN 112364691 A CN112364691 A CN 112364691A CN 202011076981 A CN202011076981 A CN 202011076981A CN 112364691 A CN112364691 A CN 112364691A
- Authority
- CN
- China
- Prior art keywords
- data
- pest
- tobacco
- disease
- planting area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 235000002637 Nicotiana tabacum Nutrition 0.000 title claims abstract description 69
- 241000607479 Yersinia pestis Species 0.000 title claims abstract description 57
- 201000010099 disease Diseases 0.000 title claims abstract description 48
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 title claims abstract description 21
- 244000061176 Nicotiana tabacum Species 0.000 title description 2
- 241000208125 Nicotiana Species 0.000 claims abstract description 67
- 238000012544 monitoring process Methods 0.000 claims abstract description 15
- 238000013528 artificial neural network Methods 0.000 claims abstract description 12
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 8
- 238000003786 synthesis reaction Methods 0.000 claims abstract description 8
- 238000005070 sampling Methods 0.000 claims abstract description 5
- 238000001228 spectrum Methods 0.000 claims abstract description 5
- 230000004927 fusion Effects 0.000 claims abstract description 4
- 230000005855 radiation Effects 0.000 claims abstract description 4
- 239000002689 soil Substances 0.000 claims description 2
- 230000003595 spectral effect Effects 0.000 description 3
- 241000238631 Hexapoda Species 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 244000025254 Cannabis sativa Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000008020 evaporation Effects 0.000 description 1
- 238000001704 evaporation Methods 0.000 description 1
- 238000003306 harvesting Methods 0.000 description 1
- 238000011835 investigation 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
- 238000001556 precipitation Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/194—Terrestrial scenes using hyperspectral data, i.e. more or other wavelengths than RGB
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Remote Sensing (AREA)
- Astronomy & Astrophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Multimedia (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Catching Or Destruction (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a tobacco pest and disease identification method, which comprises the steps of obtaining surface information data of a tobacco planting area, wherein the surface information data is obtained by a multispectral sensor carried by an unmanned aerial vehicle; acquiring Landsat data of a tobacco planting area, and performing radiation and geometric calibration on the acquired data to calculate biophysical parameters; acquiring meteorological data of a tobacco planting area; acquiring pest and disease damage data of a tobacco planting area, wherein the pest and disease damage data comprise spectra and growth environment information of tobacco in pest and pest-free sampling areas; performing multiband fusion on the acquired surface information data, Landsat data and meteorological data of the tobacco planting area to obtain a waveband synthesis data set; and (3) adopting a BP neural network to take the synthesized waveband synthesis data set as an input variable and take the pest and disease data as an output layer to train the neural network, and constructing a tobacco pest and disease monitoring characteristic parameter. According to the method, the climate conditions and the pest and disease states of the regions where the tobacco belongs can be combined, and the large-scale monitoring of the pest and disease of the tobacco can be realized simultaneously.
Description
Technical Field
The invention relates to the technical field of identification, in particular to a tobacco pest and disease identification method.
Background
The tobacco pest and disease identification is an important component of tobacco growth monitoring, and the understanding of the pest and disease state and the optimal harvesting period of tobacco has important significance for tobacco yield estimation. At present, the pest and disease damage monitoring of tobacco mainly depends on artificial ground investigation, the pest and disease damage information of the tobacco is difficult to acquire simultaneously in a large area range, and a quantitative tobacco growth evaluation means is lacked.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a tobacco pest and disease identification method to realize large-scale tobacco pest and disease monitoring and provide technical support for realizing real-time tobacco pest and disease monitoring.
In order to achieve the purpose, the technical scheme of the invention is as follows:
a tobacco pest and disease damage identification method comprises the following steps:
acquiring surface information data of a tobacco planting area, wherein the surface information data is acquired by a multispectral sensor carried by an unmanned aerial vehicle;
acquiring Landsat data of a tobacco planting area, and performing radiation and geometric calibration on the acquired data to calculate biophysical parameters;
acquiring meteorological data of a tobacco planting area;
acquiring pest and disease damage data of a tobacco planting area, wherein the pest and disease damage data comprise spectra and growth environment information of tobacco in pest and pest-free sampling areas;
performing multiband fusion on the acquired surface information data, Landsat data and meteorological data of the tobacco planting area to obtain a waveband synthesis data set;
and (3) adopting a BP neural network to take the synthesized waveband synthesis data set as an input variable and take the pest and disease data as an output layer to train the neural network, and constructing the tobacco pest and disease monitoring characteristic parameters.
Further, the biophysical parameters include an enhanced vegetation index and a normalized vegetation index.
Further, the enhanced vegetation index EVI is calculated as follows:
in the formula, ρNIR、ρREDAnd ρBLUENear infrared, red and blue bands, C, representing remote sensing images and unmanned aerial vehicle images respectively1And C2Are all constant parameters.
Further, the normalized vegetation index NDVI is calculated as follows:
in the formula, ρNIR、ρREDAnd ρBLUERespectively represent the near infrared, red light and blue light wave bands of the remote sensing image and the unmanned aerial vehicle image.
Furthermore, the meteorological data of the tobacco planting area is obtained through the ground climate data month value data of the data center of the China weather bureau, is discrete point data, and converts the point data into surface data by adopting a Critical interpolation.
Further, the growth environment information includes surface temperature and soil moisture content.
Compared with the prior art, the invention has the beneficial effects that:
the method is characterized in that high-time and spatial resolution remote sensing images are obtained based on satellite-borne and airborne multispectral remote sensing images, and a tobacco pest and disease identification method utilizing a BP neural network is provided by combining the climate conditions and pest and disease states of the region to which the tobacco belongs, so that the tobacco pest and disease monitoring in a large range is realized at the same time, and theoretical basis and technical support are provided for realizing the real-time tobacco pest and disease monitoring
Drawings
FIG. 1 is a flow chart of a tobacco pest and disease damage identification method provided by an embodiment of the invention;
FIG. 2 is a Landsat image;
FIG. 3 is an image of an unmanned aerial vehicle;
FIG. 4 is a graph of spectra;
fig. 5 is a pest grading chart.
Detailed Description
Example (b):
the technical solution of the present invention is further described below with reference to the accompanying drawings and examples.
Referring to fig. 1, the method for identifying tobacco plant diseases and insect pests provided by this embodiment includes the following steps:
and acquiring the earth surface information data of the tobacco planting area, wherein the earth surface information data is acquired by a multispectral sensor carried by the unmanned aerial vehicle. The unmanned aerial vehicle radiates and geometrically calibrates the load and the image before and after the line, and the acquired data are spliced to acquire the unmanned aerial vehicle image of a large area. The unmanned aerial vehicle images comprise high-spatial-resolution ground snapshots and surface physiological and biochemical parameters extracted based on the multiband images.
The Landsat 8-based satellite OLI land imager comprises a 15m panchromatic waveband, a 1-7 waveband and a 9-11 waveband are data with a spatial resolution of 30m, radiation and geometric calibration are carried out on data of a tobacco planting area, biophysical parameters such as EVI (enhanced vegetation index) and NDVI (normalized vegetation index) are calculated, and therefore the growth condition of tobacco is described based on the extracted biophysical parameters, and therefore the area range potentially affected by diseases and insect pests is identified.
Acquiring meteorological data of a tobacco planting area; specifically, the data of the ground climate data month value (V3.0) passes through the data center of the China weather service bureau. The meteorological data in the data set is discrete point data, and in order to obtain meteorological grids covering the whole research area, the point data is converted into surface data by adopting a Krigin interpolation
Acquiring pest and disease damage data of a tobacco planting area, wherein the pest and disease damage data comprise spectra and growth environment information of tobacco in pest and pest-free sampling areas;
performing multiband fusion on the acquired surface information data, Landsat data and meteorological data of the tobacco planting area to obtain a waveband synthesis data set;
and (3) adopting a BP neural network to take the synthesized waveband synthesis data set as an input variable and take the pest and disease data as an output layer to train the neural network, and constructing the tobacco pest and disease monitoring characteristic parameters. Namely, the spectral change characteristics of the tobacco pest and disease information are obtained by normalizing and spatially geometrically calibrating the physiological and biochemical parameter images of each earth surface and sampling in a research area, and the change information is used as an input parameter and is introduced into a BP neural network. And in the output layer, the biophysical information of the ground verification point is used as an output result so as to train a neural network and construct a simulation model suitable for large area.
Therefore, the method obtains the remote sensing images with high time and spatial resolution based on the multispectral remote sensing images on the satellite and the machine, and provides the tobacco pest and disease identification method by using the BP neural network in combination with the climate conditions and the pest and disease states of the region to which the tobacco belongs, thereby realizing the large-scale tobacco pest and disease monitoring at the same time and providing theoretical basis and technical support for realizing the real-time tobacco pest and disease monitoring.
Specifically, the enhanced vegetation index EVI is calculated as follows:
the normalized vegetation index NDVI is calculated as follows:
where ρ isNIR、ρREDAnd ρBLUERespectively representing remote-sensing imagesAnd near infrared, red and blue bands, C, of unmanned aerial vehicle images1And C2Is a constant parameter.
Therefore, the enhanced vegetation index and the normalized vegetation index can be accurately calculated through the formula.
The method is further detailed below with reference to an application scenario example:
(1) area selection: the method selects a characteristic high-quality tobacco leaf production demonstration tablet (114 degrees 11 '44' E, 25 degrees 3 '10' N) in northeast of YueBeicheng county in Guangdong province as an experimental area, and the tobacco field period is 3-6 months per year.
(2) Data collection: a meteorological dataset: air temperature, precipitation, evaporation, relative humidity and sunshine hours; landsat data: and (3) adopting a remote sensing image shared by the geographic space data cloud, carrying out radiometric calibration and atmospheric correction on the data, and carrying out accurate geometric calibration. Calculating physiological and biochemical parameters such as NDVI, EVI and the like by adopting Landsat data; unmanned aerial vehicle data: 4 wave bands images that unmanned aerial vehicle gathered.
(3) Collecting ground pest and disease data: healthy and unhealthy tobacco leaves are collected in the sample area, and different types of spectral information are measured, wherein the spectral characteristics are shown in figure 4.
Monitoring the growth vigor of the grass: and respectively taking the multi-waveband data and the pest and disease damage data fused with different data as input and output layers to construct tobacco pest and disease damage monitoring characteristic parameters, and rapidly obtaining a pest and disease damage grading diagram as shown in figure 5.
The above embodiments are only for illustrating the technical concept and features of the present invention, and the purpose thereof is to enable those skilled in the art to understand the contents of the present invention and implement the present invention accordingly, and not to limit the protection scope of the present invention accordingly. All equivalent changes or modifications made in accordance with the spirit of the present disclosure are intended to be covered by the scope of the present disclosure.
Claims (6)
1. A tobacco pest and disease damage identification method is characterized by comprising the following steps:
acquiring surface information data of a tobacco planting area, wherein the surface information data is acquired by a multispectral sensor carried by an unmanned aerial vehicle;
acquiring Landsat data of a tobacco planting area, and performing radiation and geometric calibration on the acquired data to calculate biophysical parameters;
acquiring meteorological data of a tobacco planting area;
acquiring pest and disease damage data of a tobacco planting area, wherein the pest and disease damage data comprise spectra and growth environment information of tobacco in pest and pest-free sampling areas;
performing multiband fusion on the acquired surface information data, Landsat data and meteorological data of the tobacco planting area to obtain a waveband synthesis data set;
and (3) adopting a BP neural network to take the synthesized waveband synthesis data set as an input variable and take the pest and disease data as an output layer to train the neural network, and constructing the tobacco pest and disease monitoring characteristic parameters.
2. A tobacco pest identification method according to claim 1 wherein the biophysical parameters include an enhanced vegetation index and a normalized vegetation index.
3. A tobacco pest identification method according to claim 2 wherein the enhanced vegetation index EVI is calculated as follows:
in the formula, ρNIR、ρREDAnd ρBLUENear infrared, red and blue bands, C, representing remote sensing images and unmanned aerial vehicle images respectively1And C2Are all constant parameters.
4. A method of tobacco pest identification according to claim 2 wherein the normalized vegetation index NDVI is calculated as follows:
in the formula, ρNIR、ρREDAnd ρBLUERespectively represent the near infrared, red light and blue light wave bands of the remote sensing image and the unmanned aerial vehicle image.
5. The tobacco pest and disease identification method according to claim 1, wherein the meteorological data of the tobacco growing area is obtained through ground climate data month value data of a data center of the China meteorological office, the meteorological data is discrete point data, and the point data is converted into surface data by using Critical interpolation.
6. A tobacco pest identification method according to claim 1 wherein the growth environment information includes surface temperature and soil moisture content.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011076981.XA CN112364691B (en) | 2020-10-10 | 2020-10-10 | Tobacco pest identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011076981.XA CN112364691B (en) | 2020-10-10 | 2020-10-10 | Tobacco pest identification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112364691A true CN112364691A (en) | 2021-02-12 |
| CN112364691B CN112364691B (en) | 2024-02-09 |
Family
ID=74506719
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011076981.XA Active CN112364691B (en) | 2020-10-10 | 2020-10-10 | Tobacco pest identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112364691B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113239825A (en) * | 2021-05-19 | 2021-08-10 | 四川中烟工业有限责任公司 | High-precision tobacco beetle detection method in complex scene |
| CN113435252A (en) * | 2021-05-27 | 2021-09-24 | 广西壮族自治区烟草公司百色市公司 | Tobacco pest and disease monitoring and early warning method and system based on remote sensing |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180356339A1 (en) * | 2016-08-10 | 2018-12-13 | Fuzhou University | Method of calculating tavi based on a band ratio model and solar altitude angle |
| CN110008905A (en) * | 2019-04-09 | 2019-07-12 | 安徽大学 | Regional scale stripe rust of wheat monitoring method based on the red side wave section of remote sensing image |
| CN110399819A (en) * | 2019-07-15 | 2019-11-01 | 北京洛斯达数字遥感技术有限公司 | A kind of remote sensing image residential block extraction method based on deep learning |
| CN110533595A (en) * | 2019-09-03 | 2019-12-03 | 北京麦飞科技有限公司 | A kind of method and system of crop disease and insect Spatial distributions distribution monitoring |
| CN111582055A (en) * | 2020-04-17 | 2020-08-25 | 清远市智慧农业研究院 | Aerial pesticide application route generation method and system for unmanned aerial vehicle |
-
2020
- 2020-10-10 CN CN202011076981.XA patent/CN112364691B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180356339A1 (en) * | 2016-08-10 | 2018-12-13 | Fuzhou University | Method of calculating tavi based on a band ratio model and solar altitude angle |
| CN110008905A (en) * | 2019-04-09 | 2019-07-12 | 安徽大学 | Regional scale stripe rust of wheat monitoring method based on the red side wave section of remote sensing image |
| CN110399819A (en) * | 2019-07-15 | 2019-11-01 | 北京洛斯达数字遥感技术有限公司 | A kind of remote sensing image residential block extraction method based on deep learning |
| CN110533595A (en) * | 2019-09-03 | 2019-12-03 | 北京麦飞科技有限公司 | A kind of method and system of crop disease and insect Spatial distributions distribution monitoring |
| CN111582055A (en) * | 2020-04-17 | 2020-08-25 | 清远市智慧农业研究院 | Aerial pesticide application route generation method and system for unmanned aerial vehicle |
Non-Patent Citations (3)
| Title |
|---|
| HUIQIN MA: "integrating growth and environmental parameters to discriminate powdery mildew and aphid of winter wheat using bi-temporal landsat-8 imagery", 《REMOTE SENS》, vol. 11, no. 7 * |
| 杨超;邬国锋;李清泉;王金亮;渠立权;丁凯;: "植被遥感分类方法研究进展", 地理与地理信息科学, no. 04 * |
| 毛秀华;张世良;刘锡铃;: "基于遥感影像的闽东森林病虫害等级分类技术", 宁德师范学院学报(自然科学版), no. 01 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113239825A (en) * | 2021-05-19 | 2021-08-10 | 四川中烟工业有限责任公司 | High-precision tobacco beetle detection method in complex scene |
| CN113435252A (en) * | 2021-05-27 | 2021-09-24 | 广西壮族自治区烟草公司百色市公司 | Tobacco pest and disease monitoring and early warning method and system based on remote sensing |
| CN113435252B (en) * | 2021-05-27 | 2023-09-29 | 广西壮族自治区烟草公司百色市公司 | Remote sensing-based tobacco pest monitoring and early warning method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112364691B (en) | 2024-02-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109829234B (en) | A kind of across scale Dynamic High-accuracy crop condition monitoring and yield estimation method based on high-definition remote sensing data and crop modeling | |
| CN106600434B (en) | Crop growth remote sensing monitoring method based on crop model and assimilation technology | |
| Xiao et al. | Quantitative relationships between field-measured leaf area index and vegetation index derived from VEGETATION images for paddy rice fields | |
| Bégué et al. | Spatio-temporal variability of sugarcane fields and recommendations for yield forecast using NDVI | |
| Metternicht | Vegetation indices derived from high-resolution airborne videography for precision crop management | |
| CN107273820B (en) | Remote sensing classification method and system for land coverage | |
| CN106372592B (en) | A kind of winter wheat planting area calculation method based on winter wheat area index | |
| CN110544277B (en) | Method for inverting subtropical vegetation leaf area index by unmanned aerial vehicle-mounted hyperspectral imager | |
| US10585210B2 (en) | Apparatus for radiometric correction and orthorectification of aerial imagery | |
| Sharifi | Estimation of biophysical parameters in wheat crops in Golestan province using ultra-high resolution images | |
| CN112364691B (en) | Tobacco pest identification method | |
| Breunig et al. | Assessing the effect of spatial resolution on the delineation of management zones for smallholder farming in southern Brazil | |
| CN115372286A (en) | Corn water nitrogen content inversion method based on unmanned aerial vehicle multispectral remote sensing | |
| CN111275567B (en) | SENP cotton yield estimation method based on unmanned aerial vehicle image and estimation model construction method | |
| Hama et al. | Examination of appropriate observation time and correction of vegetation index for drone-based crop monitoring | |
| Li et al. | UAV hyperspectral remote sensing estimation of soybean yield based on physiological and ecological parameter and meteorological factor in China | |
| Ahmad et al. | Spatio-temporal analysis of chickpea crop in arid environment by comparing high-resolution UAV image and LANDSAT imagery | |
| Boschetti et al. | Estimation of rice production at regional scale with a Light Use Efficiency model and MODIS time series. | |
| CN113313671A (en) | Rice yield estimation method combining satellite images and MODIS data | |
| CN116308866B (en) | Rice ear biomass estimation method and system based on canopy reflection spectrum | |
| Jurečka et al. | Estimating crop yields at the field level using Landsat and MODIS products. | |
| Dwivedi et al. | Assessment of rice biomass production and yield using semi-physical approach and remotely sensed data | |
| CN116797950A (en) | Tea tree water stress monitoring method based on unmanned aerial vehicle multispectral remote sensing | |
| Zheng et al. | Using high spatial and temporal resolution data blended from SPOT-5 and MODIS to map biomass of summer maize | |
| Liu et al. | Extraction of the corn planting area based on multi-temporal HJ-1 satellite data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |