CN106915462A - Forestry pests ＆ diseases intelligent identifying system based on multi-source image information - Google Patents
Forestry pests ＆ diseases intelligent identifying system based on multi-source image information Download PDFInfo
- Publication number
- CN106915462A CN106915462A CN201710077896.7A CN201710077896A CN106915462A CN 106915462 A CN106915462 A CN 106915462A CN 201710077896 A CN201710077896 A CN 201710077896A CN 106915462 A CN106915462 A CN 106915462A
- Authority
- CN
- China
- Prior art keywords
- image
- module
- diseases
- sensing
- vegetation index
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64C—AEROPLANES; HELICOPTERS
- B64C39/00—Aircraft not otherwise provided for
- B64C39/02—Aircraft not otherwise provided for characterised by special use
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Mining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/05—Geographic models
-
- 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
- G06V10/24—Aligning, centring, orientation detection or correction of the image
-
- 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
- G06V10/30—Noise filtering
-
- 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
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- 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
- G06V10/56—Extraction of image or video features relating to colour
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64U—UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
- B64U2101/00—UAVs specially adapted for particular uses or applications
- B64U2101/30—UAVs specially adapted for particular uses or applications for imaging, photography or videography
-
- 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
- G06V10/58—Extraction of image or video features relating to hyperspectral data
Abstract
The present invention provides a kind of forestry pests ＆ diseases intelligent identifying system based on multi-source image information, the system includes unmanned plane and earth station, the equipment of UAV flight has humiture module, communication module, control module and the d GPS locating module, sensing module and the image capture module that are connected with control module, and the humiture module is connected with control module；The communication module, realizes the communication of the control module and earth station of unmanned plane；By satellite remote-sensing image, the remote sensing image of unmanned plane and image recognition technology to forestry pests ＆ diseases information extraction, using the spectral information in time series image data and when phase information, to image capture module collection image carry out image automatic identification obtain pest and disease damage a situation arises.Relative satellite remote sensing of the present invention, airborne and spaceborne RS cost are lower, and accuracy is high, easily controllable.
Description
Technical field
The present invention relates to unmanned aerial vehicle remote sensing, satellite remote sensing, spatial data analysis treatment, image procossing and forestry technology neck
Domain；More particularly to the pest and disease damage of a kind of satellite image based on multidate, unmanned aerial vehicle remote sensing images, image recognition technology is intelligently known
Other system.
Background technology
Traditional forestry pests ＆ diseases investigation relies primarily on the modes such as artificial range estimation hand is looked into, woodland is sampled.Though these methods
Right authenticity and reliability are very high, but time-consuming, laborious, and there is representative, poor in timeliness and the drawback such as subjectivity is strong, have been difficult to
Adapt at present on a large scale pest and disease damage have a try monitoring and forecast demand.
Remote sensing technology be it is currently the only can be in the means of the continuous earth's surface information in interior quick obtaining space on a large scale, it is in woods
The many aspects such as industry the yield by estimation, Quality Prediction and pest and disease monitoring have different degrees of research and application.Due to satellite remote sensing
Image data input cost is high, periodically low, cannot be monitored in time and early warning for forestry pests ＆ diseases monitoring.With nobody
The fast development of machine technology, in forest pest control, using unmanned plane, can be king-sized heavy to landform inconvenience, area
Low-altitude aerial remote sensing monitoring is implemented in point region, and the human resources that solution prospecting faces are not enough, coverage rate is low, the low problem of efficiency.
But because forest-covered area is wide, it is impossible to which realization realizes large-scale pest and disease monitoring using unmanned plane, while nothing cannot be utilized
The remote sensing image of man-machine collection carries out intelligent automatic identification, often relies on naked eyes identification.The prison of majority pest and disease damage remote sensing at present
Survey method and device and be directed to the scale Designs such as blade, the canopy of crop, the remote sensing image of unmanned plane collection relies on naked eyes identification,
The country not yet realizes carrying out the insect Weigh sensor of multi-source image information using satellite remote-sensing image and unmanned plane image.
On the other hand, sensor Landast TM and satellite sensing that the remotely-sensed data of early stage, such as subject-oriented imaging instrument are carried
Device MODIS, due to cannot simultaneously meet spatial resolution and temporal resolution higher, to the pest and disease monitoring structure of regional scale
Into the obstacle of certain hardware condition, the more existing crop disease and insect monitoring based on satellite image often only accounts for light
Spectrum information, phase information when not considering highly important for pest and disease monitoring, monitoring result has larger uncertainty.
In recent years, it is region chi with the appearance of such as some middle high-resolutions such as environment disaster reduction moonlet, revisiting period satellite data high
Disease remote sensing monitoring on degree brings important opportunity.The generation of crop disease spectrally can show some spies with the time
Levy, can be used as the basis of remote sensing monitoring.Not yet there is method using multi-temporal satellite remote sensing data to being carried out on regional scale at present
The monitoring on a large scale of forestry disease, the region of paying close attention to for recycling unmanned plane to find satellite remote-sensing image carries out check and correction core
It is real, realize the Weigh sensor of forestry pests ＆ diseases.
The content of the invention
The technical problem to be solved in the present invention, is to provide a kind of forestry pests ＆ diseases based on multi-source image information intelligently to know
Other system, relative satellite remote sensing, airborne and spaceborne RS cost are lower, and accuracy is high, easily controllable.
What the present invention was realized in：A kind of forestry pests ＆ diseases intelligent identifying system based on multi-source image information, it is described
System includes unmanned plane and earth station, the equipment of UAV flight have humiture module, communication module, control module and with control
The connected d GPS locating module of molding block, sensing module and image capture module, the humiture module are connected with control module；
The communication module, realizes the communication of the control module and earth station of unmanned plane；By satellite remote-sensing image, the remote sensing of unmanned plane
Image and image recognition technology to forestry pests ＆ diseases information extraction, using spectral information and phase in time series image data
Information, image automatic identification acquisition pest and disease damage is carried out to the image that image capture module is gathered, and a situation arises.
Further, the sensing module includes many ripples of the pulse radar of monitoring forestry pests ＆ diseases and the monitoring forest reserves
Section spectrum scanner, infrared spectrometer.
Further, it is described sick to forestry by satellite remote-sensing image, the remote sensing image of unmanned plane and image recognition technology
The mode that insect pest information is extracted specifically includes following steps：
Step 1, download satellite remote-sensing image, and to obtain satellite remote-sensing image pre-process；
Step 2, the coverage for extracting forestry pests ＆ diseases；
The light of Mono temporal and multi-temporal vegetation indices in step 3, the time series image data of extraction satellite remote-sensing image
Spectrum signature；
Step 4, disease monitor the phase, synchronized in image capturing unmanned plane low latitude investigation；
Forest reserves image and state that step 5, unmanned plane collection draw the line interior；
Step 6, the image of control module analysis image capture module collection and remote sensing images and light from sensing module
Modal data, the pulse radar of sensing module whether there is insect, the infrared spectrometer of sensing module according to the electromagnetic wave detection being reflected back
With the spectral signature of the different-waveband of the multiband spectrum scanner collection forest reserves, and collection of illustrative plates is generated；
Step 7, pass the data in step 6 back earth station and further analyze；With reference to unmanned plane low latitude survey data, utilize
Image recognition technology, screens the spectral signature of disease monitoring；
It is step 9, different according to forest reserves growth period and whether there is pest and disease damage to be respectively established；
Step 10, a situation arises for the pest and disease damage based on model, spectral information divergence and atlas analysis forestry, the spectrum letter
Breath includes：The spectral signature of the spectral signature of vegetation index, the spectral signature of different-waveband and disease monitoring.
Further, the step 3 is specially：Employ alternative features of 13 spectral signatures as disease monitoring, 13
Individual spectral signature includes the blue RB compatible with the multispectral satellite image of most middle high-resolutions, green RG, red RR, near-infrared RNIR
Passage primary reflection rate, and normalization difference vegetation index NDVI, ratio vegetation index SR, green normalization difference vegetation
Index GNDVI, adjustment soil lightness vegetation index SAVI, triangle vegetation index TVI, improve red side ratio vegetation index MSR, non-
Linear vegetation index NLI, renormalization vegetation index RDVI, soil regulation vegetation index nine broadband vegetation indexs of OSAVI；
The vegetation index that Mono temporal and multidate two kinds of version is respectively adopted is analyzed, wherein, Mono temporal vegetation index by certain for the moment
Phase image wave band reflectivity is calculated, for reflecting Physiology and biochemistry state of the vegetation on certain time point；Multidate vegetation
Index is normalized according to the Mono temporal vegetation index of two phases and is calculated, and becomes for reflecting that pest and disease damage develops in woodland
The characteristics of change.
Further, the scope of the image wave band includes visible ray and near infrared band.
Further, the satellite remote-sensing image of described pair of acquisition carries out pretreatment includes radiation calibration, atmospheric correction, geometry
Correction and cloud removal.
Further, the coverage of the forestry pests ＆ diseases is according to forest land classification vector figure or multi_temporal images enter
Row classification is obtained.
Further, the multi_temporal images need to combine in assorting process forest land use pattern data, terrain data and
Phenology experience, takes decision tree, maximum likelihood classification or neutral net to carry out planting range extraction.
Further, the Spectra feature extraction mode of the disease monitoring is：According to the emphasis area that unmanned plane low latitude is investigated
A situation arises for domain disease, and key area is divided into normal sample and sample two parts of catching an illness；
The Mono temporal and multidate for extracting two class sample point multi-form spectral signatures from image identification system respectively are special
Value indicative；
Mono temporal or multidate version to every kind of spectral signature, using independent samples t test is relatively normal and sample of catching an illness
This difference degree；
The difference degree of a certain feature is characterized using the preset value p of t inspections, and accordingly generates an all kinds of multi-forms
Spectral signature different phases and when it is combined in p value statistical table, wherein, p value is smaller, normal and sample of catching an illness difference
Bigger, response of the feature to defect information is stronger.
The invention has the advantages that：Satellite image of the present invention based on multidate, the remote sensing image of unmanned plane, image are known
The forestry pests ＆ diseases intelligent identification technology of other technology, make full use of the spectral information in time series image data and when believe
Breath, spectral information divergence analysis is introduced forestry by combining geographic information system GIS, global position system GPS, remote sensing technology
Pest and disease damage generation area, the system that proposition is monitored on a large scale using the star in certain area-ground synchrodata to disease, has
Effect reduces the cost of the field work of disease monitoring, and the extension by point and face has been carried out to traditional disease monitoring mode, is easy to
Government department and Management offorestry department in time, accurately grasp and understand the important informations such as the generation of region disease and the order of severity.
Brief description of the drawings
The present invention is further illustrated in conjunction with the embodiments with reference to the accompanying drawings.
Fig. 1 carries out disease recognition to be based on the remote sensing image data of satellite remote-sensing image and unmanned plane in the embodiment of the present invention
Method flow schematic diagram.
Fig. 2 is the remote sensing image data collecting flowchart figure of unmanned plane in the present invention.
Fig. 3 is forestry pests ＆ diseases occurrence scope extraction flow chart in the present invention.
Specific embodiment
Refer to shown in Fig. 1 to Fig. 3, a kind of forestry pests ＆ diseases intelligent identifying system based on multi-source image information, it is special
Levy and be：The system includes unmanned plane and earth station, and the equipment of UAV flight has humiture module, communication module, control
Module and the d GPS locating module, sensing module and the image capture module that are connected with control module, the humiture module and control
Molding block is connected；The communication module, realizes the communication of the control module and earth station of unmanned plane；By satellite remote-sensing image,
The remote sensing image and image recognition technology of unmanned plane to forestry pests ＆ diseases information extraction, using the light in time series image data
Spectrum information and when phase information, to image capture module collection image carry out image automatic identification obtain pest and disease damage a situation arises.
The sensing module includes the multiband spectrum scanner, infrared of the pulse radar of monitoring forestry pests ＆ diseases and the monitoring forest reserves
Spectrometer.Humiture module is used to gather the humiture situation of forestry, and d GPS locating module is used to position unmanned plane in forestry
Position.
Wherein, it is described by satellite remote-sensing image, the remote sensing image of unmanned plane and image recognition technology to forestry pests ＆ diseases
The mode of information extraction specifically includes following steps：
Step 1, order download satellite remote-sensing image, and to obtain satellite remote-sensing image pre-process；
Step 2, the coverage for extracting forestry pests ＆ diseases；
The light of Mono temporal and multi-temporal vegetation indices in step 3, the time series image data of extraction satellite remote-sensing image
Spectrum signature；Step 3 extracting mode：On the basis of comprehensive survey is suitable to the documents and materials of crop disease monitoring both at home and abroad, respectively
Alternative features of 13 spectral signatures as disease monitoring are employed, including it is simultaneous with the multispectral satellite image of most middle high-resolutions
Blue (RB), green (RG), red (RR), the passage primary reflection rate of near-infrared (RNIR) held, and (difference vegetation refers to for normalization
Number) NDVI, (ratio vegetation index) SR, (green vegetation index) GNDVI, (adjustment soil lightness vegetation index)
SAVI, (triangle vegetation index) TVI, (improve red side ratio vegetation index) MSR, (non-linear vegetation index) NLI, (return one
Change vegetation index) RDVI, (soil regulation vegetation index) nine broadband vegetation indexs of OSAVI；(each index fixed is shown in Table 1).
The present invention is respectively adopted Mono temporal and the vegetation index of multidate two kinds of version is analyzed.Wherein, Mono temporal vegetation index by
A certain phase image wave band reflectivity is calculated, for reflecting Physiology and biochemistry state of the vegetation on certain time point；When many
Phase vegetation index is normalized according to the Mono temporal vegetation index of two phases and is calculated, for reflecting pest and disease damage in woodland
The characteristics of development and change.Assuming that there is M and N to carry out two phases for before and after, for a certain vegetation index form V1, multidate reflectivity
Computing formula is (VIN-VIM)/(VIN+VIM).Wherein, the period of VIN vegetation indexs ordinal number N, VIM vegetation index ordinal numbers M's
Phase, for n phase, is carried out combination of two by the period, and C2n multidate spectral signature is can obtain altogether.It is above-mentioned in this method
Mono temporal feature and multidate feature are as the alternative features of disease monitoring.
The vegetation characteristics of table 1 are defined
Step 4, disease monitor the phase, synchronized in image capturing unmanned plane low latitude investigation；
Forest reserves image and state that step 5, unmanned plane collection draw the line interior；
Step 6, the image of control module analysis image capture module collection and remote sensing images and light from sensing module
Modal data, pulse radar whether there is insect according to the electromagnetic wave detection being reflected back, and infrared spectrum and multiband spectrum scanner are gathered
The spectral signature of the different-waveband of the forest reserves, and generate collection of illustrative plates；
Step 7, pass the data in step 6 back earth station and further analyze.
Step 8, with reference to unmanned plane low latitude survey data, using image recognition technology, screen the spectral signature of disease monitoring；
It is step 9, different according to forest reserves growth period and whether there is pest and disease damage to be respectively established；
Step 10, a situation arises for the pest and disease damage based on model, spectral information divergence and atlas analysis forestry, the spectrum letter
Breath includes：The spectral signature of the spectral signature of vegetation index, the spectral signature of different-waveband and disease monitoring.
Wherein, the scope of the image wave band includes visible ray and near infrared band.
Wherein, the satellite remote-sensing image of described pair of acquisition carries out pretreatment includes radiation calibration, atmospheric correction, geometric correction
And cloud removal.
Wherein, the coverage of the forestry pests ＆ diseases is according to forest land classification vector figure or multi_temporal images are divided
Class is obtained.The multi_temporal images need to combine forest land use pattern data, terrain data and phenology experience in assorting process, adopt
Taking decision tree, maximum likelihood classification or neutral net carries out planting range extraction.
Wherein, the Spectra feature extraction mode of the disease monitoring is：According to the key area disease that unmanned plane low latitude is investigated
Harmful a situation arises, and key area is divided into normal sample and sample two parts of catching an illness；
The Mono temporal and multidate for extracting two class sample point multi-form spectral signatures from image identification system respectively are special
Value indicative；
Mono temporal or multidate version to every kind of spectral signature, using independent samples t test is relatively normal and sample of catching an illness
This difference degree；
The difference degree of a certain feature is characterized using the preset value p of t inspections, and accordingly generates an all kinds of multi-forms
Spectral signature different phases and when it is combined in p value statistical table, wherein, p value is smaller, normal and sample of catching an illness difference
Bigger, response of the feature to defect information is stronger.
For example：
Combined ground points for investigation data screening disease monitoring spectral signature.According to investigation sampling point disease, a situation arises, will
Sample point is divided into normal sample and sample two parts of catching an illness.According to third step method, two class sample point each spectrum are extracted respectively
The Mono temporal of feature and the characteristic value of multidate version, and calibration is compared using independent samples t test (Independentt_test)
Often with the difference degree of sample of catching an illness, the p value (p-value) checked using t characterizes the difference degree of a certain feature, and can be accordingly
The p that one all kinds of multi-form spectral signature of generation are rented in closing (multidate feature) in different phases (Mono temporal feature) and phase
Data-Statistics form.Wherein, p value is smaller, and the difference of sample of normally catching an illness is bigger, and response of the feature to defect information is stronger.
Therefore, the method for being set by threshold value is screened to all kinds of spectral signatures of Mono temporal and multidate, is retained to defect information
The strong spectral signature form of response.Under normal circumstances, p value can be set the threshold to less than 0.05,0.01 or 0.001 three
Kind.Defect information in image is weaker, and the threshold value of p value sets bigger.
Generally, postponing with phase, each spectral signature is improved constantly in the significance of difference of normal and disease sampling point,
The difference of wherein the 4th phase each feature is the most notable, and now powdery mildew is by the lower shape for having caused wheat strain value from upper infecting
State has significantly change, the even scab up to boot leaf in heavier field is infected in part, this and woodland factual survey
Situation is consistent.By setting a threshold value of P values ＜ 0.001 in this example, it is retained in and normally reaches pole with disease training sample
15 Mono temporals and multidate feature of significant difference level, 15 Mono temporals and multidate feature include respectively：Blue wave band
4th test phase RB (RB-T4), second test phase RB-T4T2 of blue wave band, the 3rd test phase of green wave band
RG-T3, the 4th test phase RG-T4 of green wave band, the 3rd of red wave band tests phase RR-T3, the 4th of red wave band
Test phase RR-T4, the 4th test phase SR-T4 of ratio vegetation index, during the 4th test of vegetation index of normalization difference
Phase NDVI-T4, second and the 4th test phase vegetation index NDVI-T4T2 of normalization difference vegetation index, green wave band is returned
One changes the 4th test phase GNDVI-T4 of difference vegetation index, green wave band normalization difference vegetation index the 4th and second
Test phase GNDVI-T4T2, the 4th test phase OSAVI-T4 of soil regulation vegetation index, improves red side ratio vegetation and refers to
The 3rd test phase NLI-T3 of the 4th test phase MSR-T4 of number and non-linear vegetation index.
The process of the spectral information divergence analysis is：Degree of correlation between by judging two pixels, by picture to be sorted
Degree of correlation highest classification is included into unit.
Below in conjunction with the accompanying drawings and specific embodiment, the present invention is described in further detail.Following examples are used to illustrate
The present invention, is not only not limited to the scope of the present invention.
Realization of the invention is adopted the following technical scheme that：
The first step：Multidate satellite remote-sensing image is ordered and downloads and pre-process.There is process according to most forestry pests ＆ diseases
Fast feature and it is currently available that satellite remote sensing date source, it is proposed that using the middle high-resolution satellite image of revisiting period high.Wave band
Scope needs covering visible light and near infrared band.The most suitable forecasting stage of local forestry pests ＆ diseases is determined first.Obtain forestry disease pest
Evil occurs to the satellite image data of multiple phases in this period.The preprocessing process of image includes radiation calibration, air school
Just, geometric correction and cloud are removed.Follow-up defect information extracts the reflectivity image data based on the multidate obtained after pretreatment
Carry out.
Second step：Application region forest reserves coverage is extracted.Forest land classification vector figure can be combined or according to many
Phase image carries out classification acquisition.Assorting process needs forest land use pattern data in connected applications region, terrain data and thing
Time experience etc., crop-planting scope extraction is carried out using supervised classification methods such as decision tree, maximum likelihood classification or neutral nets.
Follow-up forestry pests ＆ diseases information extraction is obtained being carried out in forest reserves coverage in classification, and it is come to reduce
The interference of his atural object or agrotype.
3rd step：The Mono temporal and multidate Spectra feature extraction of disease monitoring.The method is fitted in domestic object for appreciation that comprehensively light a cigarette
On the basis of the documents and materials of crop disease monitoring, alternative features of 13 spectral signatures as disease monitoring are respectively adopted, wrap
Include the indigo plant (RB) compatible with the multispectral satellite influence of most middle high-resolutions, green (RG), red (RR), near-infrared (RNIR) passage original
Beginning reflectivity, and normalization difference vegetation index (NDVI), ratio vegetation index (SR), green wave band normalization difference vegetation refer to
Number (GNDVI), triangle vegetation index (TVI) improves red side ratio vegetation index (MSR), non-linear vegetation index (NLI), soil
Earth regulation vegetation index (OSAVI) nine broadband vegetation indexs (each index fixed is shown in Table 1).This method is respectively adopted Mono temporal
The Physiology and biochemistry state navigated at certain time point with the vegetation index of multidate breeding version；Multi-temporal vegetation indices are according to two
The Mono temporal vegetation index of individual phase is normalized and is calculated, for reflecting pest and disease damage the characteristics of development and change.Assuming that
There is M and N to carry out two phases for before and after, for a certain vegetation index form V1 (V1 is the name of vegetation index form), multidate
Reflectivity computing formula is (VIN-VIM)/(VIN+VIM).For n phase, phase is carried out into combination of two, it is available altogether
C2n multidate spectral signature.In this method, above-mentioned Mono temporal feature and multidate feature are as the alternative spy of disease monitoring
Levy.
4th step：There is critical period development in disease to be investigated with the unmanned plane low latitude of image capturing time synchronized.Nobody
The investigation of machine low latitude is separated by no more than 3 days with corresponding period satellite shooting date.According to the area of application region, in sampling point setting
The density of 1 sampling point/10 sq-km should be not less than.Meanwhile, total investigation sampling point number should be no less than 30.The field of investigation includes institute
Selectable sampling point is the continuous overlay area of the forest reserves of the diameter more than 30m, and investigation content is gloomy in survey area
The onset grade of woods resource.For ease of woodland investigation and pathology management on a large scale, the forest zone block that will catch an illness be divided into gently, weigh two
Rank.For the different diseases of Different Forest resource, specific disease level delimitation canonical reference disease observes and predicts national standard to be carried out.
5th step：According to the multispectral principle of satellite remote-sensing image, suspicious forestry pests ＆ diseases generation area scope is found out,
In conjunction with GIS forestry topographic maps, the forestry topographic map of suspicious region is marked, and show its state；
6th step：The present invention includes control module and the d GPS locating module, sensing module and the image that are connected with control module
Acquisition module, sensing module includes the multiband spectrum scanning of the pulse radar of monitoring forestry pests ＆ diseases and monitoring forestry pests ＆ diseases
Instrument, infrared spectrometer.Also include humiture module, be connected with control module；Communication module, for connecting main control module and ground
Stand.
Remote sensing technique predicts that pest and disease damage in addition to from spectrum angle analysis, can also recognize disease pest using remote sensing image
The harmful forest reserves.
7th step：By step 6 is by earth station and is mounted in the multispectral image data of monitoring unmanned camera and passes
Earth station is gone back to further to analyze.
8th step：Forest reserves pest and disease damage does not recognize the pest and disease damage initial stage come also in naked eyes, and it is in the outer shadow of rainbow
Dark red tone is showed on picture, and normal crop is then red.Tone difference according to produced by image contrast can be judged
Damaged forest resource.
Because spectral reflectivity of the crop in near-infrared wavelength domain is often very high, when the forest reserves receive pest and disease damage, blade
Water content reduction, cell is collapsed therewith, and chlorophyll is reduced, therefore, their spectral reflectance meeting natures in infrared wavelength domain are reduced,
There is reflection infrared spectrum decay, cause outside rainbow in shooting, the tone of the tone than normal crop of damaged forest resource
Dark, when the normal forest reserves are for red, damaged forest resource is then rendered as kermesinus.When pest and disease damage further develops, make
The chlorophyll of forest reserves blade disappear totally, blade construction is when suffering thoroughly to destroy, image tone can then become darker so that
Adjusted in cyan is presented.According to the difference of damaged forest resource on the outer image of rainbow and normal crop tone, we quickly just can be by
The damaged forest resource judgment that naked eyes are not yet aware of is out, as shown in table 2 below.
The image feature of the healthy forest reserves of table 2 and damaged forest resource
Tenth step：It is all gloomy in large geographical area with reference to GIS technology according to forest reserves growth period different characteristics
The relevant pest and disease damage of woods resource crop rotation refers on same soil, with the time to the forest reserves cycle, in large geographical area
For being diagnosed to be geographical position and the order of severity that all pest and disease damages relevant with forest reserves crop rotation occur, the forest reserves are set up
Different growth times whether the model of pest and disease damage, so that relevant departments are consulted；
11st step：With reference to forestry pests ＆ diseases data screening disease monitoring spectral signature.According to the hair of investigation sampling point disease
Raw situation, normal sample is divided into and sample two parts of catching an illness by sample point.According to the three, the 8th one step process, two classes are extracted respectively
The Mono temporal of sample point each spectral signature and the characteristic value of multidate version, and use independent samples t test
(Independent t-test) relatively more normal and sample of catching an illness difference degree.The p value (p-value) checked using t is represented
The difference degree of a certain feature, and an all kinds of multi-form spectral signatures can be accordingly generated in different phases (Mono temporal feature)
With when combined (multidate feature) in p value statistical table.Wherein, p value is smaller, and normal and sample of catching an illness difference is bigger,
Response month of the feature to defect information is strong.Therefore, by the method for threshold setting to Mono temporal and all kinds of spectrum of multidate
Feature is screened, and is retained and is responded strong spectral signature form to defect information.Under normal circumstances, p can be set the threshold to
Value is less than 0.05,0.01 or 0.001 3 kinds.Defect information in image is weaker, and the threshold value of p value sets bigger.
As shown in figure 3, the A samples of on May 20th, 1,2016 ground unmanned plane multispectral image, extracts normalization difference vegetation index
(NDVI)>0.7 forest reserves region.
2nd, in 1 forest reserves regional extent extracted, then by near infrared spectrum feature extraction (Nir)<0.44 it is gloomy
Woods overlay area.
3rd, in 2 forest reserves regional extents extracted, characters of ground object value (DEM) is extracted by characters of ground object<100m's
Forest reserves region.
4th, the satellite remote-sensing image of on May 1st, 2016 and the unmanned aerial vehicle remote sensing A samples of May 20 ground multispectral image are folded
Plus, carry out sorting out the aggrieved insect pest forest reserves and the healthy forest reserves by Maximum likelihood classification (MLC).
Although the foregoing describing specific embodiment of the invention, those familiar with the art should manage
Solution, the specific embodiment described by us is merely exemplary, and rather than for the restriction to the scope of the present invention, is familiar with this
The technical staff in field should be covered of the invention in the equivalent modification and change made according to spirit of the invention
In scope of the claimed protection.
Claims (9)
1. a kind of forestry pests ＆ diseases intelligent identifying system based on multi-source image information, it is characterised in that：The system includes nothing
Man-machine and earth station, the equipment of UAV flight has humiture module, communication module, control module and is connected with control module
D GPS locating module, sensing module and image capture module, the humiture module is connected with control module；The communication mould
Block, realizes the communication of the control module and earth station of unmanned plane；By satellite remote-sensing image, the remote sensing image and image of unmanned plane
Identification technology to forestry pests ＆ diseases information extraction, using the spectral information in time series image data and when phase information, to figure
As the image that acquisition module is gathered carries out image automatic identification acquisition pest and disease damage, a situation arises.
2. a kind of forestry pests ＆ diseases intelligent identifying system based on multi-source image information according to claim 1, its feature
It is：The sensing module includes the multiband spectrum scanning of the pulse radar of monitoring forestry pests ＆ diseases and the monitoring forest reserves
Instrument, infrared spectrometer.
3. a kind of forestry pests ＆ diseases intelligent identifying system based on multi-source image information according to claim 1, its feature
It is：It is described by satellite remote-sensing image, the remote sensing image of unmanned plane and image recognition technology to forestry pests ＆ diseases information extraction
Mode specifically include following steps：
Step 1, download satellite remote-sensing image, and to obtain satellite remote-sensing image pre-process；
Step 2, the coverage for extracting forestry pests ＆ diseases；
The Spectral Properties of Mono temporal and multi-temporal vegetation indices in step 3, the time series image data of extraction satellite remote-sensing image
Levy；
Step 4, disease monitor the phase, synchronized in image capturing unmanned plane low latitude investigation；
Forest reserves image and state that step 5, unmanned plane collection draw the line interior；
Step 6, the image and the remote sensing images from sensing module and spectrum number of control module analysis image capture module collection
Insect is whether there is according to the electromagnetic wave detection being reflected back according to the pulse radar of, sensing module, the infrared spectrometer of sensing module and many
The spectral signature of the different-waveband of the band spectrum scanner collection forest reserves, and generate collection of illustrative plates；
Step 7, pass the data in step 6 back earth station and further analyze；With reference to unmanned plane low latitude survey data, using image
Identification technology, screens the spectral signature of disease monitoring；
It is step 9, different according to forest reserves growth period and whether there is pest and disease damage to be respectively established；
Step 10, a situation arises for the pest and disease damage based on model, spectral information divergence and atlas analysis forestry, the spectral information bag
Include：The spectral signature of the spectral signature of vegetation index, the spectral signature of different-waveband and disease monitoring.
4. a kind of forestry pests ＆ diseases intelligent identifying system based on multi-source image information according to claim 3, its feature
It is：The step 3 is specially：Employ alternative features of 13 spectral signatures as disease monitoring, 13 spectral signature bags
Include the blue RB compatible with the multispectral satellite image of most middle high-resolutions, green RG, red RR, near-infrared RNIR passage it is original anti-
Penetrate rate, and normalization difference vegetation index NDVI, ratio vegetation index SR, green wave band normalization difference vegetation index GNDVI,
Adjustment soil lightness vegetation index SAVI, triangle vegetation index TVI, the red side ratio vegetation index MSR of improvement, non-linear vegetation refer to
Number NLI, renormalization vegetation index RDVI, soil regulation vegetation index nine broadband vegetation indexs of OSAVI；List is respectively adopted
The vegetation index of phase and multidate two kinds of version is analyzed, wherein, Mono temporal vegetation index is by a certain phase image wave band
Reflectivity is calculated, for reflecting Physiology and biochemistry state of the vegetation on certain time point；Multi-temporal vegetation indices are according to two
The Mono temporal vegetation index of individual phase is normalized and is calculated, for reflecting pest and disease damage the characteristics of woodland development and change.
5. a kind of forestry pests ＆ diseases intelligent identifying system based on multi-source image information according to claim 4, its feature
It is：The scope of the image wave band includes visible ray and near infrared band.
6. a kind of forestry pests ＆ diseases intelligent identifying system based on multi-source image information according to claim 3, its feature
It is：The satellite remote-sensing image of described pair of acquisition carries out pretreatment includes that radiation calibration, atmospheric correction, geometric correction and cloud go
Remove.
7. a kind of forestry pests ＆ diseases intelligent identifying system based on multi-source image information according to claim 3, its feature
It is：The coverage of the forestry pests ＆ diseases is according to forest land classification vector figure or multi_temporal images carry out classification acquisition.
8. a kind of forestry pests ＆ diseases intelligent identifying system based on multi-source image information according to claim 7, its feature
It is：The multi_temporal images need to combine forest land use pattern data, terrain data and phenology experience in assorting process, take
Decision tree, maximum likelihood classification or neutral net carry out planting range extraction.
9. a kind of forestry pests ＆ diseases intelligent identifying system based on multi-source image information according to claim 1, its feature
It is：The Spectra feature extraction mode of the disease monitoring is：The generation of the key area disease investigated according to unmanned plane low latitude
Situation, normal sample is divided into and sample two parts of catching an illness by key area；
The Mono temporal and multidate characteristic value of two class sample point multi-form spectral signatures are extracted from image identification system respectively；
Mono temporal or multidate version to every kind of spectral signature, using independent samples t test is relatively normal and sample of catching an illness
Difference degree；
The difference degree of a certain feature is characterized using the preset value p of t inspections, and accordingly generates an all kinds of multi-form spectrum
Feature different phases and when it is combined in p value statistical table, wherein, p value is smaller, and normal and sample of catching an illness difference is got over
Greatly, response of the feature to defect information is stronger.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710077896.7A CN106915462A (en) | 2017-02-14 | 2017-02-14 | Forestry pests ＆ diseases intelligent identifying system based on multi-source image information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710077896.7A CN106915462A (en) | 2017-02-14 | 2017-02-14 | Forestry pests ＆ diseases intelligent identifying system based on multi-source image information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106915462A true CN106915462A (en) | 2017-07-04 |
Family
ID=59454153
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710077896.7A Pending CN106915462A (en) | 2017-02-14 | 2017-02-14 | Forestry pests ＆ diseases intelligent identifying system based on multi-source image information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106915462A (en) |
Cited By (39)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107682456A (en) * | 2017-11-07 | 2018-02-09 | 蔡璟 | A kind of intelligent gardens nursing system based on image and root detection |
| CN107808133A (en) * | 2017-10-23 | 2018-03-16 | 中石化石油工程地球物理有限公司 | Oil-gas pipeline safety monitoring method, system and software memory based on unmanned plane line walking |
| CN108195767A (en) * | 2017-12-25 | 2018-06-22 | 中国水产科学研究院东海水产研究所 | Estuarine wetland denizen monitoring method |
| CN108287926A (en) * | 2018-03-02 | 2018-07-17 | 宿州学院 | A kind of multi-source heterogeneous big data acquisition of Agro-ecology, processing and analysis framework |
| CN108303382A (en) * | 2018-02-06 | 2018-07-20 | 安徽大学 | A kind of winter wheat powdery mildew multi-temporal remote sensing monitoring method and its evaluation method based on AdaBoost graders |
| CN108334110A (en) * | 2018-02-06 | 2018-07-27 | 首欣（北京）科技有限公司 | A kind of forestry disease monitoring method and apparatus based on unmanned plane |
| CN108446599A (en) * | 2018-02-27 | 2018-08-24 | 首都师范大学 | A kind of high spectrum image wave band fast selecting method of p value statistic modeling independence |
| CN108535193A (en) * | 2018-03-19 | 2018-09-14 | 电子科技大学 | A kind of forestry typical case pest and disease damage remote-sensing monitoring method |
| CN108694391A (en) * | 2018-05-16 | 2018-10-23 | 黄铁成 | Populus Euphratica spring looper disaster monitoring method based on high-spectrum remote-sensing |
| CN108764285A (en) * | 2018-04-23 | 2018-11-06 | 湖北同诚通用航空有限公司 | A kind of recognition methods of pine tree Deceased wood and system based on high resolution image |
| CN108764284A (en) * | 2018-04-23 | 2018-11-06 | 湖北同诚通用航空有限公司 | The classification denoising method and system of a kind of high resolution image to pine tree Deceased wood |
| CN108873851A (en) * | 2018-09-06 | 2018-11-23 | 保定智飞航空科技有限公司 | A kind of agricultural unmanned plane managing and control system |
| CN109141371A (en) * | 2018-08-21 | 2019-01-04 | 中国科学院地理科学与资源研究所 | The disaster-stricken recognition methods of winter wheat, device and equipment |
| CN109211802A (en) * | 2018-09-13 | 2019-01-15 | 航天信德智图（北京）科技有限公司 | The Fast Extraction of the satellite monitoring infection withered masson pine of pine nematode |
| CN109491292A (en) * | 2018-11-30 | 2019-03-19 | 福建农林大学 | A kind of bamboo resource intelligent monitoring management system |
| CN109613022A (en) * | 2019-01-25 | 2019-04-12 | 华南农业大学 | A kind of method, apparatus and system of low latitude high-spectrum remote-sensing detection Citrus Huanglongbing pathogen |
| CN109635702A (en) * | 2018-07-11 | 2019-04-16 | 国家林业局森林病虫害防治总站 | Forestry biological hazards monitoring method and system based on satellite remote sensing images |
| CN109766815A (en) * | 2019-01-03 | 2019-05-17 | 银河航天（北京）科技有限公司 | A kind of pair of object event carries out pre-warning system and method |
| CN109948563A (en) * | 2019-03-22 | 2019-06-28 | 华南农业大学 | A kind of withered tree detection localization method of the pine nematode based on deep learning |
| CN110213376A (en) * | 2019-06-05 | 2019-09-06 | 黑龙江省七星农场 | A kind of information processing system and method for pest prevention |
| CN110487793A (en) * | 2019-08-29 | 2019-11-22 | 北京麦飞科技有限公司 | Pest and disease damage time DYNAMIC DISTRIBUTION monitoring method and system |
| CN110514597A (en) * | 2019-09-04 | 2019-11-29 | 北京麦飞科技有限公司 | The diseases and pests of agronomic crop monitoring method of based on star remotely-sensed data collaboration |
| CN110574611A (en) * | 2019-10-16 | 2019-12-17 | 湖南林科达农林技术服务有限公司 | Forestry pest prevention and control method and system |
| CN110926430A (en) * | 2019-11-22 | 2020-03-27 | 海南省林业科学研究所 | Air-ground integrated mangrove forest monitoring system and control method |
| CN110940636A (en) * | 2019-12-05 | 2020-03-31 | 华南农业大学 | Intelligent identification and forest information monitoring system for citrus forest diseases and insect pests |
| CN111582176A (en) * | 2020-05-09 | 2020-08-25 | 湖北同诚通用航空有限公司 | Visible light remote sensing image withered and dead wood recognition software system and recognition method |
| CN112634212A (en) * | 2020-12-14 | 2021-04-09 | 江西省林业科学院 | Hyperspectral unmanned aerial vehicle-based disease latent tree detection method and system |
| US11061155B2 (en) | 2017-06-08 | 2021-07-13 | Total Sa | Method of dropping a plurality of probes intended to partially penetrate into a ground using a vegetation detection, and related system |
| CN113196287A (en) * | 2018-12-21 | 2021-07-30 | 克莱米特公司 | Season field grade yield forecast |
| CN113670825A (en) * | 2021-08-24 | 2021-11-19 | 河南省科学院地理研究所 | Forest environment remote sensing monitoring system based on comprehensive remote sensing technology |
| WO2022016568A1 (en) * | 2020-07-22 | 2022-01-27 | 南京科沃云计算信息技术有限公司 | System for identifying pests on basis of low-altitude scanning by aircraft and method therefor |
| CN114112906A (en) * | 2021-10-12 | 2022-03-01 | 中通服咨询设计研究院有限公司 | Water body feature extraction system based on unmanned aerial vehicle low-altitude remote sensing and local topography |
| TWI765794B (en) * | 2021-07-30 | 2022-05-21 | 國立中興大學 | Rice insect pest-related health warning system and method |
| CN115131683A (en) * | 2022-08-25 | 2022-09-30 | 金乡县林业保护和发展服务中心(金乡县湿地保护中心、金乡县野生动植物保护中心、金乡县国有白洼林场) | Forestry information identification method based on high-resolution remote sensing image |
| CN115909113A (en) * | 2023-01-09 | 2023-04-04 | 广东博幻生态科技有限公司 | Method for surveying forestry pests through remote sensing monitoring of unmanned aerial vehicle |
| CN116188990A (en) * | 2023-03-10 | 2023-05-30 | 贵州师范大学 | Unmanned aerial vehicle remote sensing-based earth surface vegetation identification method and system |
| CN116258977A (en) * | 2023-05-09 | 2023-06-13 | 凉山州现代林业产业发展指导服务中心 | Forest pest control method and system based on video image recognition |
| CN116363523A (en) * | 2023-03-10 | 2023-06-30 | 浙江省测绘科学技术研究院 | Pine wood nematode epidemic monitoring method, terminal and medium based on remote sensing information |
| CN117036968A (en) * | 2023-10-09 | 2023-11-10 | 杭州稻道农业科技有限公司 | High-resolution satellite remote sensing diagnosis method and device for crop disease and insect damage |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5837997A (en) * | 1992-07-28 | 1998-11-17 | Patchen, Inc. | Structure and method for detecting plants in a field using a light pipe |
| CN102937574A (en) * | 2012-07-20 | 2013-02-20 | 北京农业信息技术研究中心 | Information extraction method for plant diseases and insect pests based on satellite images |
| CN103034910A (en) * | 2012-12-03 | 2013-04-10 | 北京农业信息技术研究中心 | Regional scale plant disease and insect pest prediction method based on multi-source information |
| CN104035412A (en) * | 2014-06-12 | 2014-09-10 | 江苏恒创软件有限公司 | Crop diseases and pest monitoring system and method based on unmanned plane |
| CN105739518A (en) * | 2014-12-11 | 2016-07-06 | 中孚航空科技（天津）有限公司 | Insect disease monitoring system based on unmanned plane multispectral remote sensing |
-
2017
- 2017-02-14 CN CN201710077896.7A patent/CN106915462A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5837997A (en) * | 1992-07-28 | 1998-11-17 | Patchen, Inc. | Structure and method for detecting plants in a field using a light pipe |
| CN102937574A (en) * | 2012-07-20 | 2013-02-20 | 北京农业信息技术研究中心 | Information extraction method for plant diseases and insect pests based on satellite images |
| CN103034910A (en) * | 2012-12-03 | 2013-04-10 | 北京农业信息技术研究中心 | Regional scale plant disease and insect pest prediction method based on multi-source information |
| CN104035412A (en) * | 2014-06-12 | 2014-09-10 | 江苏恒创软件有限公司 | Crop diseases and pest monitoring system and method based on unmanned plane |
| CN105739518A (en) * | 2014-12-11 | 2016-07-06 | 中孚航空科技（天津）有限公司 | Insect disease monitoring system based on unmanned plane multispectral remote sensing |
Cited By (53)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11061155B2 (en) | 2017-06-08 | 2021-07-13 | Total Sa | Method of dropping a plurality of probes intended to partially penetrate into a ground using a vegetation detection, and related system |
| CN107808133A (en) * | 2017-10-23 | 2018-03-16 | 中石化石油工程地球物理有限公司 | Oil-gas pipeline safety monitoring method, system and software memory based on unmanned plane line walking |
| CN107808133B (en) * | 2017-10-23 | 2021-06-15 | 中石化石油工程地球物理有限公司 | Unmanned aerial vehicle line patrol-based oil and gas pipeline safety monitoring method and system and software memory |
| CN107682456A (en) * | 2017-11-07 | 2018-02-09 | 蔡璟 | A kind of intelligent gardens nursing system based on image and root detection |
| CN108195767A (en) * | 2017-12-25 | 2018-06-22 | 中国水产科学研究院东海水产研究所 | Estuarine wetland denizen monitoring method |
| CN108195767B (en) * | 2017-12-25 | 2020-07-31 | 中国水产科学研究院东海水产研究所 | Estuary wetland foreign species monitoring method |
| CN108303382A (en) * | 2018-02-06 | 2018-07-20 | 安徽大学 | A kind of winter wheat powdery mildew multi-temporal remote sensing monitoring method and its evaluation method based on AdaBoost graders |
| CN108334110A (en) * | 2018-02-06 | 2018-07-27 | 首欣（北京）科技有限公司 | A kind of forestry disease monitoring method and apparatus based on unmanned plane |
| CN108446599A (en) * | 2018-02-27 | 2018-08-24 | 首都师范大学 | A kind of high spectrum image wave band fast selecting method of p value statistic modeling independence |
| CN108446599B (en) * | 2018-02-27 | 2021-11-05 | 首都师范大学 | Hyperspectral image band rapid selection method of p-value statistical modeling independence |
| CN108287926A (en) * | 2018-03-02 | 2018-07-17 | 宿州学院 | A kind of multi-source heterogeneous big data acquisition of Agro-ecology, processing and analysis framework |
| CN108535193A (en) * | 2018-03-19 | 2018-09-14 | 电子科技大学 | A kind of forestry typical case pest and disease damage remote-sensing monitoring method |
| CN108764284A (en) * | 2018-04-23 | 2018-11-06 | 湖北同诚通用航空有限公司 | The classification denoising method and system of a kind of high resolution image to pine tree Deceased wood |
| CN108764284B (en) * | 2018-04-23 | 2022-11-22 | 湖北同诚通用航空有限公司 | Classification and denoising method and system for high-resolution image of dead pine |
| CN108764285A (en) * | 2018-04-23 | 2018-11-06 | 湖北同诚通用航空有限公司 | A kind of recognition methods of pine tree Deceased wood and system based on high resolution image |
| CN108694391B (en) * | 2018-05-16 | 2021-11-09 | 黄铁成 | Populus diversifolia forest spring inchworm disaster monitoring method based on hyperspectral remote sensing |
| CN108694391A (en) * | 2018-05-16 | 2018-10-23 | 黄铁成 | Populus Euphratica spring looper disaster monitoring method based on high-spectrum remote-sensing |
| CN109635702A (en) * | 2018-07-11 | 2019-04-16 | 国家林业局森林病虫害防治总站 | Forestry biological hazards monitoring method and system based on satellite remote sensing images |
| CN109141371A (en) * | 2018-08-21 | 2019-01-04 | 中国科学院地理科学与资源研究所 | The disaster-stricken recognition methods of winter wheat, device and equipment |
| CN109141371B (en) * | 2018-08-21 | 2020-04-03 | 中国科学院地理科学与资源研究所 | Winter wheat disaster identification method, device and equipment |
| CN108873851A (en) * | 2018-09-06 | 2018-11-23 | 保定智飞航空科技有限公司 | A kind of agricultural unmanned plane managing and control system |
| CN109211802A (en) * | 2018-09-13 | 2019-01-15 | 航天信德智图（北京）科技有限公司 | The Fast Extraction of the satellite monitoring infection withered masson pine of pine nematode |
| CN109491292A (en) * | 2018-11-30 | 2019-03-19 | 福建农林大学 | A kind of bamboo resource intelligent monitoring management system |
| CN113196287A (en) * | 2018-12-21 | 2021-07-30 | 克莱米特公司 | Season field grade yield forecast |
| CN109766815A (en) * | 2019-01-03 | 2019-05-17 | 银河航天（北京）科技有限公司 | A kind of pair of object event carries out pre-warning system and method |
| CN109613022A (en) * | 2019-01-25 | 2019-04-12 | 华南农业大学 | A kind of method, apparatus and system of low latitude high-spectrum remote-sensing detection Citrus Huanglongbing pathogen |
| CN109948563A (en) * | 2019-03-22 | 2019-06-28 | 华南农业大学 | A kind of withered tree detection localization method of the pine nematode based on deep learning |
| CN110213376A (en) * | 2019-06-05 | 2019-09-06 | 黑龙江省七星农场 | A kind of information processing system and method for pest prevention |
| CN110487793A (en) * | 2019-08-29 | 2019-11-22 | 北京麦飞科技有限公司 | Pest and disease damage time DYNAMIC DISTRIBUTION monitoring method and system |
| CN110514597A (en) * | 2019-09-04 | 2019-11-29 | 北京麦飞科技有限公司 | The diseases and pests of agronomic crop monitoring method of based on star remotely-sensed data collaboration |
| CN110574611A (en) * | 2019-10-16 | 2019-12-17 | 湖南林科达农林技术服务有限公司 | Forestry pest prevention and control method and system |
| CN110926430A (en) * | 2019-11-22 | 2020-03-27 | 海南省林业科学研究所 | Air-ground integrated mangrove forest monitoring system and control method |
| CN110926430B (en) * | 2019-11-22 | 2021-11-26 | 海南省林业科学研究所 | Air-ground integrated mangrove forest monitoring system and control method |
| CN110940636B (en) * | 2019-12-05 | 2020-12-08 | 华南农业大学 | Intelligent identification and forest information monitoring system for citrus forest diseases and insect pests |
| CN110940636A (en) * | 2019-12-05 | 2020-03-31 | 华南农业大学 | Intelligent identification and forest information monitoring system for citrus forest diseases and insect pests |
| CN111582176A (en) * | 2020-05-09 | 2020-08-25 | 湖北同诚通用航空有限公司 | Visible light remote sensing image withered and dead wood recognition software system and recognition method |
| WO2022016568A1 (en) * | 2020-07-22 | 2022-01-27 | 南京科沃云计算信息技术有限公司 | System for identifying pests on basis of low-altitude scanning by aircraft and method therefor |
| CN112634212A (en) * | 2020-12-14 | 2021-04-09 | 江西省林业科学院 | Hyperspectral unmanned aerial vehicle-based disease latent tree detection method and system |
| CN112634212B (en) * | 2020-12-14 | 2023-08-15 | 江西省林业科学院 | Disease latent tree detection method and system based on hyperspectral unmanned aerial vehicle |
| TWI765794B (en) * | 2021-07-30 | 2022-05-21 | 國立中興大學 | Rice insect pest-related health warning system and method |
| CN113670825A (en) * | 2021-08-24 | 2021-11-19 | 河南省科学院地理研究所 | Forest environment remote sensing monitoring system based on comprehensive remote sensing technology |
| CN114112906A (en) * | 2021-10-12 | 2022-03-01 | 中通服咨询设计研究院有限公司 | Water body feature extraction system based on unmanned aerial vehicle low-altitude remote sensing and local topography |
| CN114112906B (en) * | 2021-10-12 | 2023-11-17 | 中通服咨询设计研究院有限公司 | Water body feature extraction system based on unmanned aerial vehicle low altitude remote sensing and local topography |
| CN115131683A (en) * | 2022-08-25 | 2022-09-30 | 金乡县林业保护和发展服务中心(金乡县湿地保护中心、金乡县野生动植物保护中心、金乡县国有白洼林场) | Forestry information identification method based on high-resolution remote sensing image |
| CN115131683B (en) * | 2022-08-25 | 2022-12-09 | 金乡县林业保护和发展服务中心(金乡县湿地保护中心、金乡县野生动植物保护中心、金乡县国有白洼林场) | Forestry information identification method based on high-resolution remote sensing image |
| CN115909113A (en) * | 2023-01-09 | 2023-04-04 | 广东博幻生态科技有限公司 | Method for surveying forestry pests through remote sensing monitoring of unmanned aerial vehicle |
| CN116188990A (en) * | 2023-03-10 | 2023-05-30 | 贵州师范大学 | Unmanned aerial vehicle remote sensing-based earth surface vegetation identification method and system |
| CN116363523A (en) * | 2023-03-10 | 2023-06-30 | 浙江省测绘科学技术研究院 | Pine wood nematode epidemic monitoring method, terminal and medium based on remote sensing information |
| CN116363523B (en) * | 2023-03-10 | 2023-10-20 | 浙江省测绘科学技术研究院 | Pine wood nematode epidemic monitoring method, terminal and medium based on remote sensing information |
| CN116258977B (en) * | 2023-05-09 | 2023-07-21 | 凉山州现代林业产业发展指导服务中心 | Forest pest control method and system based on video image recognition |
| CN116258977A (en) * | 2023-05-09 | 2023-06-13 | 凉山州现代林业产业发展指导服务中心 | Forest pest control method and system based on video image recognition |
| CN117036968A (en) * | 2023-10-09 | 2023-11-10 | 杭州稻道农业科技有限公司 | High-resolution satellite remote sensing diagnosis method and device for crop disease and insect damage |
| CN117036968B (en) * | 2023-10-09 | 2024-03-22 | 杭州稻道农业科技有限公司 | High-resolution satellite remote sensing diagnosis method and device for crop disease and insect damage |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106915462A (en) | Forestry pests ＆ diseases intelligent identifying system based on multi-source image information | |
| Lehmann et al. | Open-source processing and analysis of aerial imagery acquired with a low-cost unmanned aerial system to support invasive plant management | |
| Zhang et al. | Assessment of defoliation during the Dendrolimus tabulaeformis Tsai et Liu disaster outbreak using UAV-based hyperspectral images | |
| Villoslada et al. | Fine scale plant community assessment in coastal meadows using UAV based multispectral data | |
| Nagendra et al. | Remote sensing for conservation monitoring: Assessing protected areas, habitat extent, habitat condition, species diversity, and threats | |
| Whittle et al. | Detection of tropical deforestation using ALOS-PALSAR: A Sumatran case study | |
| Adelabu et al. | Evaluating the impact of red-edge band from Rapideye image for classifying insect defoliation levels | |
| Milas et al. | Different colours of shadows: Classification of UAV images | |
| Pacifici et al. | Automatic change detection in very high resolution images with pulse-coupled neural networks | |
| US9639755B2 (en) | Automated compound structure characterization in overhead imagery | |
| Gillan et al. | Integrating drone imagery with existing rangeland monitoring programs | |
| CN102937574A (en) | Information extraction method for plant diseases and insect pests based on satellite images | |
| Bhandari et al. | Improved feature extraction scheme for satellite images using NDVI and NDWI technique based on DWT and SVD | |
| Li et al. | Extending the stochastic radiative transfer theory to simulate BRF over forests with heterogeneous distribution of damaged foliage inside of tree crowns | |
| Blanco et al. | Ecological site classification of semiarid rangelands: Synergistic use of Landsat and Hyperion imagery | |
| Snavely et al. | Mapping vegetation community types in a highly disturbed landscape: integrating hierarchical object-based image analysis with lidar-derived canopy height data | |
| Guo et al. | A novel invasive plant detection approach using time series images from unmanned aerial systems based on convolutional and recurrent neural networks | |
| US20050114026A1 (en) | Sub-visible cloud cover assessment: VNIR-SWIR | |
| Mohammadpour et al. | Applications of Multi‐Source and Multi‐Sensor Data Fusion of Remote Sensing for Forest Species Mapping | |
| Whiteside et al. | Extraction of tree crowns from high resolution imagery over Eucalypt dominant tropical savannas | |
| Nimbalkar et al. | Optimal band configuration for the roof surface characterization using hyperspectral and LiDAR imaging | |
| Soltani et al. | Transfer learning from citizen science photographs enables plant species identification in UAV imagery | |
| Wang et al. | Remote Sensing Satellite Image-Based Monitoring of Agricultural Ecosystem | |
| Whiteside et al. | Vegetation map for Magela Creek floodplain using WorldView-2 multispectral image data | |
| Feng et al. | Object-based land cover mapping using adaptive scale segmentation from ZY-3 satellite images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20171218 Address after: 350000 industrial products trading center (commercial building), Zhongshan Road 23 province, Fuzhou, Fujian Province, seven Applicant after: Fujian forestry investigation and Planning Institute Applicant after: Fujian Xingyu Information Technology Co., Ltd. Address before: Room 403, No. 1, No. 1, No. 27, Lake Li Li, Mawei District, Fujian province (self trade test area) Applicant before: Fujian Xingyu Information Technology Co., Ltd. |
|
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170704 |