CN102937574A - Information extraction method for plant diseases and insect pests based on satellite images - Google Patents
Information extraction method for plant diseases and insect pests based on satellite images Download PDFInfo
- Publication number
- CN102937574A CN102937574A CN2012102545352A CN201210254535A CN102937574A CN 102937574 A CN102937574 A CN 102937574A CN 2012102545352 A CN2012102545352 A CN 2012102545352A CN 201210254535 A CN201210254535 A CN 201210254535A CN 102937574 A CN102937574 A CN 102937574A
- Authority
- CN
- China
- Prior art keywords
- disease
- image
- multidate
- sample
- monitoring
- 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
Images
Landscapes
- Investigating Or Analysing Materials By Optical Means (AREA)
- Image Processing (AREA)
Abstract
The invention provides a regional-scale monitoring method for crop diseases based on multi-temporal satellite images. The method makes full use of spectral information and temporal information in time sequence image data, combines technologies of GIS, GPS and RS, introduces spectral information divergence analysis to the crop disaster monitoring field, and provides a method and technology for large-scale monitoring the diseases by using satellite-earth synchronous data in a certain regions. The method can effectively reduce field operation cost of disease monitoring, expands a conventional disease monitoring modes from point to surface, and provides convenience for government departments and agricultural administrative departments to master and to know important information such as generation, serious degree and the like of regional-scale diseases timely and accurately.
Description
Technical field
The present invention relates to remote sensing image processing and agronomy technical field, be specifically related to a kind of method of utilizing multidate satellite image data to extract crop pest information at regional scale.
Background technology
Traditional Pests mainly relies on the modes such as artificial range estimation hand is looked into, field sampling.Although these method authenticities and reliability are higher, consuming time, effort, and have the drawbacks such as representativeness, poor in timeliness and subjectivity are strong, be difficult to adapt at present the on a large scale demand of disease and pest Real-Time Monitoring and forecast.
Remote sensing technology be at present unique can be on a large scale the means of continuous earth's surface, quick obtaining space information, it has in various degree research and application in many aspects such as Crop Estimation, Quality Prediction and pest and disease monitorings.These are applied in and have changed to a great extent traditional operation and management mode, are greatly promoting agricultural towards high-quality, efficient, ecological, safety and modernization, informationalized future development.Retrieval to the prior art document is found, find that Zhejiang University invented a kind of plant leaf blade or crown botrytis diagnostic method and system (application number CN200710069097.1) of visible and near infrared spectrum in 2007, but because the application yardstick of this technical method is limited to the crop leaf yardstick, therefore can't be used for large-scale state of illness monitoring.Simultaneously, present most disease remote-sensing monitoring methods and device are for the scale Design such as the blade of crop, canopy, the less disease monitoring that carries out regional scale based on satellite remote-sensing image.
On the other hand, early stage remotely-sensed data such as Landsat TM and MODIS, owing to can't satisfy simultaneously higher spatial resolution and temporal resolution, has consisted of the obstacle of certain hardware condition to the disease monitoring of regional scale.Spectral information has often only been considered in more existing crop pest monitoring based on satellite image, does not consider that monitoring result exists larger uncertainty for the very important time phase information of disease monitoring.In recent years, along with the appearance of heavily visiting the cycle satellite data such as some middle high-resolutions such as environment mitigation moonlet, height, for the disease remote sensing monitoring on the regional scale has brought important opportunity.Occurring on the spectrum He on the time of crop pest can show some feature, can be used as the basis of remote sensing monitoring.At present not yet there is method to utilize multidate satellite image data in the monitoring on a large scale of the enterprising row crop disease of regional scale.
Summary of the invention
The technical matters that (one) will solve
The purpose of this invention is to provide a kind of regional scale crop pest monitoring method based on the multidate satellite image, the spectral information in the sequential images data that employ one's time to the best advantage and the time phase information.
(2) technical scheme
A kind of disease and insect information extracting method based on satellite image, described method comprises the steps:
S1, order are downloaded satellite remote-sensing image, and the satellite remote-sensing image that obtains is carried out pre-service;
The planting range of S2, extraction crop;
S3, in the disease monitoring phase, when image capturing, carry out synchronous ground investigation;
S4, the Dan Shixiang that extracts image data and the spectral signature of multidate vegetation index;
The spectral signature of S5, combined ground enquiry data screening disease monitoring;
S6, a situation arises based on the disease and pest of spectral information divergence analysis crop.
Wherein, the wavelength band of described image comprises visible light and near-infrared band.
Wherein, the preprocessing process of described image comprises radiation calibration, atmospheric correction, geometry correction and cloud removal.
Wherein, the planting range of described crop is according to the acquisition of classifying of existing land classification polar plot or multidate image.
Wherein, described multidate image needs in conjunction with land use pattern data, terrain data and phenology experience in assorting process, adopts decision tree, maximum likelihood or neural network to carry out planting range and extracts.
Wherein, described when single the phase vegetation index by certain for the moment phase image wave band reflectivity calculate and obtain, be used for the Physiology and biochemistry state of reflection vegetation on certain time point; The phase vegetation index carries out normalization and calculates during the list of described multidate vegetation index phase during according to certain two, is used for the reflection disease in the characteristics of field development and change.
Wherein, the spectral signature acquisition methods of described disease monitoring is:
A situation arises according to investigation sampling point disease, and sample point is divided into normal sample and the sample two parts of catching an illness;
Extract respectively Dan Shixiang and the multidate eigenwert of the multi-form spectral signature of two class sample points from image;
To Dan Shixiang or the multidate version of every kind of spectral signature, adopt the independent sample t check than the difference degree of compared with normal and the sample of catching an illness;
Adopt the difference degree of a certain feature of p value sign of t check, and generate accordingly all kinds of multi-form spectral signatures not simultaneously mutually and the time p Data-Statistics form in combined, wherein, the p value is less, the difference normal and sample of catching an illness is larger, and feature is stronger to the response of disease information.
Wherein, the process of described spectral information divergence analysis is: by judging two degrees of correlation between pixel, pixel to be sorted is included into the highest classification of degree of correlation.
(3) beneficial effect
The present invention employ one's time to the best advantage in the sequential images data spectral information and the time phase information, in conjunction with GIS, GPS, RS technology, the spectral information divergence analysis is introduced crop disaster monitoring field, proposition utilizes the interior star of certain area-ground synchrodata that disease is carried out on a large scale the method for monitoring and technology, effectively reduce the cost of the field work of disease monitoring, and traditional disease monitoring mode carried out by point and the expansion of face, be convenient to government department and agricultural management department and in time, accurately grasp and understand that regional disease occurs and the important informations such as the order of severity.
Description of drawings
Fig. 1 is the work synoptic diagram that carries out disease monitoring in the embodiment of the invention based on the multi-temporal remote sensing image data;
Fig. 2 is monitored area scope and ground investigation sampling point distribution plan in the example;
Fig. 3 is that the wheat planting scope is extracted process flow diagram in the example;
Fig. 4 is wheat powdery mildew monitoring result synoptic diagram.
Embodiment
Below in conjunction with drawings and Examples, the specific embodiment of the present invention is described in further detail.Following examples are used for explanation the present invention, but are not used for limiting the scope of the invention.
Following technical scheme is adopted in realization of the present invention:
The first step: the multidate satellite remote-sensing image is ordered and is downloaded and pre-service.According to the fast characteristics of most crop pest generation processes and present available satellite remote sensing date source, high middle high-resolution satellite image of heavily visiting the cycle is adopted in suggestion.Wavelength band needs covering visible light and near-infrared band.In conjunction with agronomy plant protection experience, at first determine the suitableeest forecasting stage of local crop pest (be often referred to the visual symptom in field obvious period).The satellite image data of phase when obtaining disease and occuring to this period a plurality of.The preprocessing process of image comprises radiation calibration, atmospheric correction, geometry correction and cloud removal.The reflectivity image data of the multidate that follow-up disease information extraction obtains after based on pre-service carries out.
Shunyi, area, Tongzhou wheat powdery mildew to Beijing periphery in 2010 carry out disease monitoring by environment moonlet HJ-CCD and the synchronous ground points for investigation data of multidate.According to the wheat powdery mildew occurrence, selecting wheat jointing to the pustulation period is the monitoring period of time of disease, respectively on May 1st, 2010, May 13, obtains the HJ-CCD image that the fourth phase covers the application region on May 20 and May 25.The acquisition time that cooperates each phase image, each the time amount to mutually sample district, 90 ground carried out state of an illness investigation, wherein 54 points are as training sample, 36 points are as checking sample (Fig. 2).Each control time and satellite image obtain the date gap and are no more than 3 days
Second step: application region crop-planting scope is extracted.Can be in conjunction with existing land classification polar plot or according to the acquisition of classifying of multidate image.Assorting process needs in conjunction with prioris such as the land use pattern data in the application region, terrain data and phenology experiences, adopts the supervised classification methods such as decision tree, maximum likelihood or neural network to carry out the crop-planting scope and extracts.Follow-up crop pest information extraction is carried out in the crop-planting scope that classification obtains, to reduce the interference from other atural object or agrotype.
In this example the wheat planting scope is extracted decision tree classification framework in conjunction with satellite image, dem data and knowledge about phenology of employing, basic procedure is seen Fig. 3.At first according to the first phase HJ-CCD image on May 20 (winter wheat is in vigorous growth phase in this Phase study district), adopt a NDVI threshold value (NDVI〉0.7) that vegetation area and nonvegetated area territory are separated.In the vegetation area of study area, except crop, mainly comprise meadow, two kinds of vegetation types of forest.Be higher than wheat and these characteristics of forest based on the meadow at the near-infrared band reflectivity, by a Nir threshold value (Nir<0.44) wheat and forest further separated.Consider that the study area forest mainly is positioned at the mountain area of northwest, Beijing side, for this reason by a DEM threshold value (DEM<100m) can relatively easily wheat and forest be separated.On the basis that obtains preliminary wheat planting scope, adopt the sieve class function of ENVI4.7 software that the result is optimized, remove " spiced salt " pixel in the classification results, obtain the winter wheat planting area figure of study area.Adopt 60 ground validation points that this classification results is tested, the overall accuracy that winter wheat area is extracted reaches more than 90%.
The 3rd step: in disease occur the critical period and carry out ground investigation with the image capturing time synchronized.Ground investigation with corresponding period the satellite shooting date be separated by and be no more than 3 days.According to the area of application region, on arranging, sampling point should be not less than 1 sampling point/10km
2Density.Simultaneously, always investigate the sampling point number and should be no less than 30.The field of investigation comprise selectively sampling point be the continuous planting area of wheat that a diameter surpasses 30m, the content of investigation is the onset grade of crop in the survey area.For ease of field investigation and plant disease management on a large scale, that the field of will catching an illness is divided into is light, weigh two ranks.For the different diseases of Different Crop, concrete sick level delimitation canonical reference disease is observed and predicted national standard and is carried out.
The 4th step: the Dan Shixiang of disease monitoring and multidate Spectra feature extraction.The method is suitable at comprehensive survey adopting respectively 13 spectral signatures as the alternative features of disease monitoring on the documents and materials basis of crop pest monitoring both at home and abroad, comprises the indigo plant (R with the multispectral satellite image compatibility of most middle high-resolutions
B), green (R
G), red (R
R), near infrared (R
NIR) passage primary reflection rate, and NDVI, SR, GNDVI, SAVI, TVI, MSR, NLI, RDVI, nine broadband vegetation indexs of OSAVI (each Index Definition sees Table 1).The vegetation index of phase and two kinds of versions of multidate was analyzed when this method adopted list respectively.Wherein, the phase vegetation index is obtained by certain for the moment phase image wave band reflectivity calculating when single, is used for the Physiology and biochemistry state of reflection vegetation on certain time point; The phase vegetation index carries out normalization and calculates during the list of multidate vegetation index phase during according to two, is used for the reflection disease in the characteristics of field development and change.Mutually, for a certain vegetation index form VI, it is (VI that the multidate reflectivity calculates formula when supposing to have M to be former and later two with N
N-VI
M)/(VI
N+ VI
M).Phase during for n, with the time make up in twos mutually, can obtain altogether
Individual multidate spectral signature.In this method, above-mentioned when single phase character and multidate feature all as the alternative features of disease monitoring.
The definition of table 1 vegetation characteristics and form
Phase image and corresponding ground investigation sampling point extract respectively 13 spectral signatures in the table 1 during in conjunction with 4, phase and two kinds of spectral signatures of multidate when generating list respectively.Wherein, the time mutually 1 to the time 4 represent with T1-T4 respectively that mutually normalized form of phase adopts T1T2 to represent when multidate feature such as first, second.Thus, when four of this example mutually in, obtain altogether 4 kinds of phase forms when single and 6 kinds of multidate forms.
The 5th step: combined ground points for investigation data screening disease monitoring spectral signature.A situation arises according to investigation sampling point disease, and sample point is divided into normal sample and the sample two parts of catching an illness.According to the 4th method, extract respectively the eigenwert of Dan Shixiang and the multidate version of two each spectral signatures of class sample point, and adopt independent sample t check (Independent t-test) than the difference degree of compared with normal and the sample of catching an illness.Adopt the p value (p-value) of t check to characterize the difference degree of a certain feature, and can generate accordingly all kinds of multi-form spectral signatures not simultaneously phase (phase character during list) and the time p Data-Statistics form in combined (multidate feature).Wherein, the p value is less, and the difference normal and sample of catching an illness is larger, and feature is stronger to the response of disease information.Therefore, the method that passing threshold is set during to list all kinds of spectral signatures of phase and multidate screen, keep the strong spectral signature form of disease information response.Generally, can set the threshold to the p value and be lower than 0.05,0.01 or 0.001 three kind.Disease information in the image is more weak, and the threshold value setting of p value is larger.
Generally, along with the time the postponing of phase, each spectral signature improves constantly in the significance of difference of normal and disease sampling point, wherein the difference of the 4th o'clock each feature of phase is the most remarkable, this moment, powdery mildew was by descending from upper having infected so that the form of wheat plant has obvious variation, infect in the heavier field even scab has been gone up to boot leaf in part, this situation with the field factual survey conforms to.By setting the threshold value of p value<0.001, be retained in 15 of reaching utmost point significant difference level in normal and the disease training sample phase and multidate feature when single in this example, comprise respectively: R
B(R
B-T4), R
B-T4T2, R
G-T3, R
G-T4, R
R-T3, R
R-T4, SR-T4, NDVI-T3, NDVI-T4, NDVI-T4T2, GNDVI-T4, GNDVI-T4T2, OSAVI-T4, MSR-T4 and NLI-T3(table 2).
Phase and multidate feature were to the wheat powdery mildew response condition when table 2 was single
*Show that difference reaches p-value<0.05 level of significance;
*Show that difference reaches p-value<0.05 level of significance;
* *Show that difference reaches p-value<0.05 level of significance.Selected feature represents with underscore
The 6th step: based on the disease monitoring of spectral information divergence analysis.The spectrum information divergence analysis is a kind of sorting algorithm for multi-band image based on the Analysis of Entropy.Its principle is by judging two degrees of correlation between pixel, and pixel to be sorted is included into algorithm in the highest classification of degree of correlation.Suppose that x and y pixel are respectively a multi-C vector (dimension equates), x=(x
1..., x
L)
T, y=(y
1..., y
L)
T, the x of i wave band and the probability of y are respectively:
Probability to x and y on the i wave band is born respectively log-transformation, obtains I
i(x) and I
i(y), be respectively:
I
i(x)=-logp
i (3)
I
i(y)=-logq
i (4)
On this basis, can calculate the relative entropy of the relative x of y, i.e. the Kullback-Leibler information standard:
And the statistic of spectral information divergence is:
SID=D(x||y)+D(y||x) (6)
This algorithm is realized by " the Spectral Information Divergence " module among the ENVI4.7.The ground investigation sample is divided into two parts at random, and wherein 60% is used for model training, and 40% is used for modelling verification.Import respectively the sample of " normally " in the training sample, " slightly catching an illness " and " severe is caught an illness " three types during training, algorithm is judged its degree of relevancy according to the SID distance of pixel to be sorted and three class samples, put pixel under the type the highest with its similarity, and finally generate classification results figure.Actual measurement and model estimation result to sick level according to the checking sample can analyze and estimate model accuracy.
In the result images of output (Fig. 4), yellow and red area represent slightly to reach the zone that severe is caught an illness.In study area, can clearly observe the diseased region overall distribution in the scope of the Tongzhou District of the southeast, the Shunyi District in the study area the north then less disease that is subject to infects.36 investigation sampling points that are used for checking in this example, the investigation sampling point of 9 Shunyi Districts (latitude is higher than 40 °) does not all infect powdery mildew, the sampling point of all catching an illness is substantially all found in latitude is lower than 40 ° Tongzhou District, therefore, overall space distribution trend and the investigation result of disease is unanimous on the whole among this estimation result.
Above embodiment only is used for explanation the present invention; and be not limitation of the present invention; the those of ordinary skill in relevant technologies field; in the situation that does not break away from the spirit and scope of the present invention; can also make a variety of changes and modification; therefore all technical schemes that are equal to also belong to category of the present invention, and scope of patent protection of the present invention should be defined by the claims.
Claims (8)
1. the disease and insect information extracting method based on satellite image is characterized in that described method comprises the steps:
S1, order are downloaded satellite remote-sensing image, and the satellite remote-sensing image that obtains is carried out pre-service;
The planting range of S2, extraction crop;
S3, in the disease monitoring phase, when image capturing, carry out synchronous ground investigation;
S4, the Dan Shixiang that extracts image data and the spectral signature of multidate vegetation index;
The spectral signature of S5, combined ground enquiry data screening disease monitoring;
S6, a situation arises based on the disease and pest of spectral information divergence analysis crop.
Wherein, the wavelength band of described image comprises visible light and near-infrared band.
2. the method for claim 1 is characterized in that, the wavelength band of described image comprises visible light and infrared band.
3. the method for claim 1 is characterized in that, the preprocessing process of described image comprises radiation calibration, atmospheric correction, geometry correction and cloud removal.
4. the method for claim 1 is characterized in that, the planting range of described crop is according to the acquisition of classifying of existing land classification polar plot or multidate image.
5. method as claimed in claim 4 is characterized in that, described multidate image needs in conjunction with land use pattern data, terrain data and phenology experience in assorting process, adopts decision tree, maximum likelihood or neural network to carry out planting range and extracts.
6. the method for claim 1 is characterized in that, described when single the phase vegetation index by certain for the moment phase image wave band reflectivity calculate and obtain, be used for the Physiology and biochemistry state of reflection vegetation on certain time point; The phase vegetation index carries out normalization and calculates during the list of described multidate vegetation index phase during according to certain two, is used for the reflection disease in the characteristics of field development and change.
7. the method for claim 1 is characterized in that, the spectral signature acquisition methods of described disease monitoring is:
A situation arises according to investigation sampling point disease, and sample point is divided into normal sample and the sample two parts of catching an illness;
Extract respectively Dan Shixiang and the multidate eigenwert of the multi-form spectral signature of two class sample points from image;
To Dan Shixiang or the multidate version of every kind of spectral signature, adopt the independent sample t check than the difference degree of compared with normal and the sample of catching an illness;
Adopt the difference degree of a certain feature of p value sign of t check, and generate accordingly all kinds of multi-form spectral signatures not simultaneously mutually and the time p Data-Statistics form in combined, wherein, the p value is less, the difference normal and sample of catching an illness is larger, and feature is stronger to the response of disease information.
8. the method for claim 1 is characterized in that, the process of described spectral information divergence analysis is: by judging two degrees of correlation between pixel, pixel to be sorted is included into the highest classification of degree of correlation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2012102545352A CN102937574A (en) | 2012-07-20 | 2012-07-20 | Information extraction method for plant diseases and insect pests based on satellite images |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2012102545352A CN102937574A (en) | 2012-07-20 | 2012-07-20 | Information extraction method for plant diseases and insect pests based on satellite images |
Publications (1)
Publication Number | Publication Date |
---|---|
CN102937574A true CN102937574A (en) | 2013-02-20 |
Family
ID=47696485
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2012102545352A Pending CN102937574A (en) | 2012-07-20 | 2012-07-20 | Information extraction method for plant diseases and insect pests based on satellite images |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102937574A (en) |
Cited By (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104504279A (en) * | 2014-12-31 | 2015-04-08 | 中国科学院深圳先进技术研究院 | Locust plague detection method |
CN105277495A (en) * | 2015-10-26 | 2016-01-27 | 北京农业信息技术研究中心 | Method for monitoring and acquiring evaporation characteristics of fog droplets on leaf surfaces in time sequence mode |
CN105447494A (en) * | 2015-12-01 | 2016-03-30 | 二十一世纪空间技术应用股份有限公司 | Vegetable field monitoring method based on multi-source multi-temporal remote sensing image data |
CN105631818A (en) * | 2015-12-24 | 2016-06-01 | 中国农业大学 | Batch automatic geometric correction method and device of remote sensing image |
CN105825177A (en) * | 2016-03-09 | 2016-08-03 | 西安科技大学 | Remote-sensing crop disease identification method based on time phase and spectrum information and habitat condition |
CN105847411A (en) * | 2016-05-10 | 2016-08-10 | 大连理工大学 | Crop insect disease detection system |
CN106915462A (en) * | 2017-02-14 | 2017-07-04 | 福建兴宇信息科技有限公司 | Forestry pests & diseases intelligent identifying system based on multi-source image information |
CN106951692A (en) * | 2017-03-06 | 2017-07-14 | 北京师范大学 | Exemplary resource elements recognition method and device |
CN107145876A (en) * | 2017-05-24 | 2017-09-08 | 河南农业大学 | The take-all remote-sensing monitoring method and its construction method of monitoring model analyzed based on change vector |
CN108333140A (en) * | 2018-02-01 | 2018-07-27 | 福州大学 | Characteristic spectrum index and detection method for rigid bamboo poison moth hazard detection |
CN108446590A (en) * | 2018-02-07 | 2018-08-24 | 海南云保遥感科技有限公司 | A kind of application process of space remote sensing big data in the calculating of tropical agriculture disaster |
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 |
CN109360376A (en) * | 2018-09-13 | 2019-02-19 | 航天信德智图(北京)科技有限公司 | Infect the withered masson pine satellite monitoring spatial database of pine nematode |
JP2019035598A (en) * | 2017-08-10 | 2019-03-07 | 株式会社パスコ | Land cover learning data generation device, land cover learning data, land cover classification prediction device, and land cover learning data generation program |
CN109491292A (en) * | 2018-11-30 | 2019-03-19 | 福建农林大学 | A kind of bamboo resource intelligent monitoring management system |
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 |
CN110287944A (en) * | 2019-07-04 | 2019-09-27 | 吉林大学 | The crop pests monitoring method of multi-spectrum remote sensing image based on deep learning |
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 |
CN111815110A (en) * | 2020-05-30 | 2020-10-23 | 阳江市智慧农业研究院 | Agricultural production planning accurate decision-making method and system based on big data and artificial intelligence |
CN113129258A (en) * | 2021-03-02 | 2021-07-16 | 成都正和德能风险管理咨询有限公司 | Historical image tracing method for insurance target |
CN115035340A (en) * | 2022-06-13 | 2022-09-09 | 电子科技大学 | Remote sensing image classification result verification method |
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 |
CN117522377A (en) * | 2023-11-07 | 2024-02-06 | 眉山市大数据产业发展有限公司 | Big data analysis application system suitable for agricultural informatization |
Citations (2)
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 |
CN102084794A (en) * | 2010-10-22 | 2011-06-08 | 华南农业大学 | Method and device for early detecting crop pests based on multisensor information fusion |
-
2012
- 2012-07-20 CN CN2012102545352A patent/CN102937574A/en active Pending
Patent Citations (2)
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 |
CN102084794A (en) * | 2010-10-22 | 2011-06-08 | 华南农业大学 | Method and device for early detecting crop pests based on multisensor information fusion |
Non-Patent Citations (2)
Title |
---|
宫彦萍等: "《集成GIS和RS技术的作物病虫害监测预报研究进展》", 《农业工程学报》, vol. 24, 30 September 2008 (2008-09-30), pages 331 - 336 * |
张竞成: "《多源遥感数据小麦病害信息提取方法研究》", 《中国博士学位论文全文数据库农业科技辑》, no. 7, 15 July 2012 (2012-07-15) * |
Cited By (34)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104504279B (en) * | 2014-12-31 | 2017-09-15 | 中国科学院深圳先进技术研究院 | The method for detecting the plague of locusts |
CN104504279A (en) * | 2014-12-31 | 2015-04-08 | 中国科学院深圳先进技术研究院 | Locust plague detection method |
CN105277495A (en) * | 2015-10-26 | 2016-01-27 | 北京农业信息技术研究中心 | Method for monitoring and acquiring evaporation characteristics of fog droplets on leaf surfaces in time sequence mode |
CN105277495B (en) * | 2015-10-26 | 2019-05-28 | 北京农业信息技术研究中心 | A kind of time series pattern droplet blade face evaporation characteristic monitors acquisition method |
CN105447494A (en) * | 2015-12-01 | 2016-03-30 | 二十一世纪空间技术应用股份有限公司 | Vegetable field monitoring method based on multi-source multi-temporal remote sensing image data |
CN105447494B (en) * | 2015-12-01 | 2019-07-09 | 二十一世纪空间技术应用股份有限公司 | Field of vegetables monitoring method based on multi-source multi-temporal remote sensing image data |
CN105631818A (en) * | 2015-12-24 | 2016-06-01 | 中国农业大学 | Batch automatic geometric correction method and device of remote sensing image |
CN105631818B (en) * | 2015-12-24 | 2018-12-14 | 中国农业大学 | The batch-automated geometric correction method and device of remote sensing image |
CN105825177A (en) * | 2016-03-09 | 2016-08-03 | 西安科技大学 | Remote-sensing crop disease identification method based on time phase and spectrum information and habitat condition |
CN105847411A (en) * | 2016-05-10 | 2016-08-10 | 大连理工大学 | Crop insect disease detection system |
CN106915462A (en) * | 2017-02-14 | 2017-07-04 | 福建兴宇信息科技有限公司 | Forestry pests & diseases intelligent identifying system based on multi-source image information |
CN106951692A (en) * | 2017-03-06 | 2017-07-14 | 北京师范大学 | Exemplary resource elements recognition method and device |
CN107145876A (en) * | 2017-05-24 | 2017-09-08 | 河南农业大学 | The take-all remote-sensing monitoring method and its construction method of monitoring model analyzed based on change vector |
CN107145876B (en) * | 2017-05-24 | 2020-04-10 | 河南农业大学 | Wheat take-all remote sensing monitoring method based on change vector analysis and construction method of monitoring model thereof |
JP2019035598A (en) * | 2017-08-10 | 2019-03-07 | 株式会社パスコ | Land cover learning data generation device, land cover learning data, land cover classification prediction device, and land cover learning data generation program |
JP7045819B2 (en) | 2017-08-10 | 2022-04-01 | 株式会社パスコ | Land cover learning data generator, land cover learning data, land cover classification prediction device and land cover learning data generation program |
CN108333140B (en) * | 2018-02-01 | 2020-10-09 | 福州大学 | Characteristic spectral index for detecting damage of bamboo moths and detection method |
CN108333140A (en) * | 2018-02-01 | 2018-07-27 | 福州大学 | Characteristic spectrum index and detection method for rigid bamboo poison moth hazard detection |
CN108446590A (en) * | 2018-02-07 | 2018-08-24 | 海南云保遥感科技有限公司 | A kind of application process of space remote sensing big data in the calculating of tropical agriculture disaster |
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 |
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 |
CN109360376A (en) * | 2018-09-13 | 2019-02-19 | 航天信德智图(北京)科技有限公司 | Infect the withered masson pine satellite monitoring spatial database 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 |
CN110287944B (en) * | 2019-07-04 | 2022-07-01 | 吉林大学 | Crop pest monitoring method based on multispectral remote sensing image of deep learning |
CN110287944A (en) * | 2019-07-04 | 2019-09-27 | 吉林大学 | The crop pests monitoring method of multi-spectrum remote sensing image based on deep learning |
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 |
CN111815110A (en) * | 2020-05-30 | 2020-10-23 | 阳江市智慧农业研究院 | Agricultural production planning accurate decision-making method and system based on big data and artificial intelligence |
CN113129258A (en) * | 2021-03-02 | 2021-07-16 | 成都正和德能风险管理咨询有限公司 | Historical image tracing method for insurance target |
CN115035340A (en) * | 2022-06-13 | 2022-09-09 | 电子科技大学 | Remote sensing image classification result verification method |
CN115035340B (en) * | 2022-06-13 | 2024-05-14 | 电子科技大学 | Remote sensing image classification result verification method |
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 |
CN117522377A (en) * | 2023-11-07 | 2024-02-06 | 眉山市大数据产业发展有限公司 | Big data analysis application system suitable for agricultural informatization |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102937574A (en) | Information extraction method for plant diseases and insect pests based on satellite images | |
Bárta et al. | Early detection of bark beetle infestation in Norway spruce forests of Central Europe using Sentinel-2 | |
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 | |
Grinand et al. | Estimating deforestation in tropical humid and dry forests in Madagascar from 2000 to 2010 using multi-date Landsat satellite images and the random forests classifier | |
Tuanmu et al. | Mapping understory vegetation using phenological characteristics derived from remotely sensed data | |
Iverson et al. | Applications of satellite remote sensing to forested ecosystems | |
Broich et al. | Time-series analysis of multi-resolution optical imagery for quantifying forest cover loss in Sumatra and Kalimantan, Indonesia | |
Schwantes et al. | Quantifying drought-induced tree mortality in the open canopy woodlands of central Texas | |
Shendryk et al. | Mapping individual tree health using full-waveform airborne laser scans and imaging spectroscopy: A case study for a floodplain eucalypt forest | |
Peña-Barragán et al. | Object-based crop identification using multiple vegetation indices, textural features and crop phenology | |
Bhattarai et al. | Spruce budworm tree host species distribution and abundance mapping using multi-temporal Sentinel-1 and Sentinel-2 satellite imagery | |
Bourgoin et al. | UAV-based canopy textures assess changes in forest structure from long-term degradation | |
CN106915462A (en) | Forestry pests & diseases intelligent identifying system based on multi-source image information | |
Castillo et al. | LIDAR remote sensing for secondary Tropical Dry Forest identification | |
Peerbhay et al. | Detecting bugweed (Solanum mauritianum) abundance in plantation forestry using multisource remote sensing | |
Fu et al. | Spatio-temporal coupling coordination analysis between marsh vegetation and hydrology change from 1985 to 2019 using LandTrendr algorithm and Google Earth Engine | |
Zabihi et al. | A review of major factors influencing the accuracy of mapping green-attack stage of bark beetle infestations using satellite imagery: Prospects to avoid data redundancy | |
Li et al. | Extending the stochastic radiative transfer theory to simulate BRF over forests with heterogeneous distribution of damaged foliage inside of tree crowns | |
Bisquert et al. | Fire danger estimation from MODIS Enhanced Vegetation Index data: application to Galicia region (north-west Spain) | |
Lausch et al. | A range of earth observation techniques for assessing plant diversity | |
Ghosh et al. | Calcrop21: A georeferenced multi-spectral dataset of satellite imagery and crop labels | |
Smith-Tripp et al. | Landsat assessment of variable spectral recovery linked to post-fire forest structure in dry sub-boreal forests | |
Zhou et al. | Estimation of volume resources for planted forests using an advanced LiDAR and hyperspectral remote sensing | |
Esmaili et al. | Mapping of understory infested boxwood trees using high resolution imagery |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20130220 |