CN102385694A - Hyperspectral identification method for land parcel-based crop variety - Google Patents
Hyperspectral identification method for land parcel-based crop variety Download PDFInfo
- Publication number
- CN102385694A CN102385694A CN2010102725695A CN201010272569A CN102385694A CN 102385694 A CN102385694 A CN 102385694A CN 2010102725695 A CN2010102725695 A CN 2010102725695A CN 201010272569 A CN201010272569 A CN 201010272569A CN 102385694 A CN102385694 A CN 102385694A
- Authority
- CN
- China
- Prior art keywords
- hyperion
- plot
- data
- crop
- reflectivity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000002310 reflectometry Methods 0.000 claims abstract description 26
- 238000012937 correction Methods 0.000 claims abstract description 24
- 238000003709 image segmentation Methods 0.000 claims abstract description 14
- 238000005516 engineering process Methods 0.000 claims abstract description 4
- 238000005259 measurement Methods 0.000 claims abstract description 3
- 238000001228 spectrum Methods 0.000 claims description 29
- 230000003321 amplification Effects 0.000 claims description 4
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 4
- 241001269238 Data Species 0.000 claims description 2
- 230000001915 proofreading effect Effects 0.000 claims 2
- 238000012544 monitoring process Methods 0.000 abstract description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Chemical compound O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 abstract 1
- 238000000605 extraction Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 238000007476 Maximum Likelihood Methods 0.000 description 3
- 238000002405 diagnostic procedure Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000005855 radiation Effects 0.000 description 3
- 230000003595 spectral effect Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000000701 chemical imaging Methods 0.000 description 2
- 238000012804 iterative process Methods 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 241000209140 Triticum Species 0.000 description 1
- 235000021307 Triticum Nutrition 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- VMXUWOKSQNHOCA-UKTHLTGXSA-N ranitidine Chemical compound [O-][N+](=O)\C=C(/NC)NCCSCC1=CC=C(CN(C)C)O1 VMXUWOKSQNHOCA-UKTHLTGXSA-N 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Abstract
The invention relates to a hyperspectral identification method for a land parcel-based crop variety, which comprises the following steps: firstly, performing pretreatment on Hyperion data so as to remove unscaled bands which are easily influenced by water vapor in the Hyperion data; performing atmospheric correction on the data by utilizing a Flaash atmospheric correction module of ENVI; then, performing geometry correction on the Hyperion data by utilizing a topographic map or satellite data, such as corrected SPOT5, TM and the like to obtain a corrected Hyperion reflectivity image; performing outfield global positioning system (GPS) measurement on a crop variety land parcel to obtain the land parcel distribution map of the crop variety; overlying land parcel base onto the Hyperion reflectivity image to compute the characteristics of the crop variety, such as reflectivity mean value, variance and the like; by taking the reflectivity mean value, the variance and the like as the characteristics, performing image segmentation on the Hyperion reflectivity image to obtain the land parcel data based on the Hyperion reflectivity image; and according to the characteristics of the crop variety, such as the reflectivity mean value, the variance and the like, performing variety classification on the land parcel data to obtain a land parcel-based crop variety distribution map. In the hyperspectral identification method for the land parcel-based crop variety, the Hyperion hyperspectral data and outfield crop variety land parcel data are adopted to realize the drafting of the crop variety based on the image segmentation technology. The hyperspectral identification method for the land parcel-based crop variety can be used for monitoring nationwide crop varieties in the department of agriculture, and has wide market prospects and application value.
Description
Technical field
The high spectrum recognition methods of a kind of crop varieties based on the plot belongs to the digital image processing techniques field, particularly digital picture cutting techniques and digital picture sorting technique.
Background technology
The variety of crops remote sensing recognition is to adopt high spectrum resolution remote sensing technique; On the basis of crops classification, realize kind identification to crop, it provides the Back ground Information support for the precision management of crops; Be that numerous scientific research office carries out one of information source of agricultural research, significant to its research.
High spectrum crop varieties identification is one of the forward position research contents in agricultural remote sensing field, is the important content of precision agriculture remote sensing.The main traditional remote sensing sorting techniques such as supervised classification and unsupervised classification that adopt of present high spectrum crop varieties identification.
1, supervised classification method (referring to document: Zhao's inch etc. remote sensing application analysis principle and method. Beijing: Science Press; 2003) need choose representational training field as sample from study area; According to known sample; Select characteristic parameter, set up discriminant function, according to the belonging kinds of sample characteristics parameter recognition non-sample pixel.Common supervised classification method comprises: minimum distance method, maximum likelihood method etc.
Minimum distance method be with the distance in the feature space as the pixel The classification basis, comprise the minor increment diagnostic method and face the territory method recently.The minor increment diagnostic method is calculated and is treated the distance between branch pixel and the known class, pixel is belonged to a type of distance minimum; Facing the territory method recently is the popularization of minor increment diagnostic method in the multiband image; It at first calculates and treats the distance of branch pixel in each type; Get a wherein minimum distance and arrive such other distance as this pixel; Relatively treat the branch pixel at last to the distance between all categories, pixel is belonged to a type of distance minimum.
Maximum likelihood method is assigned to this pixel in the maximum classification of ownership probability through calculating each pixel for ownership probability of all categories.The spectral signature of maximum likelihood method supposition training area atural object is the same with the Nature chance phenomenon, and approximate Normal Distribution utilizes training sample to calculate characteristic parameters such as average, variance and covariance, thus the priori probability density function of calculated population.
2, not supervised classification (referring to document: plum Anxin etc. the remote sensing introduction. Beijing: Higher Education Publishing House; 2001) be under the condition that does not have the priori classification as sample; Promptly do not know category feature in advance, mainly sort out the method for merging according to the size of similarity between pixel.Not supervised classification commonly used mainly comprises classification lumping method, ISODATA etc.
The classification lumping method adopts distance to estimate the similarity degree of each sample in space distribution, cuts apart them or be merged into different clusters.The characteristics of classification lumping method are that the process of merger is that classification is carried out; In iterative process, do not adjust the measure of classification sum; If after a classification is integrated into a certain type; Just got rid of it and be included into the possibility of other classifications again, caused order of operation difference, can obtain different classification results a pixel.
ISODATA provides the coarse classification of image in original state, then according to certain criterion, like the standard deviation of iterations, the minimum pixel number of each classification, classification etc., between classification, reconfigures sample, till classification relatively rationally.The classification sum is variable in the iterative process of ISODATA, and the merging and the division of classification are arranged.Wherein, if the central point of two classifications distance is near, explain that similarity is high, two types just merge to one type; Perhaps certain type of pixel number very little, such will merge in the most close class and go.The division of classification also has two kinds of situation: a certain type of pixel number just manages to be divided into two types very little; If the classification sum very little, just that discrete type is maximum class is divided into two classifications.
Also have many other Classifying Method in Remote Sensing Image in addition, like mixed pixel stage division, fuzzy classifier method, Artificial Neural Network etc., but these method major parts only are used to realize the identification of agrotype, like the identification of paddy rice, wheat.Because the difference between the crop different cultivars is trickle, adopts above-mentioned classification method, often be difficult to realize the kind identification of crop.
Summary of the invention
The present invention provides a kind of high spectrum crop varieties recognition methods based on the plot, in order to realize utilizing the identification of high-spectrum remote sensing data to crop varieties, solves the problem that is difficult to realize other classification of crop varieties level in the remote sensing classification problem commonly used.
Technical scheme of the present invention is following:
The high spectrum recognition methods of a kind of crop varieties based on the plot is characterized in that comprising concrete steps:
The pre-service of step 1, high-spectral data.The pre-service of high-spectral data comprises contents such as wave band screening, radiant correction correction and geometry correction.The wave band screening mainly is to remove unsealed and the wave band that is subject to influence of moisture in the Hyperion data; Radiant correction then is to convert the ND value of image to reflectivity through radiation calibration and atmospheric correction, and atmospheric correction adopts the Flaash atmospheric correction module of ENVI; Geometry correction is to utilize topomap perhaps to proofread and correct satellite datas such as good SPOT5, TM to make base map, adopts ENVI to carry out, and forms the good high spectrum reflection rate image of correction.
Step 2, image segmentation.Image segmentation is in order image to be divided into the ground block object.In carrying out the process that image cuts apart, except considering the spectral properties of image, also to consider geometrical property such as the shape and the size of image, main standard is that object is inner heterogeneous minimum.Image segmentation commonly used comprises: the thresholding dividing method; Dividing method based on the edge; Dividing method based on the zone.Adopt watershed algorithm, Hyperspectral imaging is divided into the plot.
Step 3, crop varieties plot outfield are measured and feature modeling.The outfield measurement of crop varieties plot is mainly the characteristic of obtaining the plot.Adopt the GPS outfield to measure the plot latitude and longitude coordinates; And the crop varieties attribute in record plot, obtain crop varieties distribution plan based on the plot, the crop varieties distribution plan is added on the Hyperspectral imaging; Characteristics such as the reflectivity average of calculating crop varieties, variance are as the characteristic of crop varieties.
Step 4, based on the identification of the crop varieties in plot.After the crop varieties characteristic of acquisition based on the plot, utilize the characteristics such as reflectivity average, variance of crop varieties, classify, obtain high spectrum crop varieties distribution plan based on the plot to adopting image partition method to obtain the ground blocks of data.
The advantage that the present invention is compared with prior art had: the present invention adopts high-spectrum remote sensing data, utilizes image partition method to obtain high spectrum ground blocks of data, obtains the crop varieties characteristic based on the plot through the field, has realized the kind identification of crop; Compare with classic method, the present invention not only can realize the crop classification, and can realize meticulousr crop varieties identification.
Description of drawings
Fig. 1: the high spectrum recognition methods of the crop varieties based on the plot of the present invention process flow diagram;
Fig. 2: high-spectral data pretreatment process figure;
Fig. 3: image segmentation generates the plot distribution plan;
Fig. 4: crop plot outfield is measured and the feature extraction process flow diagram;
Fig. 5: test findings partial view of the present invention.
Embodiment
In order to understand technical scheme of the present invention better, introduce the present invention in detail below in conjunction with accompanying drawing and embodiment.
The high spectrum recognition methods of a kind of crop varieties of the present invention based on the plot, this method mainly comprises following step:
1, high-spectral data pre-service;
2, image segmentation generates high spectrum ground blocks of data;
3, the crop varieties outfield is measured and feature extraction;
4, classify based on the crop varieties in plot;
Concrete realization flow of the present invention is as shown in Figure 1, and each several part practical implementation details is following:
1, high-spectral data pre-service
Because the high-spectral data that adopts receives images such as sensor, atmosphere; Some wave band unsealed be subject to influence of moisture; The numerical value of sensor acquisition simultaneously is the DN value; And outfield is measured be the clutter reflections rate, therefore need carry out the noise wave band of pre-service removal high-spectral data, and convert the DN value into reflectivity through radiant correction.In addition, for satellite image data and ground survey Data Matching are got up, need carry out geometry correction.Concrete treatment scheme is as shown in Figure 2.
In the Hyperion high-spectral data, 1～7,58～78; 121～127,167～178 unsealed such as wave band such as grade be subject to influence of moisture, therefore in preprocessing process; Directly these wave bands are rejected remaining 176 wave bands, that is: 8～57,79～120,128～166,179～223.
Radiation calibration refers to convert the picture dot gray-scale value (DN) of image into radiance value this processing procedure, and radiation calibration adopts formula 1 to carry out:
L＝gain*DN+offset (1)
Wherein gain and offset obtain with the calibration back through sensor being carried out ground survey, and they offer the user as the parameter of image/sensor.In the Hyperion image; Amplification factor at visible light/near-infrared band (the 8-57 wave band of correspondence image) is 40; The amplification factor of short-wave infrared wave band (77-224 wave band) is 80; Be that visible light and near infrared gain value are 0.025, the gain value of short-wave infrared is 0.0125, and offset is zero.Substitution formula (1) just can obtain corresponding radiance value, and unit is W/ (m
2Sr μ m).
The purpose of geometric correction is to proofread and correct the distortion in images that in the process that obtains view data, is occurred, and normal the utilization selects ground control point (GCP) to carry out geometric exact correction.After the selected ground control point, select for use polynomial expression to correct model usually and correct, its mathematical expression mode is:
Wherein, (x y) is picture dot coordinate on the image, and (X is with reference to the picture dot coordinate on the image, a Y)
Ij, b
IjBe multinomial coefficient, N is polynomial number of times.N chooses the degree that depends on anamorphose, the quantity of ground control point and the size of relief distortion.Based on least squares theory, calculate the polynomial coefficient of acquisition by the ground control point of selecting, and construct polynomial expression and correct model.Correct the new coordinate that model can calculate each picture dot (x ', y ') according to polynomial expression, thereby realize the geometric exact correction of image.
2, image segmentation generates high spectrum ground blocks of data
The purpose of image segmentation is that formation is the elementary cell of class object with the object, and main standard is that object is inner heterogeneous minimum.Heterogeneous standard comprises two parts: spectroscopic standard and shape criteria.Spectroscopic standard is heterogeneous variation of spectrum that produces when merging 2 imaged objects, describes with the change of the weighting standard difference of spectral value weight.Shape criteria is to describe an amount of alteration of form, and it is realized through the idealize model of shape of two differences.Total heterogeneity value f is with the heterogeneous h of spectrum
ColorWith the heterogeneous h of shape
ShapeCalculate:
f＝wh
color+(1-w)h
shape (3)
Wherein: w---user-defined color weight (with respect to shape, variation range is 0～1).
The standard deviation size is weighed weight by the size of object itself:
Wherein: n
Merge, c, w
c, σ
Cmerge, n
Obj1, σ
Cobj1, n
Obj2, σ
Cobj12---merge the pixel number of back object, the image number of plies, the image bearing layer weight, the spectroscopic standard after the merging is poor, the pixel number of object 1 before merging, the spectroscopic standard of object 1 is poor before merging, the pixel number of object 2 before merging, the spectroscopic standard of object 2 is poor before merging.
The shape heterogeneity is by smoothness h
SmoothWith degree of compacting h
Compact2 standards constitute:
h
shape＝w
compacth
compact+(1-w
compact)h
smooth (5)
Wherein: w
Compact---user-defined degree of compacting weight (with respect to smoothness, variation range is 0～1).
The computing formula of smoothness and degree of compacting is:
Wherein: l
Merge, b
Merge, l
Obj1, l
Obj2, b
Obj1, b
Obj2---merge the girth of back object, merge the girth of the circumscribed rectangle of back object, the girth of object 1 before merging, the girth of object 2 before merging, the girth of object 1 circumscribed rectangle before merging, the girth of object 2 circumscribed rectangles before merging.
Several adjustable average property or heterogeneous standard according to shape and spectrum are cut apart image, generate imaged object.
3, the crop varieties field operation is measured and feature extraction
The crop varieties field operation is measured and the process flow diagram of feature extraction sees 4.The following step of concrete employing realizes:
1) measures through field operation GPS, obtain the 4 jiaos of latitude and longitude coordinates and the variety type in crop varieties plot;
2) the crop varieties plot of measuring is added on the target in hyperspectral remotely sensed image, forms crop varieties distribution plan based on the plot;
3) be the characteristic such as reflectivity average, variance of element analysis crop varieties with the plot, confirm reflectivity average, the variance of Different Crop kind, as crop varieties characteristic based on the plot.
4, classify based on the crop varieties in plot
After the Different Crop varietal characteristic that obtains based on the plot, utilize the Different Crop varietal characteristic, adopt the fuzzy classification method to calculate the degree of membership that the ground block object belongs to a certain type or a few types, classified in the plot.
Fuzzy classification is to be converted into the fuzzy value between 0 and 1 to eigenwert from any range, as the degree of membership of particular category.Each class in the classification schemes all has 1 class description, comprises a series of fuzzy expression in each class description again.Fuzzy rule can have only 1 condition or comprise the combination of several conditions, and expression formula can be membership function or the most contiguous expression formula.
Adopt above-mentioned steps can realize high spectrum crop varieties identification, obtain crop varieties distribution plan, for the agricultural feelings monitoring of different scale, precision agriculture management etc. provide very Useful Information based on the plot based on the plot.
Claims (5)
1. high spectrum recognition methods of the crop varieties based on the plot is characterized in that may further comprise the steps:
(1) at first the high spectrum of Hyperion is carried out pre-service, through unsealed and the removal, Flaash atmospheric correction and the geometry correction that are subject to the wave band of influence of moisture, the Hyperion reflectivity image that obtains proofreading and correct;
(2) adopt the GPS outfield to measure the plot coordinate of crop varieties; Obtain crop varieties ground blocks of data; Crop varieties plot stacked data is added to Hyperion reflectivity image, and characteristics such as the reflectivity average of statistics Different Crop kind, variance are as the characteristic of crop varieties;
(3) adopt image Segmentation Technology such as watershed algorithm, Hyperion reflectivity image is carried out image segmentation, obtain ground blocks of data based on Hyperion reflectivity image;
(4) utilize the characteristics such as reflectivity average, variance of crop varieties, obtain crop varieties distribution plan based on the plot.
2. the high spectrum recognition methods of a kind of crop varieties according to claim 1 based on the plot; It is characterized in that: said step (1) is carried out pre-service to the high spectrum of Hyperion; Be meant according to Hyperion quality of data file, remove unsealed such as 1-7,58-78,121-127,167-178 and 224-242 and be subject to the wave band of influence of moisture; Adopt ENVI to carry out atmospheric correction; At first the Hyperion data are carried out convergent-divergent; The amplification factor of visible light/near-infrared band (8-57 wave band) is 40; The amplification factor of short-wave infrared wave band (77-224 wave band) is 80, calibrates according to gain and skew Hyperion data again, adopts the Flaash atmospheric correction module of ENVI to carry out atmospheric correction again; Perhaps proofreading and correct satellite datas such as good SPOT5, Landsat-TM with 1: 10 ten thousand topomap is base map, and the Hyperion image behind the atmospheric correction is carried out geometry correction, obtains to proofread and correct Hyperion reflectivity image well.
3. the high spectrum recognition methods of a kind of crop varieties based on the plot according to claim 1 is characterized in that: carry out in the said step (2) extracting based on the high spectrum crop varieties in plot, concrete steps are following:
(a) adopt GPS that measurement of coordinates is carried out in the crop varieties plot, obtain crop varieties ground blocks of data;
(b) crop varieties plot stacked data is added on the Hyperion reflectivity image characteristics such as the reflectivity average of statistics Different Crop kind, variance;
(c), confirm the characteristic based on the plot of Different Crop according to the difference of aspects such as the reflectivity average of Different Crop kind, variance.
4. the high spectrum recognition methods of a kind of crop varieties according to claim 1 based on the plot; It is characterized in that: said step (3) image segmentation is obtained the crop field blocks of data; Be meant Hyperion reflectivity image; Adopt image Segmentation Technology such as watershed algorithm, carry out image segmentation, obtain the ground blocks of data of various places article kind.
5. the high spectrum recognition methods of a kind of crop varieties based on the plot according to claim 1 is characterized in that: said step (3) is based on the crop varieties identification in plot, and concrete steps are following:
(a) calculate the characteristic such as reflectivity average, variance in each plot;
(b) characteristics such as the reflectivity average in comparison plot, variance according to the crop plot high spectrum reflection rate characteristic that rapid (2) obtain, the belonging kinds in interpretation plot, obtain the crop varieties distribution plan based on the plot.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201010272569.5A CN102385694B (en) | 2010-09-06 | 2010-09-06 | Hyperspectral identification method for land parcel-based crop variety |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201010272569.5A CN102385694B (en) | 2010-09-06 | 2010-09-06 | Hyperspectral identification method for land parcel-based crop variety |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102385694A true CN102385694A (en) | 2012-03-21 |
| CN102385694B CN102385694B (en) | 2014-04-16 |
Family
ID=45825098
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201010272569.5A Expired - Fee Related CN102385694B (en) | 2010-09-06 | 2010-09-06 | Hyperspectral identification method for land parcel-based crop variety |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102385694B (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020649A (en) * | 2013-01-16 | 2013-04-03 | 东北林业大学 | Forest type identification method based on texture information |
| CN103278464A (en) * | 2013-04-18 | 2013-09-04 | 北京工商大学 | Method and device for fish flesh detection |
| CN103413131A (en) * | 2013-01-24 | 2013-11-27 | 中国科学院遥感与数字地球研究所 | Tower crane recognition method based on spectral and geometric characteristics |
| CN103902998A (en) * | 2012-12-27 | 2014-07-02 | 核工业北京地质研究院 | High-spectral image processing method for chlorite information extraction |
| CN104573690A (en) * | 2013-10-23 | 2015-04-29 | 核工业北京地质研究院 | Hyperspectral image processing method for extracting gypsum information |
| CN103914678B (en) * | 2013-01-05 | 2017-02-08 | 中国科学院遥感与数字地球研究所 | Abandoned land remote sensing recognition method based on texture and vegetation indexes |
| CN107644399A (en) * | 2016-07-21 | 2018-01-30 | 中电科海洋信息技术研究院有限公司 | Remote sensing image processing method |
| CN108052903A (en) * | 2017-12-13 | 2018-05-18 | 阜阳市颍东区兴牧禽业专业合作社 | Open henhouse species identification system and method |
| CN109308688A (en) * | 2018-09-25 | 2019-02-05 | 中国农业科学院农业资源与农业区划研究所 | A kind of visible light and near infrared band is spissatus and shadow removal method |
| CN110657891A (en) * | 2019-09-29 | 2020-01-07 | 浙江农林大学 | Technology for identifying plants by applying multispectral investigation camera by unmanned aerial vehicle |
| CN111209871A (en) * | 2020-01-09 | 2020-05-29 | 河南大学 | Rape planting land remote sensing automatic identification method based on optical satellite image |
| CN113252584A (en) * | 2021-04-22 | 2021-08-13 | 华南农业大学 | Crop growth detection method and system based on 5G transmission |
| CN116129281A (en) * | 2023-04-18 | 2023-05-16 | 中国人民解放军战略支援部队航天工程大学 | Sub-pixel target detection system for hyperspectral image |
| CN117456287A (en) * | 2023-12-22 | 2024-01-26 | 天科院环境科技发展（天津）有限公司 | Method for observing population number of wild animals by using remote sensing image |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1677085A (en) * | 2004-03-29 | 2005-10-05 | 中国科学院遥感应用研究所 | Agricultural application integrating system for earth observation technique and its method |
| US7194132B1 (en) * | 2002-07-09 | 2007-03-20 | The United States Of America As Represented By The Secretary Of The Navy | Method and system for detecting anomalies in multispectral and hyperspectral imagery employing the normal compositional model |
| CN101673339A (en) * | 2009-09-25 | 2010-03-17 | 北京航空航天大学 | Target identification method of high spectroscopic data rearranged based on spectral absorption characteristics |
| CN101706950A (en) * | 2009-07-13 | 2010-05-12 | 中国科学院遥感应用研究所 | High-performance implementation method for multi-scale segmentation of remote sensing images |
-
2010
- 2010-09-06 CN CN201010272569.5A patent/CN102385694B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7194132B1 (en) * | 2002-07-09 | 2007-03-20 | The United States Of America As Represented By The Secretary Of The Navy | Method and system for detecting anomalies in multispectral and hyperspectral imagery employing the normal compositional model |
| CN1677085A (en) * | 2004-03-29 | 2005-10-05 | 中国科学院遥感应用研究所 | Agricultural application integrating system for earth observation technique and its method |
| CN101706950A (en) * | 2009-07-13 | 2010-05-12 | 中国科学院遥感应用研究所 | High-performance implementation method for multi-scale segmentation of remote sensing images |
| CN101673339A (en) * | 2009-09-25 | 2010-03-17 | 北京航空航天大学 | Target identification method of high spectroscopic data rearranged based on spectral absorption characteristics |
Non-Patent Citations (3)
| Title |
|---|
| 吕杰: "基于Hyperion高光谱遥感数据的城市绿地信息提取方法的研究", 《中国优秀硕士学位论文全文数据库》 * |
| 洪霞等: "高光谱遥感在精准农业生产中的应用", 《安徽农业科学》 * |
| 邬明权等: "利用多源时序遥感数据提取大范围水稻种植面积", 《农业工程学报》 * |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103902998A (en) * | 2012-12-27 | 2014-07-02 | 核工业北京地质研究院 | High-spectral image processing method for chlorite information extraction |
| CN103914678B (en) * | 2013-01-05 | 2017-02-08 | 中国科学院遥感与数字地球研究所 | Abandoned land remote sensing recognition method based on texture and vegetation indexes |
| CN103020649A (en) * | 2013-01-16 | 2013-04-03 | 东北林业大学 | Forest type identification method based on texture information |
| CN103413131A (en) * | 2013-01-24 | 2013-11-27 | 中国科学院遥感与数字地球研究所 | Tower crane recognition method based on spectral and geometric characteristics |
| CN103413131B (en) * | 2013-01-24 | 2018-05-11 | 中国科学院遥感与数字地球研究所 | Tower crane recognition method based on spectrum and geometric properties |
| CN103278464A (en) * | 2013-04-18 | 2013-09-04 | 北京工商大学 | Method and device for fish flesh detection |
| CN103278464B (en) * | 2013-04-18 | 2015-10-21 | 北京工商大学 | Flesh of fish detection method and device |
| CN104573690A (en) * | 2013-10-23 | 2015-04-29 | 核工业北京地质研究院 | Hyperspectral image processing method for extracting gypsum information |
| CN104573690B (en) * | 2013-10-23 | 2018-03-16 | 核工业北京地质研究院 | A kind of Technique for Hyper-spectral Images Classification for gypsum information extraction |
| CN107644399A (en) * | 2016-07-21 | 2018-01-30 | 中电科海洋信息技术研究院有限公司 | Remote sensing image processing method |
| CN108052903A (en) * | 2017-12-13 | 2018-05-18 | 阜阳市颍东区兴牧禽业专业合作社 | Open henhouse species identification system and method |
| CN108052903B (en) * | 2017-12-13 | 2020-09-08 | 阜阳汇中芯自动化技术有限公司 | Open type henhouse type identification system and method |
| CN109308688A (en) * | 2018-09-25 | 2019-02-05 | 中国农业科学院农业资源与农业区划研究所 | A kind of visible light and near infrared band is spissatus and shadow removal method |
| CN109308688B (en) * | 2018-09-25 | 2021-06-25 | 中国农业科学院农业资源与农业区划研究所 | Visible light and near-infrared band thick cloud and shadow removing method |
| CN110657891A (en) * | 2019-09-29 | 2020-01-07 | 浙江农林大学 | Technology for identifying plants by applying multispectral investigation camera by unmanned aerial vehicle |
| CN110657891B (en) * | 2019-09-29 | 2021-08-10 | 浙江农林大学 | Technology for identifying plants by applying multispectral investigation camera by unmanned aerial vehicle |
| CN111209871A (en) * | 2020-01-09 | 2020-05-29 | 河南大学 | Rape planting land remote sensing automatic identification method based on optical satellite image |
| CN111209871B (en) * | 2020-01-09 | 2021-06-25 | 河南大学 | Rape planting land remote sensing automatic identification method based on optical satellite image |
| CN113252584A (en) * | 2021-04-22 | 2021-08-13 | 华南农业大学 | Crop growth detection method and system based on 5G transmission |
| CN116129281A (en) * | 2023-04-18 | 2023-05-16 | 中国人民解放军战略支援部队航天工程大学 | Sub-pixel target detection system for hyperspectral image |
| CN117456287A (en) * | 2023-12-22 | 2024-01-26 | 天科院环境科技发展（天津）有限公司 | Method for observing population number of wild animals by using remote sensing image |
| CN117456287B (en) * | 2023-12-22 | 2024-03-12 | 天科院环境科技发展（天津）有限公司 | Method for observing population number of wild animals by using remote sensing image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102385694B (en) | 2014-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102385694B (en) | Hyperspectral identification method for land parcel-based crop variety | |
| Halme et al. | Utility of hyperspectral compared to multispectral remote sensing data in estimating forest biomass and structure variables in Finnish boreal forest | |
| Millard et al. | Wetland mapping with LiDAR derivatives, SAR polarimetric decompositions, and LiDAR–SAR fusion using a random forest classifier | |
| Saha et al. | Land cover classification using IRS LISS III image and DEM in a rugged terrain: a case study in Himalayas | |
| CN107103306B (en) | Winter wheat powdery mildew remote-sensing monitoring method based on wavelet analysis and support vector machines | |
| Kandare et al. | Individual tree crown approach for predicting site index in boreal forests using airborne laser scanning and hyperspectral data | |
| CN105930772A (en) | City impervious surface extraction method based on fusion of SAR image and optical remote sensing image | |
| Kukunda et al. | Ensemble classification of individual Pinus crowns from multispectral satellite imagery and airborne LiDAR | |
| Boori et al. | Comparison of hyperspectral and multi-spectral imagery to building a spectral library and land cover classification performanc | |
| Shahi et al. | Road condition assessment by OBIA and feature selection techniques using very high-resolution WorldView-2 imagery | |
| Zhuo et al. | An improved temporal mixture analysis unmixing method for estimating impervious surface area based on MODIS and DMSP-OLS data | |
| Wang et al. | Decadal trend in agricultural abandonment and woodland expansion in an agro-pastoral transition band in Northern China | |
| Varade et al. | Unsupervised band selection of hyperspectral data based on mutual information derived from weighted cluster entropy for snow classification | |
| CN102013095A (en) | Distribution transform-based multi-sensor image fusion method | |
| Zhang et al. | Mapping freshwater marsh species in the wetlands of Lake Okeechobee using very high-resolution aerial photography and lidar data | |
| CN114694036A (en) | High-altitude area crop classification and identification method based on high-resolution images and machine learning | |
| Mishra et al. | Knowledge-based decision tree approach for mapping spatial distribution of rice crop using C-band synthetic aperture radar-derived information | |
| Krishna et al. | Hyperspectral satellite data analysis for pure pixels extraction and evaluation of advanced classifier algorithms for LULC classification | |
| Li et al. | Regression and analytical models for estimating mangrove wetland biomass in South China using Radarsat images | |
| Diana et al. | Estimation the amount of oil palm production using Artificial Neural Network and NDVI SPOT-6 Imagery | |
| CN108229426B (en) | Remote sensing image change vector change detection method based on difference descriptor | |
| Proctor et al. | Texture augmented detection of macrophyte species using decision trees | |
| CN111751295A (en) | Modeling method and application of wheat powdery mildew severity detection model based on imaging hyperspectral data | |
| Zhu et al. | Fusion of multisensor multitemporal satellite data for land cover mapping | |
| CN111882573A (en) | Cultivated land plot extraction method and system based on high-resolution image data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| ASS | Succession or assignment of patent right |
Owner name: INST. OF REMOTE SENSING APPLICATION, CHINESE ACADE Effective date: 20120508 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20120508 Address after: 100101 Beijing city Chaoyang District Datun Road No. 20 North Applicant after: Inst. of Remote Sensing Application, Chinese Academy of Sciences Address before: 100101 Beijing city Chaoyang District Datun Road No. 20 North Chinese Academy of remote sensing C block 300 Applicant before: Wu Mingquan Co-applicant before: Wang Li |
|
| C53 | Correction of patent of invention or patent application | ||
| CB02 | Change of applicant information |
Address after: 100101 Beijing city Chaoyang District Datun Road No. 20 North Applicant after: Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences Address before: 100101 Beijing city Chaoyang District Datun Road No. 20 North Applicant before: Inst. of Remote Sensing Application, Chinese Academy of Sciences |
|
| COR | Change of bibliographic data |
Free format text: CORRECT: APPLICANT; FROM: INST. OF REMOTE SENSING APPLICATION, CHINESE ACADEMY OF SCIENCES TO: INSTITUTE OF REMOTE SENSING AND DIGITAL EARTH CHINESE ACADEMY OF SCIENCES |
|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20140416 Termination date: 20170906 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |