CN105404873A - Winter wheat recognition method based on NDVI time sequence coordinate conversion - Google Patents
Winter wheat recognition method based on NDVI time sequence coordinate conversion Download PDFInfo
- Publication number
- CN105404873A CN105404873A CN201510845296.1A CN201510845296A CN105404873A CN 105404873 A CN105404873 A CN 105404873A CN 201510845296 A CN201510845296 A CN 201510845296A CN 105404873 A CN105404873 A CN 105404873A
- Authority
- CN
- China
- Prior art keywords
- winter wheat
- ndvi
- time series
- ndvi time
- coordinate conversion
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The present invention proposes a winter wheat recognition method based on NDVI time sequence coordinate conversion. According to the winter wheat recognition method provided by the present invention, an NDVI time sequence covering the growth cycle of the winter wheat is adopted; unique phenological characteristics of the winter wheat, which are distinguished from other ground features, are sufficiently utilized; by the coordinate conversion of the NDVI time sequence, differences between the winter wheat and other ground features are significantly improved; and based on an average value and a standard deviation threshold value, high accuracy recognition of the winter wheat is achieved.
Description
Technical field
The present invention is a winter wheat remote sensing recognition technology, propose a kind of winter wheat recognition methods based on NDVI time series coordinate conversion, by NDVI seasonal effect in time series coordinate conversion, significantly promote the difference of winter wheat and other atural object, achieve the high precision identification of winter wheat.
Background technology
Wheat is one of global most important cereal crops, widest in area general at grown worldwide.China's wheat is also most important cereal crops, and cultivated area accounts for 1/5th of the total sown area of cereal crops, in China's grain is formed, account for critical role.China is based on winter wheat, and extracting winter wheat planting area is timely and accurately the basis of carrying out recovery prediction, is the key factor being related to national food security and social stability.
Based on traditional winter wheat area acquisition methods of field observation, can not meet in time, obtain accurately the demand of large regions winter wheat area.Along with the high speed development of remote sensing technology, remote sensing image is widely used in winter wheat monitoring field.The early stage main identification adopting single phase remote sensing image data to carry out winter wheat, because agrotype complexity is various, obvious spectra overlapping is there is between Different Crop, easily there is " wrong point, leakage point " phenomenon when utilizing single phase remote sensing image data to carry out Crops Classification, be difficult to reach desirable nicety of grading.Along with enriching constantly of remotely-sensed data source, consider the difference of Different Crop with seasonal variations, multi-temporal remote sensing data even time series remotely-sensed data can strengthen the Spectral divisibility between Different Crop, current remotely-sensed data time series, especially normalized differential vegetation index (normalizeddifferencevegetationindex, NDVI) time series has become the focus of crop Study of recognition.
NDVI is the most frequently used index that application remote sensing technology extracts Crop Information, is widely used in Crops Classification and upgrowth situation evaluation.NDVI time series data can accurately reflect vegetation phenology information (emerge, jointing, heading, maturation), effectively weaken " the different spectrum of jljl, same object different images " phenomenon, in Crops Classification research, played vital role, the identification of winter wheat can be applied to.Comparatively popular method is the NDVI time series data based on MODIS, NOAA/AVHRR at present, but because image spatial resolution lower China in addition crop-planting classification complexity is various, plot is comparatively broken, only being made up of single atural object few pixel, winter wheat accuracy of identification is limited.Along with the transmitting of special first the satellite GF-1 satellite of China's high score, its wide covering camera (WideFieldofView carried, WFV) possess the image capturing ability of 16 meters of spatial resolutions and 4 days revisiting period, provide valid data source for high spatial resolution NDVI seasonal effect in time series builds.
At NDVI time series identification crop field, the method that current application is comparatively ripe is Decision tree classification, and the method only utilizes the several characteristic wave bands in time series, and does not consider whole sequence.The present invention proposes a kind of winter wheat recognition methods based on NDVI time series coordinate conversion for this reason, taken into full account whole NDVI time series, and operating process is simple and practical.
Summary of the invention
The present invention proposes a kind of winter wheat recognition methods based on NDVI time series coordinate conversion, make full use of the peculiar phenology feature that winter wheat is different from other crop, and by NDVI seasonal effect in time series coordinate conversion, the difference of remarkable lifting winter wheat and other atural object, achieves the high precision identification of winter wheat.
Step one: obtain the GF-1WFV image sequence in the winter wheat growth cycle, and build NDVI time series, being formed with time is horizontal ordinate, and NDVI is the NDVI time-serial position of ordinate; Step 2: by on-site inspection or historical data, obtains winter wheat sample data; Step 3: based on winter wheat sample, obtains the NDVI time-serial position of corresponding pixel, carries out arithmetic mean to the NDVI time series of all sample pixels, forms winter wheat NDVI seasonal effect in time series reference curve; Step 4: with winter wheat NDVI time series reference curve for benchmark carries out coordinate conversion to NDVI time-serial position, namely deducts reference curve by corresponding for all pixel in test site NDVI time-serial position, and wherein, the NDVI time series of pixel represents and is
, the NDVI time series reference curve of winter wheat is expressed as
, according to formula
calculate the NDVI time series transformation curve of each pixel; Step 5: based on NDVI time series transformation curve, utilize winter wheat sample data, calculate average and the standard deviation of transformation curve corresponding to sample pixel respectively, then obtain the maximal value of mean absolute value and standard deviation as the threshold value of wheat identification by statistical study, realize automatically determining of threshold value; Step 6: utilize the transformation curve that step 4 obtains, calculate average and the standard deviation of the transformation curve that each pixel is corresponding in test site respectively, and the threshold value utilizing step 5 to obtain judges, when average and standard deviation are all at threshold range, then judge that this pixel is as winter wheat, travel through whole test site, finally form winter wheat distribution plan.
Further, in described step one, the growth cycle of winter wheat is June October to next year then, guarantee there are first phase GF-1WFV data every month as far as possible, NDVI time series needs data through process such as radiation calibration, atmospheric correction, geometry corrections before building, then utilize red spectral band and near-infrared band to calculate NDVI, finally form NDVI time series.
Further, in described step 4, with winter wheat NDVI reference curve for benchmark carries out coordinate conversion, can the NDVI time series of winter wheat be controlled near 0 value, and reduce winter wheat NDVI seasonal effect in time series dispersion, improve absolute value or the NDVI seasonal effect in time series dispersion of other atural object NDVI Time Series Mean simultaneously, be conducive to the accuracy of identification promoting winter wheat.
Further, in described step 5, winter wheat sample data is representative, namely the transformation curve average utilizing sample pixel to obtain and the dynamic range of standard deviation can represent the dynamic range of whole test site winter wheat NDVI time series transformation curve average and standard deviation, and adopt average and standard deviation two threshold ranges measured as the standard of winter wheat identification.
Advantage of the present invention: the present invention adopts data mapping to construct high spatial resolution NDVI time series, NDVI time series covers the whole winter wheat growth cycle, by setting up Coordinate Transformation Models, reduce winter wheat NDVI seasonal effect in time series dispersion, and utilize sample data to complete the automatic acquisition of threshold value, achieve the lifting of winter wheat accuracy of identification.
Accompanying drawing explanation
Fig. 1 is the winter wheat recognition methods process flow diagram based on NDVI time series coordinate conversion.
Fig. 2 is the NDVI time-serial position of in October, 2014 in May, 2015 test site typical feature.
Fig. 3 is the NDVI time series transformation curve of test site typical feature.
Fig. 4 is test site winter wheat recognition result figure.
Embodiment
Below in conjunction with example, the invention will be further described, and as shown in Figure 1, the concrete implementation detail of each several part is as follows for implementing procedure of the present invention.
Step one: obtain the GF-1WFV data in the winter wheat growth cycle, and build NDVI time series; The present invention with Hengshui, Hebei province Jizhou City for test site, obtain and cover GF-1WFV data totally 8 scapes (see table 1) in winter wheat growth cycle from year May in October, 2014 to 2015, after the process such as radiation calibration, atmospheric correction, geometry correction, extract NDVI and build NDVI time series, to realize the Continuous Observation to the crop growth critical period.Wherein NDVI is the red spectral band and the near-infrared band that utilize GF-1WFV data, is calculated by formula (1).
（1）
In formula:
for near-infrared band reflectivity,
for red spectral band reflectivity.
table 1GF-1WFV image
Test site typical feature comprises forest land, impervious surface, water body, bare area, and during year May in October, 2014 to 2015, crops are based on winter wheat, and the NDVI curve map of typical feature as shown in Figure 2.
Step 2: obtain 1500 winter wheat sample datas by on-site inspection in test site, sample data is uniformly distributed as far as possible in test site.
Step 3: build reference curve based on winter wheat sample data.In case of the present invention, NDVI time series is containing 8 phases, then the NDVI time-serial position of each pixel can be expressed as
.The wheat of diverse location is due to the impact of the aspect such as sowing time, water and fertilizer condition, its NDVI time-serial position can difference to some extent, therefore, arithmetic mean (see formula (2)) is carried out to the NDVI time-serial position of all sample pixels, form winter wheat NDVI time series reference curve
.
(2)
Step 4: NDVI time series coordinate conversion.Be that benchmark carries out coordinate conversion to NDVI time-serial position with reference curve, namely corresponding for pixels all in test site NDVI time-serial position deducted reference curve (see formula (3)), obtain the NDVI time series transformation curve of each pixel
.
(3)
As shown in Figure 3, as can be seen from the figure, the NDVI time series transformation curve of winter wheat is other atural object relatively for NDVI time-serial position after coordinate conversion, its average is closer to 0, and dispersion is less, the present invention takes full advantage of this feature, achieves the high precision identification of winter wheat.
Step 5: the determination of winter wheat recognition threshold.Suppose that winter wheat sample data is representative, namely the average of the transformation curve of sample pixel and the dynamic range of standard deviation can represent the average of whole test site winter wheat transformation curve and the dynamic range of standard deviation; The threshold value of winter wheat identification comprises mean absolute value and the standard deviation of winter wheat transformation curve, based on NDVI time series transformation curve, utilize winter wheat sample data, calculate average (see formula (4)) and the standard deviation (see formula (5)) of transformation curve corresponding to sample pixel respectively, and the maximal value that statistical study obtains mean absolute value is carried out to the average of all sample pixels and standard deviation
, standard deviation maximal value
, as the threshold value of winter wheat identification.
(4)
(5)
Step 6: the identification of winter wheat.Based on NDVI time series transformation curve
, to each pixel in test site according to formula (4) and (5) computation of mean values and standard deviation, then judge whether this pixel is winter wheat, travels through whole test site according to formula (6), finally form winter wheat distribution plan (Fig. 4).The accuracy of identification of the winter wheat of this test is 97.8%.
(6)
Claims (3)
1., based on a winter wheat recognition methods for NDVI time series coordinate conversion, the method comprises the steps:
Step one: obtain the GF-1WFV image sequence in the winter wheat growth cycle, and build NDVI time series, being formed with time is horizontal ordinate, and NDVI is the NDVI time-serial position of ordinate; Step 2: by on-site inspection or historical data, obtains winter wheat sample data; Step 3: based on winter wheat sample, obtains the NDVI time-serial position of corresponding pixel, carries out arithmetic mean to the NDVI time series of all sample pixels, forms winter wheat NDVI seasonal effect in time series reference curve; Step 4: with winter wheat NDVI time series reference curve for benchmark carries out coordinate conversion to NDVI time-serial position, namely deducts reference curve by corresponding for all pixel in test site NDVI time-serial position, and wherein, the NDVI time series of pixel represents and is
, the NDVI time series reference curve of winter wheat is expressed as
, according to formula
calculate the NDVI time series transformation curve of each pixel; Step 5: based on NDVI time series transformation curve, utilize winter wheat sample data, calculate average and the standard deviation of transformation curve corresponding to sample pixel respectively, then obtain the maximal value of mean absolute value and standard deviation as the threshold value of wheat identification by statistical study, realize automatically determining of threshold value; Step 6: utilize the transformation curve that step 4 obtains, calculate average and the standard deviation of the transformation curve that each pixel is corresponding in test site respectively, and the threshold value utilizing step 5 to obtain judges, when average and standard deviation are all at threshold range, then judge that this pixel is as winter wheat, travel through whole test site, finally form winter wheat distribution plan.
2. a kind of winter wheat recognition methods based on NDVI time series coordinate conversion according to claim 1, it is characterized in that, the NDVI time series of winter wheat controls near 0 value by described coordinate conversion, and reduces winter wheat NDVI seasonal effect in time series dispersion.
3. a kind of winter wheat recognition methods based on NDVI time series coordinate conversion according to claim 1, it is characterized in that, described winter wheat sample data is the geometric position information of winter wheat, and the relatively uniform distribution in test site, representative.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510845296.1A CN105404873B (en) | 2015-11-30 | 2015-11-30 | A kind of winter wheat recognition methods based on the conversion of NDVI time series coordinates |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510845296.1A CN105404873B (en) | 2015-11-30 | 2015-11-30 | A kind of winter wheat recognition methods based on the conversion of NDVI time series coordinates |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105404873A true CN105404873A (en) | 2016-03-16 |
| CN105404873B CN105404873B (en) | 2018-09-04 |
Family
ID=55470350
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510845296.1A Active CN105404873B (en) | 2015-11-30 | 2015-11-30 | A kind of winter wheat recognition methods based on the conversion of NDVI time series coordinates |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105404873B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108280410A (en) * | 2018-01-10 | 2018-07-13 | 北京农业信息技术研究中心 | One kind being based on binary-coded crops recognition methods and system |
| CN108805079A (en) * | 2018-06-12 | 2018-11-13 | 中国科学院地理科学与资源研究所 | The recognition methods of winter wheat and device |
| CN108846337A (en) * | 2018-06-01 | 2018-11-20 | 苏州中科天启遥感科技有限公司 | A kind of hyperplane Distance Time window selection method based on support vector machines |
| 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 |
| CN109697411A (en) * | 2018-12-07 | 2019-04-30 | 河北工程大学 | A kind of ground object information extraction method based on SS difference |
| CN110119717A (en) * | 2019-05-15 | 2019-08-13 | 中国科学院遥感与数字地球研究所 | A kind of Crop classification method based on multi-temporal NDVI and LST |
| CN111382724A (en) * | 2020-04-01 | 2020-07-07 | 宿迁学院 | NDVI time sequence complex hurst-based low-temperature-resistant plant identification method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104915660A (en) * | 2015-07-01 | 2015-09-16 | 中国科学院遥感与数字地球研究所 | Winter wheat automatic recognition method based on GF-1/WFV NDVI time sequence |
| CN104951772A (en) * | 2015-07-10 | 2015-09-30 | 中国科学院遥感与数字地球研究所 | Winter wheat extraction method based on NDVI (normalized difference vegetation index) time series curve integral |
-
2015
- 2015-11-30 CN CN201510845296.1A patent/CN105404873B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104915660A (en) * | 2015-07-01 | 2015-09-16 | 中国科学院遥感与数字地球研究所 | Winter wheat automatic recognition method based on GF-1/WFV NDVI time sequence |
| CN104951772A (en) * | 2015-07-10 | 2015-09-30 | 中国科学院遥感与数字地球研究所 | Winter wheat extraction method based on NDVI (normalized difference vegetation index) time series curve integral |
Non-Patent Citations (3)
| Title |
|---|
| GUERRIC LE MAIRE ET AL: "Mapping short-rotation plantations at regional scale using MODIS time series Case of eucalypt plantations in Brazil", 《REMOTE SENSING OF ENVIRONMENT》 * |
| 张喜旺 等: "综合季相节律和特征光谱的冬小麦种植面积遥感估算", 《农业工程学报》 * |
| 王利民 等: "基于GF-1卫星遥感的冬小麦面积早期识别", 《农业工程学报》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108280410A (en) * | 2018-01-10 | 2018-07-13 | 北京农业信息技术研究中心 | One kind being based on binary-coded crops recognition methods and system |
| CN108280410B (en) * | 2018-01-10 | 2020-10-27 | 北京农业信息技术研究中心 | Crop identification method and system based on binary coding |
| CN108846337A (en) * | 2018-06-01 | 2018-11-20 | 苏州中科天启遥感科技有限公司 | A kind of hyperplane Distance Time window selection method based on support vector machines |
| CN108846337B (en) * | 2018-06-01 | 2022-07-19 | 苏州中科天启遥感科技有限公司 | Hyperplane distance time window selection method based on support vector machine |
| CN108805079A (en) * | 2018-06-12 | 2018-11-13 | 中国科学院地理科学与资源研究所 | The recognition methods of winter wheat and device |
| CN108805079B (en) * | 2018-06-12 | 2020-10-09 | 中国科学院地理科学与资源研究所 | Winter wheat identification method and device |
| 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 |
| CN109697411A (en) * | 2018-12-07 | 2019-04-30 | 河北工程大学 | A kind of ground object information extraction method based on SS difference |
| CN110119717A (en) * | 2019-05-15 | 2019-08-13 | 中国科学院遥感与数字地球研究所 | A kind of Crop classification method based on multi-temporal NDVI and LST |
| CN111382724A (en) * | 2020-04-01 | 2020-07-07 | 宿迁学院 | NDVI time sequence complex hurst-based low-temperature-resistant plant identification method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105404873B (en) | 2018-09-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105404873A (en) | Winter wheat recognition method based on NDVI time sequence coordinate conversion | |
| Zhang et al. | Improved maize cultivated area estimation over a large scale combining MODIS–EVI time series data and crop phenological information | |
| CN105740759B (en) | Semilate rice information decision tree classification approach based on feature extraction in multi-temporal data | |
| CN107609526A (en) | Rule-based fine dimension city impervious surface rapid extracting method | |
| Ballesteros et al. | Combined use of agro-climatic and very high-resolution remote sensing information for crop monitoring | |
| CN106372592A (en) | Winter wheat plantation area calculation method based on winter wheat area index | |
| CN107527014A (en) | Crops planting area RS statistics scheme of sample survey design method at county level | |
| CN104951772B (en) | A kind of winter wheat extracting method based on NDVI time-serial positions integration | |
| GB2598012A (en) | System and method for crop monitoring | |
| CN104915660A (en) | Winter wheat automatic recognition method based on GF-1/WFV NDVI time sequence | |
| CN114821362B (en) | Multi-source data-based rice planting area extraction method | |
| CN105404753A (en) | Marsh wetland mapping method based on object-oriented random forest classification method and medium-resolution remote sensing image | |
| CN109784300A (en) | A kind of crops science survey production method and system | |
| CN104951754A (en) | Sophisticated crop classifying method based on combination of object oriented technology and NDVI (normalized difference vegetation index) time series | |
| CN115376016A (en) | Actual rice field irrigation area identification method based on combination of vegetation water index and evapotranspiration | |
| Liu et al. | Estimating potato above-ground biomass by using integrated unmanned aerial system-based optical, structural, and textural canopy measurements | |
| CN109816542A (en) | A kind of crop production reduction Claims Resolution method and system | |
| Lang et al. | Detection of chlorophyll content in Maize Canopy from UAV Imagery | |
| CN115641504A (en) | Automatic remote sensing extraction method for field boundary based on crop phenological characteristics and decision tree model | |
| CN116665073A (en) | Corn yield remote sensing estimation method based on multi-source data | |
| Pauly | Applying conventional vegetation vigor indices to UAS-derived orthomosaics: issues and considerations | |
| Zhu et al. | UAV flight height impacts on wheat biomass estimation via machine and deep learning | |
| CN105868761A (en) | Urban forest vegetation coverage sampling method matched with SPOT5 (Systeme Probatoire d'Observation de la Terre 5) image | |
| CN110188955B (en) | Chlorophyll fluorescence remote sensing-based large-scale autumn grain yield estimation method | |
| Rinnamang et al. | Estimation of aboveground biomass using aerial photogrammetry from unmanned aerial vehicle in teak (Tectona grandis) plantation in Thailand |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |