CN110160992A - 一种基于植被覆盖度时间序列的农作物分类方法 - Google Patents

一种基于植被覆盖度时间序列的农作物分类方法 Download PDF

Info

Publication number
CN110160992A
CN110160992A CN201910400615.6A CN201910400615A CN110160992A CN 110160992 A CN110160992 A CN 110160992A CN 201910400615 A CN201910400615 A CN 201910400615A CN 110160992 A CN110160992 A CN 110160992A
Authority
CN
China
Prior art keywords
ndvi
time series
soil
fvc
crop
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
Application number
CN201910400615.6A
Other languages
English (en)
Inventor
占玉林
顾行发
余涛
杨健
王春梅
臧文乾
赵亚萌
王栋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Research Institute Of Space Information (langfang) Of China Science
Zhongke Satellite Application Deqing Research Institute
Institute of Remote Sensing and Digital Earth of CAS
Original Assignee
Research Institute Of Space Information (langfang) Of China Science
Zhongke Satellite Application Deqing Research Institute
Institute of Remote Sensing and Digital Earth of CAS
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Research Institute Of Space Information (langfang) Of China Science, Zhongke Satellite Application Deqing Research Institute, Institute of Remote Sensing and Digital Earth of CAS filed Critical Research Institute Of Space Information (langfang) Of China Science
Priority to CN201910400615.6A priority Critical patent/CN110160992A/zh
Publication of CN110160992A publication Critical patent/CN110160992A/zh
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/55Specular reflectivity
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/55Specular reflectivity
    • G01N2021/558Measuring reflectivity and transmission

Landscapes

  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Investigating Or Analysing Materials By Optical Means (AREA)

Abstract

本发明公开了一种基于植被覆盖度时间序列的农作物分类方法,包括如下步骤:步骤1)获取含有红光波段和近红外波段的遥感影像数据,构建覆盖农作物生长周期的遥感影像时间序列,并计算得到NDVI时间序列;步骤2)基于步骤1)得到的NDVI时间序列,计算得到植被覆盖度(FVC)时间序列(公式为FVC=(NDVI‑NDVIsoil)/(NDVIveg‑NDVIsoil),式中NDVIsoil为纯裸土的NDVI,取NDVI的第5个累计百分位数;NDVIveg为纯植被的NDVI,取NDVI的第95个累计百分位数);步骤3)通过实地调查或历史图件,获取农作物样本数据;步骤4)以FVC时间序列和样本数据作为输入,采用随机森林分类器,对研究区的农作物进行分类,形成农作物分类结果图。

Description

一种基于植被覆盖度时间序列的农作物分类方法
技术领域
本发明是一项农作物遥感精细分类技术,提出了一种基于植被覆盖度时间序列的农作物分类方法,充分利用植被覆盖度时间序列能够反应不同农作物的生长特点,有效提高农作物精细分类的精度,为农作物精细分类提供了一种新思路。
背景技术
及时、准确地掌握农作物分布信息对政府部门制定农业政策、指导农业生产具有十分重要的意义。遥感作为一种快速、大范围获取地表信息的技术手段,已广泛应用于农作物分类,获取农作物的空间分布,相对于传统的农作物监测方法,耗费较少的人力、物力和财力。
农作物类型多样,有水稻、玉米、小米等,种植结构复杂,有连作、轮作、间种与套种等种植结构;容易出现不同作物光谱相同以及同一类作物因种植模式的差异出现不同光谱信息的现象,即“同物异谱和异物同谱”。因此,单纯依靠光谱特征进行农作物提取,经常会出现“错分、漏分”的现象,难以达到预期效果。由于不同作物具有特定的生长规律和物候特征,不同生长时期的同一农作物其光谱特征不同,同一生长期的不同农作物光谱也具有差异。因此,时间序列遥感已逐步应用于农作物分类,这种方法充分利用了农作物的生长规律和物候特征。目前,归一化植被指数( Normalized Difference Vegetation Index, NDVI)时间序列数据,广泛应用于农作物分类,这种方法能够较好地反映植被物候信息,有效削弱“同物异谱,同谱异物”现象,较为流行的方法是基于MODIS、NOAA/AVHRR的NDVI时间序列数据,但由于影像空间分辨率较低,农作物分类精度有限。随着遥感数据源的不断丰富,目前中、高分辨率影像时间序列的构建逐步成为热点,而且高分辨率NDVI时间序列已经应用于农作物分类。
不同农作物在生长过程中,由于其叶子大小、稠密的差异,从而表现出植被覆盖度(Fractional Vegetation Coverage,FVC)的差异。因此,本专利提出了一种基于植被覆盖度时间序列的农作物分类方法,提升农作物的分类精度。
发明内容
本发明提出了一种基于植被覆盖度时间序列的农作物分类方法,充分利用农作物在生长过程中,不同农作物植被覆盖度的差异,有效提升了农作物遥感分类的精度,该估算方法包括如下步骤:
步骤一:获取含有红光波段和近红外波段的遥感影像数据,构建覆盖农作物生长周期的遥感影像时间序列,并计算得到NDVI时间序列;步骤二:基于步骤一得到的NDVI时间序列,计算得到植被覆盖度(FVC)时间序列(公式为FVC=(NDVI- NDVIsoil)/(NDVIveg-NDVIsoil),式中NDVIsoil为纯裸土的NDVI,取NDVI的第5个累计百分位数;NDVIveg为纯植被的NDVI,取NDVI的第95个累计百分位数);步骤三:通过实地调查或历史图件,获取农作物样本数据;步骤四:以FVC时间序列和样本数据作为输入,采用随机森林分类器,对研究区的农作物进行分类,形成农作物分类结果图。
附图说明
图1为基于植被覆盖度时间序列的农作物分类方法流程图。
图2为农作物分类结果图。
具体实施方式
下面结合实例对本发明“一种基于植被覆盖度时间序列的农作物分类方法”作进一步说明,按照实施流程(如图1所示),详细实施细节如下。
步骤一:以美国堪萨斯州巴顿县为实验区,实验区的农作物主要为玉米、苜蓿、大豆、冬小麦和高粱。获取了覆盖实验区2016年6月-12月期间的Landsat-8卫星影像(每月一期),利用这7期Landsat-8的OLI地表反射率数据分别提取NDVI。NDVI计算方法如下所示:
NDVI=(NDVI-R)⁄(NDVI+R)
其中,NIR代表近红外波段反射率,R代表红光波段反射率。
将7个时相的NDVI按照时间顺序叠加在一起形成NDVI时间序列。
步骤二:基于步骤一得到的NDVI时间序列,将序列中的每一期NDVI转化为FVC(公式为FVC=(NDVI- NDVIsoil)/(NDVIveg- NDVIsoil),式中NDVIsoil为纯裸土的NDVI,取NDVI的第5个累计百分位数;NDVIveg为纯植被的NDVI,取NDVI的第95个累计百分位数)。将转化形成的7期FVC按照时间顺序叠加在一起,形成FVC时间序列。
步骤三:从网站(http://www.nass.usda.gov/research/Cropland/SARS1a.htm)下载美国农业部制作的实验区2016年农作物分类图,获取农作物样本数据。
步骤四:以FVC时间序列和训练样本数据作为输入,采用随机森林分类器,对实验区的农作物进行分类,形成农作物分类结果图(图2),经验证其总体精度达到94.6%。

Claims (1)

1.一种基于植被覆盖度时间序列的农作物分类方法,该方法包括如下步骤:步骤1)获取含有红光波段和近红外波段的遥感影像数据,构建覆盖农作物生长周期的遥感影像时间序列,并计算得到NDVI时间序列;步骤2)基于步骤1)得到的NDVI时间序列,计算得到植被覆盖度(FVC)时间序列(公式为FVC=(NDVI- NDVIsoil)/(NDVIveg- NDVIsoil),式中NDVIsoil为纯裸土的NDVI,取NDVI的第5个累计百分位数;NDVIveg为纯植被的NDVI,取NDVI的第95个累计百分位数);步骤3)通过实地调查或历史图件,获取农作物样本数据;步骤4)以FVC时间序列和样本数据作为输入,采用随机森林分类器,对研究区的农作物进行分类,形成农作物分类结果图。
CN201910400615.6A 2019-05-15 2019-05-15 一种基于植被覆盖度时间序列的农作物分类方法 Pending CN110160992A (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910400615.6A CN110160992A (zh) 2019-05-15 2019-05-15 一种基于植被覆盖度时间序列的农作物分类方法

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910400615.6A CN110160992A (zh) 2019-05-15 2019-05-15 一种基于植被覆盖度时间序列的农作物分类方法

Publications (1)

Publication Number Publication Date
CN110160992A true CN110160992A (zh) 2019-08-23

Family

ID=67634618

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910400615.6A Pending CN110160992A (zh) 2019-05-15 2019-05-15 一种基于植被覆盖度时间序列的农作物分类方法

Country Status (1)

Country Link
CN (1) CN110160992A (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111678871A (zh) * 2020-06-16 2020-09-18 中国气象科学研究院 一种非生长季植被覆盖度遥感估算方法
CN111695606A (zh) * 2020-05-25 2020-09-22 中国科学院东北地理与农业生态研究所 一种多类型城市绿地分类方法
CN114494844A (zh) * 2021-12-13 2022-05-13 中国气象科学研究院 高海拔区域植被类型识别方法、装置及电子设备

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106908415A (zh) * 2017-02-24 2017-06-30 郑州大学 一种基于修正ndvi时间序列的大区域农作物全生育期墒情监测方法
CN107909607A (zh) * 2017-12-11 2018-04-13 河北省科学院地理科学研究所 一种年度区域植被覆盖度计算方法

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106908415A (zh) * 2017-02-24 2017-06-30 郑州大学 一种基于修正ndvi时间序列的大区域农作物全生育期墒情监测方法
CN107909607A (zh) * 2017-12-11 2018-04-13 河北省科学院地理科学研究所 一种年度区域植被覆盖度计算方法

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
关舒婧等: "华南地区典型种植园地遥感分类研究", 《地球信息科学》 *
张喜旺等: "基于中高分辨率遥感的植被覆盖度时相变换方法", 《生态学报》 *
杨闫君等: "基于 GF-1/WFV NDVI时间序列数据的作物分类", 《农业工程学报》 *
郑朝菊等: "近15年中国西南地区植被覆盖度动态变化", 《国土资源遥感》 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111695606A (zh) * 2020-05-25 2020-09-22 中国科学院东北地理与农业生态研究所 一种多类型城市绿地分类方法
CN111678871A (zh) * 2020-06-16 2020-09-18 中国气象科学研究院 一种非生长季植被覆盖度遥感估算方法
CN114494844A (zh) * 2021-12-13 2022-05-13 中国气象科学研究院 高海拔区域植被类型识别方法、装置及电子设备

Similar Documents

Publication Publication Date Title
Waldhoff et al. Multi-Data Approach for remote sensing-based regional crop rotation mapping: A case study for the Rur catchment, Germany
Zeng et al. A hybrid approach for detecting corn and soybean phenology with time-series MODIS data
CN110287944B (zh) 基于深度学习的多光谱遥感影像的农作物虫害监测方法
Peña et al. Assessing fruit-tree crop classification from Landsat-8 time series for the Maipo Valley, Chile
Amin et al. Prototyping Sentinel-2 green LAI and brown LAI products for cropland monitoring
Kumar et al. Remote sensing for agriculture and resource management
CN110160992A (zh) 一种基于植被覆盖度时间序列的农作物分类方法
CN110119717A (zh) 一种基于时序ndvi与lst的农作物分类方法
Sankar et al. Non-destructive estimation of leaf area of durian (Durio zibethinus)–An artificial neural network approach
Olanrewaju et al. GGE biplot analysis of genotype× environment interaction and yield stability in Bambara groundnut
Scudiero et al. Workflow to establish time-specific zones in precision agriculture by spatiotemporal integration of plant and soil sensing data
Hentze et al. Evaluating crop area mapping from MODIS time-series as an assessment tool for Zimbabwe’s “fast track land reform programme”
CN110532967A (zh) 一种基于哨兵1号rvi时间序列的农作物分类方法
Backoulou et al. Processed multispectral imagery differentiates wheat crop stress caused by greenbug from other causes
Liu et al. Detecting crop phenology from vegetation index time-series data by improved shape model fitting in each phenological stage
Phan et al. Understanding dense time series of Sentinel-1 backscatter from rice fields: Case study in a province of the Mekong Delta, Vietnam
Yonah et al. Unmanned aerial vehicle-based remote sensing in monitoring smallholder, heterogeneous crop fields in Tanzania
Triscowati et al. Multitemporal remote sensing data for classification of food crops plant phase using supervised random forest
WO2023109652A1 (zh) 水稻种植提取及复种指数监测方法、系统、终端及存储介质
Ganeva et al. Phenotypic traits estimation and preliminary yield assessment in different phenophases of wheat breeding experiment based on UAV multispectral images
Dube et al. Remote sensing of invasive Lantana camara (Verbenaceae) in semiarid savanna rangeland ecosystems of South Africa
Jewan et al. The feasibility of using a low-cost near-infrared, sensitive, consumer-grade digital camera mounted on a commercial UAV to assess Bambara groundnut yield
Ahmed et al. Probability density functions based classification of MODIS NDVI time series data and monitoring of vegetation growth cycle
Bai et al. Estimation of soybean yield parameters under lodging conditions using RGB information from unmanned aerial vehicles
Mangiarotti et al. Can the global modeling technique be used for crop classification?

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20190823

RJ01 Rejection of invention patent application after publication