CN112560659A - 一种区域橡胶林遥感识别方法 - Google Patents

一种区域橡胶林遥感识别方法 Download PDF

Info

Publication number
CN112560659A
CN112560659A CN202011457408.3A CN202011457408A CN112560659A CN 112560659 A CN112560659 A CN 112560659A CN 202011457408 A CN202011457408 A CN 202011457408A CN 112560659 A CN112560659 A CN 112560659A
Authority
CN
China
Prior art keywords
rubber forest
forest
rubber
vegetation
landsat
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
Application number
CN202011457408.3A
Other languages
English (en)
Other versions
CN112560659B (zh
Inventor
肖池伟
封志明
李鹏
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.)
Institute of Geographic Sciences and Natural Resources of CAS
Original Assignee
Institute of Geographic Sciences and Natural Resources 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 Institute of Geographic Sciences and Natural Resources of CAS filed Critical Institute of Geographic Sciences and Natural Resources of CAS
Priority to CN202011457408.3A priority Critical patent/CN112560659B/zh
Publication of CN112560659A publication Critical patent/CN112560659A/zh
Application granted granted Critical
Publication of CN112560659B publication Critical patent/CN112560659B/zh
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/10Terrestrial scenes
    • G06V20/188Vegetation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/53Querying
    • G06F16/535Filtering based on additional data, e.g. user or group profiles
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/587Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/40Extraction of image or video features
    • G06V10/44Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02ATECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Library & Information Science (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Image Processing (AREA)
  • Cultivation Of Plants (AREA)

Abstract

本发明公开了一种区域橡胶林遥感识别方法,包括以下步骤:筛选橡胶林与其他地类的兴趣点和兴趣区,生成橡胶林样本点图库;构建橡胶林和其他地类的变化曲线,根据NDVI动态曲线判别橡胶林和其他地类的差异,确定橡胶林物候期;结合获取的气象站点逐日的降水、气温数据,基于橡胶林落叶和新叶萌生现象的发生时间窗口信息,引入Landsat相应波段与植被-水分指数产品,对比橡胶林的物候差异;依据Landsat‑NBR与Landsat‑NDMI等多个植被-水分指数两两组合,对橡胶林落叶期和生叶期组合的植被-水分指数进行归一化处理,结合归一化结果和植被图层掩膜提取橡胶林。本发明的优点是:充分考虑区域物候差异且兼顾纹理特征,能全面提取胶林分布信息,为区域层面橡胶林监测提供有力支撑。

Description

一种区域橡胶林遥感识别方法
技术领域
本发明涉及橡胶林遥感识别技术领域,特别涉及一种基于MODIS/Landsat植被指数和物候特征的区域橡胶林遥感识别方法。
背景技术
天然橡胶作为国防和经济建设不可或缺的战略物质,也是热带地区的重要支柱产业和脱贫致富的主要途径。橡胶林扩展已成为全球天然橡胶重要产区土地利用/覆盖变化(LUCC)的主要表现形式和重要动因。然而,在区域层面对橡胶林的地域特征、动态变化与扩展规律等科学问题缺乏系统、深入研究。
橡胶林遥感调查最早见于上世纪40年代的飞机勘探。橡胶树在雨季枝繁叶茂,与其他常绿植被的光谱反射特征非常相似,但在每年旱季因其经历从落叶到新叶萌生的过程而与周围地物(特别是自然林)存在明显差异。热带地区橡胶林遥感识别的突破口是其旱季落叶和新叶萌生过程的植被-水分周期性变化。橡胶林的独特物候时间窗口及Landsat等光学卫星旱季高质量成像情况,使得观测历史较长的Landsat影像成为开展橡胶林物候遥感反演的最佳数据源。
地方尺度橡胶林遥感监测较早见于80年代,以最大似然、支持向量机、决策树和随机森林等方法为主。比较而言,物候算法因其充分考虑了橡胶树(林)关键生育期的独特生理现象(落叶-新叶萌生)而显示出巨大潜力。由于橡胶林物候差异,利用固定时间窗口影像难以准确揭示区域层面橡胶林的总体分布格局。如申请者2020年1月上中旬在越南由北向南的实地考察了解到北部橡胶树尚处于绿叶阶段,而南部则普遍处于落叶期。由此,准确识别、快捷方便和大范围监测橡胶林物候期变化显得尤为重要,并需要加强植被-水分变化与橡胶林物候特征的关系及其区域差异研究。
Landsat等遥感数据产品共享政策及其分析就绪数据(ARD/2018)产品与遥感大数据平台(Google Earth Engine,GEE)的推出,将为回溯橡胶林时空动态变化提供可靠数据源。得益于此,在像元尺度基于橡胶林落叶-新叶萌生的物候遥感方法探索方兴未艾,并在减少数据需求和提高分类精度具有较大优势,如单窗口、双窗口、三窗口、阈值法、变化率比值法和改进型归一化烧垦指数等。但是,橡胶林物候遥感算法仍有很大完善空间。与波段归一化相比,植被-水分指数组合减少了因饱和度与地形变化等噪音引起的误差,其应用前景广阔。该组合方法的实现需预先准确揭示橡胶林落叶和新叶萌生发生的时间信息及其差异,特别是大规模地区。
现有技术公开了橡胶林传统遥感监测方法包括监督分类、非监督分类、光谱混合分类、面向对象、逻辑回归和机器学习(如支持向量机、随机森林和神经网络)等。比较而言,物候算法因其充分考虑了橡胶树(林)关键生育期的独特生理现象(落叶-新叶萌生)而显示出巨大潜力,由于橡胶林物候差异,利用固定时间窗口Landsat影像难以准确揭示区域层面橡胶林的总体分布格局。
基于指数组合和物候特征的橡胶林遥感监测方法,具体步骤如下:
(1)基于逐日MODIS-NDVI数据,判定橡胶林的落叶期和生叶期
(2)分别选取橡胶林落叶期和生叶期2景Landsat影像,从波段到植被指数;
(3)对落叶期和生叶期的植被指数进行归一化;
(4)对归一化后的指数进行重归一化,然后提取。
上述现有技术橡胶林传统遥感监测方法的缺陷是1、未充分考虑橡胶林生理与物候特征及其区域差异,工作量大,2、误差较大、混合像元。
发明内容
本发明针对现有技术的缺陷,提供了一种区域橡胶林遥感识别方法,解决了现有技术中存在的缺陷。
为了实现以上发明目的,本发明采取的技术方案如下:
一种区域橡胶林遥感识别方法,包括以下步骤:
步骤1,基于野外采样照片和GPS点位,确定橡胶林种植密集区,通过样带方法筛选橡胶林与其他地类的兴趣点(POIs)和兴趣区(ROIs),并生成橡胶林样本点图库;
步骤2,利用逐日MODIS-NDVI指数产品数据,构建橡胶林和其他地类的变化曲线,据NDVI动态曲线判别橡胶林和其他地类的差异;
步骤3,依据橡胶林NDVI指数动态曲线,利用小波分析方法自动检测橡胶林落叶-新叶萌生前后的突变阈值(波峰/谷),据此确定橡胶林物候期;
步骤4,结合获取的气象站点逐日的降水、气温数据,基于步骤3确定的橡胶林落叶和新叶萌生现象的发生时间窗口信息,引入免费发布的Landsat相应波段(如NIR、SWIR等)与植被-水分指数(如NBR、NDVI、NDMI等)产品,并对比橡胶林从南到北、从东到西的物候差异。
步骤5,依据Landsat-NBR与Landsat-NDMI等植被-水分指数两两组合,对橡胶林落叶期和生叶期组合的植被-水分指数进行归一化处理,结合归一化结果和植被图层掩膜提取橡胶林。
与现有技术相比,本发明的优点在于:
充分考虑区域物候差异且兼顾纹理特征,能全面提取胶林分布信息,为区域层面橡胶林监测提供有力支撑。
附图说明
图1是本发明实施例遥感识别方法流程图。
具体实施方式
为使本发明的目的、技术方案及优点更加清楚明白,以下根据附图并列举实施例,对本发明做进一步详细说明。
如图1所示,一种区域橡胶林遥感识别方法,包括:
1、基于野外景观定位照片与GE高清影像,大致确定橡胶林种植密集区,进而通过样带方法筛选橡胶林与其他地类(如自然林)的兴趣点/样本点(POIs)、兴趣区/样本区(ROIs),利用MODIS-NDVI植被指数产品数据,揭示年际/年内橡胶林和其他地类(自然林)的动态变化,据此确定橡胶林与其他地类的差异。
2、依据橡胶林NDVI时序动态曲线,利用小波分析等方法自动检测橡胶林落叶-新叶萌生前后的突变阈值(波峰/谷);结合与气象站点逐日的降水、气温数据,获取橡胶林落叶和新叶萌生现象的发生时间窗口信息,并分析植被-水分指数与其物候特征的关系。在此基础上引入Landsat相应波段与植被-水分指数,对比研究区域尺度(如中南半岛)橡胶林从南到北、从东到西的物候差异。
3、依据Landsat植被-水分指数组合特征,发展一套即基于橡胶林从落叶到新叶萌生的物候特征,又充分考虑区域物候差异且兼顾纹理特征(如北部山区为“圈层”,南部平原为“垄状”),亦能全面提取胶林分布信息的遥感识别算法。
本领域的普通技术人员将会意识到,这里所述的实施例是为了帮助读者理解本发明的实施方法,应被理解为本发明的保护范围并不局限于这样的特别陈述和实施例。本领域的普通技术人员可以根据本发明公开的这些技术启示做出各种不脱离本发明实质的其它各种具体变形和组合,这些变形和组合仍然在本发明的保护范围内。

Claims (1)

1.一种区域橡胶林遥感识别方法,其特征在于,包括以下步骤:
步骤1,基于野外采样照片和GPS点位,确定橡胶林种植密集区,通过样带方法筛选橡胶林与其他地类的兴趣点和兴趣区,并生成橡胶林样本点图库;
步骤2,利用逐日MODIS-NDVI指数产品数据,构建橡胶林和其他地类的变化曲线,根据NDVI动态曲线判别橡胶林和其他地类的差异;
步骤3,依据橡胶林NDVI指数动态曲线,利用小波分析方法自动检测橡胶林落叶-新叶萌生前后的突变阈值,波峰/谷,据此确定橡胶林物候期;
步骤4,结合获取的气象站点逐日的降水、气温数据,基于步骤3确定的橡胶林落叶和新叶萌生现象的发生时间窗口信息,引入Landsat相应波段与植被-水分指数产品,相应波段为NIR和SWIR,植被-水分指数包括:NBR、NDVI和NDMI,并对比橡胶林从南到北、从东到西的物候差异;
步骤5,依据Landsat-NBR与Landsat-NDMI植被-水分指数两两组合,对橡胶林落叶期和生叶期组合后的植被-水分指数进行归一化处理,结合归一化结果和植被图层掩膜提取橡胶林。
CN202011457408.3A 2020-12-11 2020-12-11 一种区域橡胶林遥感识别方法 Active CN112560659B (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011457408.3A CN112560659B (zh) 2020-12-11 2020-12-11 一种区域橡胶林遥感识别方法

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011457408.3A CN112560659B (zh) 2020-12-11 2020-12-11 一种区域橡胶林遥感识别方法

Publications (2)

Publication Number Publication Date
CN112560659A true CN112560659A (zh) 2021-03-26
CN112560659B CN112560659B (zh) 2023-02-03

Family

ID=75062926

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011457408.3A Active CN112560659B (zh) 2020-12-11 2020-12-11 一种区域橡胶林遥感识别方法

Country Status (1)

Country Link
CN (1) CN112560659B (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113723254A (zh) * 2021-08-23 2021-11-30 三明学院 一种毛竹林分布的识别方法、装置、设备和存储介质
CN114332628A (zh) * 2022-01-05 2022-04-12 中国科学院地理科学与资源研究所 一种基于典型物候及膜网特征的生姜快速遥感提取方法

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110047867A1 (en) * 2003-11-07 2011-03-03 Holland Kyle H Plant treatment based on a water invariant chlorophyll index
CN111652092A (zh) * 2020-05-19 2020-09-11 中南林业科技大学 基于Sentinel-2A数据监测森林覆盖变化的方法

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110047867A1 (en) * 2003-11-07 2011-03-03 Holland Kyle H Plant treatment based on a water invariant chlorophyll index
CN111652092A (zh) * 2020-05-19 2020-09-11 中南林业科技大学 基于Sentinel-2A数据监测森林覆盖变化的方法

Non-Patent Citations (7)

* Cited by examiner, † Cited by third party
Title
WENANG ANUROGO ET AL.: "Pixel-based Remote Sensing Data Processing for Estimating Rubber Plantations Productivity", 《IEEE XPLORE》 *
于信芳 等: "基于MODIS NDVI数据的东北森林物候期监测", 《资源科学》 *
任冲 等: "多源数据林地类型的精细分类方法", 《林业科学》 *
寇卫利: "基于多源遥感的橡胶林时空演变研究", 《中国博士学位论文全文数据库 农业科技辑》 *
廖谌婳 等: "西双版纳橡胶林面积遥感监测和时空变化", 《农业工程学报》 *
李宇宸 等: "基于Google Earth Engine的中老缅交界区橡胶林分布遥感提取", 《农业工程学报》 *
陈小敏 等: "海南岛天然橡胶林春季物候期的遥感监测", 《中国农业气象》 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113723254A (zh) * 2021-08-23 2021-11-30 三明学院 一种毛竹林分布的识别方法、装置、设备和存储介质
CN114332628A (zh) * 2022-01-05 2022-04-12 中国科学院地理科学与资源研究所 一种基于典型物候及膜网特征的生姜快速遥感提取方法
CN114332628B (zh) * 2022-01-05 2023-06-16 中国科学院地理科学与资源研究所 一种基于典型物候及膜网特征的生姜快速遥感提取方法

Also Published As

Publication number Publication date
CN112560659B (zh) 2023-02-03

Similar Documents

Publication Publication Date Title
Peña-Barragán et al. Object-based crop identification using multiple vegetation indices, textural features and crop phenology
George et al. Forest tree species discrimination in western Himalaya using EO-1 Hyperion
Bunting et al. The delineation of tree crowns in Australian mixed species forests using hyperspectral Compact Airborne Spectrographic Imager (CASI) data
CN112560659B (zh) 一种区域橡胶林遥感识别方法
CN113033670A (zh) 一种基于Sentinel-2A/B数据的水稻种植面积提取方法
Marcinkowska-Ochtyra et al. Subalpine and alpine vegetation classification based on hyperspectral APEX and simulated EnMAP images
US20220392215A1 (en) System and Method for Mapping Land Cover Types with Landsat, Sentinel-1, and Sentinel-2 Images
El Hoummaidi et al. Using unmanned aerial systems and deep learning for agriculture mapping in Dubai
CN109063660B (zh) 一种基于多光谱卫星影像的作物识别方法
CN116310840A (zh) 一种融合多关键物候期光谱特征的冬小麦遥感识别方法
Medina Machin et al. Vegetation species mapping in a coastal-dune ecosystem using high resolution satellite imagery
CN114581768A (zh) 一种作物倒伏无人机监测方法及装置
CN116091938A (zh) 一种针对单季稻种植面积的多源遥感监测方法
Som-ard et al. Mapping of crop types in 1989, 1999, 2009 and 2019 to assess major land cover trends of the Udon Thani Province, Thailand
CN115294460A (zh) 雷竹林退化程度确定方法、介质和电子设备
CN111898681B (zh) 一种基于遥感云平台与决策树的火烧迹地精细提取方法
CN111582035B (zh) 一种果树树龄识别方法、装置、设备及存储介质
Thenkabail et al. Hyperspectral narrowband data propel gigantic leap in the earth remote sensing
Susantoro et al. Impact of oil and gas field in sugar cane condition using landsat 8 in Indramayu area and its surrounding, West Java province, Republic of Indonesia
CN112179853A (zh) 基于影像阴影去除的果树冠层氮素含量遥感反演方法及系统
Dai et al. Object-oriented classification of rubber plantations from Landsat satellite imagery
Yoshikawa et al. Estimating variable acreage of cultivated paddy fields from preceding precipitation in a tropical watershed utilizing Landsat TM/ETM
Mezzi et al. Olive Tree Classification and Inventory with Medium Resolution Multi-spectral Satellite Imagery
Sudianto et al. Classification of Sugarcane Area Using Landsat 8 and Random Forest based on Phenology Knowledge
Varmaghani et al. Early‐season classification of corn and soybean using bayesian discriminant analysis on satellite images

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant