ass日本风韵熟妇pics男人扒开女人屁屁桶到爽|扒开胸露出奶头亲吻视频|邻居少妇的诱惑|人人妻在线播放|日日摸夜夜摸狠狠摸婷婷|制服 丝袜 人妻|激情熟妇中文字幕|看黄色欧美特一级|日本av人妻系列|高潮对白av,丰满岳妇乱熟妇之荡,日本丰满熟妇乱又伦,日韩欧美一区二区三区在线

基于多時相Sentinel-2A的縣域農作物分類
CSTR:
作者:
作者單位:

作者簡介:

通訊作者:

中圖分類號:

基金項目:

甘肅農業(yè)大學科技創(chuàng)新基金-學科建設基金項目(GAU-XKJS-2018-208)和國家自然科學基金項目(31760693)


Fine Classification of County Crops Based on Multi-temporal Images of Sentinel-2A
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 圖/表
  • |
  • 訪問統(tǒng)計
  • |
  • 參考文獻
  • |
  • 相似文獻
  • |
  • 引證文獻
  • |
  • 資源附件
  • |
  • 文章評論
    摘要:

    利用遙感技術精準地獲取區(qū)域農作物種植結構數(shù)據(jù),,對指導農業(yè)生產,、制定農業(yè)政策具有重要意義,。以景泰縣為研究區(qū),,以多時相Sentinel-2A遙感影像為數(shù)據(jù)源,,計算時序歸一化植被指數(shù)(Normalized difference vegetation index,,NDVI)和紅邊歸一化植被指數(shù)(Red edge normalized vegetation index,,RENDVI)及其組合特征(NDVI+RENDVI,、NDVI-RENDVI和NDVI&RENDVI),,分析作物特征曲線,,并采用隨機森林法分別以5種特征參數(shù)作為分類特征對研究區(qū)農作物進行精細分類。結果表明:根據(jù)形態(tài)特征,,研究區(qū)農作物特征值曲線可劃分為3種類型:高值型(玉米,、水稻、胡麻和馬鈴薯),、低值型(洋蔥,、大棚作物和砂田瓜果)和開口型(春小麥、春小麥-秋油葵),。高值型和低值型可在7,、8月影像中區(qū)分,開口型和前兩種類型在5月和9月影像上的特征值有明顯差異,。3種類型內的作物可以通過不同時相影像區(qū)分,,高值型的4種作物在9月影像上通過成熟期差異可以區(qū)分;低值型的3種作物的特征值差異在全年影像上都可以明顯體現(xiàn),;開口型的兩種作物利用9月影像可以明顯區(qū)分,。利用NDVI、RENDVI,、NDVI+RENDVI,、NDVI-RENDVI和NDVI&RENDVI 5種特征分類的總體精度分別為82.14%、78.16%,、81.17%,、75.64%和86.20%,Kappa系數(shù)分別為0.78,、0.74,、0.77、0.71和0.83,,總體精度和Kappa系數(shù)由大到小依次為NDVI&RENDVI,、NDVI,、NDVI+RENDVI、RENDVI,、NDVI-RENDVI,說明RENDVI輔助NDVI可以有效提高分類精度(精度較僅用NDVI提高4.06個百分點),。選擇合適的時期和分類特征,利用Sentinel-2A特有的紅邊波段數(shù)據(jù)及其較高的空間分辨率在縣域農作物精細分類上具有較好的精度,。

    Abstract:

    It is a challenge to acquire accurately regional crop structure information by using remote sensing technology at county scale for the possible reasons of cultivated land fragmentation, scattered distribution and complex planting structure. Jingtai County was taken as the research area, and multitemporal Sentinel-2A remote sensing image was used as the data source to construct the time sequences of five kinds of feature parameters, which were normalized difference vegetation index (NDVI), red edge normalized vegetation index (RENDVI), and their combinations (NDVI+RENDVI, NDVI-RENDVI as well as NDVI&RENDVI). The random forest method was used to classify the crops based on five kinds of feature parameters. The results were as follows: according to the shape, the multitemporal VI (vegetation index) feature curve of crops was divided into three types, which were called highlevel, including corn, rice, flax and potato, lowlevel, including onion, greenhouse crops and sandyfield crops, and openend type, including spring wheat and spring wheatautumn oil sunflowers, respectively. Openend type could be identified by images of May or September, meanwhile, highlevel type and lowlevel type could be distinguished by images of July or August. Among each type, crops could be identified by using images of different times. For highlevel type, four crops showed significant differences in the images of mature period, for lowlevel type, images in September could supply much information to distinguish two crops, and as for as openend type, there were significant differences for three crops all through four growing stages. The sequence of overall accuracy of classification results by five kinds of feature parameters from large to small was NDVI&RENDVI, NDVI, NDVI+RENDVI, RENDVI and NDVI-RENDVI. 

    參考文獻
    相似文獻
    引證文獻
引用本文

吳靜,呂玉娜,李純斌,李全紅.基于多時相Sentinel-2A的縣域農作物分類[J].農業(yè)機械學報,2019,50(9):194-200. WU Jing, Lü Yu’na, LI Chunbin, LI Quanhong. Fine Classification of County Crops Based on Multi-temporal Images of Sentinel-2A[J]. Transactions of the Chinese Society for Agricultural Machinery,2019,50(9):194-200.

復制
分享
文章指標
  • 點擊次數(shù):
  • 下載次數(shù):
  • HTML閱讀次數(shù):
  • 引用次數(shù):
歷史
  • 收稿日期:2019-06-03
  • 最后修改日期:
  • 錄用日期:
  • 在線發(fā)布日期: 2019-09-10
  • 出版日期:
文章二維碼