基于中尺度光谱和时序物候特征提取南方丘陵山区茶园

doi:10.6046/gtzyyg.2019.01.19

摘要
图/表
参考文献
相关文章
Metrics

全文: PDF(6918 KB)

HTML
输出: BibTeX | EndNote (RIS)

摘要

南方丘陵山区茶园空间分布的提取对于南方经济发展和生态环境保护有重要意义。为此提出一种基于中尺度光谱和时序物候特征的茶园提取方法。利用MODIS增强植被指数(enhanced vegetation index,EVI)和归一化植被指数(normalized difference vegetation index,NDVI)数据产品选择Landsat影像的最适时间窗口,使用面向对象方法和决策树分类模型提取初步分类结果,使用MODIS-EVI植被时序数据提取不同植被物候参数,完成茶园分布范围提取。以福建省漳州市和安溪县为研究区进行茶园提取,经检验,总体分类精度达到85.71%,Kappa系数达到0.83,其中茶园的生产者精度为83.72%,用户精度为90.00%; 提取结果与漳州市和安溪县茶园种植面积的公开统计数据接近。结果表明,该方法可获得较高的茶园提取精度。提取结果可以为南方经济发展和政府有关部门对茶园的调控提供一定参考和指导。

	服务

	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	马超
	杨飞
	王学成

关键词 ：遥感, 面向对象方法, 茶园, 物候参数, 决策树

Abstract：

The extraction of the spatial distribution of tea plantations in hilly areas of southern China is of great importance for economic development and ecological environment protection in southern China. Therefore, a method of tea plantation based on mesoscale spectrum and temporal phenology characteristics is proposed. The study used MODIS enhanced vegetation index (EVI) and normalized difference vegetation index (NDVI) data products to select the optimal time window for Landsat images. The preliminary classification results were extracted using the object-oriented method and the decision tree classification model. For extracting the distribution of tea plantation, different vegetation phenology parameters were obtained by using MODIS-EVI vegetation timing data. Verification results showed that the overall classification accuracy reached 85.71% and the Kappa coefficient reached 0.83, with the accuracy of tea plantation producers reaching 83.72% and the user precision reaching 90.00%. The extraction results are close to the open statistics of tea plantation area in Zhangzhou City and Anxi County. The results show that this method can obtain high tea plantation extraction accuracy and the classification results can provide some reference and guidance for the economic development of southern China and the government departments' regulation of the tea plantation.

Key words： remote sensing object-oriented method tea plantations phenological parameters decision tree

收稿日期: 2017-07-24 出版日期: 2019-03-14

TP79S127

基金资助:国家重点研发计划项目"全球变化对资源环境系统影响及脆弱性模拟评估"(2017YFA0604804);中国科学院前沿科学重点研究项目"城市化与生态环境相互作用的全空间地理信息的模拟分析"(QYZDY-SSW-DQC007)

通讯作者: 杨飞

作者简介: 马超(1994-),女,主要研究方向为遥感地学分析。Email: mac.16s@igsnrr.ac.cn。

引用本文:

马超, 杨飞, 王学成. 基于中尺度光谱和时序物候特征提取南方丘陵山区茶园[J]. 国土资源遥感, 2019, 31(1): 141-148.
Chao MA, Fei YANG, Xuecheng WANG. Extracting tea plantations in southern hilly and mountainous region based on mesoscale spectrum and temporal phenological features. Remote Sensing for Land & Resources, 2019, 31(1): 141-148.

链接本文:

https://www.gtzyyg.com/CN/10.6046/gtzyyg.2019.01.19 或 https://www.gtzyyg.com/CN/Y2019/V31/I1/141

Fig.1 研究区遥感影像

Tab.1 数据源介绍

Fig.2 不同空间分辨率数据对比

Fig.3 茶园种植区提取流程

Fig.4 2015年MODIS-NDVI和MODIS-EVI时序曲线

Fig.5 物候参数示意图

Tab.2 不同地物物候参数对比

Fig.6 决策树分类方法构建

Fig.7 茶园分布提取结果

Tab.3 精度评价

Tab.4 统计数据与分类结果对比

[1]	韩旭 . 中国茶叶种植地域的历史变迁研究[D]. 杭州:浙江大学, 2013.
	Han X . A Study on the Changes in Tea Planting Regions in the History of China[D]. Hangzhou:Zhejiang University, 2013.
[2]	陈明枢, 吕居永, 冯廷佺 , 等. 漳州市华安等4个老区县茶产业发展情况调研报告[J]. 福建茶叶, 2013,35(1):2-4. doi: 10.3969/j.issn.1005-2291.2013.01.001
	Chen M S, Lyu J Y, Feng T Q , et al. Investigation report on the development of tea industry in four old areas in Zhangzhou City[J]. Tea in Fujian, 2013,35(1):2-4.
[3]	任冲, 鞠洪波, 张怀清 , 等. 多源数据林地类型的精细分类方法[J]. 林业科学, 2016,52(6):54-65. doi: 10.11707/j.1001-7488.20160607
	Ren C, Ju H B, Zhang H Q , et al. Multi-source data for forest land type precise classification[J]. Scientia Silvae Sinicae, 2016,52(6):54-65.
[4]	高孟绪, 王卷乐, 柏中强 , 等. 基于RapidEye影像的农村居民地遥感监测———以江西省泰和县为例[J]. 国土资源遥感, 2016,28(1):130-135.doi: 10.6046/gtzyyg.2016.01.19. doi: 10.6046/gtzyyg.2016.01.19
	Gao M X, Wang J L, Bai Z Q , et al. Remote sensing monitoring of rural residential land based on RapidEye satellite images:A case study of Taihe County,Jiangxi Province[J]. Remote Sensing for Land and Resources, 2016,28(1):130-135.doi: 10.6046/gtzyyg.2016.01.19.
[5]	Aplin P . Remote sensing:Land cover[J]. Progress in Physical Geography, 2004,28(2):283-293.
[6]	Wang L, Sousa W P, Gong P . Integration of object-based and pixel-based classification for mapping mangroves with IKONOS imagery[J]. International Journal of Remote Sensing, 2004,25(24):5655-5668. doi: 10.1080/014311602331291215
[7]	刘晓娜, 封志明, 姜鲁光 . 基于决策树分类的橡胶林地遥感识别[J]. 农业工程学报, 2013,29(24):163-172,365. doi: 10.3969/j.issn.1002-6819.2013.24.022
	Liu X N, Feng Z M, Jiang L G . Application of decision tree classification to rubber plantations extraction with remote sensing[J]. Transactions of the Chinese Society of Agricultural Engineering, 2013,29(24):163-172,365.
[8]	徐岳仁, 何宏林, 陈立泽 , 等. 基于CBERS数据的福建南平地质灾害动态遥感解译[J]. 国土资源遥感, 2014,26(3):153-159.doi: 10.6046/gtzyyg.2014.03.25. doi: 10.6046/gtzyyg.2014.03.25
	Xu Y R, He H L, Chen L Z , et al. Dynamic remote sensing interpretation of geological disasters in Nanping City of Fujian Province using CBERS serial data[J]. Remote Sensing for Land and Resources, 2014,26(3):153-159.doi: 10.6046/gtzyyg.2014.03.25.
[9]	刘晓娜, 封志明, 姜鲁光 , 等. 西双版纳橡胶林地的遥感识别与数字制图[J]. 资源科学, 2012,34(9):1769-1780.
	Liu X N, Feng Z M, Jiang L G , et al. Rubber plantations in Xishuangbanna:Remote sensing identification and digital mapping[J]. Resources Science, 2012,34(9):1769-1780.
[10]	Rao N R, Kapoor M, Sharma N , et al. Yield prediction and waterlogging assessment for tea plantation land using satellite image-based techniques[J]. International Journal of Remote Sensing, 2007,28(7-8):1561-1576. doi: 10.1080/01431160600904980
[11]	Dihkan M, Guneroglu N, Karsli F , et al. Remote sensing of tea plantations using an SVM classifier and pattern-based accuracy assessment technique[J]. International Journal for Remote Sensing, 2013,34(23):8549-8565. doi: 10.1080/01431161.2013.845317
[12]	Dutta R, Stein A, Patel N R . Delineation of diseased tea patches using MXL and texture based classification[J]. The International Archives of the Photogrammetry,Remote Sensing and Spatial Information Sciences, 2008,37(B4):1693-1700.
[13]	徐伟燕, 孙睿, 金志凤 . 基于资源三号卫星影像的茶树种植区提取[J]. 农业工程学报, 2016,32(s1):161-168. doi: 10.11975/j.issn.1002-6819.2016.z1.023
	Xu W Y, Sun R, Jin Z F . Extracting tea plantations based on ZY-3 satellite data[J]. Transactions of the Chinese Society of Agricultural Engineering, 2016,32(s1):161-168.
[14]	裴志远, 杨邦杰 . 多时相归一化植被指数NDVI的时空特征提取与作物长势模型设计[J]. 农业工程学报, 2000,16(5):20-22. doi: 10.3321/j.issn:1002-6819.2000.05.005
	Pei Z Y, Yang B J . Analysis of multi-temporal and multi-spatial character of NDVI and crop condition models development[J]. Transactions of the Chinese Society of Agricultural Engineering, 2000,16(5):20-22.
[15]	徐爽, 沈润平, 杨晓月 . 利用不同植被指数估算植被覆盖度的比较研究[J]. 国土资源遥感, 2012,24(4):95-100.doi: 10.6046/gtzyyg.2012.04.16. doi: 10.6046/gtzyyg.2012.04.16
	Xu S, Shen R P, Yang X Y . A comparative study of different vegetation indices for estimating vegetation coverage based on the dimidiate pixel model[J]. Remote Sensing for Land and Resources, 2012,24(4):95-100.doi: 10.6046/gtzyyg.2012.04.16.
[16]	Rouse J W J, Haas R H, Schell J A , et al. Monitoring vegetation systems in the great plains with ERTS[J]. Nasa Special Publication, 1973,351:309-317.
[17]	刘昌振, 舒红, 张志 , 等. 基于多尺度分割的高分遥感图像变异函数纹理提取和分类[J]. 国土资源遥感, 2015,27(4):47-53.doi: 10.6046/gtzyyg.2015.04.08. doi: 10.6046/gtzyyg.2015.04.08
	Liu C Z, Shu H, Zhang Z , et al. Variogram texture extraction and classification of high resolution remote sensing images based on multi-resolution segmentation[J]. Remote Sensing for Land and Resources, 2015,27(4):47-53.doi: 10.6046/gtzyyg.2015.04.08.
[18]	Rathcke B, Elizabeth P L . Phenological patterns of terrestrial plants[J]. Annual Review of Ecology and Systematics, 1985,16:179-214. doi: 10.1146/annurev.es.16.110185.001143
[19]	范德芹, 赵学胜, 朱文泉 , 等. 植物物候遥感监测精度影响因素研究综述[J]. 地理科学进展, 2016,35(3):304-319. doi: 10.18306/dlkxjz.2016.03.005
	Fan D Q, Zhao X S, Zhu W Q , et al. Review of influencing factors of accuracy of plant phenology monitoring based on remote sensing data[J]. Progress in Geography, 2016,35(3):304-319.
[20]	李红军, 郑力, 雷玉平 , 等. 基于EOS/MODIS数据的NDVI与EVI比较研究[J]. 地理科学进展, 2007,26(1):26-32. doi: 10.3969/j.issn.1007-6301.2007.01.003
	Li H J, Zheng L, Lei Y P , et al. Comparison of NDVI and EVI based on EOS/MODIS data[J]. Progress in Geography, 2007,26(1):26-32.
[21]	王正兴, 刘闯 , Huete A. 植被指数研究进展:从AVHRR-NDVI到MODIS-EVI[J]. 生态学报, 2003,23(5):979-987. doi: 10.3321/j.issn:1000-0933.2003.05.020
	Wang Z X, Liu C, Huete A . From AVHRR-NDVI to MODIS-EVI:Advances in vegetation index research[J]. Acta Ecologica Sinica, 2003,23(5):979-987.
[22]	辜智慧 . 中国农作物复种指数的遥感估算方法研究——基于SPOT/VGT多时相NDVI遥感数据[D]. 北京:北京师范大学, 2003.
	Gu Z H . A Study of Calculating Multiple Cropping Index of Crop in China Using SPOT/VGT Multi Temporal NDVI Data[D]. Beijing:Beijing Normal University, 2003.
[23]	王学成, 杨飞, 高星 , 等. 基于NDVI阈值法的森林冰冻受灾范围精确提取[J]. 地球信息科学学报, 2017,19(4):549-558. doi: 10.3969/j.issn.1560-8999.2017.04.013
	Wang X C, Yang F, Gao X , et al. Precise extraction of damaged forest range caused by ice-snow frozen disaster based on the NDVI threshold method[J]. Journal of Geo-Information Science, 2017,19(4):549-558.
[24]	康峻, 侯学会, 牛铮 , 等. 基于拟合物候参数的植被遥感决策树分类[J]. 农业工程学报, 2014,30(9):148-156. doi: 10.3969/j.issn.1002-6819.2014.09.019
	Kang J, Hou X H, Niu Z , et al. Decision tree classification based on fitted phenology parameters from remotely sensed vegetation data[J]. Transactions of the Chinese Society of Agricultural Engineering, 2014,30(9):148-156.
[25]	平跃鹏 . 基于MODIS时间序列地表物候特征分析及农作物分类[D]. 哈尔滨:哈尔滨师范大学, 2016.
	Ping Y P . Crop Classification Based on Analysis of Phenological Characteristics of MODIS Times Series[D]. Harbin:Harbin Normal University, 2016.
[26]	Savitzky A, Golay M J E, . Smoothing and differentiation of data by simplified least squares procedures.[J]. Analytical Chemistry, 1964,36(8):1627-1639. doi: 10.1021/ac60214a047
[27]	Lloyd D . A phenological classification of terrestrial vegetation cover using shortwave vegetation index imagery[J]. International Journal of Remote Sensing, 1990,11(12):2269-2279. doi: 10.1080/01431169008955174

[1]	李伟光, 侯美亭. 植被遥感时间序列数据重建方法简述及示例分析[J]. 自然资源遥感, 2022, 34(1): 1-9.
[2]	丁波, 李伟, 胡克. 基于同期光学与微波遥感的茅尾海及其入海口水体悬浮物反演[J]. 自然资源遥感, 2022, 34(1): 10-17.
[3]	高琪, 王玉珍, 冯春晖, 马自强, 柳维扬, 彭杰, 季彦桢. 基于改进型光谱指数的荒漠土壤水分遥感反演[J]. 自然资源遥感, 2022, 34(1): 142-150.
[4]	张秦瑞, 赵良军, 林国军, 万虹麟. 改进遥感生态指数的宜宾市三江汇合区生态环境评价[J]. 自然资源遥感, 2022, 34(1): 230-237.
[5]	贺鹏, 童立强, 郭兆成, 涂杰楠, 王根厚. 基于地形起伏度的冰湖溃决隐患研究——以希夏邦马峰东部为例[J]. 自然资源遥感, 2022, 34(1): 257-264.
[6]	刘文, 王猛, 宋班, 余天彬, 黄细超, 江煜, 孙渝江. 基于光学遥感技术的冰崩隐患遥感调查及链式结构研究——以西藏自治区藏东南地区为例[J]. 自然资源遥感, 2022, 34(1): 265-276.
[7]	王茜, 任广利. 高光谱遥感异常信息在阿尔金索拉克地区铜金矿找矿工作中的应用[J]. 自然资源遥感, 2022, 34(1): 277-285.
[8]	吕品, 熊丽媛, 徐争强, 周学铖. 基于FME的矿山遥感监测矢量数据图属一致性检查方法[J]. 自然资源遥感, 2022, 34(1): 293-298.
[9]	张大明, 张学勇, 李璐, 刘华勇. 一种超像素上Parzen窗密度估计的遥感图像分割方法[J]. 自然资源遥感, 2022, 34(1): 53-60.
[10]	薛白, 王懿哲, 刘书含, 岳明宇, 王艺颖, 赵世湖. 基于孪生注意力网络的高分辨率遥感影像变化检测[J]. 自然资源遥感, 2022, 34(1): 61-66.
[11]	宋仁波, 朱瑜馨, 郭仁杰, 赵鹏飞, 赵珂馨, 朱洁, 陈颖. 基于多源数据集成的城市建筑物三维建模方法[J]. 自然资源遥感, 2022, 34(1): 93-105.
[12]	于新莉, 宋妍, 杨淼, 黄磊, 张艳杰. 结合空间约束的卷积神经网络多模型多尺度船企场景识别[J]. 自然资源遥感, 2021, 33(4): 72-81.
[13]	李轶鲲, 杨洋, 杨树文, 王子浩. 耦合模糊C均值聚类和贝叶斯网络的遥感影像后验概率空间变化向量分析[J]. 自然资源遥感, 2021, 33(4): 82-88.
[14]	艾璐, 孙淑怡, 李书光, 马红章. 光学与SAR遥感协同反演土壤水分研究进展[J]. 自然资源遥感, 2021, 33(4): 10-18.
[15]	李特雅, 宋妍, 于新莉, 周圆锈. 卫星热红外温度反演钢铁企业炼钢月产量估算模型[J]. 自然资源遥感, 2021, 33(4): 121-129.

Viewed

Full text

Abstract

Cited

Shared

Discussed