基于时差特征与随机森林的水稻种植面积提取

doi:10.11873/j.issn.1004-0323.2016.6.1140

遥感技术与应用

2016, Vol. 31

Issue (6): 1140-1149 DOI: 10.11873/j.issn.1004-0323.2016.6.1140

遥感应用

基于时差特征与随机森林的水稻种植面积提取

雷小雨¹,卓莉¹,叶涛²,陶海燕¹,王芳³

(1.中山大学地理科学与规划学院,广东省城市化与地理环境空间模拟重点实验室,
综合地理信息研究中心,广东广州 510275;
2.北京师范大学地表过程与资源生态国家重点实验室,北京 100875;
3.广州大学地理科学学院,广东广州 510006)

A Paddy Rice Planting Area Extraction Method Using Random Forest based on Multi-temporal Differences

Lei Xiaoyu¹,Zhuo Li¹,Ye Tao²,Tao Haiyan¹,Wang Fang³

(1.Guangdong Provincial Key Laboratory of Urbanization and Geo\|simulation,
Center of Integrated Geographi Information Analysis,School of Geography and Planning,
Sun Yat\|sen University,Guangzhou 510275,China;
2.State Key Laboratory of Earth Surface Processes and Resource Ecology,
Beijing Normal University,Beijing 100875,China;
3.School of Geography Science,Guangzhou University,Guangzhou 510006,China)

全文: PDF(8719 KB)

摘要：

准确提取水稻种植面积是探讨气候变化背景下水稻生产与粮食安全的重要前提。我国南方的水稻种植区域,地块破碎且受云雨天气影响严重,如何充分利用有限时相的数据获得较高精度的水稻面积提取是亟需解决的关键问题。提出了一种利用两个时相的数据,通过构建差值特征突出水稻物候变化的特点,并与随机森林算法结合高精度提取水稻种植面积的方法。将之应用于湖南省常德市鼎城区的水稻种植面积提取,结果表明:采用本方法进行水稻提取的最终总体精度达到93.01%,Kappa系数0.91,与单时相提取结果相比,总体精度提高了近3%。为了进一步分析差值特征对其他分类器的改进效果,分别将差值特征与决策树和随机森林组合,并分析了两种组合提取水稻的精度。研究发现构建的差值特征能够有效反映植物的生长状况,增加地物的可区分性,可为对象的分割及分类提供更多有用的信息,能够有效改善水稻种植面积的提取精度。


关键词： 水稻提取; 特征波段; 多时相; 差值波段

Abstract:

To accurately extract the growing area of paddy rice is a significant premise of paddy rice production and food security under the background of climate change.based on the current situation that paddy rice extraction is beset with difficulties in southern china,where clouds and rain appear in high frequency during growing seaon,how to take full advantage of the limited images to obtain accurate paddy rice planting area is a desiderated problem.In this study,we combined remotely sensed data from two different dates and brought out D\|value bands,using object\|oriented Random Forest to achieve the goal of rice extraction.The D\|value bands,indicating the difference between a character derived from two different time phases,can be generated from traditional characteristic bands including vegetation indexes,water index,prominent component analysis and Tasseled Cap results,as well as the original bands.We applied this method to extract paddy rice planting area in Dingcheng District,Changde,Hunnan Province,China,and results show that,the accuracy of paddy rice extraction was improved to 93% by 3 percent compared with single\|phased method,and the kappa coefficient reaches 91 in the study area.To further analyze the effect of D\|value bands in other classifiers,we compared the accuracy of combination of D\|value bands with decision tree and Random Forest,separately.Results show that the D\|value bands provides infromation in both subject segementation and classification,which can effectively improve the accuracy of paddy rice planting area extraction.

Key words: Crop extraction Characteristic bands Multi-temporal D-value bands

收稿日期: 2015-08-08 出版日期: 2016-12-30

TP 75

基金资助:

国家自然科学基金面上项目“基于遥感与智能优化方法的承灾体信息提取及分布模拟研究”（41371499）。

通讯作者: 卓莉（1973-），女，湖南张家界人，副教授，主要从事资源环境遥感与地理信息系统研究。Email：zhuoli@mail.sysu.edu.cn。

作者简介: 雷小雨（1992-），女，陕西西安人，硕士研究生，主要从事植被遥感研究。Email：ileixiaoyu@126.com。

	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
	雷小雨
	卓莉
	叶涛
	陶海燕
	王芳

引用本文:

雷小雨,卓莉,叶涛,陶海燕,王芳. 基于时差特征与随机森林的水稻种植面积提取[J]. 遥感技术与应用, 2016, 31(6): 1140-1149.

Lei Xiaoyu,Zhuo Li,Ye Tao,Tao Haiyan,Wang Fang. A Paddy Rice Planting Area Extraction Method Using Random Forest based on Multi-temporal Differences. Remote Sensing Technology and Application, 2016, 31(6): 1140-1149.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2016.6.1140 或 http://www.rsta.ac.cn/CN/Y2016/V31/I6/1140

［1］Li Yan,Peng Shaolin,Liao Qifang,et al.Rice Yield Estimation in Regional Scale by Using Radarsat SNB SAR Images［J］.Advances in Earth Science,2013,18(1):109115.［李岩,彭少麟,廖其芳,等.Radarsat SNB SAR数据在大面积水稻估产中的应用研究［J］.地球科学进展,2013,18(1):109115.］

［2］Liu Jianhong,Zhu Wenquan,Sun Guannan,et al.Endmember Abundance Calibration Method for Paddy Rice Area Extraction from MODIS Data based on Independent Component Analysis［J］.Transaction of the Chinese Society of Agricultural Engineering,2012,28(9):103108.［刘建红,朱文泉,孙冠楠,等.MODIS水稻面积提取中独立成分端元丰度校正办法［J］.农业工程学报,2012,28(9):103108.］

［3］Huang Jingfeng,Wang Renchao,Jiang Hengxian,et al.Selection of Optimum Periods for Rice Estimation Using Remote Sensing Data based on GIS［J］.Chinese Journal of Applied Ecology,2002,13(3):290294.［黄敬峰,王人潮,蒋亨显,等.基于GIS的浙江省水稻遥感估产最佳时相选择［J］.应用生态学报,2002,13(3):290294.］

［4］Li Weiguo,Li Bingbai,Shi Cunlin.Research Progress in Rice Condition Monitoring based on Growth Model and Remote Sensing［J］.Chinese Agricultural Science Bulletin,2006,22(9):457461.［李卫国,李秉柏,石村林.基于模型和遥感的水稻长势监测研究进展［J］.中国农业通报,2006,22(9):457461.］

［5］Zheng Changchun,Wang Xiuzhen,Huang Jingfeng.Mapping Paddy Rice Planting Area in Zhejing Province Using Multitemporal MODIS Images［J］.Journal of Zhejiang University(Agric & LifeSci),2009,35(1):98104.［郑长春,王秀珍,黄敬峰.多时相MODIS影像的浙江省水稻种植面积信息提取方法研究［J］.浙江大学学报(农业与生命科学版),2009,35(1):98104.］

［6］Tang Yanlin,Huang Jingfeng,Wang Renchao,et al.Comparison of Yield Estimation Simulated Models of Rice by Remote Sensing［J］.Transactions of the Chinese Society of Agricultural Engineering,2004,20(1):166171.［唐延林,黄敬峰,王人潮,等.水稻遥感估产模拟模式比较［J］.农业工程学报,2004,20(1):166171.］

［7］Li Yuzhu,Zeng Yan.Study on Methods of Rice Planting Area Estimation at Regional Scale Using NOAA/AVHRR Data［J］.Journal of Remote Sensing,1998,2(2):125130.［李郁竹,曾燕.应用NOAA/AVHRR数据测算局地水稻种植面积方法研究［J］.遥感学报,1998,2(2):125130.］

［8］QiuXinfa,Zeng Yan.Estimation of Rice Planting Area by Virtue of NOAA/AVHRR Thermal Infrared Data［J］.Journal of Nanjing Institute of Meterology,2000,23(1):2428.［邱新法,曾燕.中红外和热红外在测算水稻种植面积上的应用［J］.南京气象学院学报,2000,23(1):2428.］

［9］Liu Dan,Yu Chenglong,Li Shuai,et al.Rice Planting Extraction in Northern Heilongjiang Province based on Remote Sensing［J］.Chinese Agricultural Science Bulletin,2013,29(27):3034.［刘丹,于成龙,李帅,等.基于遥感的黑龙江省东部水稻种植信息提取［J］.中国农学通报,2013,29(27):3034.］〖JP〗

［10］Wang Lin,Jing Yuanshu,Yang Shenbin.Study on Extraction of Rice Cropping Area Using Multitemporal Remote Sensing Data［J］.Chinese Journal of Agricultural Resources and Regional Planning,2013,34(2):2025.［王琳,景元书,杨沈斌.基于多时相遥感数据提取水稻种植面积的研究［J］.中国农业资源与区划,2013,34(2):2025.］

［11］Zhang Youshui,Yuan Lifeng,Yao Yonghui.Study on Extraction of Paddy Rice Fields from Multitemporal MODIS Images［J］.Journal of Remote Sensing,2007,11(2):282288.［张友水,原立峰,姚永慧.多时相MODIS影像水田信息提取研究［J］.遥感学报,2007,11(2):282288.］

［12］Yang Xiaohuan,Zhang Xiangping,Jiang Dong.Extraction of Multicrop Planting Areas from MODIS Data［J］.Resource Science,2004,26(4):1722.［杨晓唤,张香平,江东.基于MODIS时序NDVI特征提取多作物播种面积的方法［J］.资源科学,2004,26(4):1722.］

［13］Xiao X M,Stephen B,et al.Mapping Paddy Rice Agriculture in Southern China Using Multitemporal MODIS Images［J］.Remote Sensing of Environment,2005,95:480492

［14］Xiao X,Stephen B,et al.Mapping Paddy Rice Agriculture in South and Southeast Asia Using Multitemporal MODIS Images［J］.Remote Sensing of Environment,2006,100:95113.

［15］Wu Mingquan,Wang Changyao,Niu Zheng.Mapping Paddy Fields in Large Areas,based on Time Series Multisensors Data［J］.Transactions of the Chinese Society of Agricultural Engineering,2010,26(7):240244.［邬明权,王长耀,牛铮.利用多源时序遥感数据提取大范围水稻种植面积［J］.农业工程学报,2010,26(7):240244.］

［16］Li Yang,Jiang Nan,Lü Heng,et al.Decision Tree Classification based on Multitemporal Characteristic Bands of Rice［J］.Geography and GeoInformation Science,2010,26(2):1114.［李扬,江南,吕恒,等.基于水稻特征波段的决策树分类研究［J］.地理与地理信息科学,2010,26(2):1114.］

［17］Hot K.The Random Subspace Method for Constructing Decision Forests［J］IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(8):832844.

［18］Breiman L.Random Forests［J］.Machine Learning,2001,45(1):532.

［19］Hot K.Random Decision Forest［C］//Proceedings of the 3rd International Conference on Document Analysis and Recognition,Montreal,Canada,1995,8:278282.

［20］MaMing,Yue Cairong,Zhang Yunfei,et al.Comparative Study of Different Classification Methods of Land Cover based on TM Images［J］.Journal of Green Science and Technology,2014(3):14.［马明,岳彩荣,张云飞,等.基于TM影响的土地覆盖分类比较研究［J］.绿色科技,2014,(3):14.］

［21］Richardson A J,Weigand C L.Distinguishing Vegetation from Soil Background Information［J］.Photogrammetric Engineering and Remote Sensing,1977,43(12):15411552.

［22］Gitelson A A.Wide Dynamic Range Vegetation Index for Remote Quantification of Characteristics of Vegetation［J］.Journal Plant Physiology,2004,161:165173.

［23］Bannari A,Morin D,Bonn F,et al.A Review of Vegetation Indices［J］.Remote Sensing Reviews,1995,13(12):95120.

［24］Pan X,Uchida S,Liang Y,et al.Discriminating Different Landuse Types by Using Multitemporal NDXI in a Rice Planting Area［J］.International Journal of Remote Sensing,2010,(3):585596.

［25］Hunt J.E R,Rock B N.Detection of Changes in Leaf Water Content Using Near and MiddleInfrared Reflectances［J］.Remote Sensing of Environment,1989,30(1):4354.

［26］VanNiel T G,Mcvicar T R,Fang H,et al.Calculating Environmental Moisture for Perfield Discrimination of Rice Crop［J］.International Journal of Remote Sensing,2003,24(4):885890.

［27］Kauth R J,Thomas G S.The Tasseled Cap:A Graphic Description of the Spectraltemporal Development of Agricultural Crops as Seen in Landsat［C］//Proceedings of Symposium on Machine Processing of Remotely Sensed Data,West Lafayette,Indiana,1976:4151.

［28］MengYali,Cao Weixing,Zhou Zhiguo,et al.A processbased Model for Simulating Phasic Development and Phenology in Rice［J］.Scientia Agricultural Sinica,2003,36(11):13641367.［孟亚利,曹卫星,周志国,等.基于生长过程的水稻阶段发育与物候期模拟模型［J］.中国农业科学,2003,36(11):13641367.］

[1]	张祥，陈报章，赵慧，汪磊. 基于时序Sentinel-1A数据的农田土壤水分变化检测分析[J]. 遥感技术与应用, 2017, 32(2): 338-345.
[2]	雷光斌,李爱农,谭剑波,张正健,边金虎,靳华安,赵伟,曹小敏. 基于多源多时相遥感影像的山地森林分类决策树模型研究[J]. 遥感技术与应用, 2016, 31(1): 31-41.
[3]	张焕雪,曹新,李强子,张淼,郑新奇. 基于多时相环境星NDVI时间序列的农作物分类研究[J]. 遥感技术与应用, 2015, 30(2): 304-311.
[4]	白黎娜, 王琫瑜, 田昕, 卢颖, 杨永恬. 基于多时相ENVISat ASAR数据的冬小麦识别方法—以北京通州试验区为例[J]. 遥感技术与应用, 2010, 25(4): 458-463.
[5]	齐腊, 黄文江, 陈玲, 王纪华, 王锦地. 基于多时相TM和北京一号卫星影像的春播进度遥感监测 [J]. 遥感技术与应用, 2010, 25(3): 328-333.
[6]	马丽,徐新刚,刘良云,黄文江,贾建华,程一沛. 基于多时相NDVI及特征波段的作物分类研究[J]. 遥感技术与应用, 2008, 23(5): 520-524.
[7]	竞霞,王锦地,王纪华,黄文江,刘良云. 基于分区和多时相遥感数据的山区植被分类研究[J]. 遥感技术与应用, 2008, 23(4): 394-397.
[8]	齐腊,刘良云,赵春江,王纪华,王锦地. 基于遥感影像时间序列的冬小麦种植监测最佳时相选择研究[J]. 遥感技术与应用, 2008, 23(2): 154-160.
[9]	付琨, 尤红建, 胡岩峰. 多时相星载SAR图像精配准技术研究[J]. 遥感技术与应用, 2007, 22(5): 637-641.
[10]	廖静娟, 郭华东, 邵芸. 多时相SAR干涉测量数据探测地表特征变化[J]. 遥感技术与应用, 2005, 20(6): 543-546.
[11]	钟家强, 王润生. 一种稳健的多时相遥感图像相对辐射校正方法[J]. 遥感技术与应用, 2005, 20(6): 611-615.
[12]	竞　霞, 刘良云, 张　超, 王纪华, 贾建华, 李国靖. 利用多时相NDVI 监测京郊冬小麦种植信息[J]. 遥感技术与应用, 2005, 20(2): 238-242.
[13]	金亚秋. 极化散射与SAR 遥感信息获取[J]. 遥感技术与应用, 2005, 20(1): 6-10.
[14]	张荣群,张玮,袁志龙. 多时相ERS-2 SAR图像在作物分类中的预处理方法研究[J]. 遥感技术与应用, 2000, 15(1): 60-62.

Viewed

Full text

Abstract

Cited

Shared

Discussed