[1]钟怡琪,李家国,韩杰,等.基于哨兵影像与多特征优选的溧阳市上兴镇水稻识别[J].江苏农业学报,2023,(08):1688-1697.[doi:doi:10.3969/j.issn.1000-4440.2023.08.008]
　ZHONG Yi-qi,LI Jia-guo,HAN Jie,et al.Identification of rice in Shangxing Town, Liyang City based on Sentinel image and multi-feature optimization[J].,2023,(08):1688-1697.[doi:doi:10.3969/j.issn.1000-4440.2023.08.008]
点击复制

基于哨兵影像与多特征优选的溧阳市上兴镇水稻识别()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2023年08期
页码:
1688-1697
栏目:
农业信息工程
出版日期:
2023-12-31

文章信息/Info

Title:
Identification of rice in Shangxing Town, Liyang City based on Sentinel image and multi-feature optimization
作者:
钟怡琪1; 李家国2; 韩杰3; 邵雯1
(1.南京信息工程大学地理科学学院,江苏南京210044；2.中国科学院空天信息创新研究院,北京100094；3.许昌学院城市与环境学院,河南许昌461000)
Author(s):
ZHONG Yi-qi1; LI Jia-guo2; HAN Jie3; SHAO Wen1
(1.School of Geographical Sciences, Nanjing University of Information Science & Technology, Nanjing 210044, China;2.Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China;3.College of Urban and Environmental Sciences, Xuchang University, Xuchang 461000, China)
关键词:
水稻识别; 特征优选; 随机森林; 遥感影像
Keywords:
identification of rice; feature optimization; random forest; remote sensing image
分类号:
S127；S511
DOI:
doi:10.3969/j.issn.1000-4440.2023.08.008
文献标志码:
A
摘要:
水稻是中国三大粮食作物之一,提供准确、及时的水稻种植信息对水稻生产管理、水稻种植保险赔偿以及国家粮食安全指导、政策制定和实施等具有重要意义。针对中国南方水稻种植地块破碎、种植结构复杂等造成的水稻识别难点,为提高水稻识别精度,本研究以哨兵一号(Sentinel-1)、哨兵二号(Sentinel-2)遥感影像为数据源,构建光谱特征、植被/水体指数特征、纹理特征和雷达特征等特征集,设置包括优选特征在内的7种特征组合,采用随机森林算法对江苏省常州市溧阳市上兴镇的水稻进行识别。结果表明,在光谱特征中,红边波段对于水稻识别精度有着较高的提升作用。光谱特征结合植被/水体指数特征、雷达特征后,水稻识别精度有所提高。基于优选特征进行分类的精度最高,总体分类精度、Kappa系数分别为93.26%、0.904 8。综上,结合遥感影像的光谱特征、植被/水体指数特征和雷达特征等并进行特征优选可以提高水稻识别精度。
Abstract:
Rice is one of the three major food crops in China. Providing accurate and timely rice planting information is of great significance to rice production management, rice planting insurance compensation, national food security guidance, policy formulation and implementation. Aiming at the difficulties in rice identification caused by the fragmentation of rice cultivation plots and the complexity of cultivation structure in southern China, and in order to improve the accuracy of rice identification, this study used Sentinel-1 and Sentinel-2 remote sensing images as data sources, constructed the feature sets including spectral features, vegetation/water index features, texture features, and radar features, set up seven combinations of features including the preferred features and adopted the random forest algorithm for the identification of the rice in Shangxing Town, Liyang City, Changzhou City, Jiangsu province, China. The results showed that among the spectral features, the red-edge band had a high improvement effect on the identification accuracy of rice. After combining spectral features with vegetation/water index features and radar features, the identification accuracy of rice was improved. And the classification based on the preferred features had the highest accuracy, with the overall accuracy and Kappa coefficient of 93.26% and 0.904 8, respectively. In summary, the combination of the spectral features of remote sensing images, vegetation/water index features and radar features and feature optimization can improve the accuracy of rice recognition.

参考文献/References:

[1]庞乾林,林海,阮刘青,等. 中国稻米文化和现代成就[J]. 中国稻米,2004(3):3-5.
[2]赵凌,赵春芳,周丽慧,等. 中国水稻生产现状与发展趋势[J]. 江苏农业科学,2015,43(10):105-107.
[3]章秀福,王丹英,方福平,等. 中国粮食安全和水稻生产[J]. 农业现代化研究,2005(2):85-88.
[4]梁成权,庄恒扬,高辉,等. GIS技术在水稻优质高产栽培中的应用研究进展[J]. 中国稻米,2013,19(2):14-17.
[5]JIN C, XIAO X, DONG J, et al. Mapping paddy rice distribution using multi-temporal Landsat imagery in the Sanjiang Plain, northeast China[J]. Frontiers of Earth Science,2016,10(1):49-62.
[6]孙华生,黄敬峰,彭代亮. 利用MODIS数据识别水稻关键生长发育期[J]. 遥感学报,2009,13(6):1122-1137.
[7]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):98-104.
[8]刘仁钊,廖文峰. 遥感图像分类应用研究综述[J]. 地理空间信息,2005,3(5):11-13.
[9]杨沈斌,景元书,王琳,等. 基于MODIS时序数据提取河南省水稻种植分布[J]. 大气科学学报,2012,35(1):113-120.
[10]吕婷婷,刘闯. 基于MODIS数据的泰国耕地信息提取[J]. 农业工程学报,2010,26(2):244-250.
[11]牛明香,赵庚星,李尊英,等. 南四湖湿地遥感信息分区分层提取研究[J]. 地理与地理信息学,2004,20(2):45-48,52.
[12]何昭欣,张淼,吴炳方,等. Google Earth Engine支持下的江苏省夏收作物遥感提取[J]. 地球信息科学学报,2019,21(5):752-766.
[13]汪传建,赵庆展,马永建,等. 基于卷积神经网络的无人机遥感农作物分类[J]. 农业机械学报,2019,50(11):161-168.
[14]温小乐,钟奥,胡秀娟. 基于随机森林特征选择的城市绿化乔木树种分类[J]. 地球信息科学学报,2018,20(12):1777-1786.
[15]刘元亮,李艳,吴剑亮. 基于LSWI和NDVI时间序列的水田信息提取研究[J]. 地理与地理信息科学,2015,31(3):32-37.
[16]苗翠翠,江南,彭世揆,等. 基于NDVI时序数据的水稻种植面积遥感监测分析——以江苏省为例[J]. 地球信息科学学报,2011,13(2):273-280.
[17]王文静,张霞,赵银娣,等. 综合多特征的Landsat8时序遥感图像棉花分类方法[J]. 遥感学报,2017,21(1):115-124.
[18]贾坤,李强子. 农作物遥感分类特征变量选择研究现状与展望[J]. 资源科学,2013,35(12):2507-2516.
[19]王娜,李强子,杜鑫,等. 单变量特征选择的苏北地区主要农作物遥感识别[J]. 遥感学报,2017,21(4):519-530.
[20]PENG H, LONG F, DING C. Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(8):1226-1238.
[21]程希萌,沈占锋,邢廷炎,等. 基于mRMR特征优选算法的多光谱遥感影像分类效率精度分析[J]. 地球信息科学学报,2016,18(6):815-823.
[22]王李娟,孔钰如,杨小冬,等. 基于特征优选随机森林算法的农耕区土地利用分类[J]. 农业工程学报,2020,36(4):244-250.
[23]周廷刚,郭达志,盛业华. 灰度矢量多波段遥感影像纹理特征及其描述[J]. 西安科技学院学报,2000,20(4):336-338.
[24]张勇攀,蒋玲梅,邱玉宝,等. 不同地物类型微波发射率特征分析[J]. 光谱学与光谱分析,2010,30(6):1446-1451.
[25]郑煜,陈圣波,陈彦冰,等. 基于Sentinel-1A雷达数据和Sentinel-2A多光谱数据特征融合的地物分类[J]. 世界地质,2021,40(2):438-444.
[26]王利民,刘佳,杨福刚,等. GF-1 卫星多时相组合近红外数据水稻识别能力[J]. 农业工程学报,2017,33(23):196-202.
[27]梁继,郑镇炜,夏诗婷,等. 高分六号红边特征的农作物识别与评估[J]. 遥感学报,2020,24(10):1168-1179.
[28]张影,王珍,孙政,等. Sentinel-2红边波段在水稻识别中作用研究——以浙江省德清县为例[J]. 中国农业资源与区划,2021,42(12):144-153.
[29]刘道芳,王景山,李胜阳. 高分六号卫星红边波段及红边植被指数对水稻分类精度的影响[J]. 河南科学,2021,39(9):1417-1423.
[30]KANFG Y P, MENG Q Y, LIU M, et al. Crop classification based on red edge features analysis of GF-6 WFV data[J]. Sensors,2021,21(13):4328.
[31]JIANG X Q, FANG S H, HUANG X, et al. Rice mapping and growth monitoring based on time series GF-6 images and red-edge bands[J]. Remote Sensing,2021,13(4):579.
[32]张悦琦,李荣平,穆西晗,等. 基于多时相GF-6遥感影像的水稻种植面积提取[J]. 农业工程学报,2021,37(17):189-196.
[33]CHEN D, HUANG J, JACKSON T J. Vegetation water content estimation for corn and soybeans using spectral indices derived from MODIS near- and short-wave infrared bands[J]. Remote Sensing of Environment,2005,98(2/3):225-236.

相似文献/References:

[1]朱泊东金京,罗洪斌,龙飞,等.基于变量优选的机载激光雷达对林分平均高的反演[J].江苏农业学报,2022,38(03):706.[doi:doi:10.3969/j.issn.1000-4440.2022.03.016]
　ZHU Bo-dong,JIN Jing,LUO Hong-bin,et al.Inversion of average forest stand height based on variable selection by airborne laser radar[J].,2022,38(08):706.[doi:doi:10.3969/j.issn.1000-4440.2022.03.016]
[2]曾学亮,郭熙,钟亮,等.基于多源遥感特征融合与卷积神经网络(CNN)的丘陵地区水稻识别[J].江苏农业学报,2024,(01):93.[doi:doi:10.3969/j.issn.1000-4440.2024.01.010]
　ZENG Xue-liang,GUO Xi,ZHONG Liang,et al.Rice identification in hilly areas based on multi-source remote sensing feature fusion and convolutional neural networks (CNN)[J].,2024,(08):93.[doi:doi:10.3969/j.issn.1000-4440.2024.01.010]

备注/Memo

备注/Memo:
收稿日期:2022-11-14基金项目:国家自然科学基金项目(41971391)；国家重点研发计划项目(2020YFE0200700)；安徽省重点研究与开发计划项目(2021003、2022107020028)；2022年度许昌学院国家级科研项目培育基金项目(2022GJPY007)作者简介:钟怡琪(1998-),女,江西吉安人,硕士研究生,主要从事水稻遥感识别与估产研究。(E-mail)20201210035@nuist.edu.cn通讯作者:李家国,(E-mail)jacoli@126.com
更新日期/Last Update: 2024-01-15