首页|基于Sentinel-1和Sentinel-2的不同物候期农作物识别研究

基于Sentinel-1和Sentinel-2的不同物候期农作物识别研究

扫码查看
原文链接
  • 万方数据
  • 维普
为减少农作物提取过程中受光学数据成像质量的影响,基于Google Earth Engine平台,采用Sentinel-1和Sentinel-2数据,分别对小麦越冬期、返青期、孕穗期、成熟期四个物候期进行小麦和油菜的识别.使用随机森林方法对构建的光谱特征、植被指数特征、红边指数特征、纹理特征和极化特征共34个特征进行优选,构建特征集;并对比最小距离、决策树、支持向量机、随机森林四种分类器在四个物候期的识别结果,确定最优的分类器;同时还验证了极化特征在四个物候期对识别结果的影响.研究结果表明,在四个物候期中最优的分类器均为随机森林,其中识别精度从高到低的物候期分别为小麦的孕穗期、成熟期、返青期、越冬期,总体精度(OA)分别为92.91％、91.93％、90.24％、87.69％,Kappa系数分别为91.00％、89.92％、87.61％、84.53％.在四个物候期中加入极化特征均能提高识别的精度,其中在小麦的返青期和成熟期更为明显.
Crop Identification Study Based on Sentinel-1 and Sentinel-2 for Different Phenological Periods
In order to reduce the influence of optical data imaging quality in the process of crop extraction,Senti-nel-1 and Sentinel-2 data were used based on Google Earth Engine platform to identify wheat and rape respective-ly in four phenological periods:overwintering period,regreening period,booting period and maturity period.A feature set is constructed by using a random forest method to preferentially select the optimal features from a set of 34 features consisting of spectral features,vegetation index features,red edge index features,texture features and polarisation features.It also compared the recognition results of four classifiers,namely,minimum distance,decision tree,support vector machine and random forest,in the four phenological periods to determine the opti-mal classifier;and also verified the influence of polarization features on the recognition results in the four pheno-logical periods.The results showed that the optimal classifier was random forest in all four phenological periods;the phenological periods with the highest to lowest recognition accuracy were wheat booting,maturity,regreen-ing and overwintering,with OA of 92.91％,91.93％,90.24％and 87.69％,and Kappa coefficients of 91.00％,89.92％,87.61％and 84.53％;The inclusion of polarisation features in each of the four phenological periods im-proved the accuracy of identification,more so in the two phenological periods of wheat,greening and maturity.

phenological periodscrop identificationSentinel-lSentinel-2Google Earth Enginerandom forest

常竹、李虎、陈冬花、刘玉锋、邹陈、陈健、韩伟杰

展开 >

安徽师范大学地理与旅游学院,安徽 芜湖 241000

资源环境与地理信息工程安徽省工程技术研究中心,安徽 芜湖 241000

滁州学院计算机与信息工程学院,安徽 滁州 239000

物候期 农作物识别 Sentinel-1 Sentinel-2 Google Earth Engine 随机森林

高分辨率对地观测系统科技重大专项安徽省科技重大专项安徽省重点研发计划安徽省重点研发计划安徽省特支计划(2019)安徽省高等学校协同创新项目安徽省自然科学基金安徽省高等学校自然科学研究重点项目滁州市科技计划

76-Y50G14-0038-22/23202003a0602000220210032022107020028GXXT-2021-0482208085QD107KJ2021A10632021ZD013

2024

10.14182/J.cnki.1001-2443.2024.01.005

安徽师范大学学报(自然科学版)
安徽师范大学

安徽师范大学学报(自然科学版)

CSTPCD
影响因子：0.435
ISSN：1001-2443
年,卷(期)：2024.47(1)
  • 24