多时相高分一号影像在丘陵地区大宗农作物提取中的应用
【目的】基于多时相的高分一号(GF-1)影像,利用面向地块对象分类法提取广西崇左市江州区大宗农作物种植面积,为南方多云雨丘陵地区提取作物信息提供参考。【方法】以2 m分辨率的GF-1影像为数据源,采用人机交互的方式准确识别地表覆盖的地块信息,基于对多时相GF-1影像进行云影检测,并处理生成影像的光谱、归一化植被指数(NDVI)、亮度等特征,采用面向地块对象的分类方法提取甘蔗、水稻和香蕉的作物信息。【结果】根据混淆矩阵评价分类的结果可知,提取大宗农作物的总体精度为90.08%,Kappa系数达0.85,满足农业成果应用的精度要求。【结论】利用有效影像数据,结合地块数据完成作物信息提取,该技术方法...
Saved in:
Published in | 南方农业学报 Vol. 48; no. 1; pp. 181 - 188 |
---|---|
Main Author | |
Format | Journal Article |
Language | Chinese |
Published |
广西农业科学院农业科技信息研究所,南宁,530007
2017
|
Subjects | |
Online Access | Get full text |
ISSN | 2095-1191 |
DOI | 10.3969/j:issn.2095-1191.2017.01.181 |
Cover
Summary: | 【目的】基于多时相的高分一号(GF-1)影像,利用面向地块对象分类法提取广西崇左市江州区大宗农作物种植面积,为南方多云雨丘陵地区提取作物信息提供参考。【方法】以2 m分辨率的GF-1影像为数据源,采用人机交互的方式准确识别地表覆盖的地块信息,基于对多时相GF-1影像进行云影检测,并处理生成影像的光谱、归一化植被指数(NDVI)、亮度等特征,采用面向地块对象的分类方法提取甘蔗、水稻和香蕉的作物信息。【结果】根据混淆矩阵评价分类的结果可知,提取大宗农作物的总体精度为90.08%,Kappa系数达0.85,满足农业成果应用的精度要求。【结论】利用有效影像数据,结合地块数据完成作物信息提取,该技术方法能够准确提取丘陵地区大宗农作物信息,为解决南方多云雨丘陵地区提取作物信息难题提供了有效途径。 |
---|---|
Bibliography: | 45-1381/S QIN Ze-lin,XIE Guo-xue,LI Yu-xiang,LAN Zong-bao,SU Qiu-qun,XIE Fu-qian,ZHANG Jia-mei,ZHANG Xiu-long(Agricultural Science and Technology Information Research Institute, Guangxi Academy of Agricultural Sciences, Nanning 530007, China) multi-temporal; GF-1; hill; staple crop; information extraction Objective】Based on multi-temporal GF-1 image, this paper extracted the planting area of staple crops in Jiangzhou, Chongzuo, Guangxi by using object-oriented classification, and provided reference for crop information extraction in southern hilly region. 【Method】Based on GF-1 image with 2 m resolution, human-computer interaction was conducted to accurately identify parcels information under land coverage. Cloud shadow detection was conducted based on multi-temporal GF-1 image. Features of the generated image such as spectrum, normalized differential vegetation index(NDVI) and brightness were processed. Crop information of sugarcane, rice and banana were extracted using object-oriented classification method. 【Re |
ISSN: | 2095-1191 |
DOI: | 10.3969/j:issn.2095-1191.2017.01.181 |