魏永霞,杨军明,吴昱,王斌,SHEHAKK M,侯景翔.基于多源数据融合模型的水稻面积提取[J].农业机械学报,2018,49(10):300-306.
WEI Yongxia,YANG Junming,WU Yu,WANG Bin,SHEHAKK M,HOU Jingxian.Rice Planting Area Extraction Based on Multi-source Data Fusion[J].Transactions of the Chinese Society for Agricultural Machinery,2018,49(10):300-306.
摘要点击次数: 111
全文下载次数: 73
基于多源数据融合模型的水稻面积提取   [下载全文]
Rice Planting Area Extraction Based on Multi-source Data Fusion   [Download Pdf][in English]
投稿时间:2018-04-04  
DOI:10.6041/j.issn.1000-1298.2018.10.034
中文关键词:  水稻  遥感  数据融合  光谱耦合技术  模糊C聚类算法
基金项目:国家重点研发计划项目(2016YFC0400101)、国家自然科学基金项目(51009026)和农业部农业水资源高效利用重点实验室开放项目(2015002)
作者单位
魏永霞 东北农业大学 
杨军明 东北农业大学 
吴昱 东北林业大学
黑龙江农垦勘测设计研究院 
王斌 东北农业大学 
SHEHAKK M 东北农业大学 
侯景翔 东北农业大学 
中文摘要:中高空间分辨率影像数据缺失是高空间分辨率作物空间分布提取的主要限制因素,针对部分地区的中高空间分辨率遥感影像缺失使得作物提取的关键生育期无卫星覆盖的问题,提出了一种基于模糊C聚类算法的多源遥感植被指数数据融合方法,融合Landsat和MODIS数据生成高时空分辨率的植被指数数据,对融合生成的多时相植被指数数据进行聚类后获取各类的时序植被指数曲线。通过与水稻标准时序植被指数曲线进行光谱相似性分析来提取水稻的空间分布。经测试表明,该方法能够获得相对较高的精度,可应用于中高分辨率遥感数据缺失地区的高空间分辨率作物空间分布信息提取
WEI Yongxia  YANG Junming  WU Yu  WANG Bin  SHEHAKK M  HOU Jingxian
Northeast Agricultural University,Northeast Agricultural University,Northeast Forestry University;Heilongjiang Agricultural Reclamation Survey and Research Institute,Northeast Agricultural University,Northeast Agricultural University and Northeast Agricultural University
Key Words:rice  remote sensing  data fusion  spectral matching technique  fuzzy C-clustering algorithm
Abstract:The absence of medium and high spatial resolution image data is the main limiting factor for extraction of spatial distribution of crops with high spatial resolution. A multi-source remote sensing vegetation index data fusion model based on fuzzy C-clustering algorithm was proposed to solve the problem of no satellite image data coverage in the critical growth period of crop extraction, and it was used to generate vegetation index data with high temporal and spatial resolution by combining Landsat with MODIS vegetation index data. Standard series EVI curve was obtained by ground sample, and the fuzzy C-clustering algorithm was used to classify the vegetation index data generated by the data fusion model into several classes, and series EVI curve of each classes was obtained by using the average value of each class as the class value. The spatial distribution of rice was extracted by spectral correlation similarity analysis of standard series EVI curve and class series curve. Accuracy of the method was tested by Google Earth image and ground sample, and the accuracy were 0.92 and 0.94, respectively, thus it was thought that the method can get relatively high accuracy. The method can be applied to extract the spatial distribution information of crops that had high spatial resolution in the areas of lacking high resolution remote sensing image data. And the multi-source remote sensing vegetation index data fusion models can be used to generate vegetation index data with high spatial and temporal resolution.

Transactions of the Chinese Society for Agriculture Machinery (CSAM), in charged of China Association for Science and Technology (CAST), sponsored by CSAM and Chinese Academy of Agricultural Mechanization Science(CAAMS), started publication in 1957. It is the earliest interdisciplinary journal in Chinese which combines agricultural and engineering. It always closely grasps the development direction of agriculture engineering disciplines and the published papers represent the highest academic level of agriculture engineering in China. Currently, nearly 8,000 papers have been already published. There are around 3,000 papers contributed to the journal each year, but only around 600 of them will be accepted. Transactions of CSAM focuses on a wide range of agricultural machinery, irrigation, electronics, robotics, agro-products engineering, biological energy, agricultural structures and environment and more. Subjects in Transactions of the CSAM have been embodied by many internationally well-known index systems, such as: EI Compendex, CA, CSA, etc.

   下载PDF阅读器