期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：2006
卷号：XXXVI-8/W48
页码：59-64
出版社：Copernicus Publications
摘要：The first part of this paper presents a methodology on crop acreage estimations using the MODIS 16-day composite NDVI product. Particular emphasis is placed on a good quality crop mask and a good quality validation dataset. A novel approach which is based on the sampling of pure fields has been developed. The novel approach has been tested in previous work using a traditional maximum likelihood classification for 5 different crops. This novel approach has been further developed in this paper by applying a rule based approach which allows the estimation of winter wheat acreage in the study region. The advantage of such an approach is its simplicity, reasonable dataset input requirements and its potentially good forecasting capabilities. Training and rules are based on the year 2002. Results from this approach are shown together with an inter-comparison study which covers the second part of this paper. An inter-comparison study as part of the GEOLAND project in the Observatory for Food Monitoring (OFM) was carried out. In order to study the capabilities of the different methods to estimate crop acreage 2 study areas were chosen, Belgium and the South- West of Russia. 3 crop types namely winter crops, maize and sugarbeet /potatoes were compared for Belgium for the year 2003 from the partners Infoterra France (ITF) and Vito. For the Russian test site, a common study area was defined for all 3 partners (Vito, ITF and JRC) which includes 6 Sub-Oblast administrative regions (districts) and winter crops were chosen as the common crop type. An extended area (22 districts) was defined for the 2 partners Vito and JRC. For the common test sites differences of the acreage estimates are highlighted, absolute errors and root mean square errors are examined and the significant differences of the datasets are explored
关键词：Crop Area Estimations; Methods Comparison; South-East Russia; Remote Sensing
