Envisat ASAR在水稻识别中的应用

Envisat ASAR Application in Paddy Discrimination

合成孔径雷达(SAR)具有全天时全天候工作的能力,是南方多云地区水稻识别监测的有利手段.该文利用目前世界上最先进的EnvisatASAR数据,在长乐市进行水稻提取.在常规预处理的基础上对多时相数据进行自动配准和主成分变换,并采用面向对象法进行水稻的提取,精度为89.1%.结果表明:利用多时相双极化ASAR数据进行水稻信息的提取在南方多云地区具有一定实用意义.

Synthetic Aperture Radar （SAR） is an effective remote sensing data source for agricultural applications in tropical and subtropical regions due to its all-weather and all-time working capacity. ENVISAT ASAR is the most advanced satellite radarimaging instrument. In this paper, multi temporal ASAR alternative polarization data are used for the identification of rice crop in Changle. A procedure has been developed using multi-date ASAR data for rice crop identification. The procedure comprises two parts： data preprocessing and classification of multi-date data for rice field. Some novel methods are applied in image preprocessing such as correlation matching for image co-registration and the principle component transform. Object-oriented classifier is used for classification. By adopting the procedure, classification accuracy of 89. 1% is achieved on the test sites with multi-temporal Envisat ASAR data. The final result indicats that using multi-temporal ASAR data can distill paddy field area well, especially in the cloudy southern China. The technique for paddy monitoring is of practicable use.