摘要
提出了一种基于智能生态细胞的遥感信息提取方法。该方法综合了作物的物候特征、光谱演化特征和空间相关性的反馈信息,融合了元胞自动机、模糊推理和BP神经网络智能计算思想。以2009年多时相Landsat7 ETM遥感影像作为数据源,进行了基于智能生态细胞的烤烟种植面积监测。监测结果表明,该方法可以有效提高遥感信息提取精度,具有实际应用价值。
A remote sensing information extraction method based on smart ecological cells is put forward.In the method,the crop phenological characteristics,spectral evolution characteristics and special correlation feedback are combined and the cellular automata,fuzzy reasoning and BP neural network intelligent computation are fused.By taking the multi-temporal Landsat-7 ETM images as the experimental data,the monitoring of tobacco acreage planting area based on smart ecological cells is carried out.The monitoring result shows that this method can effectively improve the extraction accuracy of remote sensing information and is of value to practical applications.
出处
《红外》
CAS
2011年第8期18-24,28,共8页
Infrared
基金
中国博士后科学基金(20080430586)
国家科技支撑项目(2008BAK50B01)
关键词
智能生态细胞
元胞自动机
模糊推理
BP神经网络
物候特征
smart ecological cell
cellular automata
fuzzy reasoning
BP neural network
phenological characteristics
