摘要
通过对目标知识库、目标数据库、地理信息系统(GIS)、形状分析和模式识别等技术的研究,提出了一种基于知识的目标识别方法。该方法提取目标遥感图像的空间特征和光谱特征,结合GIS空间分析功能,根据知识库中的先验知识进行推理,实现了典型目标的判别和提取。
Based on the research on target knowledge base, target database, texture analysis, shape analysis, this paper proposed a new knowledge based method for typical target identification from remote sensing image. By extracting the texture characters and shape characters, joining with spatial analysis in GIS, reasoning according to the prior knowledge in the knowledge base, this method can identify and extract typical target from remote sensing images.
出处
《铀矿地质》
CAS
CSCD
2008年第6期354-362,共9页
Uranium Geology
关键词
知识库
图像数据库
形状分析
目标识别
knowledge base
image database
texture analysis
target identification