欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
通过有效地利用多源遥感数据,基于灰度共生矩阵和双边滤波等方法提取建筑物的低层特征,并通过SVM初分类得到建筑物的高层语义特征,将低层特征与高层特征进行有效地融合成为新的特征用于建筑物提取.实验结果表明,进行多特征融合后的建筑物提取的完整率和正确率都得到了提高.
英文摘要：
Gray level co-occurrence matrix and bilateral filtering method was used to extract the low- level features and then SVM classifier was applied to get the high level semantic feature. The low- level features and high level semantic feature were merged together, and fed to SVM classifier to further extract buildings. Experimental results show that the completeness and correctness of building extraction of the proposed algorithm are improved obviously.
同期刊论文项目
同项目期刊论文
期刊信息
位置：