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：
高光谱图像得到了越来越广泛的应用，但较低的空间分辨率严重地影响着它的应用效果，其超分辨率方法受到学术界的高度重视，但一直没有得到很好的解决．为此，建立低分辨率资源图像与高分辨率目标图像之间的关系模型；引入关联感兴趣光谱端元的算子进行空间变换；应用凸集投影（POCS）算法实现超分辨率复原．实验表明，该超分辨率方法具有超分辨率效果好、复杂度低、抗噪声性能强和保护感兴趣类别等优点．
英文摘要：
Hyperspectral imagery （HSI） is used in more and more fields, but its low spatial resolution limits the application severely. The super-resolution algorithm is highly regarded in the academic circle, but has not been solved well. In this case, the paper mainly focuses on the following aspects： A relation model between low-resolution source HSI and high-resolution target HSI was constructed; In the modeling, space transformation was imple- mented by introducing the operator related to endmembers （EMs） of interest ; Projection onto convex set （POCS） algorithm was used to realize the super-resolution （SR） recovery. Experiments show that the proposed SR method has good recovery effect, low computational complexity, robust noise resistance, and can preserve classes of interest.
同期刊论文项目
同项目期刊论文
位置：