摘要
提出了一种基于目标检测的多源遥感图像特征融合方法。首先,在单源图像上检测目标,利用图像的大地坐标信息,自动截取包含目标的同一地区的局部遥感图像,再分别提取多源遥感图像上目标的特征信息,根据其中冗余的特征信息对提取的目标区域进行关联,再由关联检验确保特征关联的正确性,最后对目标特征进行融合决策得到特征融合结果。实验结果表明,方法能有效地利用多源遥感图像的信息,提高所获取目标特征的准确度。
An effective feature fusion strategy based on target detection is proposed. This method firstly detect targets in optical images and cuts the SAR sub images of the same location by adopting the geodetic coordinates information of images. It then detects targets in SAR sub images, independently extracts the features of multi - source detection results and makes the extracted areas associated according to the redundant feature information. An association verification method is presented to assure the correctness of the association. Finally, all the features are fused to get a more accurate and integral description of targets. Results obtained prove that this method can fully use the information of multi - source remote sensing images and improve the accuracy of targets features.
出处
《计算机仿真》
CSCD
2008年第4期224-227,共4页
Computer Simulation
基金
国家863高技术研究发展计划资助课题(2002AA783055)
关键词
多源遥感图像
目标检测
特征关联
特征融合
Multi -source remote sensing images
Target detection
Feature association
Feature level fusion
