基于图像混合特征的城市绿地遥感图像配准

Urban green space remote sensing image registration using image mixed features

为了解决同一场景城市绿地遥感图像因视角变化等原因不在同一坐标系,以致于不能对其进行变化检测的问题,提出一种基于图像混合特征的遥感图像配准方法. 1)提取SIFT特征点:从待配准图像和参考图像提取足够的SIFT特征点;2)基于混合特征的SIFT特征点配准:首先在特征点集Y和X之间进行对应关系评估,然后利用对应关系建立空间映射函数不断更新形变后源点集的位置;3)图像配准:基于源点集和形变后的源点集来构造一个映射函数,从而对图像进行配准.在与当前流行的4种算法(SIFT、CPD、RSOC、GLMDTPS)的对比实验中,提出的算法均给出了精确的配准结果,在大部分实验中其性能超过了其他算法.

A remote sensing image registration method based on image mixed features was proposed in order to solve the problem that the remote sensing images of urban green space in the same scene are not in the same coordinate system due to the change of viewpoint, and the change detection cannot be performed. Firstly, SIFT- based feature point extraction: exact sufficient SIFT feature points from the sensed image and the reference image. Secondly, SIFT feature point registration based on mixed features: the correspondence estimation between the feature point set Y and X, and then the correspondence was used to establish a spatial mapping function to continuously update the position of the transformed source point set. Thirdly, image registration: a mapping function was constructed based on the source point set and the transformed source point set to register the image. The experimental results show that, compared with four popular methods (SIFT, CPD, RSOC, GLMDTPS), the proposed method all gives accurate registration results, even presents better performance than the other methods in most cases.