摘要
傅里叶梅林变换是比较优秀的图像配准方法之一,但此方法不适用于倾斜影像。针对此问题提出了一种基于投影变换与Fourier-Mellin变换相结合的图像配准方法。该方法首先根据投影构像方程计算标准图像与待配准图像之间的投影变换矩阵;然后根据投影变换矩阵对待配准影像做倾斜校正;最后对纠正后的待配准影像与标准影像进行Fourier-Mellin变换,得到准确的配准参数。实验结果表明,该方法使得Fourier-Mellin变换的图像配准方法不仅适用于相对平行影像对之间配准,也适用于非相对平行影像对配准,且在直观与客观上都比传统傅里叶梅林变换配准结果好。
Fourier-Merlin transform is one of the best image registration methods,but the method is not suitable for tilting images.The image registration method based on projection transformation and Fourier-Mellin transform is proposed to solve this problem.The method firstly calculates the projection transformation matrix between the standard image and the image to be registered according to the projection conforming equation,secondly corrects the image to be registered according to the projection transformation matrix.Then,Fourier-Mellin transform is performed on the corrected image and the standard image to obtain the registration parameters.Eventually,the experiment results show that this method makes the image registration method of Fourier-Mellin transform not only applicable to the registration of the parallel image pairs,but also can be applied to the registration of non-parallel image pairs.What’s more,the results are intuitively and objectively superior to the traditional Fourier transform.
作者
高东阳
刘亚琼
Gao Dong-yang;Liu Ya-qiong(School of Geomatics and Urban Spatial Information,Beijing University of Civil Engineering and Architecture, Beijing 100044, China)
出处
《现代测绘》
2017年第6期19-22,共4页
Modern Surveying and Mapping
基金
国家自然科学基金项目(40771178)
