为了进一步提高彩色遥感图像的配准精度,针对遥感图像配准过程中色彩信息利用率低的问题,提出一种改进的SURF(Speeded Up Robust Feature)彩色遥感图像配准算法.该算法首先在对彩色遥感图像进行特征点检测基础上,对特征点描述算子进行改进,以使颜色空间变换后得到的特征点色彩信息添加到原描述算子中;其次,对特征点描述算子进行归一化处理,以增加算子的独特性和对旋转、尺度、光照的鲁棒性;最后,利用Hession矩阵的迹提高精度以及欧氏距离比率完成特征点匹配,得到正确匹配点对,再通过变换矩阵参数估计和插值处理得到配准图像.实验结果表明,在保证实时性的条件下,该算法相比经典SIFT算法和SURF算法,准确性和稳定性都有一定提高,具有一定的理论和应用价值.%To further improve the registration precision of color remote sensing image,an improved SURF registration algorithm is put forward aiming at solving the problem of low utilization rate of color information.Firstly,based on the detection of feature points,a modified descriptor was constructed adding in color information got with color space transformation;then the normalized processing for the modified descriptor was done to increase its uniqueness and robustness to rotation,scale and illumination;finally,by trace of Hession matrix to improve precision,the correct matching points could be acquired through the Euclidean distance ratio.And the registered image was obtained based on parameter estimation and interpolation processing.Experimental results show,compared with the original SURF algorithm,that the improved algorithm has certain improvement in terms of accuracy and stability while guaranteeing the real time.It has certain values in both theory and practice.
展开▼
