提出了一种基于直线特征的对尺度变化和旋转变化不敏感的遥感影像和GIS数据自动整体配准方法.该方法利用在变换模型转换后GIS数据中参考线段上的端点和影像上对应特征线段的距离为零建立相似性测度,以共线条件方程作为变换模型,通过改进的霍夫变换进行优化求解,同时得到变换模型参数即外方位元素和匹配结果,实现了遥感影像和GIS数据的自动配准及遥感影像的外部定向.实验结果表明,该方法具有较高的可靠性和配准精度.%An automatically total registration method was proposed, which was based on straight line features and insensitive to rotational and scale transformation. In this method, similarity measure was established according to the distance which is zero between end points of reference line from GIS data and corresponding line in the image after applying transform model. The collinearity equation was chosen as transform model. A modified Hough transform was adopted to obtain transform model parameters optimally, namely elements of exterior orientation, and matching results. The automatic registration between the remote sensing image and GIS data was achieved as well as the exterior orientation of the remote sensing image. Experimental results proved the reliability and accuracy of the proposed method.
展开▼
