DSM辅助下城区大比例尺正射影像镶嵌线智能检测

传统算法以重叠区域色彩(或灰度)差值图像为正射影像镶嵌线检测基础，可以很好地避开色差区域，但对建筑物高密集的城区效果不明显。本文以高精度数字表面模型为检测基础，通过智能识别处理手段对地面区域与非地面区域进行良好区分。传统镶嵌线检测算法都是以迭代运算为基础的智能算法，算法复杂度高。本文发展出一种贪婪蛇型算法，该算法仅与搜索步距、方向旋转间隔、以及重叠区域宽度等三个因素相关，具有速度快，效率高等优点。针对典型的城市区域进行镶嵌线检测实验，结果表明DSM辅助下的城区正射影像镶嵌线能很好地避开房屋等明显地表实体，并且贪婪蛇型算法能有效地进行最优路径检测。

Seamlines Intelligent Detection in Large-scale Urban Orthoimage Mosaicking

Ground regional and non-ground area are accurately distinguished by processing high-precision DSM.Most of traditional seamlines detection algorithms are based on iterative calculations,and have high complexity.It is proposed a new algorithm named greedy snake algorithm.The new algorithm is only associated with three parameters: searching step,direction rotation interval and region width.Experiments for urban areas for orthophoto seamlines detection show that the seamlines can avoid buildings well,and the gr...