图像拼接中的特征模板提取优化方法

Optimization Method for Characteristic Template Extraction in Image Mosaic

为了提高拼接算法的鲁棒性和效率,提出了一种基于边缘特征和行程编码索引的最优特征模板提取策略.最优模板包含了尽可能多的图像特征,模板中参与运算的只是具有边缘位置特征和灰度变化显著的像素点,通过行程编码方法构建索引模板以指定特征像素集合,从而显著提高了配准精度和匹配速度.

The optimal template pick-up strategy based on edge features and run length encoding index is invented and it makes a breakthrough in the robustness and speed of template matching algorithm.The optimal template contains image characteristics as much as possible while only the pixels which have edge character and distinct gray value changes participate in the matching operation.Both the precision and speed of template matching algorithm are improved remarkably.