论文部分内容阅读
针对成像制导中对实时性和准确性的要求,提出了一种基于对数极坐标变换的图像抗旋转和尺度变化的LMA算法。在图像匹配过程中用LMA算法对两幅图像透视变换矩阵的8个未知参数进行拟合。匹配过程中用多分辨率金字塔法对图像进行分解,采用由粗到精的搜索策略,减少计算量并避免了误匹配。通过对照片进行匹配测试,证明了这种方法的有效性和实用价值。
In order to meet the requirement of real-time and accuracy in imaging guidance, an LMA algorithm based on logarithmic polar coordinate transformation is proposed. In the process of image matching, we use LMA algorithm to fit the eight unknown parameters of two image perspective transformation matrices. Matching process using multi-resolution pyramid method of image decomposition, using coarse to fine search strategy to reduce the amount of computation and to avoid the mismatch. Through the matching test photos, this method proved the effectiveness and practical value.