Joint photometric and geometric image registration in the total least square sense
Joint photometric and geometric image registration in the total least square sense
复制标题
DOI：
10.1016/j.patrec.2011.08.004
复制
发表时间：
2011-11
期刊：
影响因子：
--
通讯作者：
H. Luong;B. Goossens;A. Pižurica;W. Philips
中科院分区：
文献类型：
--
作者：
H. Luong;B. Goossens;A. Pižurica;W. Philips
本文提出了一种新颖的鲁棒图像对齐技术，该技术在总体最小二乘（TLS）意义上执行联合几何和光度配准。因此，我们采用总体最小二乘度量代替文献中常用的普通最小二乘（OLS）度量。虽然 OLS 模型足以解决几何配准问题，但在处理光度变形时它无法给出相互一致的估计。通过引入新的TLS模型，我们获得了相互一致的参数。实验结果表明，与现有的联合配准算法相比，我们的方法在存在噪声的情况下确实更加一致和准确。
This paper presents a novel robust image alignment technique that performs joint geometric and photometric registration in the total least square (TLS) sense. Therefore, we employ the total least square metric instead of the ordinary least square (OLS) metric, which is commonly used in the literature. While the OLS model is sufficient to tackle geometric registration problems, it gives no mutually consistent estimates when dealing with photometric deformations. By introducing a new TLS model, we obtain mutually consistent parameters. Experimental results show that our method is indeed more consistent and accurate in presence of noise compared to existing joint registration algorithms.