Robust Feature Matching for Remote Sensing Image Registration Based on $L_{q}$ -Estimator
Robust Feature Matching for Remote Sensing Image Registration Based on $L_{q}$ -Estimator
复制标题
DOI：
10.1109/lgrs.2016.2620147
复制
发表时间：
2016-11
影响因子：
4.8
通讯作者：
Jiayuan Li;Qingwu Hu;M. Ai
中科院分区：
文献类型：
--
作者：
Jiayuan Li;Qingwu Hu;M. Ai
本文提出了一种基于lq估计的遥感图像鲁棒特征匹配算法。我们从尺度不变特征变换等特征匹配方法提供的一组初始匹配开始，然后重点研究污染观测值的全局变换估计和异常值消除。我们使用仿射模型来描述全局变换，并基于lq -范数最小化了一个新的代价函数。我们应用增广拉格朗日函数和乘子交替方向法来解决这类非凸非光滑优化问题。在实际遥感数据上的大量实验证明了该方法的有效性、高效性和鲁棒性。我们的方法优于最先进的方法，可以轻松处理高达90%异常值的情况。此外，该方法比RANSAC更快。
This letter proposes a robust feature matching algorithm for remote sensing images based on lq -estimator. We start with a set of initial matches provided by a feature matching method such as scale-invariant feature transform and then focus on global transformation estimation from contaminated observations and outliers elimination as well. We use an affine model to describe the global transformation and minimize a new cost function based on lq -norm. We apply an augmented Lagrangian function and an alternating direction method of multipliers to solve such a nonconvex and nonsmooth optimization problem. Extensive experiments on real remote sensing data demonstrate that the proposed method is effective, efficient, and robust. Our method outperforms state-of-the-art methods and can easily handle situations with up to 90% outliers. In addition, the proposed method is much faster than RANSAC.