Dynamically Removing False Features in Pyramidal Lucas-Kanade Registration
Dynamically Removing False Features in Pyramidal Lucas-Kanade Registration
复制标题
动态去除金字塔 Lucas-Kanade 配准中的虚假特征
DOI：
10.1109/tip.2014.2331140
复制
发表时间：
2014-08-01
影响因子：
10.6
通讯作者：
Che, Xiangjiu
中科院分区：
文献类型：
--
作者：
Niu, Yan;Xu, Zhiwen;Che, Xiangjiu
金字塔Lucas-Kanade(LK)光流是一种被各种尖端消费应用广泛采用的实时配准技术。传统上，LK算法被选择性地应用于具有较强空间变化的图像特征点，其中包括纹理区域中的离群点。为了检测和丢弃错误选择的特征，以往的方法通常在流量计算完成后评估每个特征的优度。这样的筛选过程会产生额外的成本。本文为LK算法的用户提供了一个方便(但不明显)的工具，在不降低算法效率的情况下去除虚假特征。我们提出了一个置信度预测器，它直接从底层数据评估LK系统的不适定性，其代价比求解该系统的成本低。然后，我们将我们的置信度预测器结合到过程到精细的LK配准中，以动态地检测错误特征并在早期阶段终止它们的流计算。这通过防止误差传播来提高配准精度，并通过在错误特征上节省运行时间来保持(或增加)计算速度。在最先进的基准测试上的实验结果验证了该方法比相关工作更准确和高效。
Pyramidal Lucas-Kanade (LK) optical flow is a real-time registration technique widely employed by a variety of cutting edge consumer applications. Traditionally, the LK algorithm is applied selectively to image feature points that have strong spatial variation, which include outliers in textured areas. To detect and discard the falsely selected features, previous methods generally assess the goodness of each feature after the flow computation is completed. Such a screening process incurs additional cost. This paper provides a handy (but not obvious) tool for the users of the LK algorithm to remove false features without degrading the algorithm's efficiency. We propose a confidence predictor, which evaluates the ill-posedness of an LK system directly from the underlying data, at a cost lower than solving the system. We then incorporate our confidence predictor into the course-to-fine LK registration to dynamically detect false features and terminate their flow computation at an early stage. This improves the registration accuracy by preventing the error propagation and maintains (or increases) the computation speed by saving the runtime on false features. Experimental results on state-of-the-art benchmarks validate that our method is more accurate and efficient than related works.