Online robust image alignment via iterative convex optimization
Online robust image alignment via iterative convex optimization
复制标题
DOI：
10.1109/cvpr.2012.6247878
复制
发表时间：
2012-06
期刊：
影响因子：
--
通讯作者：
Yi Wu;Bin Shen;Haibin Ling
中科院分区：
文献类型：
--
作者：
Yi Wu;Bin Shen;Haibin Ling
在本文中，我们研究了在线对齐新到达的图像和先前对齐好的图像的问题。受最近使用低秩分解[16]的批量图像对齐进展的启发，我们将对齐后的新到达的图像视为由对齐良好的图像线性稀疏重建。该任务是通过一系列最小化l范数的凸优化来完成的。之后，以两种不同的方式进行在线基更新：(1)已知先验的大型图像数据集联合配准的两阶段增量对齐；(2)动态增加的图像序列的贪婪在线对齐，例如在跟踪场景中。在(1)中，我们首先通过检查重构残差对容易对齐的基图像进行顺序采集，然后在第二阶段使用采集到的基集对所有图像逐一重新对齐。在(2)中，在跟踪过程中，如果新目标设置的图像基与已有的基图像有明显区别，我们就动态地对其进行丰富。该方法在继承稀疏性优点的同时，具有较高的时间效率，能够处理大图像集和视觉跟踪等实时任务。通过对图像集对齐和视觉跟踪的大量实验，验证了所提出的在线鲁棒对齐算法的有效性。
In this paper we study the problem of online aligning a newly arrived image to previously well-aligned images. Inspired by recent advances in batch image alignment using low rank decomposition [16], we treat the newly arrived image, after alignment, as being linearly and sparsely reconstructed by the well-aligned ones. The task is accomplished by a sequence of convex optimization that minimizes the l\-norm. After that, online basis updating is pursued in two different ways: (1) a two-stage incremental alignment for joint registration of a large image dataset which is known a prior, and (2) a greedy online alignment of dynamically increasing image sequences, such as in the tracking scenario. In (1), we first sequentially collect basis images that are easily aligned by checking their reconstruction residuals, followed by the second stage where all images are re-aligned one-by-one using the collected basis set. In (2), during the tracking process, we dynamically enrich the image basis set by the new target if it significantly distinguishes itself from existing basis images. While inheriting the benefits of sparsity, our method enjoys the great time efficiency and therefore be capable of dealing with large image set and real time tasks such as visual tracking. The efficacy of the proposed online robust alignment algorithm is verified with extensive experiments on image set alignment and visual tracking, in reference with state-of-the-art methods.