基于稀疏正则化与降采样测量的稠密光流估计
Dense Optical Flow Estimation Using Sparse Regularizers from Reduced Measurements
AI总结：
本文提出将 l1 稀疏正则化引入变分光流估计，利用光流梯度的稀疏性从少量线性测量中恢复稠密光流，从而降低计算复杂度和内存需求。
摘要：
光流是场景中物体表观运动的模式。光流的计算是众多计算机视觉任务中的关键组成部分，例如目标检测、视觉目标跟踪和活动识别。尽管已有大量研究，但高效处理运动中的突变仍然是运动估计中的一个挑战。本文提出了新颖的变分正则化方法来解决这一问题，因为这些方法允许将不同的数学概念结合到一个联合能量最小化框架中。在本工作中，我们将信号稀疏性的概念引入到用于运动估计的变分正则化中。所提出的正则化使用鲁棒的 l1 范数，该范数促进稀疏性并处理运动不连续性。通过使用这种正则化，我们促进了光流梯度的稀疏性。这种稀疏性有助于即使在仅有少量测量的情况下也能恢复信号。我们探索了使用该正则化器从一组有限的线性测量中恢复光流。我们的研究结果表明，利用光流导数的稀疏性可以降低计算复杂度和内存需求。
英文摘要：
Optical flow is the pattern of apparent motion of objects in a scene. The computation of optical flow is a critical component in numerous computer vision tasks such as object detection, visual object tracking, and activity recognition. Despite a lot of research, efficiently managing abrupt changes in motion remains a challenge in motion estimation. This paper proposes novel variational regularization methods to address this problem since they allow combining different mathematical concepts into a joint energy minimization framework. In this work, we incorporate concepts from signal sparsity into variational regularization for motion estimation. The proposed regularization uses a robust l1 norm, which promotes sparsity and handles motion discontinuities. By using this regularization, we promote the sparsity of the optical flow gradient. This sparsity helps recover a signal even with just a few measurements. We explore recovering optical flow from a limited set of linear measurements using this regularizer. Our findings show that leveraging the sparsity of the derivatives of optical flow reduces computational complexity and memory needs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
