论文标题
在边缘保护变异模型上，用于光流估计
On an Edge-Preserving Variational Model for Optical Flow Estimation
论文作者
论文摘要
众所周知，由于现代实施实践，类似于Horn和Schunck模型的古典配方仍然在很大程度上具有竞争力。在大多数情况下，这些模型的表现优于许多现代流动估计方法。鉴于此，我们为光流的$ l^1 $正则化方法提出了有效的实施设计。我们提出的模型的数学良好性在有限变化的函数$ bv（ω，\ mathbb {r}^2）$的功能空间中进行了研究。实施方案以多个步骤设计。使用强大的Chambolle-Pock原始偶算法计算流场。在最近的Castro和Donoho的研究中，我们将迭代中位过滤的启发式方法扩展到了我们的流量估计。此外，为了完善流动边缘，我们将Li和Osher建立的加权中位过滤器作为后处理步骤。我们在Middlebury数据集上进行的实验表明，与基于最新的角和Schunck的某些分量方法相比，所提出的方法达到了最佳的平均角和终点错误。
It is well known that classical formulations resembling the Horn and Schunck model are still largely competitive due to the modern implementation practices. In most cases, these models outperform many modern flow estimation methods. In view of this, we propose an effective implementation design for an edge-preserving $L^1$ regularization approach to optical flow. The mathematical well-posedness of our proposed model is studied in the space of functions of bounded variations $BV(Ω,\mathbb{R}^2)$. The implementation scheme is designed in multiple steps. The flow field is computed using the robust Chambolle-Pock primal-dual algorithm. Motivated by the recent studies of Castro and Donoho we extend the heuristic of iterated median filtering to our flow estimation. Further, to refine the flow edges we use the weighted median filter established by Li and Osher as a post-processing step. Our experiments on the Middlebury dataset show that the proposed method achieves the best average angular and end-point errors compared to some of the state-of-the-art Horn and Schunck based variational methods.
