INRIA Centre de Rennes Bretagne Atlantique, Rennes, France.
IEEE Trans Image Process. 2012 Apr;21(4):1437-51. doi: 10.1109/TIP.2011.2179053. Epub 2011 Dec 9.
Selecting optimal models and hyperparameters is crucial for accurate optical-flow estimation. This paper provides a solution to the problem in a generic Bayesian framework. The method is based on a conditional model linking the image intensity function, the unknown velocity field, hyperparameters, and the prior and likelihood motion models. Inference is performed on each of the three levels of this so-defined hierarchical model by maximization of marginalized a posteriori probability distribution functions. In particular, the first level is used to achieve motion estimation in a classical a posteriori scheme. By marginalizing out the motion variable, the second level enables to infer regularization coefficients and hyperparameters of non-Gaussian M-estimators commonly used in robust statistics. The last level of the hierarchy is used for selection of the likelihood and prior motion models conditioned to the image data. The method is evaluated on image sequences of fluid flows and from the "Middlebury" database. Experiments prove that applying the proposed inference strategy yields better results than manually tuning smoothing parameters or discontinuity preserving cost functions of the state-of-the-art methods.
选择最优模型和超参数对于准确的光流估计至关重要。本文在通用贝叶斯框架中提供了一种解决方案。该方法基于一个条件模型，将图像强度函数、未知速度场、超参数以及先验和似然运动模型联系起来。在这个定义的分层模型的三个层次中的每一个上，通过最大化边缘化后验概率分布函数来进行推理。具体来说，第一层用于在经典的后验方案中实现运动估计。通过边缘化运动变量，第二层可以推断出通常在稳健统计学中使用的非高斯 M 估计器的正则化系数和超参数。分层的最后一层用于根据图像数据选择似然和先验运动模型。该方法在流体流动的图像序列和“Middlebury”数据库上进行了评估。实验证明，应用所提出的推理策略比手动调整平滑参数或最先进方法的保持不连续代价函数的效果更好。
