Microsoft Corporation, Redmond, WA 98052, USA.
IEEE Trans Image Process. 1998;7(9):1242-57. doi: 10.1109/83.709656.
Motion discontinuities arise when there are occlusions or multiple moving objects in the scene that is imaged. Conventional regularization techniques use smoothness constraints but are not applicable to motion discontinuities. In this paper, we show that discontinuous (or multiple) motion estimation can be viewed as a multicomponent harmonic retrieval problem. From this viewpoint, a number of established techniques for harmonic retrieval ran be applied to solve the challenging problem of discontinuous (or multiple) motion. Compared with existing techniques, the resulting algorithm is not iterative, which not only implies computational efficiency but also obviates concerns regarding convergence or local minima. It also adds flexibility to spatio-temporal techniques which have suffered from lack of explicit modeling of discontinuous motion. Experimental verification of our framework on both synthetic data as well as real image data is provided.
当场景中存在遮挡或多个运动物体时，会出现运动不连续。传统的正则化技术使用平滑约束，但不适用于运动不连续。在本文中，我们表明不连续（或多个）运动估计可以看作是多分量谐波恢复问题。从这个角度来看，许多已有的谐波恢复技术都可以应用于解决不连续（或多个）运动的挑战性问题。与现有技术相比，所得到的算法不是迭代的，这不仅意味着计算效率，而且消除了对收敛或局部最小值的担忧。它还为时空技术增加了灵活性，这些技术一直缺乏对不连续运动的明确建模。在合成数据和真实图像数据上对我们的框架进行了实验验证。
