Towards Ultimate Motion Estimation: Combining Highest Accuracy with Real-Time Performance

Although variational methods are among the most accurate techniques for estimating the optical flow, they have not yet entered the field of real-time vision. Main reason is the great popularity of standard numerical schemes that are easy to implement, however, at the expense of being too slow for real-time performance. In our paper we address this problem in two ways: (i) We present an improved version of the highly accurate technique of Brox et al. [9]. Thereby we show that a separate robustification of the constancy assumptions is very useful, in particular if the 1-norm is used as penalizer. As a result, a method is obtained that yields the lowest angular errors in the literature. (ii) We develop an efficient numerical scheme for the proposed approach that allows real-time performance for sequences of size 160 ? 120. To this end, we combine two hierarchical strategies: A coarse-to-fine warping strategy as implementation of a fixed point iteration for a non-convex optimisation probl...

• Type: Conference
• Year: 2005
• Where: ICCV
• Authors: Andrés Bruhn, Joachim Weickert
• Keywords: Computer Vision, Efficient Numerical Scheme, ICCV 2005, Lowest Angular Errors, Non-convex Optimisation Problem, Real-time Performance, Standard Numerical Schemes