Improved Accuracy in Gradient-Based Optical Flow Estimation
Author: Brandt, J.W.
Source: International Journal of Computer Vision, Volume 25, Number 1, October 1997 , pp. 5-22(18)
Abstract:Optical flow estimation by means of first derivatives can produce surprisingly accurate and dense optical flow fields. In particular, recent empirical evidence suggests that the method that is based on local optimization of first-order constancy constraints is among the most accurate and reliable methods available. Nevertheless, a systematic investigation of the effects of the various parameters for this algorithm is still lacking. This paper reports such an investigation. Performance is assessed in terms of flow-field accuracy, density, and resolution. The investigation yields new information regarding pre-filter, differentiator, least-squares neighborhood, and reliability test selection. Several changes to previously-employed parameter settings result in significant overall performance improvements, while they simultaneously reduce the computational cost of the estimator.
Keywords: optical flow
Document Type: Regular Paper
Affiliations: Advanced Systems Division, Silicon Graphics Computer Systems, 2011 N. Shoreline Blvd., Mountain View, CA, 94043. E-mail: firstname.lastname@example.org
Publication date: October 1, 1997