Robust Optical Flow Estimation Based on a Sparse Motion Trajectory Set

David Gibson, Michael Spann

Research output: Contribution to journalArticle

31 Citations (Scopus)


This paper presents an approach to the problem of estimating a dense optical flow field. The approach is based on a multiframe, irregularly spaced motion trajectory set, where each trajectory describes the motion of a given point as a function of time. From this motion trajectory set a dense flow field is estimated using a process of interpolation. A set of localized motion models are estimated, with each pixel labeled as belonging to one of the motion models. A Markov random field framework is adopted, allowing the incorporation of contextual constraints to encourage region-like structures. The approach is compared with a number of conventional optical flow estimation algorithms taken over a number of real and synthetic sequences. Results indicate that the method produces more accurate results for sequences with known ground truth flow. Also, applying the method to real sequences with unknown flow results in lower DFD, for all of the sequences tested.
Original languageEnglish
Pages (from-to)431-445
Number of pages15
JournalIEEE Transactions on Image Processing
Issue number4
Publication statusPublished - 1 Apr 2003


Dive into the research topics of 'Robust Optical Flow Estimation Based on a Sparse Motion Trajectory Set'. Together they form a unique fingerprint.

Cite this