direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Page Content

Scientific Publications

Robust Local Optical Flow: Dense Motion Vector Field Interpolation
Citation key 1498Geistert2016
Author Jonas Geistert and Tobias Senst and Thomas Sikora
Title of Book Picture Coding Symposium
Pages 1–5
Year 2016
Address Nuremberg, Germany
Month dec
Note In IEEE-Explore zugefügt am 24 April 2017! Electronic ISSN: 2472-7822 DOI: 10.1109/PCS.2016.7906352
Publisher IEEE
Abstract Optical flow methods integrating sparse point correspondences have made significant contribution in the field of optical flow estimation. Especially for the goal of estimating motion accurately and efficiently sparse-to-dense interpolation schemes for feature point matches have shown outstanding performances. Concurrently, local optical flow methods have been significantly improved with respect to long-range motion estimation in environments with varying illumination. This motivates us to propose a sparse-to-dense approach based on the Robust Local Optical Flow method. We study the performance of different efficient motion vector interpolation techniques for recent optical low benchmarks. Compared state-of-the-art method the proposed approach is significantly faster while remaining competitive accuracy on Middlebury, KITTI 2015 and MPI-Sintel data-set.
Link to publication Download Bibtex entry

Zusatzinformationen / Extras

Quick Access:

Schnellnavigation zur Seite über Nummerneingabe

Auxiliary Functions