TU Berlin

Fachgebiet NachrichtenübertragungWiss. Veröffentlichungen

Inhalt des Dokuments

zur Navigation

Wissenschaftliche Veröffentlichungen

Robust Local Optical Flow: Dense Motion Vector Field Interpolation
Zitatschlüssel 1498Geistert2016
Autor Jonas Geistert and Tobias Senst and Thomas Sikora
Buchtitel Picture Coding Symposium
Seiten 1–5
Jahr 2016
Adresse Nuremberg, Germany
Monat dec
Notiz In IEEE-Explore zugefügt am 24 April 2017! Electronic ISSN: 2472-7822 DOI: 10.1109/PCS.2016.7906352
Verlag IEEE
Zusammenfassung 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 zur Publikation Download Bibtex Eintrag



Schnellnavigation zur Seite über Nummerneingabe