2D instantaneous frequency-based method for motion estimation using total variation

Victor Murray, Paul Rodriguez, Marios S. Pattichis

Producción científica: Capítulo del libro/informe/acta de congresoContribución a la conferenciarevisión exhaustiva

2 Citas (Scopus)

Resumen

We present a first approach to a new method to compute the motion estimation in digital videos using the two-dimensional instantaneous frequency information computed using amplitude-modulation frequency-modulation (AM-FM) methods. The optical flow vectors are computed using an iteratively reweighted norm for total variation (IRN-TV) algorithm. We compare the proposed method using synthetic videos versus a previous three-dimensional AM-FM based method and available motion estimation methods such as a phase-based, Horn-Schunck and the Lucas-Kanade methods. The results are promising producing a full density estimation with more accurate results than the other methods.

Idioma originalInglés
Título de la publicación alojada2014 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2014
EditorialInstitute of Electrical and Electronics Engineers Inc.
Páginas1009-1013
Número de páginas5
ISBN (versión digital)9781479970889
DOI
EstadoPublicada - 5 feb. 2014
Evento2014 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2014 - Atlanta, Estados Unidos
Duración: 3 dic. 20145 dic. 2014

Serie de la publicación

Nombre2014 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2014

Conferencia

Conferencia2014 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2014
País/TerritorioEstados Unidos
CiudadAtlanta
Período3/12/145/12/14

Huella

Profundice en los temas de investigación de '2D instantaneous frequency-based method for motion estimation using total variation'. En conjunto forman una huella única.

Citar esto