Analytic Solutions for Multiple Motions

C. Mota; I. Stuke; E. Barth

doi:10.1109/ICIP.2001.958644

Analytic Solutions for Multiple Motions

C. Mota, I. Stuke, E. Barth

Abstract

A novel framework for single and multiple motion estimation is presented. It is based on a generalized structure tensor that contains blurred products of directional derivatives. The order of differentiation increases with the number of motions but more general linear filters can be used instead of derivatives. From the general framework, a hierarchical algorithm for motion estimation is derived and its performance is demonstrated on a synthetic sequence.

Original language	English
Pages	917-920
Number of pages	4
DOIs	https://doi.org/10.1109/ICIP.2001.958644
Publication status	Published - 01.01.2001
Event	IEEE International Conference on Image Processing 2001 - Thessaloniki, Greece Duration: 07.10.2001 → 10.10.2001 Conference number: 58802

Conference

Conference	IEEE International Conference on Image Processing 2001
Abbreviated title	ICIP 2001
Country/Territory	Greece
City	Thessaloniki
Period	07.10.01 → 10.10.01

Access to Document

10.1109/ICIP.2001.958644

Cite this

@conference{86ad8edb61d14adf9fb0e64d70ed66a5,

title = "Analytic Solutions for Multiple Motions",

abstract = "A novel framework for single and multiple motion estimation is presented. It is based on a generalized structure tensor that contains blurred products of directional derivatives. The order of differentiation increases with the number of motions but more general linear filters can be used instead of derivatives. From the general framework, a hierarchical algorithm for motion estimation is derived and its performance is demonstrated on a synthetic sequence.",

author = "C. Mota and I. Stuke and E. Barth",

year = "2001",

month = jan,

day = "1",

doi = "10.1109/ICIP.2001.958644",

language = "English",

pages = "917--920",

note = "IEEE International Conference on Image Processing 2001 , ICIP 2001 ; Conference date: 07-10-2001 Through 10-10-2001",

}

TY - CONF

T1 - Analytic Solutions for Multiple Motions

AU - Mota, C.

AU - Stuke, I.

AU - Barth, E.

N1 - Conference code: 58802

PY - 2001/1/1

Y1 - 2001/1/1

N2 - A novel framework for single and multiple motion estimation is presented. It is based on a generalized structure tensor that contains blurred products of directional derivatives. The order of differentiation increases with the number of motions but more general linear filters can be used instead of derivatives. From the general framework, a hierarchical algorithm for motion estimation is derived and its performance is demonstrated on a synthetic sequence.

AB - A novel framework for single and multiple motion estimation is presented. It is based on a generalized structure tensor that contains blurred products of directional derivatives. The order of differentiation increases with the number of motions but more general linear filters can be used instead of derivatives. From the general framework, a hierarchical algorithm for motion estimation is derived and its performance is demonstrated on a synthetic sequence.

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-0035158891&origin=inward&txGid=c3e90180598e8e81a1a1eb43f75f4947

U2 - 10.1109/ICIP.2001.958644

DO - 10.1109/ICIP.2001.958644

M3 - Conference Papers

SP - 917

EP - 920

T2 - IEEE International Conference on Image Processing 2001

Y2 - 7 October 2001 through 10 October 2001

ER -

Analytic Solutions for Multiple Motions

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this