Abstract
A closed-form solution for motion estimation from first-order flow in two `distinct' image regions is described. Uniqueness is guaranteed when these correspond to surface patches with different normal vectors. Given an image sequence, we show how the image may be segmented into regions with the necessary properties, optical flow is computed for these regions, and motion parameters are computed. The method can be applied to arbitrary scenes and camera motions. We will explain why it is more robust than other techniques that require the knowledge of the full flow or information up to the second-order terms of it. Experimental results are presented to support the theoretical derivations.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the IEEE Workshop on Visual Motion |
| Place of Publication | Los Alamitos, CA, United States |
| Publisher | Publ by IEEE |
| Pages | 132-139 |
| Number of pages | 8 |
| ISBN (Print) | 0818621532 |
| State | Published - Dec 1 1991 |
| Event | Proceedings of the IEEE Workshop on Visual Motion - Princeton, NJ, USA Duration: Oct 7 1991 → Oct 9 1991 |
Other
| Other | Proceedings of the IEEE Workshop on Visual Motion |
|---|---|
| City | Princeton, NJ, USA |
| Period | 10/7/91 → 10/9/91 |
Fingerprint
ASJC Scopus subject areas
- Engineering(all)
Cite this
Motion recovery from image sequences using first-order optical flow information. / Negahdaripour, Shahriar; Lee, S.
Proceedings of the IEEE Workshop on Visual Motion. Los Alamitos, CA, United States : Publ by IEEE, 1991. p. 132-139.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Motion recovery from image sequences using first-order optical flow information
AU - Negahdaripour, Shahriar
AU - Lee, S.
PY - 1991/12/1
Y1 - 1991/12/1
N2 - A closed-form solution for motion estimation from first-order flow in two `distinct' image regions is described. Uniqueness is guaranteed when these correspond to surface patches with different normal vectors. Given an image sequence, we show how the image may be segmented into regions with the necessary properties, optical flow is computed for these regions, and motion parameters are computed. The method can be applied to arbitrary scenes and camera motions. We will explain why it is more robust than other techniques that require the knowledge of the full flow or information up to the second-order terms of it. Experimental results are presented to support the theoretical derivations.
AB - A closed-form solution for motion estimation from first-order flow in two `distinct' image regions is described. Uniqueness is guaranteed when these correspond to surface patches with different normal vectors. Given an image sequence, we show how the image may be segmented into regions with the necessary properties, optical flow is computed for these regions, and motion parameters are computed. The method can be applied to arbitrary scenes and camera motions. We will explain why it is more robust than other techniques that require the knowledge of the full flow or information up to the second-order terms of it. Experimental results are presented to support the theoretical derivations.
UR - http://www.scopus.com/inward/record.url?scp=0026262728&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0026262728&partnerID=8YFLogxK
M3 - Conference contribution
SN - 0818621532
SP - 132
EP - 139
BT - Proceedings of the IEEE Workshop on Visual Motion
PB - Publ by IEEE
CY - Los Alamitos, CA, United States
ER -