Abstract
Original language | English |
---|---|
Title of host publication | Visual Communications and Image Processing 2002, San Jose, CA, USA |
Place of Publication | Bellingham |
Publisher | SPIE |
Pages | 687-697 |
DOIs | |
Publication status | Published - 2002 |
Event | Visual Communications and Image Processing 2002 (VCIP 2002), January 20-25, 2002, San Jose, CA, USA - San Jose, CA, United States Duration: 20 Jan 2002 → 25 Jan 2002 |
Publication series
Name | Proceedings of SPIE |
---|---|
Volume | 4671 |
ISSN (Print) | 0277-786X |
Conference
Conference | Visual Communications and Image Processing 2002 (VCIP 2002), January 20-25, 2002, San Jose, CA, USA |
---|---|
Abbreviated title | VCIP 2002 |
Country | United States |
City | San Jose, CA |
Period | 20/01/02 → 25/01/02 |
Other | Viual Communications and Image Processing 2002 |
Fingerprint
Cite this
}
Feature point selection for object-based motion estimation on a Programmable Device. / Wittebrood, R.B.; Haan, de, G.
Visual Communications and Image Processing 2002, San Jose, CA, USA. Bellingham : SPIE, 2002. p. 687-697 (Proceedings of SPIE; Vol. 4671).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review
TY - GEN
T1 - Feature point selection for object-based motion estimation on a Programmable Device
AU - Wittebrood, R.B.
AU - Haan, de, G.
PY - 2002
Y1 - 2002
N2 - Recently, we reported on a recursive algorithm enabling real-time object-based motion estimation (OME) for standard definition video on a digital signal processor (DSP). The algorithm approximates the motion of objects in the image with parametric motion models and creates a segmentation mask by assigning the best matching model to image parts on a block-by-block basis. A parameter estimation module determines the parameters of the motion models on a small fraction of the pictorial data called feature points. In this paper, we propose a new, computationally very efficient, feature point selection method that improves the convergence of the motion parameter estimation process.
AB - Recently, we reported on a recursive algorithm enabling real-time object-based motion estimation (OME) for standard definition video on a digital signal processor (DSP). The algorithm approximates the motion of objects in the image with parametric motion models and creates a segmentation mask by assigning the best matching model to image parts on a block-by-block basis. A parameter estimation module determines the parameters of the motion models on a small fraction of the pictorial data called feature points. In this paper, we propose a new, computationally very efficient, feature point selection method that improves the convergence of the motion parameter estimation process.
U2 - 10.1117/12.453112
DO - 10.1117/12.453112
M3 - Conference contribution
T3 - Proceedings of SPIE
SP - 687
EP - 697
BT - Visual Communications and Image Processing 2002, San Jose, CA, USA
PB - SPIE
CY - Bellingham
ER -