Abstract
In this paper, we propose a new method for estimating camera motion parameters based on optical flow models. Camera motion parameters are generated using linear combinations of optical flow models. The proposed method first creates these optical flow models, and then linear decompositions are performed on the input optical flows calculated from adjacent images in the video sequence, which are used to estimate the coefficients of each optical flow model. These coefficients are then applied to the parameters used to create each optical flow model, and the camera motion parameters implied in the adjacent images can be estimated through a linear composition of the weighted parameters.We demonstrated that the proposed method estimates the camera motion parameters accurately and at a low computational cost as well as robust to noise residing in the video sequence being analyzed.
| Original language | English |
|---|---|
| Pages (from-to) | 767-779 |
| Number of pages | 13 |
| Journal | Pattern Recognition |
| Volume | 37 |
| Issue number | 4 |
| DOIs | |
| Publication status | Published - 2004 Apr 1 |
Fingerprint
Keywords
- Estimation of camera motion parameters
- Linear composition
- Linear decomposition
- Optical flows
- Video sequences
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition
- Signal Processing
- Electrical and Electronic Engineering
Cite this
Qualitative estimation of camera motion parameters from the linear composition of optical flow. / Park, Sang Cheol; Lee, Hyoung S.; Lee, Seong Whan.
In: Pattern Recognition, Vol. 37, No. 4, 01.04.2004, p. 767-779.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Qualitative estimation of camera motion parameters from the linear composition of optical flow
AU - Park, Sang Cheol
AU - Lee, Hyoung S.
AU - Lee, Seong Whan
PY - 2004/4/1
Y1 - 2004/4/1
N2 - In this paper, we propose a new method for estimating camera motion parameters based on optical flow models. Camera motion parameters are generated using linear combinations of optical flow models. The proposed method first creates these optical flow models, and then linear decompositions are performed on the input optical flows calculated from adjacent images in the video sequence, which are used to estimate the coefficients of each optical flow model. These coefficients are then applied to the parameters used to create each optical flow model, and the camera motion parameters implied in the adjacent images can be estimated through a linear composition of the weighted parameters.We demonstrated that the proposed method estimates the camera motion parameters accurately and at a low computational cost as well as robust to noise residing in the video sequence being analyzed.
AB - In this paper, we propose a new method for estimating camera motion parameters based on optical flow models. Camera motion parameters are generated using linear combinations of optical flow models. The proposed method first creates these optical flow models, and then linear decompositions are performed on the input optical flows calculated from adjacent images in the video sequence, which are used to estimate the coefficients of each optical flow model. These coefficients are then applied to the parameters used to create each optical flow model, and the camera motion parameters implied in the adjacent images can be estimated through a linear composition of the weighted parameters.We demonstrated that the proposed method estimates the camera motion parameters accurately and at a low computational cost as well as robust to noise residing in the video sequence being analyzed.
KW - Estimation of camera motion parameters
KW - Linear composition
KW - Linear decomposition
KW - Optical flows
KW - Video sequences
UR - http://www.scopus.com/inward/record.url?scp=1542316657&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=1542316657&partnerID=8YFLogxK
U2 - 10.1016/j.patcog.2003.07.012
DO - 10.1016/j.patcog.2003.07.012
M3 - Article
AN - SCOPUS:1542316657
VL - 37
SP - 767
EP - 779
JO - Pattern Recognition
JF - Pattern Recognition
SN - 0031-3203
IS - 4
ER -