Errors-in-variables modeling in optical flow estimation

IEEE Transactions on Image Processing

Volumn 10, Issue 10, 2001, Pages 1528-1540

  Ng, Lydia ^a,b   Solo, Victor ^a,c  

^a IEEE   (United States)

^b Insightful Corporation   (United States)

^c UNIVERSITY OF NEW SOUTH WALES   (Australia)

Author keywords

Errors in variables (EIV); Motion estimation; Neighborhood size selection; Optical flow; Sprent's procedure; Stein's unbiased risk estimators (SURE)

Indexed keywords

ERRORS IN VARIABLES; NEIGHBORHOOD SIZE SELECTION; OPTICAL FLOW ESTIMATION; STEIN UNBIASED RISK ESTIMATORS;

ERROR ANALYSIS; IMAGE ANALYSIS; MATHEMATICAL MODELS; OPTICAL FLOWS;

MOTION ESTIMATION;

EID: 0035473852     PISSN: 10577149     EISSN: None     Source Type: Journal    
DOI: 10.1109/83.951538     Document Type: Article

References (18)

1. Determining optical flow
2. An iterative image registration technique with an application to stereo vision
3. The total least squares problem: Computational aspects and analysis
4. Computational and theoretical issues in optical flow estimation
5. Simultaneous multiple optical flow estimation
6. Total least squares fitting spatio-temporal derivatives to smooth optical flow fields
7. A new fast motion estimation method based on total least squares for video encoding
8. Total least squares estimation of stereo optical flow
9. Statistical optimization for geometric computation: Theory and practice
10. Optical flow detection using a general noise model
11. Optical flow estimation and the interaction between measurement errors at adjacent pixel positions
12. Errors-in-variables modeling in optical flow problems
13. Choosing the optimal neighborhood size in optical flow problems with errors-in-variables modeling
14. A generalized least-squares approach to linear functional relationships
15. Performance of optical flow techniques
16. A data-driven method for choosing smoothing parameters in optical flow problems
17. Bandwidth choice for nonparametric regression