DocumentCode :
383371
Title :
Motion prediction using VC-generalization bounds
Author :
Wechsler, Harry ; Duric, Zoran ; Li, Fayin ; Cherkassky, Vladimir S.
Author_Institution :
Dept. of Comput. Sci., George Mason Univ., Fairfax, VA, USA
Volume :
1
fYear :
2002
fDate :
2002
Firstpage :
151
Abstract :
Describes an application of statistical learning theory (SLT) for motion prediction. SLT provides analytical VC-generalization bounds for model selection; these bounds relate unknown prediction risk (generalization performance) and known quantities such as the number of training samples, empirical error, and a measure of model complexity called the VC-dimension. We use the VC-generalization bounds for the problem of choosing optimal motion models from small sets of image measurements (flow). We present results of experiments on image sequences for motion interpolation and extrapolation; these results demonstrate the strengths of our approach.
Keywords :
extrapolation; generalisation (artificial intelligence); image sequences; interpolation; learning (artificial intelligence); motion estimation; VC-dimension; VC-generalization bounds; empirical error; generalization performance; image flow; image measurements; image sequences; model complexity; model selection; motion extrapolation; motion interpolation; motion prediction; optimal motion models; statistical learning theory; training samples; unknown prediction risk; Application software; Computer errors; Computer vision; Noise robustness; Parameter estimation; Predictive models; Risk analysis; Solid modeling; Statistical analysis; Statistical learning;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition, 2002. Proceedings. 16th International Conference on
ISSN :
1051-4651
Print_ISBN :
0-7695-1695-X
Type :
conf
DOI :
10.1109/ICPR.2002.1044635
Filename :
1044635
Link To Document :
بازگشت