A method is presented for estimating the number of rigid objects moving independently and separating the feature points tracked on a motion image into individual objects by clustering. In the method, feature points are firstly mapped into a low dimensional space suitable for grouping them into each object. In this low dimensional space, clusters are extracted sequentially by a graph spectral method. The number of clusters i.e. objects can be estimated on the basis of the variation in the cohesiveness of extracted clusters. We show by numerical experiments that the present method is robust to moderate measurement noises and distortion by perspective projection.
Separation of multiple objects in motion images by clustering
Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001 ; 1 ; 219-224 vol.1
2001-01-01
498191 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Separation of Multiple Objects in Motion Images by Clustering
British Library Conference Proceedings | 2001
|Estimating Distances to Objects From Motion in Images
Online Contents | 1996
Motion planning for multiple moving objects
NTIS | 1995
|Estimating Distances To Objects From Motion In Images
NTRS | 1996
|Unsupervised Identification of Multiple Objects of Interest from Multiple Images: dISCOVER
Springer Verlag | 2007
|