LAAV segments motion via locally affine feature-set affinities as pre-processing for random voting, claiming higher accuracy and lower cost than pairwise methods.
Motion Segmentation by SCC on the Hopkins 155 Database
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We apply the Spectral Curvature Clustering (SCC) algorithm to a benchmark database of 155 motion sequences, and show that it outperforms all other state-of-the-art methods. The average misclassification rate by SCC is 1.41% for sequences having two motions and 4.85% for three motions.
fields
cs.CV 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Motion Segmentation Using Locally Affine Atom Voting
LAAV segments motion via locally affine feature-set affinities as pre-processing for random voting, claiming higher accuracy and lower cost than pairwise methods.