Data Management

Motion Segmentation by SCC on the Hopkins 155 Database

Download Now Date Added: Sep 2009
Format: PDF

The authors 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. Multiframe motion segmentation is a very important yet challenging problem in computer vision. Given multiple image frames of a dynamic scene taken by a (possibly moving) camera, the task is to segment the point correspondences in those views into different motions undertaken by the moving objects.