Marius Leordeanu, Robert T. Collins, and Martial Hebert,
" Unsupervised Learning of Object Features from Video Sequences,"
IEEE Computer Vision and Pattern Recognition (CVPR'05),
San Diego, CA, June 2005, pp.1142-1149.
We develop an efficient algorithm for unsupervised learning of object
models as constellations of features, from low resolution video
sequences. The input images typically contain single or multiple
objects that change in pose, scale and degree of occlusion. Also, the
objects can move significantly between consecutive frames. The content
of an input sequence is unlabeled so the learner has to cluster the
data based on the data's implicit coherence over time and space. Our
approach takes advantage of the dependent pairwise co-occurrences of
objects' features within local neighborhoods vs. the independent
behavior of unrelated features. We couple or decouple pairs of
features based on a probabilistic interpretation of their pairwise
statistics and then extract objects as connected components of
Click here for
full paper (655342 bytes, pdf file).