Unsupervised Learning of Object Features from Video Sequences

Marius Leordeanu and Robert Collins
IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR '05), July, 2005, pp. 1142 - 1149.


Download
  • Adobe portable document format (pdf) (655KB)
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract
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 features.

Keywords
unsupervised learning, object recognition, tracking

Notes
Number of pages: 8

Text Reference
Marius Leordeanu and Robert Collins, "Unsupervised Learning of Object Features from Video Sequences," IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR '05), July, 2005, pp. 1142 - 1149.

BibTeX Reference
@inproceedings{Leordeanu_2005_5230,
   author = "Marius Leordeanu and Robert Collins",
   title = "Unsupervised Learning of Object Features from Video Sequences",
   booktitle = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR '05)",
   pages = "1142 - 1149",
   month = "July",
   year = "2005",
   volume = "1",
}