Using Co-Occurrence and Segmentation to Learn Feature-Based Object Models from Video
Stepleton, T.
Tai Sing Lee
Robot. Inst., Carnegie Mellon Univ., Pittsburgh, PA;
Abstract
A number of recent systems for unsupervised feature- based learning of object models take advantage of cooccurrence: broadly, they search for clusters of discriminative features that tend to coincide across multiple still images or video frames. An intuition behind these efforts is that regularly co-occurring image features are likely to refer to physical traits of the same object, while features that do not often co-occur are more likely to belong to different objects. In this paper we discuss a refinement to these techniques in which multiple segmentations establish meaningful contexts for co-occurrence, or limit the spatial regions in which two features are deemed to co-occur. This approach can reduce the variety of image data necessary for model learning and simplify the incorporation of less discriminative features into the model.
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
