We present an approach for persistent tracking of moving objects observed by non-overlapping and moving cameras. Our approach robustly recovers the geometry of non-overlapping vie...
While a large number of vision applications rely on the mapping between 3D scenes and their corresponding 2D camera images, the question that occurs to most researchers is what, i...
In this paper, we present a novel solution of image segmentation based on positiveness by regarding the segmentation as one of the graph-theoretic clustering problems. On the cont...
A number of recent systems for unsupervised featurebased learning of object models take advantage of cooccurrence: broadly, they search for clusters of discriminative features tha...
Current feature-based object recognition methods use information derived from local image patches. For robustness, features are engineered for invariance to various transformation...
As tracking systems become more effective at reliably tracking multiple objects over extended periods of time within single camera views and across overlapping camera views, incre...
Adaptive background modeling/subtraction techniques are popular, in particular, because they are able to cope with background variations that are due to lighting variations. Unfor...
Leonid Taycher, John W. Fisher III, Trevor Darrell
Isomap is an exemplar of a set of data driven nonlinear dimensionality reduction techniques that have shown promise for the analysis of images and video. These methods parameteriz...
In this paper, we propose a coherent framework for joint key-frame extraction and object-based video segmentation. Conventional key-frame extraction and object segmentation are us...