Visually track several moving persons engaged in close interactions is known to be a very hard problem, though 3-D approaches based on stereo vision and plan-view maps offer much ...
Alessandro Bevilacqua, Luigi di Stefano, Pietro Az...
We present here a prototype video analysis and retrieval system, called NeTra-V, that is being developed to build an object-based video representation for functionalities such as s...
This paper describes an approach for generating Binary Partition Tree [7] representations and video object segmentations using a novel region merging strategy based on motion simi...
Global shape information is an effective top-down complement
to bottom-up figure-ground segmentation as well
as a useful constraint to avoid drift during adaptive tracking.
We p...
This paper presents a 3D object recognition method that exploits the spatio-temporal coherence of image sequences to capture the object most relevant features. We start from an im...