The goal of this work is to detect and track the articulated pose of a human in signing videos of more than one hour in length. In particular we wish to accurately localise hands and arms, despite fast motion and a cluttered and changing background.
We cast the problem as inference in a generative model of the image, and propose a complete model which accounts for self-occlusion of the arms. Under this model, limb detection is expensive ... [truncated at 450 characters in length]
|Author||Patrick Buehler; Mark Everingham; Daniel P. Huttenlocher; et al|
|Faculty||Mathematical,Physical & Life Sciences Division - Engineering Science School of Computing Computer Science Department Mathematical,Physical & Life Sciences Division - Engineering Science|
|Abstract||Predicate abstraction is a major method for verification of software. However, the generation of the abstract Boolean program from the set of predicates and the original program suffers from an exponential number of theorem prover calls as well as from soundness issues. This paper presents a novel technique that uses an efficient SAT solver for generating the abstract transition relations of ANSI-C programs. The SAT-based approach computes a more ... [truncated at 450 characters in length]|
|Author||Edmund Clarke; Daniel Kroening; Natasha Sharygina; et al|
|Faculty||Computer Science Department Mathematical,Physical & Life Sciences Division - Computing Laboratory Informatics Department|