Human activity can be described as a sequence of 3D body postures. The traditional approach to recognition and 3D reconstruction of human activity has been to track motion in 3D, m...
It is known that recovering projection matrices from planar con gurations is ambiguous, thus, posing the problem of model selection | is the scene planar 2D or non-planar 3D? For ...
This paper describes a novel view-based learning algorithm for 3D object recognition from 2D images using a network of linear units. The SNoW learning architecture is a sparse netw...
Abstract. The main goal of this paper is to put well-established techniques for two-view motion analysis in the context of the theory of Total Least Squares and to make clear that ...
Abstract. This paper presents a new algorithm for structure from motion from an arbitrary number of tracked features over an arbitrary number of images, which possesses several adv...
Philip F. McLauchlan, Ian D. Reid, David W. Murray