In this paper it is shown how to use corresponding conics in two images to estimate the epipolar geometry, the fundamental/essential matrix and reconstruct the scene. The corresponding conics can be images of either a planar conic or silhouettes of a quadric. It is shown that one conic correspondence gives two constraints on the fundamental matrix and a method to estimate the fundamental matrix...

In this paper we consider the problem of estimating the fundamental matrix from point correspondences. It is well known that the most accurate estimates of this matrix are obtained by criteria minimizing geometric errors when the data are aaected by noise. It is also well known that these criteria amount to solving non-convex optimization problems and, hence, their solution is aaected by the op...

In this paper, a new method for deter~niriing an optimized caniera viewpoint for soccer scene by tracking a ball is proposed. Soccer scene is taken by multiple fixed cameras. First, template matching is irnplemented for images taken with each camera to detect arid to track a ball. If the ball is occluded in one of images, tlie ball is tracked by using the position of the extracted ball in other...

We present an original multiple views method to perform a robust and detailed 3D reconstruction of a static scene from several images taken by one or more uncalibrated cameras. Making use only of fundamental matrices we are able to combine even heterogeneous video and/or photo sequences. In particular we give a characterization of camera matrices space consistent with a given fundamental matrix...

Human action recognition from videos draws tremendous interest in the past many years. In this work, we first find that the trifocal tensor resides in a twelve dimensional subspace of the original space if the first two views are already matched and the fundamental matrix between them is known, which we refer to as subtensor. Then we use the subtensor to perform the task of action recognition u...

Consider two views of a multi-body scene consisting of k planar bodies moving in pure translation one relative to the other. We show that the fundamental matrices, one per body, live in a 3-dimensional subspace, which when represented as a step-3 extensor is the common transversal on the collection of extensors defined by the homography matrices H1; :::; Hk of the moving planes. We show that as...

Abstract: In this paper, the global exponential stability of BAM neural networks with inertial term and time delay are investigated. By chosen proper variable substitution the system is transformed to f rst order differential equation. Then some new suff cient conditions, which can ensure the globally exponential stability of the system are obtained by constructing suitable Lyapunov functional,...