We address the problem of detection and tracking of moving objects in a video stream obtained from a moving airborne platform. The proposed method relies on a graph representation...
We propose an efficient solution to the general M-view projective reconstruction problem, using matrix factorization and iterative least squares. The method can accept input with ...
We formulate stereo matching as an extremal surface extraction problem. This is made possible by embedding the disparity surface inside a volume where the surface is composed of v...
We introduce an approach to feature-based object recognition, using maximum a posteriori (MAP) estimation under a Markov random field (MRF) model. This approach provides an effici...
A new approach to characterizing the performance of point-correspondence algorithms is presented. Instead of relying on any \ground truth', it uses the self-consistency of th...
Abstract. Condensation is a popular algorithm for sequential inference that resamples a sampled representation of the posterior. The algorithm is known to be asymptotically correct...
This paper offers a novel detection method, which works well even in the case of a complicated image collection – for instance, a frontal face under a large class of linear tran...
This paper introduces a new multi-view reconstruction problem called approximate N -view stereo. The goal of this problem is to recover a oneparameter family of volumes that are in...
We describe in this paper closed-form solutions to the following problems in multi-view geometry of n'th order curves: i recovery of the fundamental matrix from 4 or more c...