We propose a novel algorithm for segmenting multiple motions of different types from point correspondences in multiple affine or perspective views. Since point trajectories associ...
?This paper presents a computational paradigm called Data-Driven Markov Chain Monte Carlo (DDMCMC) for image segmentation in the Bayesian statistical framework. The paper contribut...
Current vision systems are designed to perform in clear weather. Needless to say, in any outdoor application, there is no escape from "bad" weather. Ultimately, computer...
In this paper, we present a vision system for object recognition in aerial images, which enables broader mission profiles for Micro Air Vehicles (MAVs). The most important factors ...
The paper introduces a new framework for feature learning in classification motivated by information theory. We first systematically study the information structure and present a n...