We present a fast, simple location recognition and image localization method that leverages feature correspondence and geometry estimated from large Internet photo collections. Suc...
Detecting moving objects using stationary cameras is an important precursor to many activity recognition, object recognition and tracking algorithms. In this paper, three innovati...
Getting trapped in suboptimal local minima is a perennial problem in model based vision, especially in applications like monocular human body tracking where complex nonlinear para...
We present a novel approach for analyzing two-dimensional (2D) flow field data based on the idea of invariant moments. Moment invariants have traditionally been used in computer vi...
Michael Schlemmer, Manuel Heringer, Florian Morr...
Information about dynamic spatial fields, such as temperature, windspeed, or the concentration of gas pollutant in the air, is important for many environmental applications. At th...