We view the task of change detection as a problem of object recognition from learning. The object is defined in a 3D space where the time is the 3rd dimension. We propose two com...
Many computer vision and pattern recognition algorithms are very sensitive to the choice of an appropriate distance metric. Some recent research sought to address a variant of the...
We introduce an algorithm for space-variant filtering of video based on a spatio-temporal Laplacian pyramid and use this algorithm to render videos in order to visualize prerecor...
In this paper we present an evaluation method for stereo matching systems and sensors especially for real world indoor applications. We estimate ground truth reference images by i...
Martin Humenberger, Daniel Hartermann, Wilfried Ku...
Labeling objects in images is an essential prerequisite for many visual learning and recognition applications that depend on training data, such as image retrieval, object detecti...