We investigate the problem of automatically creating 3D models of man-made environments that we represent as collections of textured planes. A typical approach is to automatically...
In this paper, we investigate how an unlabeled image corpus can facilitate the segmentation of any given image. A simple yet efficient multi-task joint sparse representation model...
We describe a method for processing large amounts of volumetric data collected from a Knife Edge Scanning Microscope (KESM). The neuronal data that we acquire consists of thin, br...
Bruce H. McCormick, David Mayerich, John Keyser, P...
This paper proposes a scheme to detect and locate the players and the ball on the grass playfield in soccer videos. We put forward a shape analysisbased approach to identify the pl...
Our goal is to detect and track moving vehicles on a road observed from cameras placed on poles or buildings. Inter-vehicle occlusion is significant under these conditions and tra...