Carnegie Mellon News

Carnegie Mellon University (CMU) researchers have developed methods for combining the views of 480 video cameras to perform large-scale three-dimensional (3D) motion reconstruction. CMU professor Yaser Sheikh says the techniques could one day be applied to large-scale reconstructions of sporting events or performances captured by hundreds of cameras wielded by spectators. The new method estimates visibility using motion as a cue. For example, if a point on a person's chest is being tracked and most cameras show that point is moving to the right, a camera that picks up motion in the opposite direction is probably seeing a person or object that is in between the target and the camera. To read further, please visit http://www.cmu.edu/news/stories/archives/2014/july/july17_reconstructing3Dmotion.html.