Alper YILMAZ Mubarak Ali Shah University of Central Florida {yilmaz, shah}@cs.ucf.edu Abstract In this study, a new framework for parsing a video sequence into shots is presented. The new algorithm uses eigenspace decomposition of the RGB color space to describe the frames in a more descriptive coordinate system. The new basis eliminates the stumbling blocks of current shot detection approaches...

A new variational region based model for a simultaneous image segmentation and a rigid registration is proposed. The purpose of the model is to segment and register novel images simultaneously using a modified piecewise constant Mumford-Shah functional and region intensity values. The segmentation is obtained by minimizing a modified piecewise constant Mumford-Shah functional. A registration is...

© Operating System Support for NVM+DRAM Hybrid Main Memory Jeffrey C. Mogul, Eduardo Argollo, Mehul Shah, Paolo Faraboschi

In this paper we present a video segmentation procedure obtained minimizing a modified version of the simplified Mumford Shah functional used for image partition. This procedure uses a graph with spatial and temporal connections to model a video sequence. The temporal connections are defined pre-computing the dense optical flow using methods available in the literature. To simplify the function...