Selecting Salient Frames for Spatiotemporal Video Modeling and Segmentation

Abstract

We propose a new statistical generative model for spatiotemporal video segmentation. The objective is to partition a video sequence into homogeneous segments that can be used as "building blocks" for semantic video segmentation. The baseline framework is a Gaussian mixture model (GMM)-based video modeling approach that involves a six-dimensional… (More)
DOI: 10.1109/TIP.2007.908283

Topics

16 Figures and Tables

Cite this paper

@article{Song2007SelectingSF, title={Selecting Salient Frames for Spatiotemporal Video Modeling and Segmentation}, author={Xiaomu Song and Guoliang Fan}, journal={IEEE Transactions on Image Processing}, year={2007}, volume={16}, pages={3035-3046} }