Numerous approaches in image processing and computer vision are making use of super-pixels as a pre-processing step. Among the different methods producing such over-segmentation of an image, the graph-based approach of Felzenszwalb and Huttenlocher is broadly employed. One of its interesting properties is that the regions are computed in a greedy manner in quasi-linear time. The algorithm may be trivially extended to video segmentation by considering a video as a 3D volume, however, this can not be the case for causal segmentation, when subsequent frames are unknown. We propose an efficient video segmentation approach that computes temporally consistent pixels in a causal manner, filling the need for causal and real time applications.
@article{arxiv.1301.1671,
title = {Causal graph-based video segmentation},
author = {Camille Couprie and Clément Farabet and Yann LeCun},
journal= {arXiv preprint arXiv:1301.1671},
year = {2013}
}