Anestis Papazoglou, Vittorio Ferrari

Overview

This software implements the full video segmentation pipeline of [1]. It produces foreground-background segmentations of a test video, without any manual initialisation. The software was developed under 64-bit Linux with Matlab R2012b/R2013a. There is no guarantee it will run on other operating systems or Matlab versions (though it probably will).

How fast is it?

The code typically takes 0.5 seconds/frame on a desktop PC, excluding the optical flow computation. For the optical flow, we have bundled the code of [2] in our release, which we have found that it takes 3.5 seconds/frame on average for an image size of 350×400. If you have a CUDA capable GPU, we also bundle a wrapper for the code of [3] which typically takes 1 second/frame for the same image size.

Applications

The software has been used by Han et al. who placed second in the object detection from video category of ILSVRC2015.

Examples

Downloads

References

1. Fast object segmentation in unconstrained video
   Anestis Papazoglou, Vittorio Ferrari,
   In International Conference on Computer Vision (ICCV), 2012.
   
2. Object segmentation by long term analysis of point trajectories
   T. Brox and J. Malik,
   In European Conference on Computer Vision (ECCV), 2010.
3. Dense point trajectories by gpu-accelerated large displacement optical flow
   N. Sundaram, T. Brox, and K. Keutzer,
   In European Conference on Computer Vision (ECCV), 2010.