Home

Awesome

Introduction

Package containing the Matlab implementation of the code behind: The 2017 DAVIS Video Object Segmentation Challenge.

You can find the Python implementation here.

Code Installation

  1. Adapt the value of db_root_dir.m to point to the root dir where DAVIS is uncompressed in your system (contains folders Annotations and JPEGImages)
  2. Run the script startup.m to add the necessary paths and perform some checks.
  3. [If necessary] Recompile using the script build.m in case the startup script detects some files missing.

Code Usage

Evaluate your technique

Helper functions

Two helper scripts are found in the folder helpers:

Citation

Please cite DAVIS 2017 and DAVIS 2016 in your publications if it helps your research:

@article{Pont-Tuset_arXiv_2017,
  author    = {Jordi Pont-Tuset and Federico Perazzi and Sergi Caelles and
               Pablo Arbel\'aez and Alexander Sorkine-Hornung and Luc {Van Gool}},
  title     = {The 2017 DAVIS Challenge on Video Object Segmentation},
  journal   = {arXiv:1704.00675},
  year      = {2017}
}

@inproceedings{Perazzi_CVPR_2016,
  author    = {Federico Perazzi and
               Jordi Pont-Tuset and
               Brian McWilliams and
               Luc {Van Gool} and
               Markus Gross and
               Alexander Sorkine-Hornung},
  title     = {A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation},
  booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year      = {2016}
}

Contacts