OSTD

Online Stochastic Tensor Decomposition for Background Subtraction in Multispectral Video Sequences

Highlights
* An online stochastic framework for tensor decomposition to deal with multi-dimensional and streaming data.
* And, the use of multispectral video sequences instead of standard mono/trichromatic images, enabling a better background subtraction.

Citation
If you use this code for your publications, please cite it as (Online Reference):

@inproceedings{ostd,
author = {Sobral, Andrews and Javed, Sajid and Ki Jung, Soon and Bouwmans, Thierry and Zahzah, El-hadi},
title = {Online Tensor Decomposition for Background Subtraction in Multispectral Video Sequences},
booktitle = {IEEE International Conference on Computer Vision Workshops (ICCVW)},
address = {Santiago, Chile},
year = {2015},
month = {December},
url = {https://github.com/andrewssobral/ostd}
}

Source code
hyperspectral/ - hyperspectral image sequences
hyperspectral/fet.py - foreground evaluation tool in python
STOC-RPCA/ - stochastic RPCA
OSTD.m - proposed algorithm
demo.m - demo file

License
The source code is available only for academic/research purposes (non-commercial).

Problems or Questions
If you have any problems or questions, please contact the author: Andrews Sobral (andrewssobral at gmail dot com)