Based on computer vision algorithms, this software enables to synchronize slides with the corresponding video recording.

• Author : Sebastien Campion / INRIA Texmex Team / http://www.irisa.fr/texmex

GNU AFFERO GENERAL PUBLIC LICENSE v3

make deb

Python packages -------------

make pydist

https://github.com/scampion/slideotracker

Download and extract :

http://slideotracker.gforge.inria.fr/demo/demo.tar.gz

Run :

slideo -i test/data/video.avi tests/data/slide*.jpg

#extract pdf pages to jpeg using ImageMagick
mkdir /tmp/mypdf/
convert <your.pdf> /tmp/mypdf/slide.jpg
#Run the tracker  
python slideotracker.py -v ./path/to/my/video.ogv -o results.txt /tmp/mypdf/slide*

try also :

python slideotracker.py -i tests/data/short_test.txt

Results in Javascript format :

slides=[0, 1, 2];

frames=[500, 850, 950];

Results in CSV format :

#slide_number;star_frame;end_frame

0;0;500

1;500;850

2;850;950

... .. .

Open the following file with your browser :

/usr/share/slideo/html/player.html?mediafile=data/video.ogv&slidedir=data/slides&fps=25

• scikit-learn
• OpenCV 2.1

• geometric robustification ... in progress
• optimize time computing
• documentation / How it works

• Images used for the logo : Dropline Nuovo! from http://art.gnome.org/themes/icon
• RMLL 2010 video for the data test