Joe KroeseNavigate back to the homepage

Dance Montage

Joe Kroese
April 3rd, 2019 · 1 min read

Proposed Process


  1. Create archive of film.
  2. Run a pose detection algorithm on all of it, outputing joint data of the detected poses. (Dataset A)
  3. Film some fresh choreography.
  4. Run the pose detection algorithm on this. Again, outputting joint data. (Dataset B)
  5. Run an algorithm that, for each frame, of B finds the pose from the archive (A), that is most similar.
  6. Place the most similar frames in order and export as a film.

West Side Story mapped with openpose

Things we need

Pose detection algorithm. Can use openpose - tick.

Fresh choreography. I can put on some trousers and then I’ll be right with you - tick.

Algorithm that can find the most similar pose . Need some time to develop an optimal one of these, but won’t be too hard.

Mood board

Mario Klingemann is doing cool things GANs.

Something like this, but with frames from dance videos instead of drawings at each point. And 24 frames per second instead of this slow.

349 from Kristen Lauth Shaeffer on Vimeo.

I suspect it may look a bit like ‘Loving Vincent’ in which every frame is an oil painting. There is something disjointed about the animation but there is enough for a coherent and moving pattern to emerge.

More articles from Joe Kroese

Phylogenesis of Dance

Using 3D tracking to investigate the evolutionary history of dance

April 2nd, 2019 · 1 min read

Some Stars Look Back

An artwork with 3D sensors asking what it would be like if nature was as interested in us as we are in it

March 3rd, 2019 · 1 min read
© 2017–2020 Joe Kroese
Link to $ to $ to $ to $