Animal gaits from video: comparative studies

Graphical Models (GMOD), Volume 68, Number 2, page 212-234 - mar 2006
Download the publication : gmod_final.pdf [1.3Mo]  
We present a method for animating 3D models of animals from existing live video sequences such as wild life documentaries. Videos are first segmented into binary images on which Principal Component Analysis (PCA) is applied. The time-varying coordinates of the images in the PCA space are then used to generate 3D animation. This is done through interpolation with Radial Basis Functions (RBF) of 3D pose examples associated with a small set of key-images extracted from the video. In addition to this processing pipeline, our main contributions are: an automatic method for selecting the best set of key-images for which the designer will need to provide 3D pose examples, and a simple algorithm based on PCA images to resolve 3D pose prediction ambiguities. These ambiguities are inherent to many animal gaits when only monocular view is available.

Images and movies


BibTex references

  author       = "Favreau, Laurent and Reveret, Lionel and Depraz, Christine and Cani, Marie-Paule",
  title        = "Animal gaits from video: comparative studies",
  journal      = "Graphical Models (GMOD)",
  number       = "2",
  volume       = "68",
  pages        = "212-234",
  month        = "mar",
  year         = "2006",
  url          = ""

Other publications in the database

» Laurent Favreau : in lab LJK base , in team EVASION base
» Lionel Reveret : in lab LJK base , in team EVASION base
» Christine Depraz : in lab LJK base , in team EVASION base
» Marie-Paule Cani : in lab LJK base , in team EVASION base