Human Pose Recovery approaches have been studied in the
eld of Computer Vision for the last 40 years. Several approaches have
been reported, and signi cant improvements have been obtained in both
data representation and model design. However, the problem of Human
Pose Recovery in uncontrolled environments is far from being solved.
In this paper, we de ne a global taxonomy to group the model based
methods and discuss their main advantages and drawbacks.
CitacióPerez-Sala, X.; Escalera Guerrero, Sergio; Angulo, C. Survey on 2D and 3D human pose recovery. A: International Conference of the Catalan Association for Artificial Intelligence. "Artificial Intelligence Research and Development. Proceedings of the 15th International Conference of the Catalan Association for Artificial Intelligence". Alacant: IOS Press, 2012, p. 101-110.