Survey on Spatio-Temporal View Invariant Human Pose Recovery

Human Pose Recovery approaches have been studied in the field of Computer Vision for the last 40 years. Several approaches have been reported, and significant 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 define a global taxonomy to group the existing methods and discuss their main advantages and drawbacks, identifying new challenging lines of research.