This paper presents a method to create a model of an articulated object using the planar motion in an initialization video. The model consists of rigid parts connected by points of articulation. The rigid parts are described by the positions of salient feature-points tracked throughout the video. Following a filtering step that identifies points that belong to different objects, rigid parts are found by a grouping process in a graph pyramid. Valid articulation points are selected by verifying multiple hypotheses for each pair of parts.


Artner, N., Ion, A., & Kropatsch, W. (2011). Spatio-Temporal Extraction of Articulated Models in a Graph Pyramid Graph-Based Representations in Pattern Recognition. In GbRPR’11 Proceedings of the 8th international conference on Graph-based representations in pattern recognition (pp. 215–224). Lecture Notes in Computer Science, Vol. 6658, Springer/Xiaoyi Jiang, Miquel Ferrer, Andrea Torsello. http://hdl.handle.net/20.500.12708/53843