Discovering motion hierarchies via tree-structured coding of trajectories

Juan-Manuel Perez-Rua, Tomas Crivelli, Patrick Perez and Patrick Bouthemy

Abstract

The dynamic content of physical scenes is largely compositional, that is, the movements of the objects and of their parts are hierarchically organized and relate through composition along this hierarchy. This structure also prevails in the apparent 2D motion that a video captures. Accessing this visual motion hierarchy is important to get a better understanding of dynamic scenes and is useful for video manipulation. We propose to capture it through learned, tree-structured sparse coding of point trajectories. We leverage this new representation within an unsupervised clustering scheme to partition hierarchically the trajectories into meaningful groups. We show through experiments on motion capture data that our model is able to extract moving segments along with their organization. We also present competitive results on the task of segmenting objects in video sequences from trajectories.

Session

Posters 2

Files

Extended Abstract (PDF, 239K)
Paper (PDF, 807K)
Supplemental Materials (ZIP, 14M)

DOI

10.5244/C.30.106
https://dx.doi.org/10.5244/C.30.106

Citation

Bibtex

        @inproceedings{BMVC2016_106,
        	title={Discovering motion hierarchies via tree-structured coding of trajectories},
        	author={Juan-Manuel Perez-Rua, Tomas Crivelli, Patrick Perez and Patrick Bouthemy},
        	year={2016},
        	month={September},
        	pages={106.1-106.12},
        	articleno={106},
        	numpages={12},
        	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
        	publisher={BMVA Press},
        	editor={Richard C. Wilson, Edwin R. Hancock and William A. P. Smith},
        	doi={10.5244/C.30.106},
        	isbn={1-901725-59-6},
        	url={https://dx.doi.org/10.5244/C.30.106}
        }