Mixing Body-Part Sequences for Human Pose Estimation - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2014

Mixing Body-Part Sequences for Human Pose Estimation


In this paper, we present a method for estimating articulated human poses in videos. We cast this as an optimization problem defined on body parts with spatio-temporal links between them. The resulting formulation is unfortunately intractable and previous approaches only provide approximate solutions. Although such methods perform well on certain body parts, e.g., head, their performance on lower arms, i.e., elbows and wrists, remains poor. We present a new approximate scheme with two steps dedicated to pose estimation. First, our approach takes into account temporal links with subsequent frames for the less-certain parts, namely elbows and wrists. Second, our method decomposes poses into limbs, generates limb sequences across time, and recomposes poses by mixing these body part sequences. We introduce a new dataset "Poses in the Wild", which is more challenging than the existing ones, with sequences containing background clutter, occlusions, and severe camera motion. We experimentally compare our method with recent approaches on this new dataset as well as on two other benchmark datasets, and show significant improvement.
Fichier principal
Vignette du fichier
posecvpr2014.pdf (3.72 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-00978643 , version 1 (14-04-2014)



Anoop Cherian, Julien Mairal, Karteek Alahari, Cordelia Schmid. Mixing Body-Part Sequences for Human Pose Estimation. CVPR - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2014, Columbus, OH, United States. pp. 2361-2368, ⟨10.1109/CVPR.2014.302⟩. ⟨hal-00978643⟩
1062 View
5494 Download



Gmail Mastodon Facebook X LinkedIn More