Mixing Body-Part Sequences for Human Pose Estimation
Citations Over TimeTop 1% of 2014 papers
Abstract
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.
Related Papers
- → Stationary clutter rejection in echocardiography(2005)28 cited
- → Review of visual clutter and its effects on pilot performance: A new look at past research(2012)9 cited
- → Evidence of Clutter Avoidance in Complex Scenes(2010)7 cited
- → Clutter rejection limitations from ambiguous range clutter(2002)5 cited
- → Method for Estimating Representative Values of Clutter Heights for Recommendation ITU-R P.452(2009)3 cited