Mixing Body-Part Sequences for Human Pose Estimation

In this paper, we present a method for estimating articu-lated 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 approx-imate 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 tempo-ral 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 cam-era motion. We experimentally compare our method with recent approaches on this new dataset as well as on two other benchmark datasets, and show significant improve-ment. 1