Tracking Human Pose by Tracking Symmetric Parts

Abstract

The human body is structurally symmetric. Tracking by detection approaches for human pose suffer from double counting, where the same image evidence is used to explain two separate but symmetric parts, such as the left and right feet. Double counting, if left unaddressed can critically af- fect subsequent processes, such as action recognition, af- fordance estimation, and pose reconstruction. In this work, we present an occlusion aware algorithm for tracking hu- man pose in an image sequence, that addresses the problem of double counting. Our key insight is that tracking human pose can be cast as a multi-target tracking problem where the ”targets” are related by an underlying articulated struc- ture. The human body is modeled as a combination of sin- gleton parts (such as the head and neck) and symmetric pairs of parts (such as the shoulders, knees, and feet). Sym- metric body parts are jointly tracked with mutual exclusion constraints to prevent double counting by reasoning about occlusion. We evaluate our algorithm on an outdoor dataset with natural background clutter, a standard indoor dataset (HumanEva-I), and compare against a state of the art pose estimation algorithm.