Carrying Object Detection Using Pose Preserving Dynamic Shape Models

摘要

In this paper, we introduce a framework for carrying object detection in different people from different views using pose preserving dynamic shape models. We model dynamic shape deformations in different people using kinematics manifold embedding and decomposable generative models by kernel map and multilinear analysis. The generative model supports pose-preserving shape reconstruction in different people, views and body poses. Iterative estimation of shape style and view with pose preserving generative model allows estimation of outlier in addition to accurate body pose. The model is also used for hole filling in the background-subtracted silhouettes using mask generated from the best fitting shape model. Experimental results show accurate estimation of carrying objects with hole filling in discrete and continuous view variations.