Unconstrained Person Identification from Ceiling Using Multiview Learning for Tabletop Users

Abstract

A novel unconstrained person identification method is presented in this paper. This method is for tabletop systems which exist not only in daily life but also in working environments such as offices and factories. Recent state-of-the-art ubicomp, computer-vision, and CSCW studies have tried to recognize a user's activities and actions on a table using a ceiling-mounted device that overlooks the table, since we can install the ceiling-mounted device in an environment with limited space such as daily life environments and factory environments. Instead of conventional unconstrained person identification methods, such as face identification, we focus on a user's soft biometrics that can be captured from the ceiling such as the shoulder length, shape of the head, and posture of the back to achieve unconstrained person identification by using a ceiling-mounted depth camera. We achieve robust person identification by combining the soft biometrics within a framework of multiview learning. Multiview learning allows us to deal effectively with data consisting of features from multiple sources with different data distributions, i.e., multiple soft biometrics in our case. Our experimental evaluation revealed that our proposed method achieved high identification accuracy of about 94%.