Automatic Houseware Registration System using Egocentric Vision and Faster R-CNN for Informationally-Structured Environment

Abstract

In this paper, we present a system to register housewares in a room to database automatically to maintain an informationally-structured environment. We assume that housewares requested by a user are likely to be appeared in an egocentric vision of the user. The proposed system captures the egocentric vision by a smart glass, detects multi-class objects in images using CNN, and registers it to the database. We demonstrate the developed system enables to register several objects in a room automatically.