I see you: How to improve wearable activity recognition by leveraging information from environmental cameras

Gernot Bahle, Paul Lukowicz, K. Kunze, K. Kise

In: Proceedings of the 2013 IEEE International Conference on Pervasive Computing and Communications (PERCOM Workshops). IEEE International Conference on Pervasive Computing and Communications (PerCom-13) March 18-22 San Diego CA United States Seiten 409-412 IEEE 4/2013.


In this paper we investigate how vision based devices (cameras or the Kinect controller) that happen to be in the users' environment can be used to improve and fine tune on body sensor systems for activity recognition. Thus we imagine a user with his on body activity recognition system passing through a space with a video camera (or a Kinect), picking up some information, and using it to improve his system. The general idea is to correlate an anonymous ”stick figure” like description of the motion of a user's body parts provided by the vision system with the sensor signals as a means of analyzing the sensors' properties. In the paper we for example demonstrate how such a correlation can be used to determine, without the need to train any classifiers, on which body part a motion sensor is worn.

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence