Self-location recognition using azimuth invariant features and wearable sensors

Self-location capability is a very useful and informative attribute for wearable systems. This paper proposes a method for identifying a user´s location from an omnidirectional image sensor, a GPS data source and wireless LAN data. Azimuth-invariant features are extracted from an omnidirectional image by integrating pixel information circumferentially, thus enabling a user to independently recognize his/her location from the omnidirectional image feature, the GPS data and the wireless LAN data projected into a sub-space made from the learning data. We show the effectiveness of our method by experimental results in real data.