Indoor Pedestrian Motion Detection Via Spatial Clustering and Mapping

The proliferation of location-based services has driven the rapid development of indoor localization technology. The conventional location fingerprinting based localization approach suffers from the time-consuming and labor-intensive process of fingerprint database construction, and meanwhile, the widely known simultaneous localization and mapping seriously depends on various motion sensors. In response to these compelling problems, we propose a new indoor pedestrian motion detection approach without the assistance of location fingerprinting or motion sensing. Specifically, first of all, the motion paths are constructed by the motion model of the pedestrian in the target environment. Second, after collecting the wireless local area network (WLAN) received signal strength (RSS) sequence on each motion path, the concept of density-based spatial clustering is adopted to generate the RSS clusters, and in each, the RSS data are with the similar motion patterns. Third, based on the hotspot mapping relations between the physical subareas and RSS clusters, the target is located into the physical subarea mapped by the RSS cluster, which is most similar to the newly collected RSS data. Finally, the experimental results demonstrate that the proposed approach is capable of performing target localization as well as exploring the motion behavior of the pedestrian in an indoor environment.