PROJECT TITLE :

ALIMC: Activity Landmark-Based Indoor Mapping via Crowdsourcing

ABSTRACT:

Indoor maps are integral to pedestrian navigation systems, a necessary component of intelligent transportation systems (ITS). During this paper, we have a tendency to propose ALIMC, i.e., Activity Landmark-based Indoor Mapping system via Crowdsourcing. ALIMC will automatically construct indoor maps for anonymous buildings while not any prior knowledge using crowdsourcing knowledge collected by smartphones. ALIMC abstracts the indoor map using a link-node model in which the pathways are the links and therefore the intersections of the pathways are the nodes, like corners, elevators, and stairs. When passing through the nodes, pedestrians do the corresponding activities, that are detected by smartphones. After activity detection, ALIMC extracts the activity landmarks from the crowdsourcing data and clusters the activity landmarks into different clusters, each of which is treated as a node of the indoor map. ALIMC then estimates the relative distances between all the nodes and obtains a distance matrix. Based on the gap matrix, ALIMC generates a relative indoor map using the multidimensional scaling technique. Finally, ALIMC converts the relative indoor map into an absolute one based mostly on several reference points. To judge ALIMC, we tend to implement ALIMC in an office building. Experiment results show that the eightieth percentile error of the mapping accuracy is regarding zero.8-one.five m.