Abstract
Indoor map construction by crowdsourcing has been an attractive topic. Previous works mostly focused on the indoor layout, which could be regarded as a grammar map. In this paper, we utilize CRF (conditional random field) to generate a semantic map in a mall scenario, herein predicting the function of each compartment in the grammar map. The semantic map construction consists of three steps. First, individual user’s activity patterns are featured by collecting and analyzing sensor data of smartphones. Second, the indoor layout is decided by crowdsourcing users’ uploading tracks that are obtained from the activity patterns. Third, the function of each compartment is inferred by CRF on basis of the previous two-step output. Experiments verified the prediction effectiveness and presented the prediction accuracy. This research discovers a possibility of semantic map construction without intensive labor.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
