Crowd detection and occupancy estimation through indirect environmental measurements

摘要: In this paper, the real-time estimation of indoor occupancy has been evaluated starting from processing environmental parameters. The proposed system is based on a low cost and non-invasive wireless sensor network infrastructure for distributed acquisition simple quantities like temperature humidity. algorithm structured in three successive phases detection, filtering, classification order to face with high variability instability such quantities. problem recast as an inverse solved by means customized learning-by-example strategy (i.e., phase). A measurement campaign museum area carried out preliminary experimental results have obtained assess potentialities limitations strategy.