A Novel Framework for Data Registration and DaFusion in Presence of Multi-modal Sensors

摘要

This article presents a novel framework to register and fuse hetero-geneous sensory data. Our approach is based on geometrically registration ofsensory data onto a set of virtual parallel planes and then applying an occu-pancy grid for each layer. This framework is useful in surveillance applicationsin presence of multi-modal sensors and can be used specially in tracking andhuman behavior understanding areas. The multi-modal sensors set in this workcomprises of some cameras, inertial measurement sensors (IMU), laser rangefinders (LRF) and a binaural sensing system. For registering data from each oneof these sensors an individual approach is proposed. After registering multi-modal sensory data on various geometrically parallel planes, a two-dimensionaloccupancy grid (as a layer) is applied for each plane.