Sensing the presence of occupants and estimating the occupancy level in an indoor environment are the fundamental requirements for various applications performing remote monitoring, home automation and optimal resource planning. Data generated from a set of passive heterogeneous sensors deployed for this purpose are multimodal and streaming in nature. This work aims to formulate the human occupancy estimation in an indoor environment as a multi-class problem and proposes a edge-based data management framework for human occupancy estimation. The proposed framework is low-cost and light-weight in addition to being capable of performing real-time inference. Also testbed experimentation results is provided to justify the performance of the proposed scheme. © 2020 IEEE.