Heterogeneous Coverage Analysis for Collaborative Classification in Multimedia Sensor Networks
Dong Zhao, Huadong Ma and Liang Liu
Multimedia Sensor Networks (MSNs) promise an unprecedented opportunity for surveillance applications. This paper investigates the coverage problem from the perspective of multi-class target/event classification in MSNs. Specially, we present a binary-classification-tre based framework for collaborative target/event classification and provide two typical cases. Different from the traditional homogeneous coverage problem, the coverage arising in the binary-classification-tre based classification paradigm is heterogeneous, because it requires that each point in the surveillance region is covered by multiple types of sensor nodes. In this paper, we propose a general framework for the heterogeneous coverage analysis. Specially, we propose two kinds of heterogeneous sensing models for the two cases. Then, under the random uniform deployment strategy, we analyze how the coverage probability changes with the sensors number and the parameters of the sensing models. Extensive simulation results show the validity of our models and theoretical analysis.
Keywords: Multimedia sensor network; heterogeneous coverage; collaborative classification sensing model.