Sensor fusion for bimodal generalized likelihood ratio test with unknown noise variances

TL;DR

This paper develops a sensor fusion method using a generalized likelihood ratio test for bimodal detection, accounting for unknown noise variances, and employs Meijer G-function theory for analysis.

Contribution

It introduces a novel fusion architecture based on the GLRT for bimodal sensors with unknown noise variances, with new analytical expressions for test statistic distributions.

Findings

Derived the distribution of the test statistic under both hypotheses.

Proposed a fusion architecture based on the GLRT principle.

Developed a methodology using Meijer G-function for analysis.

Abstract

In this paper we address the problem of sensor fusion. We formulate the joint detection problem using a general linear observation model and inter-modality independence assumption for noises. We derive the fusion architecture based on the generalized likelihood ratio principle and calculate the expressions for the distributions of the test statistic under the signal present and the null hypotheses. To obtain these results we develop a methodology for the joint detection algorithm analysis based on the theory of the Meijer G-function.