In this paper, we propose a methodology for the application of Bayesian Optimization to the optimization of parameters in multi-sensor fusion systems. We apply this methodology to a state-of-the-art fusion model and demonstrate its efficacy in the optimization of fusion model parameters, including temporal decay, sensor priors and the event threshold, by employing Tree-Structured Parzen Estimators. The efficacy of the proposed methodology is evaluated by comparing the performance of the optimized system with that of a standard fusion system on a data set in the context of railway security. The results demonstrate a significant improvement in key metrics such as accuracy, false positive rate and F1-Score.

In the domain of railway infrastructure, monitoring and securing the operational stability remains a significant problem. Vandalism, trespassing, sabotage and theft are constant threats, endangering the safety and integrity of the entire system. At the same time monitoring of these systems is becoming harder and harder as the systems grow and the amount of data produced by the surveillance equipment scales accordingly. Additionally, since specific sensor modalities can have weaknesses in detecting one kind of threat, it is often necessary to install different sensors to get a better understanding of the situation. In this paper we present a fusion model based on Probabilistic Occupancy Maps (POM) and Bayesian Inference for environmental mapping of critical events such as vandalism and trespassing in the vicinity of railway infrastructure. We show that this approach helps to increase accuracy, while simultaneously decreasing the amount of false alarms generated by a system.